Resource List
List all resources, or create a new resource.
GET /api/t/?dataFormat=%22FASTA%22
{ "count": 939, "next": "?page=2", "previous": null, "list": [ { "name": "pathotypr", "description": "A fast, offline, pathogen-agnostic toolkit for lineage classification and marker-driven genotyping from whole-genome sequencing data. Bring your own SNP marker panel for any microbial pathogen — pathotypr handles the rest. Ships with curated panels for Mycobacterium tuberculosis complex (MTBC): 3,707 lineage-defining SNPs and over 102,000 resistance-associated mutations. Works with assembled genomes (FASTA) and raw reads (FASTQ). Available as command-line interface and cross-platform desktop GUI (Tauri).", "homepage": "https://github.com/PathoGenOmics-Lab/pathotypr", "biotoolsID": "pathotypr", "biotoolsCURIE": "biotools:pathotypr", "version": [ "1.0.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3196", "term": "Genotyping" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0920", "term": "Genotype/phenotype report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "train — Build a Random Forest classifier from labeled genomes.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3225", "term": "Variant classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0920", "term": "Genotype/phenotype report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "predict — Assign lineages to genomes using a pre-trained Random Forest model.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3196", "term": "Genotyping" }, { "uri": "http://edamontology.org/operation_3225", "term": "Variant classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0920", "term": "Genotype/phenotype report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "classify — Call known SNP markers in assembled genomes against a user-defined marker panel.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3196", "term": "Genotyping" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0920", "term": "Genotype/phenotype report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "split-fastq — Alignment-free genotyping directly from raw reads using k-mer matching.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0346", "term": "Sequence similarity search" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0920", "term": "Genotype/phenotype report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "match — Find the closest reference genome from a set of references for raw reads.", "cmd": null } ], "toolType": [ "Command-line tool", "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" }, { "uri": "http://edamontology.org/topic_0625", "term": "Genotype and phenotype" }, { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_3305", "term": "Public health and epidemiology" }, { "uri": "http://edamontology.org/topic_3474", "term": "Machine learning" } ], "operatingSystem": [], "language": [ "Rust" ], "license": "AGPL-3.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [ { "url": "https://github.com/PathoGenOmics-Lab/pathotypr/releases", "type": "Binaries", "note": null, "version": null }, { "url": "https://github.com/PathoGenOmics-Lab/pathotypr", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "https://github.com/PathoGenOmics-Lab/pathotypr/tree/main/docs", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.64898/2026.03.24.714002", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Paula Ruiz-Rodriguez", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0003-0727-5974", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Maintainer" ], "note": null }, { "name": "Mireia Coscolla", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0003-0752-0538", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "I2SysBio (CSIC - Universitat de València)", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "PathoGenOmics Lab", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Division", "typeRole": [ "Provider" ], "note": null } ], "owner": "paururo", "additionDate": "2026-04-02T11:29:54.022786Z", "lastUpdate": "2026-04-02T11:29:54.029869Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MHCcluster", "description": "Functional cluster of MHC class I molecules (MHCI) based on their predicted binding specificity.", "homepage": "http://cbs.dtu.dk/services/MHCcluster/", "biotoolsID": "mhccluster", "biotoolsCURIE": "biotools:mhccluster", "version": [ "2.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3459", "term": "Functional clustering" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1353", "term": "Sequence motif" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0872", "term": "Phylogenetic tree" }, "format": [ { "uri": "http://edamontology.org/format_2006", "term": "Phylogenetic tree format" } ] }, { "data": { "uri": "http://edamontology.org/data_1636", "term": "Heat map" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] } ], "note": "provides heat-map and graphical tree-based visualizations of the functional relationship between MHC class I and class II variants", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_2830", "term": "Immunoproteins, genes and antigens" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": "Other", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge (with restrictions)", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://cbs.dtu.dk/services", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://www.cbs.dtu.dk/services/MHCcluster-2.0/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1007/s00251-013-0714-9", "pmid": "23775223", "pmcid": "PMC3750724", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "MHCcluster, a method for functional clustering of MHC molecules", "abstract": "The identification of peptides binding to major histocompatibility complexes (MHC) is a critical step in the understanding of T cell immune responses. The human MHC genomic region (HLA) is extremely polymorphic comprising several thousand alleles, many encoding a distinct molecule. The potentially unique specificities remain experimentally uncharacterized for the vast majority of HLA molecules. Likewise, for nonhuman species, only a minor fraction of the known MHC molecules have been characterized. Here, we describe a tool, MHCcluster, to functionally cluster MHC molecules based on their predicted binding specificity. The method has a flexible web interface that allows the user to include any MHC of interest in the analysis. The output consists of a static heat map and graphical tree-based visualizations of the functional relationship between MHC variants and a dynamic TreeViewer interface where both the functional relationship and the individual binding specificities of MHC molecules are visualized. We demonstrate that conventional sequence-based clustering will fail to identify the functional relationship between molecules, when applied to MHC system, and only through the use of the predicted binding specificity can a correct clustering be found. Clustering of prevalent HLA-A and HLA-B alleles using MHCcluster confirms the presence of 12 major specificity groups (supertypes) some however with highly divergent specificities. Importantly, some HLA molecules are shown not to fit any supertype classification. Also, we use MHCcluster to show that chimpanzee MHC class I molecules have a reduced functional diversity compared to that of HLA class I molecules. MHCcluster is available at www.cbs.dtu.dk/services/MHCcluster-2.0. © 2013 Springer-Verlag Berlin Heidelberg.", "date": "2013-09-01T00:00:00Z", "citationCount": 60, "authors": [ { "name": "Thomsen M." }, { "name": "Lundegaard C." }, { "name": "Buus S." }, { "name": "Lund O." }, { "name": "Nielsen M." } ], "journal": "Immunogenetics" } } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Morten Nielsen", "email": "mniel@cbs.dtu.dk", "url": null, "orcidid": "http://orcid.org/0000-0001-7885-4311", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "liuyang", "additionDate": "2015-01-21T13:29:32Z", "lastUpdate": "2026-03-20T11:08:19.028012Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "HTSlib", "description": "The main purpose of HTSlib is to provide access to genomic information files, both alignment data (SAM, BAM, and CRAM formats) and variant data (VCF and BCF formats). The library also provides interfaces to access and index genome reference data in FASTA format and tab-delimited files with genomic coordinates. It is utilized and incorporated into both SAMtools and BCFtools.", "homepage": "http://www.htslib.org/", "biotoolsID": "htslib", "biotoolsCURIE": "biotools:htslib", "version": [ "1.0", "1.1", "1.2", "1.2.1", "1.3", "1.3.1", "1.3.2", "1.4", "1.4.1", "1.5", "1.6", "1.7", "1.8", "1.9", "1.10", "1.10.1", "1.10.2", "1.11", "1.12", "1.13", "1.14", "1.15", "1.15.1", "1.16", "1.17", "1.18", "1.19", "1.20", "1.21.1", "1.22", "1.22.1", "1.22.2", "1.23", "1.23.1" ], "otherID": [], "relation": [ { "biotoolsID": "samtools", "type": "usedBy" }, { "biotoolsID": "bcftools", "type": "usedBy" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2409", "term": "Data handling" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0924", "term": "Sequence trace" }, "format": [ { "uri": "http://edamontology.org/format_3462", "term": "CRAM" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_2573", "term": "SAM" }, { "uri": "http://edamontology.org/format_2572", "term": "BAM" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_3498", "term": "Sequence variations" }, "format": [ { "uri": "http://edamontology.org/format_3020", "term": "BCF" }, { "uri": "http://edamontology.org/format_3016", "term": "VCF" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0924", "term": "Sequence trace" }, "format": [ { "uri": "http://edamontology.org/format_3462", "term": "CRAM" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_2573", "term": "SAM" }, { "uri": "http://edamontology.org/format_2572", "term": "BAM" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_3498", "term": "Sequence variations" }, "format": [ { "uri": "http://edamontology.org/format_3020", "term": "BCF" }, { "uri": "http://edamontology.org/format_3016", "term": "VCF" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Library" ], "topic": [ { "uri": "http://edamontology.org/topic_3071", "term": "Data management" } ], "operatingSystem": [ "Windows", "Linux", "Mac" ], "language": [ "C" ], "license": "MIT", "collectionID": [ "Animal and Crop Genomics" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/samtools/htslib", "type": [ "Repository" ], "note": null }, { "url": "http://www.htslib.org/support/#lists", "type": [ "Mailing list" ], "note": null }, { "url": "https://github.com/samtools/htslib/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "http://www.htslib.org/download/", "type": "Downloads page", "note": null, "version": null } ], "documentation": [ { "url": "http://www.htslib.org/doc/#manual-pages", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/gigascience/giab007", "pmid": "33594436", "pmcid": "PMC7931820", "type": [ "Primary" ], "version": null, "note": "HTSlib: C library for reading/writing high-throughput sequencing data.", "metadata": null } ], "credit": [ { "name": "Wellcome Sanger Institute", "email": "samtools@sanger.ac.uk", "url": "https://www.sanger.ac.uk/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider", "Primary contact" ], "note": null }, { "name": "Samtools Help mailing list", "email": null, "url": "https://lists.sourceforge.net/lists/listinfo/samtools-help", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Project", "typeRole": [ "Support" ], "note": null } ], "owner": "awhitwham", "additionDate": "2017-08-20T16:07:58Z", "lastUpdate": "2026-03-18T17:33:38.200309Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics", "smoe" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "QUAST", "description": "QUAST stands for QUality ASsessment Tool. \nIt evaluates a quality of genome assemblies by computing various metrics and providing nice reports.", "homepage": "http://quast.sourceforge.net/quast", "biotoolsID": "quast", "biotoolsCURIE": "biotools:quast", "version": [ "v.5.3.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_3180", "term": "Sequence assembly validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [], "note": "# Running quast on a eukaryotic genome", "cmd": "quast -ek assembly.fa --out output_prefix" } ], "toolType": [ "Workflow" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Perl", "Python", "C" ], "license": "GPL-2.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/ablab/quast", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/ablab/quast/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [ { "url": "http://quast.bioinf.spbau.ru/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btt086", "pmid": "23422339", "pmcid": "PMC3624806", "type": [], "version": null, "note": null, "metadata": { "title": "QUAST: Quality assessment tool for genome assemblies", "abstract": "Limitations of genome sequencing techniques have led to dozens of assembly algorithms, none of which is perfect. A number of methods for comparing assemblers have been developed, but none is yet a recognized benchmark. Further, most existing methods for comparing assemblies are only applicable to new assemblies of finished genomes; the problem of evaluating assemblies of previously unsequenced species has not been adequately considered. Here, we present QUAST - a quality assessment tool for evaluating and comparing genome assemblies. This tool improves on leading assembly comparison software with new ideas and quality metrics. QUAST can evaluate assemblies both with a reference genome, as well as without a reference. QUAST produces many reports, summary tables and plots to help scientists in their research and in their publications. In this study, we used QUAST to compare several genome assemblers on three datasets. QUAST tables and plots for all of them are available in the Supplementary Material, and interactive versions of these reports are on the QUAST website. © 2013 The Author.", "date": "2013-04-15T00:00:00Z", "citationCount": 6872, "authors": [ { "name": "Gurevich A." }, { "name": "Saveliev V." }, { "name": "Vyahhi N." }, { "name": "Tesler G." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "QUAST Support", "email": "quast.support@cab.spbu.ru", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:16:01Z", "lastUpdate": "2026-03-13T09:39:06.494933Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-CZ", "Keiler_Collier", "rathor2611" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "WEBnma", "description": "WEBnm@ provides quick, automated computation and analysis of low-frequency normal modes for protein structures.", "homepage": "http://apps.cbu.uib.no/webnma", "biotoolsID": "webnma", "biotoolsCURIE": "biotools:webnma", "version": [ "3.5" ], "otherID": [], "relation": [ { "biotoolsID": "numpy", "type": "uses" }, { "biotoolsID": "biopython", "type": "uses" }, { "biotoolsID": "matplotlib", "type": "uses" }, { "biotoolsID": "mustang", "type": "uses" }, { "biotoolsID": "dssp", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0570", "term": "Structure visualisation" }, { "uri": "http://edamontology.org/operation_0244", "term": "Protein flexibility and motion analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1460", "term": "Protein structure" }, "format": [ { "uri": "http://edamontology.org/format_1476", "term": "PDB" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [ { "uri": "http://edamontology.org/format_3508", "term": "PDF" } ] }, { "data": { "uri": "http://edamontology.org/data_1354", "term": "Sequence profile" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "Constructs elastic network model from alpha carbon coordinates of the protein, and computes properties to describe large scale conformations. Computes normal modes, fluctuation profiles, inter-residue correlations, conformational overlap analysis and vector field representations. Structural amino acid profiles, and normal mode characteristics describing protein motion, visualized in plots and decorated structure visualizations. White space delimited tabular data for normal modes and the provided plots", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2487", "term": "Protein structure comparison" }, { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0886", "term": "Structure alignment" }, "format": [ { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" } ] }, { "data": { "uri": "http://edamontology.org/data_1460", "term": "Protein structure" }, "format": [ { "uri": "http://edamontology.org/format_1476", "term": "PDB" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [ { "uri": "http://edamontology.org/format_3508", "term": "PDF" } ] }, { "data": { "uri": "http://edamontology.org/data_0889", "term": "Structural profile" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "Performs comparative analysis of the normal modes of protein structures. Computes the Bhattacharyya Coefficient (BC) and the Root Mean Squared Inner Product (RMSIP) of aligned parts of the proteins. Alignment of sets of proteins to be compared. Multiple protein structures Heatmaps, dendrograms and structural amino acid profiles for visual comparison of structural similarity. White space delimited tabular data for the provided plots", "cmd": null } ], "toolType": [ "Web API", "Suite" ], "topic": [ { "uri": "http://edamontology.org/topic_2814", "term": "Protein structure analysis" }, { "uri": "http://edamontology.org/topic_0736", "term": "Protein folds and structural domains" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [ "BiB tools", "CBU tools", "UiB tools", "ELIXIR-NO", "ELIXIR-Norway" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "Norway" ], "elixirCommunity": [ "3D-BioInfo" ], "link": [ { "url": "https://github.com/reuter-group/webnma3", "type": [ "Repository", "Issue tracker" ], "note": null }, { "url": "https://elixir.no/helpdesk", "type": [ "Helpdesk" ], "note": "Helpdesk and support for ELIXIR Norway services." } ], "download": [], "documentation": [ { "url": "http://apps.cbu.uib.no/webnma3/howto/single", "type": [ "Quick start guide" ], "note": null }, { "url": "http://apps.cbu.uib.no/webnma3/qanda", "type": [ "FAQ" ], "note": null }, { "url": "http://apps.cbu.uib.no/webnma3/about", "type": [ "General", "Citation instructions" ], "note": null } ], "publication": [ { "doi": "10.1186/s12859-014-0427-6", "pmid": "25547242", "pmcid": "PMC4339738", "type": [ "Primary" ], "version": "2.0", "note": null, "metadata": { "title": "WEBnmat v2.0: Web server and services for comparing protein flexibility", "abstract": "Background: Normal mode analysis (NMA) using elastic network models is a reliable and cost-effective computational method to characterise protein flexibility and by extension, their dynamics. Further insight into the dynamics-function relationship can be gained by comparing protein motions between protein homologs and functional classifications. This can be achieved by comparing normal modes obtained from sets of evolutionary related proteins. Results: We have developed an automated tool for comparative NMA of a set of pre-aligned protein structures. The user can submit a sequence alignment in the FASTA format and the corresponding coordinate files in the Protein Data Bank (PDB) format. The computed normalised squared atomic fluctuations and atomic deformation energies of the submitted structures can be easily compared on graphs provided by the web user interface. The web server provides pairwise comparison of the dynamics of all proteins included in the submitted set using two measures: the Root Mean Squared Inner Product and the Bhattacharyya Coefficient. The Comparative Analysis has been implemented on our web server for NMA, WEBnmat, which also provides recently upgraded functionality for NMA of single protein structures. This includes new visualisations of protein motion, visualisation of inter-residue correlations and the analysis of conformational change using the. In addition, programmatic access to WEBnmat is now available through a SOAP-based web service. WEBnmat is available at. Conclusion: WEBnmat v2.0 is an online tool offering unique capability for comparative NMA on multiple protein structures. Along with a convenient web interface, powerful computing resources, and several methods for mode analyses, WEBnmat facilitates the assessment of protein flexibility within protein families and superfamilies. These analyses can give a good view of how the structures move and how the flexibility is conserved over the different structures.", "date": "2014-12-30T00:00:00Z", "citationCount": 87, "authors": [ { "name": "Tiwari S.P." }, { "name": "Fuglebakk E." }, { "name": "Hollup S.M." }, { "name": "Skjaerven L." }, { "name": "Cragnolini T." }, { "name": "Grindhaug S.H." }, { "name": "Tekle K.M." }, { "name": "Reuter N." } ], "journal": "BMC Bioinformatics" } }, { "doi": "10.1186/1471-2105-6-52", "pmid": "15762993", "pmcid": "PMC1274249", "type": [ "Primary" ], "version": "1.0", "note": null, "metadata": { "title": "WEBnm@: A web application for normal mode analyses of proteins", "abstract": "Background: Normal mode analysis (NMA) has become the method of choice to investigate the slowest motions in macromolecular systems. NMA is especially useful for large biomolecular assemblies, such as transmembrane channels or virus capsids. NMA relies on the hypothesis that the vibrational normal modes having the lowest frequencies (also named soft modes) describe the largest movements in a protein and are the ones that are functionally relevant. Results: We developed a web-based server to perform normal modes calculations and different types of analyses. Starting from a structure file provided by the user in the PDB format, the server calculates the normal modes and subsequently offers the user a series of automated calculations; normalized squared atomic displacements, vector field representation and animation of the first six vibrational modes. Each analysis is performed independently from the others and results can be visualized using only a web browser. No additional plug-in or software is required. For users who would like to analyze the results with their favorite software, raw results can also be downloaded. The application is available on http://www.bioinfo.no/tools/normalmodes. We present here the underlying theory, the application architecture and an illustration of its features using a large transmembrane protein as an example. Conclusion: We built an efficient and modular web application for normal mode analysis of proteins. Non specialists can easily and rapidly evaluate the degree of flexibility of multi-domain protein assemblies and characterize the large amplitude movements of their domains. © 2005 Hollup et al; licensee BioMed Central Ltd.", "date": "2005-03-11T00:00:00Z", "citationCount": 105, "authors": [ { "name": "Hollup S.M." }, { "name": "Salensminde G." }, { "name": "Reuter N." } ], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": "Nathalie Reuter", "email": "Nathalie.Reuter@uib.no", "url": "http://www.cbu.uib.no/reuter/", "orcidid": "https://orcid.org/0000-0002-3649-7675", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Developer" ], "note": null }, { "name": "Sandhya P Tiwari", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0002-0747-3826", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Kidane M Tekle", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Tristan Cragnolini", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Svenn H Grindhaug", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Lars Skjærven", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Gisle Salensminde", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Edvin Fuglebakk", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Siv M Hollup", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Department of Molecular Biology, University of Bergen, Norway", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Computational Biology Unit, Department of Informatics, University of Bergen, Norway", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "UiB", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null } ], "owner": "UiB", "additionDate": "2016-03-17T13:51:10Z", "lastUpdate": "2026-03-11T08:56:55.566213Z", "editPermission": { "type": "group", "authors": [ "eca008", "korbinib" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Mapler", "description": "Mapler is a pipeline for assessing assembly quality in taxonomically rich metagenomes sequenced with HiFi reads. It incorporates state-of-the-art metrics and facilitates the comparison of assembly strategies.", "homepage": "https://github.com/Nimauric/Mapler", "biotoolsID": "mapler", "biotoolsCURIE": "biotools:mapler", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0310", "term": "Sequence assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0924", "term": "Sequence trace" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3180", "term": "Sequence assembly validation" }, { "uri": "http://edamontology.org/operation_3731", "term": "Sample comparison" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3914", "term": "Quality control report" }, "format": [ { "uri": "http://edamontology.org/format_3751", "term": "DSV" }, { "uri": "http://edamontology.org/format_2330", "term": "Textual format" }, { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3798", "term": "Read binning" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Workflow", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [], "language": [ "Bash", "Python" ], "license": "AGPL-3.0", "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/Nimauric/Mapler", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1093/BIOINFORMATICS/BTAF334", "pmid": "40478660", "pmcid": "PMC12205171", "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Nicolas Maurice", "email": "nicolas.maurice@inria.fr", "url": null, "orcidid": "https://orcid.org/0009-0009-9615-2765", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Claire Lemaitre", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0001-8675-170X", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Riccardo Vicedomini", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0002-7706-0998", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Clémence Frioux", "email": "clemence.frioux@inria.fr", "url": null, "orcidid": "https://orcid.org/0000-0003-2114-0697", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "nimauric", "additionDate": "2026-02-22T14:20:37.167505Z", "lastUpdate": "2026-03-10T15:44:03.311515Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "NetPhos", "description": "Neural network predictions for serine, threonine and tyrosine phosphorylation sites in eukaryotic proteins.", "homepage": "http://cbs.dtu.dk/services/NetPhos/", "biotoolsID": "netphos", "biotoolsCURIE": "biotools:netphos", "version": [ "2.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3092", "term": "Protein feature detection" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1277", "term": "Protein features" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] }, { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] } ], "note": "produces neural network predictions for serine, threonine and tyrosine phosphorylation sites in eukaryotic proteins", "cmd": null } ], "toolType": [ "Command-line tool", "Web application", "Web service" ], "topic": [ { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": "Other", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge (with restrictions)", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://cbs.dtu.dk/services", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://www.cbs.dtu.dk/services/NetPhos/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1006/jmbi.1999.3310", "pmid": "10600390", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Sequence and structure-based prediction of eukaryotic protein phosphorylation sites", "abstract": "Protein phosphorylation at serine, threonine or tyrosine residues affects a multitude of cellular signaling processes. How is specificity in substrate recognition and phosphorylation by protein kinases achieved? Here, we present an artificial neural network method that predicts phosphorylation sites in independent sequences with a sensitivity in the range from 69% to 96%. As an example, we predict novel phosphorylation sites in the p300/CBP protein that may regulate interaction with transcription factors and histone acetyltransferase activity. In addition, serine and threonine residues in p300/CBP that can be modified by O-linked glycosylation with N-acetylglucosamine are identified. Glycosylation may prevent phosphorplation at these sites, a mechanism named yin-yang regulation. The prediction server is available on the Internet at http://www.cbs.dtu.dk/services/NetPhos/or via e-mail to NetPhos@@@cbs.dtu.dk.", "date": "1999-12-17T00:00:00Z", "citationCount": 2373, "authors": [ { "name": "Blom N." }, { "name": "Gammeltoft S." }, { "name": "Brunak S." } ], "journal": "Journal of Molecular Biology" } } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": null, "url": "http://www.bioinformatics.dtu.dk/english/Service/Contact", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Nicolaj Blom", "email": "nblom@kt.dtu.dk", "url": null, "orcidid": "http://orcid.org/0000-0001-7787-7853", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "owner": "CBS", "additionDate": "2015-06-29T10:13:32Z", "lastUpdate": "2026-03-05T12:16:41.386128Z", "editPermission": { "type": "group", "authors": [ "I3raf", "Rubika" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BigSeqKit", "description": "The Next Generation Sequencing (NGS) raw data are stored in FASTA and FASTQ text-based file formats. Common operations on FASTA/Q files include searching, filtering, sampling, deduplication and sorting, among others. We can find several tools in the literature for FASTA/Q file manipulation but none of them are well fitted for large files of tens of GB (likely TBs in the near future) since mostly they are based on sequential processing. The exception is seqkit that allows some routines to use a few threads but, in any case, the scalability is very limited. To deal with this issue, we introduce BigSeqKit, a parallel toolkit to manipulate FASTA/Q files at scale with speed and scalability at its core. BigSeqKit takes advantage of an HPC-Big Data framework (IgnisHPC) to parallelize and optimize the commands included in seqkit. In this way, in most cases it is from tens to hundreds of times faster than other state-of-the-art tools such as seqkit, samtools and pyfastx.", "homepage": "https://github.com/citiususc/BigSeqKit", "biotoolsID": "bigseqkit", "biotoolsCURIE": "biotools:bigseqkit", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3192", "term": "Sequence trimming" }, { "uri": "http://edamontology.org/operation_0372", "term": "DNA transcription" }, { "uri": "http://edamontology.org/operation_0371", "term": "DNA translation" }, { "uri": "http://edamontology.org/operation_0233", "term": "Sequence conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Library", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "cesarpomar", "additionDate": "2023-05-22T15:10:32.141196Z", "lastUpdate": "2026-03-01T11:28:15.208151Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "PLAST", "description": "PLAST is a heuristical method to search for highest scoring local alignments between a DNA sequence query and a graphical pangenome. It takes as input a plain DNA sequence and a pangenome which may either be a set of (multiple) FASTA or FASTQ files or a sequence graph constructed by the tool Bifrost. It then outputs statistically meaningful (gapped) alignments in the style of the NCBI BLAST standard output format. Alignments are calculated based on a \"seed-and-extend approach\" while traversing the sequence graph. Biologically meaningful alignments are filtered by using an alignment statistic explicitly developed for sequence-to-graph alignments involving graphical pangenomes.", "homepage": "https://github.com/tischulz1/plast", "biotoolsID": "pangenome-blast", "biotoolsCURIE": "biotools:pangenome-blast", "version": [ "0.0.1-0.2.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0495", "term": "Local alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1211", "term": "unambiguous pure nucleotide" } ] }, { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_3975", "term": "GFA 1" }, { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1333", "term": "BLAST results" } ] } ], "note": "In order to search for alignments within the pangenome graph, \nA pangenome graph used to search for alignments consists of (1) a file in GFA format containing all sequences of the graph, (2) a binary file produced by the tool itself or the software \"Bifrost\" and (3) a program-specific index data structure in binary format.", "cmd": "PLAST Search -i pangenomeGraphCommonFilePrefix -q fileContainingOneQueryPerLine" }, { "operation": [ { "uri": "http://edamontology.org/operation_0227", "term": "Indexing" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0850", "term": "Sequence set" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0850", "term": "Sequence set" }, "format": [ { "uri": "http://edamontology.org/format_3975", "term": "GFA 1" }, { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] } ], "note": "If a pangenome graph already exists and only an index has to be built, FASTA/FASTQ files are not needed.", "cmd": "PLAST Build -i pangenomeGraphCommonFilePrefix -R *.fasta" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0797", "term": "Comparative genomics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Mac", "Windows" ], "language": [ "C++" ], "license": "GPL-3.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://gitlab.ub.uni-bielefeld.de/gi/plast", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/tischulz1/plast", "type": [ "Mirror" ], "note": null } ], "download": [], "documentation": [ { "url": "https://gitlab.ub.uni-bielefeld.de/gi/plast/-/blob/master/README.md", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btab077", "pmid": "33532821", "pmcid": "PMC8388040", "type": [ "Primary", "Method", "Benchmarking study" ], "version": null, "note": null, "metadata": { "title": "Detecting high-scoring local alignments in pangenome graphs", "abstract": "Motivation: Increasing amounts of individual genomes sequenced per species motivate the usage of pangenomic approaches. Pangenomes may be represented as graphical structures, e.g. compacted colored de Bruijn graphs, which offer a low memory usage and facilitate reference-free sequence comparisons. While sequence-to-graph mapping to graphical pangenomes has been studied for some time, no local alignment search tool in the vein of BLAST has been proposed yet. Results: We present a new heuristic method to find maximum scoring local alignments of a DNA query sequence to a pangenome represented as a compacted colored de Bruijn graph. Our approach additionally allows a comparison of similarity among sequences within the pangenome. We show that local alignment scores follow an exponential-tail distribution similar to BLAST scores, and we discuss how to estimate its parameters to separate local alignments representing sequence homology from spurious findings. An implementation of our method is presented, and its performance and usability are shown. Our approach scales sublinearly in running time and memory usage with respect to the number of genomes under consideration. This is an advantage over classical methods that do not make use of sequence similarity within the pangenome.", "date": "2021-08-15T00:00:00Z", "citationCount": 6, "authors": [ { "name": "Schulz T." }, { "name": "Wittler R." }, { "name": "Rahmann S." }, { "name": "Hach F." }, { "name": "Stoye J." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Bielefeld University", "email": null, "url": "https://www.uni-bielefeld.de/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Genome Informatics", "email": null, "url": "https://gi.cebitec.uni-bielefeld.de/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Tizian Schulz", "email": "plast-service@cebitec.uni-bielefeld.de", "url": null, "orcidid": "https://orcid.org/0000-0003-0744-7078", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "tizian", "additionDate": "2021-05-06T06:18:52Z", "lastUpdate": "2026-02-26T11:22:02.485629Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "cuffcompare", "description": "Compare assembled transcripts to a reference annotation and track Cufflinks transcripts across multiple experiments.", "homepage": "http://cole-trapnell-lab.github.io/cufflinks/", "biotoolsID": "cuffcompare", "biotoolsCURIE": "biotools:cuffcompare", "version": [ "2.2.1.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0492", "term": "Multiple sequence alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_1975", "term": "GFF3" }, { "uri": "http://edamontology.org/format_2306", "term": "GTF" } ] }, { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_2306", "term": "GTF" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "C++" ], "license": null, "collectionID": [ "Cufflinks", "galaxyPasteur" ], "maturity": "Mature", "cost": null, "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://galaxy.pasteur.fr/tool_runner?tool_id=toolshed.pasteur.fr/repos/fmareuil/cuffcompare/cuffcompare/2.2.1.0", "type": [ "Galaxy service" ], "note": null } ], "download": [], "documentation": [ { "url": "http://cole-trapnell-lab.github.io/cufflinks/cuffcompare/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1038/nbt.1621", "pmid": "20436464", "pmcid": "PMC3146043", "type": [ "Primary" ], "version": null, "note": null, "metadata": null }, { "doi": "10.1093/nar/gkw343", "pmid": "27137889", "pmcid": "PMC4987906", "type": [ "Other" ], "version": null, "note": null, "metadata": null }, { "doi": "10.7490/f1000research.1114334.1", "pmid": null, "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Galaxy Support Team", "email": "galaxy@pasteur.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "hmenager", "additionDate": "2016-12-19T14:29:34Z", "lastUpdate": "2026-02-26T11:14:58.790920Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "fur", "description": "The program fur takes as input a set of target genome sequences and a set of related genome sequences, the neighbors. It returns the sequence regions common to all targets that are absent form the neighbors. Such regions can be used as candidate genetic markers.", "homepage": "https://github.com/evolbioinf/fur", "biotoolsID": "fur", "biotoolsCURIE": "biotools:fur", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2998", "term": "Nucleic acid comparison" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2887", "term": "Nucleic acid sequence record" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_3344", "term": "Biomedical science" } ], "operatingSystem": [], "language": [ "Go" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "bebatut", "additionDate": "2026-02-16T08:19:06.415244Z", "lastUpdate": "2026-02-16T08:19:06.417279Z", "editPermission": { "type": "public", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "metabuli", "description": "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid", "homepage": "https://metabuli.steineggerlab.com", "biotoolsID": "metabuli", "biotoolsCURIE": "biotools:metabuli", "version": [], "otherID": [], "relation": [ { "biotoolsID": "mmseqs2", "type": "uses" }, { "biotoolsID": "gtdb", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" } ], "operatingSystem": [ "Windows", "Mac", "Linux" ], "language": [ "C++" ], "license": "GPL-3.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/steineggerlab/Metabuli/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/steineggerlab/Metabuli", "type": [ "Repository" ], "note": "github repository" } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1038/s41592-024-02273-y", "pmid": "38769467", "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [], "owner": "milot-mirdita", "additionDate": "2023-06-07T03:22:25.847061Z", "lastUpdate": "2026-02-12T14:21:25.897853Z", "editPermission": { "type": "group", "authors": [ "vashokan" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "sourmash", "description": "Compute and compare MinHash signatures for DNA data sets.", "homepage": "https://sourmash.readthedocs.io/en/latest/", "biotoolsID": "sourmash", "biotoolsCURIE": "biotools:sourmash", "version": [ "2.0a8" ], "otherID": [], "relation": [ { "biotoolsID": "gtdb", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0346", "term": "Sequence similarity search" }, { "uri": "http://edamontology.org/operation_0289", "term": "Sequence distance matrix generation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2975", "term": "Nucleic acid sequence (raw)" }, "format": [ { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" } ] } ], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3751", "term": "DSV" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Library", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" }, { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [], "license": "BSD-3-Clause", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/sourmash-bio/sourmash", "type": [ "Repository" ], "note": "github repository" } ], "download": [], "documentation": [], "publication": [ { "doi": "10.12688/f1000research.19675.1", "pmid": "31508216", "pmcid": "PMC6720031", "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "C. Titus Brown", "email": "ctbrown@ucdavis.edu", "url": "http://github.com/dib-lab/sourmash/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "diblab", "additionDate": "2018-06-27T22:03:41Z", "lastUpdate": "2026-02-12T14:14:38.842520Z", "editPermission": { "type": "group", "authors": [ "luizirber", "vashokan" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Bakta", "description": "Rapid & standardized annotation of bacterial genomes, MAGs & plasmids", "homepage": "https://github.com/oschwengers/bakta", "biotoolsID": "bakta", "biotoolsCURIE": "biotools:bakta", "version": [ "v1.12.0" ], "otherID": [], "relation": [ { "biotoolsID": "diamond", "type": "uses" }, { "biotoolsID": "hmmer3", "type": "uses" }, { "biotoolsID": "infernal", "type": "uses" }, { "biotoolsID": "trnascan-se", "type": "uses" }, { "biotoolsID": "blast", "type": "uses" }, { "biotoolsID": "aragorn", "type": "uses" }, { "biotoolsID": "pilercr", "type": "uses" }, { "biotoolsID": "deepsig", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0362", "term": "Genome annotation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0925", "term": "Sequence assembly" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_2914", "term": "Sequence features metadata" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2012", "term": "Sequence coordinates" }, "format": [ { "uri": "http://edamontology.org/format_1975", "term": "GFF3" } ] }, { "data": { "uri": "http://edamontology.org/data_2886", "term": "Protein sequence record" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1364", "term": "Hidden Markov model" }, "format": [ { "uri": "http://edamontology.org/format_3329", "term": "HMMER3" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1270", "term": "Feature table" }, "format": [ { "uri": "http://edamontology.org/format_1936", "term": "GenBank format" }, { "uri": "http://edamontology.org/format_1975", "term": "GFF3" }, { "uri": "http://edamontology.org/format_3464", "term": "JSON" }, { "uri": "http://edamontology.org/format_1927", "term": "EMBL format" }, { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2886", "term": "Protein sequence record" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_2887", "term": "Nucleic acid sequence record" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [ { "uri": "http://edamontology.org/format_3604", "term": "SVG" }, { "uri": "http://edamontology.org/format_3603", "term": "PNG" } ] }, { "data": { "uri": "http://edamontology.org/data_1772", "term": "Score" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": "bakta --db <db-path> --prefix <prefix> --output <output-path> genome.fasta" } ], "toolType": [ "Web application", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Tools" ], "elixirNode": [ "Germany" ], "elixirCommunity": [], "link": [ { "url": "https://github.com/oschwengers/bakta", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/oschwengers/bakta/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://bioconda.github.io/recipes/bakta/README.html", "type": [ "Other" ], "note": null }, { "url": "https://bakta.computational.bio", "type": [ "Service" ], "note": null } ], "download": [ { "url": "https://zenodo.org/records/14916843", "type": "Other", "note": "Mandatory annotation database", "version": "v6.0" } ], "documentation": [ { "url": "https://github.com/oschwengers/bakta/blob/main/README.md", "type": [ "General" ], "note": null }, { "url": "https://github.com/oschwengers/bakta/blob/main/CONTRIBUTION.md", "type": [ "Contributions policy" ], "note": null }, { "url": "https://github.com/oschwengers/bakta/blob/main/CODE_OF_CONDUCT.md", "type": [ "Code of conduct" ], "note": null }, { "url": "https://bakta.readthedocs.io/", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1099/mgen.0.000685", "pmid": "34739369", "pmcid": "PMC8743544", "type": [ "Primary" ], "version": "1.1", "note": null, "metadata": null }, { "doi": "10.1093/nar/gkaf335", "pmid": "40271661", "pmcid": "PMC12230652", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Oliver Schwengers", "email": "oliver.schwengers@cb.jlug.de", "url": "https://github.com/oschwengers", "orcidid": "https://orcid.org/0000-0003-4216-2721", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Developer", "Maintainer" ], "note": null }, { "name": "Justus Liebig University Giessen", "email": null, "url": "https://www.uni-giessen.de", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null } ], "owner": "oschwengers", "additionDate": "2021-05-08T17:25:21Z", "lastUpdate": "2026-01-29T12:11:19.042627Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-CZ", "bebatut" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "MetaPhlAn", "description": "Computational tool for profiling the composition of microbial communities from metagenomic shotgun sequencing data.", "homepage": "http://segatalab.cibio.unitn.it/tools/metaphlan/index.html", "biotoolsID": "metaphlan", "biotoolsCURIE": "biotools:metaphlan", "version": [], "otherID": [], "relation": [ { "biotoolsID": "gtdb", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_2573", "term": "SAM" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3751", "term": "DSV" } ] } ], "note": null, "cmd": "metaphlan <fastq_input> --input_type fastq -o <output>" }, { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3751", "term": "DSV" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3751", "term": "DSV" } ] } ], "note": "Convert SGB-based profile to GTDB taxonomy", "cmd": "sgb_to_gtdb_profile.py -i <metaphlan_output> -o <gtdb_metaphlan_output>" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_0194", "term": "Phylogenomics" } ], "operatingSystem": [ "Linux", "Mac", "Windows" ], "language": [ "Python" ], "license": "MIT", "collectionID": [ "Animal and Crop Genomics" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://github.com/biobakery/MetaPhlAn", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1038/nmeth.2066", "pmid": "22688413", "pmcid": "PMC3443552", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": null, "email": null, "url": "https://groups.google.com/forum/#!forum/metaphlan-users", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "admin", "additionDate": "2017-08-20T15:57:59Z", "lastUpdate": "2026-01-28T10:35:56.506019Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics", "ELIXIR-CZ", "bebatut", "vashokan" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "kraken2", "description": "Kraken 2 is the newest version of Kraken, a taxonomic classification system using exact k-mer matches to achieve high accuracy and fast classification speeds. This classifier matches each k-mer within a query sequence to the lowest common ancestor (LCA) of all genomes containing the given k-mer. The k-mer assignments inform the classification algorithm.\nAny assumption that Kraken’s raw read assignments can be directly translated into species or strain-level abundance estimates is flawed. Bracken (Bayesian Reestimation of Abundance after Classification with KrakEN), estimates species abundances in metagenomics samples by probabilistically re-distributing reads in the taxonomic tree. (Lu, Jennifer et al. “Bracken: estimating species abundance in metagenomics data.”)", "homepage": "https://github.com/DerrickWood/kraken2", "biotoolsID": "kraken2", "biotoolsCURIE": "biotools:kraken2", "version": [ "2.0.8-beta" ], "otherID": [], "relation": [ { "biotoolsID": "kraken", "type": "isNewVersionOf" }, { "biotoolsID": "bracken", "type": "usedBy" }, { "biotoolsID": "gtdb", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": "`kraken2 --db <kraken2_database> <input.fastq>`" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" }, { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" }, { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" } ], "operatingSystem": [], "language": [ "Perl", "C++" ], "license": "MIT", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/DerrickWood/kraken2", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/DerrickWood/kraken2/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "https://github.com/DerrickWood/kraken2/archive/v2.0.8-beta.tar.gz", "type": "Source code", "note": null, "version": "2.0.8-beta" } ], "documentation": [ { "url": "https://github.com/DerrickWood/kraken2/wiki/Manual", "type": [ "User manual" ], "note": null }, { "url": "https://benlangmead.github.io/aws-indexes/k2", "type": [ "User manual" ], "note": "Links to multiple Kraken 2 and bracken databases and indexes" } ], "publication": [ { "doi": "10.1101/762302", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Derrick E. Wood", "email": null, "url": null, "orcidid": "http://orcid.org/0000-0002-7429-1854", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Jennifer Lu", "email": null, "url": null, "orcidid": "http://orcid.org/0000-0001-9167-2002", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Ben Langmead", "email": "langmea@cs.jhu.edu", "url": null, "orcidid": "http://orcid.org/0000-0003-2437-1976", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "anand-anshu", "additionDate": "2019-09-13T12:51:16Z", "lastUpdate": "2026-01-28T10:34:30.102754Z", "editPermission": { "type": "group", "authors": [ "vashokan", "Keiler_Collier" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "SingleM", "description": "Novelty-inclusive microbial community profiling of shotgun metagenomes", "homepage": "https://wwood.github.io/singlem/", "biotoolsID": "singlem", "biotoolsCURIE": "biotools:singlem", "version": [], "otherID": [], "relation": [ { "biotoolsID": "gtdb", "type": "uses" }, { "biotoolsID": "globdb", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://wwood.github.io/singlem/", "type": [ "General", "Command-line options", "Installation instructions" ], "note": null } ], "publication": [ { "doi": "10.1101/2024.01.30.578060", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [], "owner": "benjwoodcroft", "additionDate": "2024-03-23T21:36:23.370696Z", "lastUpdate": "2026-01-28T10:30:54.345544Z", "editPermission": { "type": "group", "authors": [ "vashokan" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "FastOMA", "description": "FastOMA is a scalable software package to infer orthology relationship.", "homepage": "https://github.com/dessimozlab/FastOMA", "biotoolsID": "fastoma", "biotoolsCURIE": "biotools:fastoma", "version": [ "0.5.1" ], "otherID": [], "relation": [ { "biotoolsID": "omamer", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3947", "term": "Phylogenetic tree reconciliation" }, { "uri": "http://edamontology.org/operation_2479", "term": "Protein sequence analysis" }, { "uri": "http://edamontology.org/operation_3209", "term": "Genome comparison" }, { "uri": "http://edamontology.org/operation_0291", "term": "Sequence clustering" }, { "uri": "http://edamontology.org/operation_0540", "term": "Phylogenetic inference (from molecular sequences)" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2886", "term": "Protein sequence record" }, "format": [ { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" } ] }, { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_1910", "term": "newick" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1245", "term": "Sequence cluster (protein)" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3148", "term": "Gene family report" }, "format": [ { "uri": "http://edamontology.org/format_3850", "term": "OrthoXML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0797", "term": "Comparative genomics" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "Python" ], "license": "MPL-2.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "Switzerland" ], "elixirCommunity": [], "link": [ { "url": "https://github.com/dessimozlab/FastOMA", "type": [ "Repository" ], "note": null }, { "url": "https://omabrowser.org", "type": [ "Service" ], "note": null } ], "download": [], "documentation": [ { "url": "https://github.com/DessimozLab/FastOMA/blob/main/README.md", "type": [ "Quick start guide" ], "note": null } ], "publication": [ { "doi": "10.1038/s41592-024-02552-8", "pmid": "39753922", "pmcid": "PMC11810774", "type": [], "version": null, "note": null, "metadata": { "title": "Orthology inference at scale with FastOMA", "abstract": "", "date": "2025-02-01T00:00:00Z", "citationCount": 8, "authors": [], "journal": "Nature Methods" } } ], "credit": [], "owner": "adrian.altenhoff", "additionDate": "2025-12-22T13:40:13.527477Z", "lastUpdate": "2025-12-22T13:46:09.227488Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "globalamfungi", "description": "The GlobalAMFungi Database is an open-access, global repository of arbuscular mycorrhizal (AM) fungal occurrence data compiled from high-throughput sequencing studies. It aggregates millions of DNA sequence observations of AM fungi from thousands of geographically referenced environmental samples, together with rich metadata on sampling location and environmental context, to map the global distribution and diversity of these key plant symbionts. The resource is designed to be community-driven and FAIR (Findable, Accessible, Interoperable, Reusable), supporting research into AM fungal ecology, biogeography, and how environmental factors shape their diversity.", "homepage": "https://globalamfungi.com/", "biotoolsID": "globalamfungi", "biotoolsCURIE": "biotools:globalamfungi", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3431", "term": "Data deposition" }, { "uri": "http://edamontology.org/operation_0226", "term": "Annotation" }, { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0857", "term": "Sequence search results" }, "format": [ { "uri": "http://edamontology.org/format_2310", "term": "FASTA-HTML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" }, { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" }, { "uri": "http://edamontology.org/topic_3810", "term": "Agricultural science" } ], "operatingSystem": [], "language": [ "R" ], "license": "CC-BY-4.0", "collectionID": [ "ELIXIR-CZ", "Czech Republic" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Data" ], "elixirNode": [ "Czech Republic" ], "elixirCommunity": [ "Plant Sciences" ], "link": [ { "url": "https://globalamfungi.com/", "type": [ "Helpdesk", "Repository", "Service" ], "note": null } ], "download": [], "documentation": [ { "url": "https://globalamfungi.com/", "type": [ "User manual", "Citation instructions", "Quick start guide", "Contributions policy", "General" ], "note": null } ], "publication": [ { "doi": "10.1111/nph.19283", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": null, "abstract": null, "date": null, "citationCount": 0, "authors": [], "journal": null } } ], "credit": [ { "name": "Tomas Vetrovsky", "email": "vetrovsky@biomed.cas.cz", "url": null, "orcidid": "https://orcid.org/0000-0002-0831-486X", "gridid": null, "rorid": "02p1jz666", "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Developer", "Contributor" ], "note": null }, { "name": "ELIXIR-CZ", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Consortium", "typeRole": [], "note": null } ], "owner": "TomasVetrovsky", "additionDate": "2025-12-16T11:00:25.334832Z", "lastUpdate": "2025-12-16T11:00:25.337448Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ASAFind", "description": "ASAFind is a software that predicts the intracellular location of proteins in cells with four membrane-bound complex plastids of red algal origin. \nThese plastids evolved via eukaryote-eukaryote endosymbiosis and for example can be found in diatoms and cryptophytes. ASAFind uses protein sequence data and external predictions of signal peptides (by the tools SignalP and TargetP), and predicts plastid proteins, and proteins that are targeted to the periplastidic compartment from these data; optionally, a graphical output can generated.", "homepage": "https://asafind.jcu.cz/", "biotoolsID": "asafind", "biotoolsCURIE": "biotools:asafind", "version": [ "2.0" ], "otherID": [], "relation": [ { "biotoolsID": "signalp", "type": "uses" }, { "biotoolsID": "targetp", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2489", "term": "Subcellular localisation prediction" }, { "uri": "http://edamontology.org/operation_0239", "term": "Sequence motif recognition" }, { "uri": "http://edamontology.org/operation_0422", "term": "Protein cleavage site prediction" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2886", "term": "Protein sequence record" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1270", "term": "Feature table" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1277", "term": "Protein features" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Script", "Command-line tool", "Web service" ], "topic": [ { "uri": "http://edamontology.org/topic_2229", "term": "Cell biology" }, { "uri": "http://edamontology.org/topic_0078", "term": "Proteins" }, { "uri": "http://edamontology.org/topic_0780", "term": "Plant biology" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "Python" ], "license": "CC-BY-SA-4.0", "collectionID": [ "ELIXIR-CZ", "Czech Republic" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Tools" ], "elixirNode": [ "Czech Republic" ], "elixirCommunity": [ "Plant Sciences", "Marine Metagenomics", "Microbial Biotechnology" ], "link": [ { "url": "https://asafind.jcu.cz", "type": [ "Service" ], "note": "Web Service" }, { "url": "https://github.com/ASAFind/ASAFind-2", "type": [ "Repository" ], "note": "Information and source code, for local installation or development" } ], "download": [ { "url": "https://asafind.jcu.cz/download-page/", "type": "Downloads page", "note": "Download page on web-service, links to repository", "version": "2.0" } ], "documentation": [ { "url": "https://asafind.jcu.cz/download-page/", "type": [ "Installation instructions" ], "note": null } ], "publication": [ { "doi": "10.1111/tpj.70138", "pmid": "40464854", "pmcid": "PMC12136025", "type": [ "Primary" ], "version": "2.0", "note": "Publication of the current version of ASAFind (2.0)", "metadata": { "title": "ASAFind 2.0: multi-class protein targeting prediction for diatoms and algae with complex plastids", "abstract": "", "date": "2025-06-01T00:00:00Z", "citationCount": 0, "authors": [], "journal": "Plant Journal" } }, { "doi": "10.1111/tpj.12734", "pmid": "25438865", "pmcid": "PMC4329603", "type": [ "Other" ], "version": "1.0", "note": "Publication of the first version of ASAFind", "metadata": { "title": "Plastid proteome prediction for diatoms and other algae with secondary plastids of the red lineage", "abstract": "", "date": "2015-02-01T00:00:00Z", "citationCount": 138, "authors": [], "journal": "Plant Journal" } }, { "doi": "10.48550/arXiv.2303.02509", "pmid": null, "pmcid": null, "type": [ "Benchmarking study" ], "version": "1.0", "note": "Benchmarking of the performance of the first version of ASAFind", "metadata": null } ], "credit": [ { "name": "Marta Vohnoutová", "email": "mvohnoutova@jcu.cz", "url": "https://www.jcu.cz/cz/univerzita/lide/clovek?identita=Vohnoutova_Marta_61699", "orcidid": "https://orcid.org/0000-0002-8915-8626", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Contributor", "Developer", "Maintainer" ], "note": null }, { "name": "Ansgar Gruber", "email": "agruber@prf.jcu.cz", "url": "https://www.jcu.cz/cz/univerzita/lide/clovek?identita=Gruber_Ansgar_118401", "orcidid": "https://orcid.org/0000-0002-5876-4391", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Developer", "Documentor" ], "note": null } ], "owner": "martavohnoutova", "additionDate": "2025-12-15T14:17:14.627791Z", "lastUpdate": "2025-12-15T17:36:43.189214Z", "editPermission": { "type": "group", "authors": [ "agruber" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "metagWGS", "description": "metagWGS is a workflow dedicated to the analysis of metagenomic data. It allows assembly, taxonomic annotation, and functional annotation of predicted genes. Since release 2.3, binning step with the possibility of cross-alignment is included. It has been developed in collaboration with several CATI BIOS4biol agents. Funded by Antiselfish Project (Labex Ecofect), ExpoMicoPig project (France Futur elevage) and SeqOccIn project (CPER - Occitanie Toulouse / FEDER), ATB_Biofilm funded by PNREST Anses, France genomique (ANR-10-INBS-09-08) and Resalab Ouest.", "homepage": "https://forgemia.inra.fr/genotoul-bioinfo/metagwgs", "biotoolsID": "metagwgs", "biotoolsCURIE": "biotools:metagwgs", "version": [ "2.3", "2.5.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_1915", "term": "Format" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3672", "term": "Gene functional annotation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3917", "term": "Count matrix" }, "format": [ { "uri": "http://edamontology.org/format_1915", "term": "Format" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0524", "term": "De-novo assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Workflow" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "France" ], "elixirCommunity": [], "link": [ { "url": "https://forge.inrae.fr/genotoul-bioinfo/metagwgs", "type": [ "Repository" ], "note": "See documentation, source code and functionnal test documentation." } ], "download": [ { "url": "https://forgemia.inra.fr/genotoul-bioinfo/metagwgs-test-datasets", "type": "Test data", "note": "Functional tests data and script", "version": null } ], "documentation": [ { "url": "https://genotoul-bioinfo.pages-forge.inrae.fr/metagwgs/master/index.html", "type": [ "User manual" ], "note": "We provide up to date installation documentation, usage documentation, output description and functionnal test datasets and procedure." } ], "publication": [], "credit": [ { "name": "Claire Hoede", "email": "claire.hoede@inrae.fr", "url": null, "orcidid": "https://orcid.org/0000-0001-5054-7731", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "GenoToul bioinformatics facility", "email": null, "url": "http://bioinfo.genotoul.fr/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Division", "typeRole": [ "Provider" ], "note": null } ], "owner": "choede", "additionDate": "2022-04-19T09:32:41.303637Z", "lastUpdate": "2025-12-11T14:51:44.804907Z", "editPermission": { "type": "group", "authors": [ "pbordron" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Jalview", "description": "Jalview is a free cross-platform program for multiple sequence alignment editing, visualisation and analysis. Use it to align, view and edit sequence alignments, analyse them with phylogenetic trees and principal components analysis (PCA) plots and explore molecular structures and annotation.", "homepage": "https://www.jalview.org/", "biotoolsID": "Jalview", "biotoolsCURIE": "biotools:Jalview", "version": [ "2.11.5.1" ], "otherID": [], "relation": [ { "biotoolsID": "jabaws", "type": "uses" }, { "biotoolsID": "chimera", "type": "uses" }, { "biotoolsID": "chimerax", "type": "uses" }, { "biotoolsID": "pymol", "type": "uses" }, { "biotoolsID": "bioconda", "type": "includedIn" }, { "biotoolsID": "3d-beacons", "type": "uses" }, { "biotoolsID": "uniprot", "type": "uses" }, { "biotoolsID": "pfam", "type": "uses" }, { "biotoolsID": "ensembl", "type": "uses" }, { "biotoolsID": "pdb", "type": "uses" }, { "biotoolsID": "rfam", "type": "uses" }, { "biotoolsID": "3d-beacons", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3081", "term": "Sequence alignment editing" }, { "uri": "http://edamontology.org/operation_0324", "term": "Phylogenetic tree analysis" }, { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1948", "term": "nbrf/pir" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" }, { "uri": "http://edamontology.org/format_3015", "term": "Pileup" }, { "uri": "http://edamontology.org/format_1938", "term": "GFF2-seq" }, { "uri": "http://edamontology.org/format_3313", "term": "BLC" }, { "uri": "http://edamontology.org/format_3311", "term": "RNAML" }, { "uri": "http://edamontology.org/format_1915", "term": "Format" }, { "uri": "http://edamontology.org/format_3774", "term": "BioJSON (Jalview)" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" }, { "uri": "http://edamontology.org/format_1477", "term": "mmCIF" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" }, { "uri": "http://edamontology.org/format_3016", "term": "VCF" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1939", "term": "GFF3-seq" }, { "uri": "http://edamontology.org/format_1947", "term": "GCG MSF" } ] }, { "data": { "uri": "http://edamontology.org/data_0886", "term": "Structure alignment" }, "format": [ { "uri": "http://edamontology.org/format_1476", "term": "PDB" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1948", "term": "nbrf/pir" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_3015", "term": "Pileup" }, { "uri": "http://edamontology.org/format_3313", "term": "BLC" }, { "uri": "http://edamontology.org/format_3774", "term": "BioJSON (Jalview)" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" }, { "uri": "http://edamontology.org/format_3464", "term": "JSON" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1947", "term": "GCG MSF" } ] }, { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [ { "uri": "http://edamontology.org/format_3466", "term": "EPS" }, { "uri": "http://edamontology.org/format_1915", "term": "Format" }, { "uri": "http://edamontology.org/format_2331", "term": "HTML" }, { "uri": "http://edamontology.org/format_3604", "term": "SVG" }, { "uri": "http://edamontology.org/format_3603", "term": "PNG" } ] } ], "note": "Other Input formats:\nAMSA (.amsa);\nJnetFile (.concise, .jnet);\nPFAM (.pfam);\nSubstitution matrix (.matrix);\nJalview Project File (.jvp);\nJalview Feature File (.features, .jvfeatures);\nJalview Annotations File (.annotations, .jvannotations);\nPredicted Aligned Error (PAE) Matrix File (.json)\n...\nOther Output formats:\nPFAM (.pfam);\nBioJS (.biojs) (interactive HTML/Javascript);\nJalview Project File (.jvp);", "cmd": null } ], "toolType": [ "Desktop application", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0092", "term": "Data visualisation" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [], "license": "GPL-3.0", "collectionID": [ "ELIXIR-UK" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Tools", "Interoperability" ], "elixirNode": [ "UK" ], "elixirCommunity": [], "link": [ { "url": "https://discourse.jalview.org/", "type": [ "Discussion forum" ], "note": null }, { "url": "https://issues.jalview.org/", "type": [ "Issue tracker" ], "note": null }, { "url": "https://www.jalview.org/development/jalview_develop/", "type": [ "Other" ], "note": "Latest development version" }, { "url": "https://gitlab.jalview.org/jalview/jalview.git", "type": [ "Repository" ], "note": null }, { "url": "https://twitter.com/Jalview", "type": [ "Social media" ], "note": "Twitter feed" }, { "url": "https://www.youtube.com/channel/UCIjpnvZB770yz7ftbrJ0tfw", "type": [ "Social media" ], "note": "YouTube training videos" }, { "url": "https://www.linkedin.com/company/104771886/", "type": [ "Social media" ], "note": null } ], "download": [ { "url": "https://www.jalview.org/download", "type": "Downloads page", "note": null, "version": null }, { "url": "https://www.jalview.org/download/source/", "type": "Source code", "note": null, "version": null }, { "url": "https://www.jalview.org/download/?os=all", "type": "Binaries", "note": "Binaries for all platforms", "version": null }, { "url": "https://www.jalview.org/favicon.svg", "type": "Icon", "note": null, "version": null }, { "url": "https://www.jalview.org/download/other/jar/", "type": "Binaries", "note": "Executable JAR file", "version": null } ], "documentation": [ { "url": "https://www.jalview.org/about/citation", "type": [ "Citation instructions" ], "note": null }, { "url": "https://www.jalview.org/training/", "type": [ "Training material" ], "note": "Hands-on exercises, Training courses and Training videos" }, { "url": "https://www.jalview.org/help/faq", "type": [ "FAQ" ], "note": null }, { "url": "https://www.jalview.org/help/documentation/", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btp033", "pmid": "19151095", "pmcid": "PMC2672624", "type": [], "version": null, "note": null, "metadata": { "title": "Jalview Version 2-A multiple sequence alignment editor and analysis workbench", "abstract": "", "date": "2009-05-07T00:00:00Z", "citationCount": 7717, "authors": [], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Jim Procter", "email": null, "url": "http://www.lifesci.dundee.ac.uk/people/jim-procter", "orcidid": "https://orcid.org/0000-0002-7865-7382", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Geoff Barton", "email": null, "url": "https://www.lifesci.dundee.ac.uk/people/geoff-barton", "orcidid": "https://orcid.org/0000-0002-9014-5355", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "owner": "ben_s", "additionDate": "2019-02-13T17:01:40Z", "lastUpdate": "2025-12-11T14:16:30.074724Z", "editPermission": { "type": "group", "authors": [ "ben_s", "jimprocter" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "emapper2gbk", "description": "creation of genbank files from Eggnog-mapper annotation outputs", "homepage": "https://github.com/AuReMe/emapper2gbk", "biotoolsID": "emapper2gbk", "biotoolsCURIE": "biotools:emapper2gbk", "version": [ "0.3.2" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0925", "term": "Sequence assembly" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1233", "term": "Sequence set (protein)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_2012", "term": "Sequence coordinates" }, "format": [ { "uri": "http://edamontology.org/format_2305", "term": "GFF" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1270", "term": "Feature table" }, "format": [ { "uri": "http://edamontology.org/format_2205", "term": "GenBank-like format (text)" } ] } ], "note": "Genomic -single mode", "cmd": "genomes -fn genome.fna -fp proteome.faa -gff genome.gff -n \"Escherichia coli\"" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_4011", "term": "Data rescue" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": "LGPL-3.0", "collectionID": [ "AuReMe" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/AuReMe/emapper2gbk", "type": [ "Repository" ], "note": null }, { "url": "https://pypi.org/project/emapper2gbk/", "type": [ "Software catalogue" ], "note": "Access to Python library" } ], "download": [ { "url": "https://github.com/AuReMe/emapper2gbk.git", "type": "Source code", "note": null, "version": "0.3.2" }, { "url": "https://pypi.org/project/emapper2gbk/#files", "type": "Software package", "note": null, "version": "0.3.2" } ], "documentation": [ { "url": "https://github.com/AuReMe/emapper2gbk", "type": [ "Installation instructions", "User manual" ], "note": null } ], "publication": [], "credit": [ { "name": "Arnaud", "email": null, "url": "https://github.com/ArnaudBelcour", "orcidid": "https://orcid.org/0000-0003-1170-0785", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "Noe_Robert", "additionDate": "2025-12-10T13:18:28.703003Z", "lastUpdate": "2025-12-10T16:49:05.332576Z", "editPermission": { "type": "group", "authors": [ "jgot" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "South Green Genome Hubs", "description": "The South Green Genome Hub is a suite of crop-specific community portals to manage genomic datasets with focus on tropical and Mediterranean plants. Currently developed on Banana, Cacao, Coffee, Grass, Rice, Vanilla, Citrus and Sugarcane, genome hubs provide access to multiple datasets (e.g. assemblies, gene product information, metabolic pathways, gene families, transcriptomics and genetic markers).", "homepage": "https://banana-genome-hub.southgreen.fr/", "biotoolsID": "South_Green_Genome_Hubs", "biotoolsCURIE": "biotools:South_Green_Genome_Hubs", "version": [], "otherID": [], "relation": [ { "biotoolsID": "tripal", "type": "uses" }, { "biotoolsID": "banana_genome_hub", "type": "includes" }, { "biotoolsID": "coffee_genome_hub", "type": "includes" }, { "biotoolsID": "cocoa_genome_hub", "type": "includes" }, { "biotoolsID": "rice_genome_hub", "type": "includes" }, { "biotoolsID": "sugarcane_genome_hub", "type": "includes" }, { "biotoolsID": "southgreen", "type": "includedIn" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3208", "term": "Genome visualisation" }, { "uri": "http://edamontology.org/operation_0338", "term": "Sequence database search" }, { "uri": "http://edamontology.org/operation_2403", "term": "Sequence analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0968", "term": "Keyword" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3810", "term": "Agricultural science" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_3308", "term": "Transcriptomics" }, { "uri": "http://edamontology.org/topic_0797", "term": "Comparative genomics" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" } ], "operatingSystem": [], "language": [ "JavaScript", "PHP" ], "license": "GPL-2.0", "collectionID": [ "Genome Hub" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [ "Data", "Tools" ], "elixirNode": [ "France" ], "elixirCommunity": [], "link": [ { "url": "https://github.com/SouthGreenPlatform/genomehubs", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [ { "url": "https://banana-genome-hub.southgreen.fr/content/term-service", "type": [ "Terms of use" ], "note": null } ], "publication": [ { "doi": "10.1093/database/bat035", "pmid": "23707967", "pmcid": "PMC3662865", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The banana genome hub", "abstract": "", "date": "2013-12-01T00:00:00Z", "citationCount": 150, "authors": [], "journal": "Database" } }, { "doi": "10.1093/nar/gku1108", "pmid": "25392413", "pmcid": "PMC4383925", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The coffee genome hub: A resource for coffee genomes", "abstract": "", "date": "2015-01-28T00:00:00Z", "citationCount": 52, "authors": [], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/hr/uhac221", "pmid": "36479579", "pmcid": "PMC9720444", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The banana genome hub: a community database for genomics in the Musaceae", "abstract": "", "date": "2022-01-01T00:00:00Z", "citationCount": 29, "authors": [], "journal": "Horticulture Research" } }, { "doi": "10.1016/j.xplc.2022.100330", "pmid": "35617961", "pmcid": "PMC9482989", "type": [ "Usage" ], "version": null, "note": null, "metadata": { "title": "A chromosome-level, haplotype-phased Vanilla planifolia genome highlights the challenge of partial endoreplication for accurate whole-genome assembly", "abstract": "", "date": "2022-09-12T00:00:00Z", "citationCount": 26, "authors": [], "journal": "Plant Communications" } } ], "credit": [ { "name": "Gaetan Droc", "email": "droc@cirad.fr", "url": null, "orcidid": "https://orcid.org/0000-0003-1849-1269", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Developer", "Documentor", "Provider", "Support" ], "note": null }, { "name": "Alexis Dereeper", "email": "alexis.dereeper@ird.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Mathieu Rouard", "email": "m.rouard@cgiar.org", "url": null, "orcidid": "https://orcid.org/0000-0003-1849-1269", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Primary contact", "Maintainer", "Support" ], "note": null }, { "name": "Valentin Guignon", "email": "v.guignon@cgiar.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Chrisitine Tranchant", "email": "christine.tranchant@ird.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Stéphanie Bocs", "email": "stephanie.sidibe-bocs@cirad.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "owner": "mrouard", "additionDate": "2020-02-26T09:24:43Z", "lastUpdate": "2025-11-27T09:14:28.500250Z", "editPermission": { "type": "group", "authors": [ "gdroc", "Droc" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "trimAl", "description": "Tool for the automated removal of spurious sequences or poorly aligned regions from a multiple sequence alignment.", "homepage": "https://trimal.readthedocs.io", "biotoolsID": "trimal", "biotoolsCURIE": "biotools:trimal", "version": [ "1.5.1", "2.0-RC" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0492", "term": "Multiple sequence alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1916", "term": "Alignment" }, "format": [ { "uri": "http://edamontology.org/format_1998", "term": "phylipnon" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" } ] }, { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" } ], "operatingSystem": [ "Mac", "Windows", "Linux" ], "language": [ "C++" ], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/inab/trimal", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://github.com/inab/trimal", "type": "Source code", "note": null, "version": "1.5.1" }, { "url": "https://github.com/inab/trimal/tree/2.0_RC", "type": "Source code", "note": null, "version": "2.0-RC" } ], "documentation": [ { "url": "http://trimal.cgenomics.org/", "type": [ "General" ], "note": "Old versions" }, { "url": "https://trimal.readthedocs.io", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btp348", "pmid": "19505945", "pmcid": "PMC2712344", "type": [], "version": null, "note": null, "metadata": { "title": "trimAl: A tool for automated alignment trimming in large-scale phylogenetic analyses", "abstract": "", "date": "2009-08-01T00:00:00Z", "citationCount": 8679, "authors": [], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Salvador Capella-Gutierrez", "email": "salcagu@gmail.com", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": null, "email": "tgabaldon@crg.es", "url": "http://gabaldonlab.crg.es/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "scapella", "additionDate": "2017-04-15T08:42:53Z", "lastUpdate": "2025-11-26T09:30:50.611915Z", "editPermission": { "type": "group", "authors": [ "nico_bsc", "sergitobara" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MMseqs2", "description": "MMseqs2 (Many-against-Many sequence searching) is a software suite to search and cluster huge protein and nucleotide sequence sets. MMseqs2 is open source software implemented in C++ for Linux, MacOS, and (as beta version, via cygwin) Windows. The software is designed to run on multiple cores and servers and exhibits very good scalability. MMseqs2 can run 10000 times faster than BLAST. At 100 times its speed it achieves almost the same sensitivity. It can perform profile searches with the same sensitivity as PSI-BLAST at over 400 times its speed.\n\nMMseqs2 includes Linclust, the first clustering algorithm whose runtime scales linearly With Linclust we clustered 1.6 billion metagenomic sequence fragments in 10 h on a single server to 50% sequence identity.", "homepage": "https://mmseqs.com", "biotoolsID": "MMseqs2", "biotoolsCURIE": "biotools:MMseqs2", "version": [], "otherID": [], "relation": [ { "biotoolsID": "mmseqs", "type": "isNewVersionOf" }, { "biotoolsID": "plass", "type": "usedBy" }, { "biotoolsID": "linclust", "type": "includes" }, { "biotoolsID": "metaeuk", "type": "usedBy" }, { "biotoolsID": "conterminator", "type": "usedBy" }, { "biotoolsID": "spacepharer", "type": "usedBy" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0346", "term": "Sequence similarity search" }, { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0850", "term": "Sequence set" }, "format": [ { "uri": "http://edamontology.org/format_2182", "term": "FASTQ-like format (text)" }, { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0857", "term": "Sequence search results" }, "format": [ { "uri": "http://edamontology.org/format_1333", "term": "BLAST results" } ] } ], "note": null, "cmd": "mmseqs easy-search query.fasta target.fasta output.m8 tmp" }, { "operation": [ { "uri": "http://edamontology.org/operation_0291", "term": "Sequence clustering" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0850", "term": "Sequence set" }, "format": [ { "uri": "http://edamontology.org/format_2182", "term": "FASTQ-like format (text)" }, { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1235", "term": "Sequence cluster" }, "format": [] } ], "note": null, "cmd": "mmseqs easy-cluster input.fasta output tmp\nmmseqs easy-linclust input.fasta output tmp" }, { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0850", "term": "Sequence set" }, "format": [ { "uri": "http://edamontology.org/format_2182", "term": "FASTQ-like format (text)" }, { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [] } ], "note": null, "cmd": "mmseqs easy-taxonomy query.fasta targetDB output tmp" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0078", "term": "Proteins" }, { "uri": "http://edamontology.org/topic_0077", "term": "Nucleic acids" }, { "uri": "http://edamontology.org/topic_0623", "term": "Gene and protein families" }, { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" } ], "operatingSystem": [ "Windows", "Linux", "Mac" ], "language": [ "C++" ], "license": "MIT", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/soedinglab/mmseqs2/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/soedinglab/mmseqs2", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://github.com/soedinglab/MMseqs2/releases", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "https://github.com/soedinglab/MMseqs2/blob/master/README.md", "type": [ "General" ], "note": null }, { "url": "https://github.com/soedinglab/mmseqs2/wiki", "type": [ "User manual" ], "note": null }, { "url": "https://github.com/soedinglab/MMseqs2/wiki/Tutorials", "type": [ "Training material" ], "note": "Tutorial material" } ], "publication": [ { "doi": "10.1038/nbt.3988", "pmid": "29035372", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets", "abstract": "", "date": "2017-11-01T00:00:00Z", "citationCount": 2439, "authors": [], "journal": "Nature Biotechnology" } }, { "doi": "10.1101/079681", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null }, { "doi": "10.1038/s41467-018-04964-5", "pmid": "29959318", "pmcid": "PMC6026198", "type": [ "Method" ], "version": null, "note": null, "metadata": { "title": "Clustering huge protein sequence sets in linear time", "abstract": "", "date": "2018-12-01T00:00:00Z", "citationCount": 577, "authors": [], "journal": "Nature Communications" } }, { "doi": "10.1093/bioinformatics/bty1057", "pmid": "30615063", "pmcid": "PMC6691333", "type": [ "Method" ], "version": null, "note": null, "metadata": { "title": "MMseqs2 desktop and local web server app for fast, interactive sequence searches", "abstract": "", "date": "2019-08-15T00:00:00Z", "citationCount": 366, "authors": [], "journal": "Bioinformatics" } }, { "doi": "10.1101/2020.11.27.401018", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null }, { "doi": "10.1093/bioinformatics/btab184", "pmid": "33734313", "pmcid": "PMC8479651", "type": [], "version": null, "note": "MMseqs2 Taxonomy", "metadata": { "title": "Fast and sensitive taxonomic assignment to metagenomic contigs", "abstract": "", "date": "2021-09-15T00:00:00Z", "citationCount": 162, "authors": [], "journal": "Bioinformatics" } }, { "doi": "10.1101/2024.11.13.623350v1", "pmid": null, "pmcid": null, "type": [], "version": null, "note": "MMseqs2-GPU preprint", "metadata": null }, { "doi": "10.1038/s41592-025-02819-8", "pmid": null, "pmcid": null, "type": [], "version": null, "note": "MMseqs2-GPU", "metadata": { "title": "GPU-accelerated homology search with MMseqs2", "abstract": "", "date": "2025-10-01T00:00:00Z", "citationCount": 0, "authors": [], "journal": "Nature Methods" } } ], "credit": [], "owner": "milot-mirdita", "additionDate": "2019-07-03T16:03:27Z", "lastUpdate": "2025-11-10T08:28:33.612233Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "prolfquapp", "description": "A command-line tool for differential expression analysis in quantitative proteomics", "homepage": "https://github.com/prolfqua/prolfquapp", "biotoolsID": "prolfquapp", "biotoolsCURIE": "biotools:prolfquapp", "version": [ "0.1.6" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3741", "term": "Differential protein expression profiling" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2603", "term": "Expression data" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" }, { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2603", "term": "Expression data" }, "format": [ { "uri": "http://edamontology.org/format_3620", "term": "xlsx" }, { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": "./prolfqua_dea.sh -i data_dir/ -d annotation.xlsx -y config.yaml -w NameOfAnalysis -s DIANN\n# and again you run the version within the docker container with\n# ./prolfquapp_docker.sh prolfqua_dea.sh -i data_dir/ -d annotation.xlsx -y config.yaml -w NameOfAnalysis -s DIANN" }, { "operation": [ { "uri": "http://edamontology.org/operation_2428", "term": "Validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2603", "term": "Expression data" }, "format": [ { "uri": "http://edamontology.org/format_3620", "term": "xlsx" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3914", "term": "Quality control report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0571", "term": "Expression data visualisation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2603", "term": "Expression data" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" }, { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2603", "term": "Expression data" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" }, { "uri": "http://edamontology.org/format_3508", "term": "PDF" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "R" ], "license": "MIT", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/prolfqua/prolfquapp", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/prolfqua/prolfquapp/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "https://github.com/prolfqua/prolfquapp/releases/tag/0.1.6", "type": "Downloads page", "note": null, "version": "0.1.6" } ], "documentation": [ { "url": "https://github.com/prolfqua/prolfquapp/blob/master/README.md", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1021/acs.jproteome.4c00911", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": "0.0.6", "note": null, "metadata": { "title": "prolfquapp ─ A User-Friendly Command-Line Tool Simplifying Differential Expression Analysis in Quantitative Proteomics", "abstract": "", "date": "2025-02-07T00:00:00Z", "citationCount": 1, "authors": [], "journal": "Journal of Proteome Research" } } ], "credit": [], "owner": "n.m.palmblad@lumc.nl", "additionDate": "2025-02-28T15:04:33.594183Z", "lastUpdate": "2025-11-06T14:37:12.116175Z", "editPermission": { "type": "group", "authors": [ "thatmariia" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "PeptideShaker", "description": "PeptideShaker is a search engine independent platform for interpretation of proteomics identification results from multiple search engines, currently supporting X!Tandem, MS-GF+, MS Amanda, OMSSA, MyriMatch, Comet, Tide, Mascot, Andromeda and mzIdentML. By combining the results from multiple search engines, while re-calculating PTM localization scores and redoing the protein inference, PeptideShaker attempts to give you the best possible understanding of your proteomics data", "homepage": "http://compomics.github.io/projects/peptide-shaker.html", "biotoolsID": "peptideshaker", "biotoolsCURIE": "biotools:peptideshaker", "version": [ "3.0.11" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3694", "term": "Mass spectrum visualisation" }, { "uri": "http://edamontology.org/operation_3631", "term": "Peptide identification" }, { "uri": "http://edamontology.org/operation_2428", "term": "Validation" }, { "uri": "http://edamontology.org/operation_3755", "term": "PTM localisation" }, { "uri": "http://edamontology.org/operation_3501", "term": "Enrichment analysis" }, { "uri": "http://edamontology.org/operation_0570", "term": "Structure visualisation" }, { "uri": "http://edamontology.org/operation_3767", "term": "Protein identification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" } ] }, { "data": { "uri": "http://edamontology.org/data_2536", "term": "Mass spectrometry data" }, "format": [ { "uri": "http://edamontology.org/format_3651", "term": "MGF" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2992", "term": "Protein structure image" }, "format": [ { "uri": "http://edamontology.org/format_3579", "term": "JPG" }, { "uri": "http://edamontology.org/format_3604", "term": "SVG" } ] }, { "data": { "uri": "http://edamontology.org/data_3754", "term": "GO-term enrichment data" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] }, { "data": { "uri": "http://edamontology.org/data_2969", "term": "Sequence image" }, "format": [ { "uri": "http://edamontology.org/format_3547", "term": "Image format" } ] }, { "data": { "uri": "http://edamontology.org/data_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Desktop application", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" }, { "uri": "http://edamontology.org/topic_3520", "term": "Proteomics experiment" }, { "uri": "http://edamontology.org/topic_0644", "term": "Proteome" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "Java" ], "license": "Apache-2.0", "collectionID": [ "de.NBI", "Proteomics", "BioInfra.Prot" ], "maturity": null, "cost": null, "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [ { "url": "https://github.com/compomics/peptide-shaker", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "http://compomics.github.io/projects/peptide-shaker.html#read-me", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1038/nbt.3109", "pmid": "25574629", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "PeptideShaker enables reanalysis of MS-derived proteomics data sets: To the editor", "abstract": "", "date": "2015-01-01T00:00:00Z", "citationCount": 449, "authors": [], "journal": "Nature Biotechnology" } } ], "credit": [ { "name": "BioInfra.Prot", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Dominik Kopczynsk", "email": "dominik.kopczynski@isas.de", "url": "http://compomics.github.io/projects/peptide-shaker.html", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "BioInfra.Prot", "additionDate": "2016-10-20T10:31:19Z", "lastUpdate": "2025-11-01T15:59:45.423975Z", "editPermission": { "type": "group", "authors": [ "proteomics.bio.tools", "veits@bmb.sdu.dk" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NGP", "description": "Simulation of next-generation proteomics (NGP) based on single-molecule sequencing.", "homepage": "https://github.com/magnuspalmblad/NGP", "biotoolsID": "ngp", "biotoolsCURIE": "biotools:ngp", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2426", "term": "Modelling and simulation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3869", "term": "Simulation" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" }, { "uri": "http://edamontology.org/format_3508", "term": "PDF" } ] } ], "note": null, "cmd": null } ], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1021/acs.jproteome.1c00136", "pmid": "33904308", "pmcid": "PMC8185883", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Theoretical Considerations for Next-Generation Proteomics", "abstract": "", "date": "2021-06-04T00:00:00Z", "citationCount": 5, "authors": [], "journal": "Journal of Proteome Research" } } ], "credit": [], "owner": "n.m.palmblad@lumc.nl", "additionDate": "2025-10-29T16:12:04.796577Z", "lastUpdate": "2025-10-29T16:12:04.798957Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NetStart", "description": "Prediction of eukaryotic translation initiation sites using a protein language model.\n\nNetStart 2.0 is a deep learning-based model that predicts canonical translation initiation sites in mRNA transcripts in species across the eukaryotic domain, including vertebrates, invertebrates, plants, fungi, and protists. \n\nThe model integrates the ESM-2 protein language model for assessing transitions from non-coding to coding regions with local start codon sequence context and taxonomical information. It has been trained on sequences from 60 phylogenetically diverse eukaryotic species.\n\nIf you need help with the bioinformatics programs, see the \"Getting Help\" section at the server site at the link.", "homepage": "https://services.healthtech.dtu.dk/services/NetStart-2.0/", "biotoolsID": "netstart_2.0", "biotoolsCURIE": "biotools:netstart_2.0", "version": [ "2.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3767", "term": "Protein identification" }, { "uri": "http://edamontology.org/operation_0362", "term": "Genome annotation" }, { "uri": "http://edamontology.org/operation_0477", "term": "Protein modelling" }, { "uri": "http://edamontology.org/operation_0439", "term": "Translation initiation site prediction" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3495", "term": "RNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1772", "term": "Score" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_3512", "term": "Gene transcripts" }, { "uri": "http://edamontology.org/topic_0108", "term": "Protein expression" }, { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "Python" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/lsandvad/netstart2", "type": [ "Repository" ], "note": "GitHub with code and instructions and to download and run the program locally" }, { "url": "https://services.healthtech.dtu.dk/services/NetStart-2.0/", "type": [ "Service" ], "note": "NetStart 2.0 server where sequences can be uploaded directly without having to download the program (hosted by DTU Health Tech)." } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1186/S12859-025-06220-2", "pmid": "40830753", "pmcid": "PMC12366053", "type": [ "Method" ], "version": "2.0", "note": null, "metadata": { "title": "NetStart 2.0: prediction of eukaryotic translation initiation sites using a protein language model", "abstract": "", "date": "2025-12-01T00:00:00Z", "citationCount": 0, "authors": [], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": "Line Sandvad Nielsen", "email": "line.s.nielsen@bio.ku.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Henrik Nielsen", "email": "henni@dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "linesandvad", "additionDate": "2025-10-27T16:27:24.014603Z", "lastUpdate": "2025-10-28T17:34:39.042070Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MS Annika", "description": "MS Annika is a crosslink search engine based on MS Amanda, aimed at identifying crosslinks of cleavable and non-cleavable crosslinkers from MS2 and MS3 spectra. It can deal with a wide variety of cross-linkers and provides robust and transparent FDR control based on a target-decoy approach. MS Annika is available free of charge as a plug-in for Proteome Discoverer.", "homepage": "https://github.com/hgb-bin-proteomics/MSAnnika", "biotoolsID": "ms_annika", "biotoolsCURIE": "biotools:ms_annika", "version": [ "Proteome Discoverer 3.2: MS Annika 3.0 v3.0.7", "Proteome Discoverer 3.1: MS Annika 3.0 v3.0.7", "Proteome Discoverer 3.0: MS Annika 2.0 v1.1.4fix", "Proteome Discoverer 2.5: MS Annika 2.0 v1.1.3", "Proteome Discoverer 2.4: MS Annika v1.0.0", "Proteome Discoverer 2.3: MS Annika v1.0.0" ], "otherID": [], "relation": [ { "biotoolsID": "ms_amanda", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3631", "term": "Peptide identification" }, { "uri": "http://edamontology.org/operation_3646", "term": "Peptide database search" }, { "uri": "http://edamontology.org/operation_3755", "term": "PTM localisation" }, { "uri": "http://edamontology.org/operation_3645", "term": "PTM identification" }, { "uri": "http://edamontology.org/operation_3649", "term": "Target-Decoy" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0943", "term": "Mass spectrum" }, "format": [ { "uri": "http://edamontology.org/format_3651", "term": "MGF" }, { "uri": "http://edamontology.org/format_3712", "term": "Thermo RAW" } ] }, { "data": { "uri": "http://edamontology.org/data_2886", "term": "Protein sequence record" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0857", "term": "Sequence search results" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Plug-in" ], "topic": [ { "uri": "http://edamontology.org/topic_0130", "term": "Protein folding, stability and design" }, { "uri": "http://edamontology.org/topic_0736", "term": "Protein folds and structural domains" }, { "uri": "http://edamontology.org/topic_0128", "term": "Protein interactions" }, { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" }, { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" } ], "operatingSystem": [ "Windows" ], "language": [ "C#" ], "license": "Freeware", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/hgb-bin-proteomics/MSAnnika", "type": [ "Repository" ], "note": "MS Annika version archive" } ], "download": [ { "url": "https://github.com/hgb-bin-proteomics/MSAnnika/raw/master/releases/latest/PD3.2/latest.zip", "type": "Software package", "note": "Latest MS Annika version for Proteome Disoverer 3.2", "version": "PD3.2:latest" }, { "url": "https://github.com/hgb-bin-proteomics/MSAnnika/raw/master/releases/latest/PD3.1/latest.zip", "type": "Software package", "note": "Latest MS Annika version for Proteome Disoverer 3.1", "version": "PD3.1:latest" }, { "url": "https://github.com/hgb-bin-proteomics/MSAnnika/raw/master/releases/latest/PD3.0/latest.zip", "type": "Software package", "note": "Latest MS Annika version for Proteome Disoverer 3.0", "version": "PD3.0:latest" }, { "url": "https://github.com/hgb-bin-proteomics/MSAnnika/raw/master/releases/latest/PD2.5/latest.zip", "type": "Software package", "note": "Latest MS Annika version for Proteome Disoverer 2.5", "version": "PD2.5:latest" } ], "documentation": [ { "url": "https://hgb-bin-proteomics.github.io/MSAnnika/", "type": [ "General" ], "note": null }, { "url": "https://github.com/hgb-bin-proteomics/MSAnnika/raw/master/MS_Annika_3.0_UserManual.pdf", "type": [ "User manual" ], "note": null }, { "url": "https://github.com/hgb-bin-proteomics/MSAnnika/raw/master/tutorial/MS_Annika_3.0_Tutorial.pdf", "type": [ "Training material" ], "note": "Detailed tutorial how to use MS Annika" }, { "url": "https://www.youtube.com/watch?v=L1lVt35PYv4", "type": [ "Training material" ], "note": "Detailed tutorial how to use MS Annika" } ], "publication": [ { "doi": "10.1021/acs.jproteome.0c01000", "pmid": "33852321", "pmcid": "PMC8155564", "type": [ "Primary" ], "version": "1.0", "note": "MS Annika for cleavable crosslink identification from MS2 spectra", "metadata": { "title": "MS Annika: A New Cross-Linking Search Engine", "abstract": "", "date": "2021-05-07T00:00:00Z", "citationCount": 22, "authors": [], "journal": "Journal of Proteome Research" } }, { "doi": "10.1021/acs.jproteome.3c00325", "pmid": "37566781", "pmcid": "PMC10476269", "type": [ "Primary" ], "version": "2.0", "note": "MS Annika 2.0 for cleavable crosslink identification from MS3 spectra", "metadata": { "title": "MS Annika 2.0 Identifies Cross-Linked Peptides in MS2-MS3-Based Workflows at High Sensitivity and Specificity", "abstract": "", "date": "2023-09-01T00:00:00Z", "citationCount": 5, "authors": [], "journal": "Journal of Proteome Research" } }, { "doi": "10.1038/s42004-024-01386-x", "pmid": "39702463", "pmcid": "PMC11659399", "type": [ "Primary" ], "version": "3.0", "note": "MS Annika 3.0 for non-cleavable crosslink identification", "metadata": { "title": "Proteome-wide non-cleavable crosslink identification with MS Annika 3.0 reveals the structure of the C. elegans Box C/D complex", "abstract": "", "date": "2024-12-01T00:00:00Z", "citationCount": 2, "authors": [], "journal": "Communications Chemistry" } } ], "credit": [ { "name": "Viktoria Dorfer", "email": "viktoria.dorfer@fh-hagenberg.at", "url": "http://bioinformatics.fh-hagenberg.at/", "orcidid": "https://orcid.org/0000-0002-5332-5701", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Micha Birklbauer", "email": "micha.birklbauer@fh-hagenberg.at", "url": "http://bioinformatics.fh-hagenberg.at/", "orcidid": "https://orcid.org/0009-0005-1051-179X", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "michabirklbauer", "additionDate": "2023-07-26T14:40:01.768324Z", "lastUpdate": "2025-10-26T02:38:48.643054Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "EPIK", "description": "Precise and scalable evolutionary placement with informative k-mers.", "homepage": "https://github.com/phylo42/EPIK", "biotoolsID": "epik", "biotoolsCURIE": "biotools:epik", "version": [ "0.2.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0323", "term": "Phylogenetic inference" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_0955", "term": "Data index" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0872", "term": "Phylogenetic tree" }, "format": [ { "uri": "http://edamontology.org/format_3464", "term": "JSON" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0084", "term": "Phylogeny" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "C++", "Python" ], "license": "MIT", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1093/BIOINFORMATICS/BTAD692", "pmid": "37975872", "pmcid": "PMC10701097", "type": [], "version": "0.2.0", "note": null, "metadata": { "title": "EPIK: Precise and scalable evolutionary placement with informative k-mers", "abstract": "", "date": "2023-12-01T00:00:00Z", "citationCount": 2, "authors": [], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Nikolai Romashchenko", "email": "nromashchenko@lirmm.fr", "url": null, "orcidid": "https://orcid.org/0000-0002-2264-5219", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Eric Rivals", "email": "rivals@lirmm.fr", "url": null, "orcidid": "https://orcid.org/0000-0003-3791-3973", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "nromashchenko", "additionDate": "2024-05-03T08:43:04.841443Z", "lastUpdate": "2025-10-02T12:41:03.856493Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "SQUARNA", "description": "SQUARNA is a tool for RNA secondary structure prediction. It can take a single RNA sequence or an alignment of sequences as input. SQUARNA handles pseudoknots and can predict alternative structures. SQUARNA allows structural restraints and chemical probing data as additional input and is available at https://github.com/febos/SQUARNA.", "homepage": "https://github.com/febos/SQUARNA", "biotoolsID": "squarna", "biotoolsCURIE": "biotools:squarna", "version": [ "2.3" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0278", "term": "RNA secondary structure prediction" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3495", "term": "RNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" } ] }, { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" } ] }, { "data": { "uri": "http://edamontology.org/data_0889", "term": "Structural profile" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0880", "term": "RNA secondary structure" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" } ] }, { "data": { "uri": "http://edamontology.org/data_1772", "term": "Score" }, "format": [] } ], "note": "Input can be a single or several RNA sequences or an alignment of RNA sequences along with structural restraints and/or chemical probing data on base reactivities", "cmd": "SQUARNA i=inputfile [OPTIONS]" } ], "toolType": [ "Command-line tool", "Script", "Library" ], "topic": [ { "uri": "http://edamontology.org/topic_3307", "term": "Computational biology" }, { "uri": "http://edamontology.org/topic_0077", "term": "Nucleic acids" }, { "uri": "http://edamontology.org/topic_0081", "term": "Structure analysis" }, { "uri": "http://edamontology.org/topic_0097", "term": "Nucleic acid structure analysis" }, { "uri": "http://edamontology.org/topic_0082", "term": "Structure prediction" }, { "uri": "http://edamontology.org/topic_0099", "term": "RNA" }, { "uri": "http://edamontology.org/topic_0659", "term": "Functional, regulatory and non-coding RNA" }, { "uri": "http://edamontology.org/topic_3511", "term": "Nucleic acid sites, features and motifs" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "Python" ], "license": "Apache-2.0", "collectionID": [ "3D-BioInfo-Nucleic-Acid" ], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/febos/SQUARNA", "type": [ "Repository" ], "note": "GitHub repository" }, { "url": "https://pypi.org/project/SQUARNA/", "type": [ "Software catalogue" ], "note": "PyPi repository page" } ], "download": [ { "url": "https://doi.org/10.5281/zenodo.8292325", "type": "Downloads page", "note": null, "version": "2.3" }, { "url": "https://pypi.org/project/SQUARNA/", "type": "Software package", "note": "pip install SQUARNA", "version": "2.3" } ], "documentation": [ { "url": "https://github.com/febos/SQUARNA/blob/main/README.md", "type": [ "User manual" ], "note": null }, { "url": "https://pypi.org/project/SQUARNA/", "type": [ "Installation instructions" ], "note": "pip install SQUARNA" } ], "publication": [ { "doi": "10.1101/2023.08.28.555103", "pmid": null, "pmcid": null, "type": [], "version": null, "note": "biorxiv preprint", "metadata": null } ], "credit": [ { "name": "Eugene F Baulin", "email": "efbaulin@gmail.com", "url": "https://scholar.google.com/citations?user=sjfDaUwAAAAJ&hl=en", "orcidid": "https://orcid.org/0000-0003-4694-9783", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Primary contact", "Support" ], "note": "https://imol.institute/leaders/baulin-group/" } ], "owner": "febos", "additionDate": "2023-09-05T09:39:45.613658Z", "lastUpdate": "2025-09-26T10:35:19.637909Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "REPET", "description": "The REPET package integrates bioinformatics pipelines dedicated to detect, annotate and analyze transposable elements (TEs) in genomic sequences. The main pipelines are (i) TEdenovo, which search for interspersed repeats, build consensus sequences and classify them according to TE features, and (ii)\n TEannot, which mines a genome with a library of TE sequences, for instance the one produced by the TEdenovo pipeline, to provide TE annotations exported into GFF3 files.", "homepage": "https://urgi.versailles.inrae.fr/Tools/REPET", "biotoolsID": "repet", "biotoolsCURIE": "biotools:repet", "version": [ "v3.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0379", "term": "Repeat sequence detection" }, { "uri": "http://edamontology.org/operation_0237", "term": "Repeat sequence analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1270", "term": "Feature table" }, "format": [ { "uri": "http://edamontology.org/format_2206", "term": "Sequence feature table format (text)" } ] }, { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [ { "uri": "http://edamontology.org/format_1939", "term": "GFF3-seq" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0157", "term": "Sequence composition, complexity and repeats" }, { "uri": "http://edamontology.org/topic_0654", "term": "DNA" }, { "uri": "http://edamontology.org/topic_0097", "term": "Nucleic acid structure analysis" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "C++", "Python" ], "license": "CECILL-2.0", "collectionID": [ "REPET", "elixir-fr-sdp-2019", "URGI" ], "maturity": "Legacy", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Tools" ], "elixirNode": [ "France" ], "elixirCommunity": [], "link": [ { "url": "https://urgi.versailles.inrae.fr/download/repet/", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://urgi.versailles.inrae.fr/download/repet/REPET_linux-x64-3.0.tar.gz", "type": "Source code", "note": null, "version": "v3.0" } ], "documentation": [ { "url": "https://urgi.versailles.inrae.fr/Tools/REPET", "type": [ "General" ], "note": "see also https://urgi.versailles.inrae.fr/Tools/REPET/README" }, { "url": "https://urgi.versailles.inrae.fr/Tools/REPET/INSTALL", "type": [ "Installation instructions" ], "note": null }, { "url": "https://urgi.versailles.inrae.fr/Tools/REPET/TEdenovo-tuto", "type": [ "User manual" ], "note": "See also https://urgi.versailles.inra.fr/Tools/REPET/TEannot-tuto" }, { "url": "https://forgemia.inra.fr/urgi-anagen/wiki-repet/-/wikis/REPET-V3.0-tutorial", "type": [ "Training material" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pone.0091929", "pmid": "24786468", "pmcid": "PMC4008368", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "PASTEC: An automatic transposable element classification tool", "abstract": "", "date": "2014-05-02T00:00:00Z", "citationCount": 226, "authors": [], "journal": "PLoS ONE" } }, { "doi": "10.1371/journal.pone.0016526", "pmid": "21304975", "pmcid": "PMC3031573", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Considering transposable element diversification in de novo annotation approaches", "abstract": "", "date": "2011-02-09T00:00:00Z", "citationCount": 355, "authors": [], "journal": "PLoS ONE" } }, { "doi": "10.1371/journal.pcbi.0010022", "pmid": "16110336", "pmcid": "PMC1185648", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Combined evidence annotation of transposable elements in genome sequences", "abstract": "", "date": "2005-01-01T00:00:00Z", "citationCount": 279, "authors": [], "journal": "PLoS Computational Biology" } }, { "doi": "10.1007/s00239-003-0007-2", "pmid": "15008403", "pmcid": null, "type": [ "Method" ], "version": null, "note": null, "metadata": { "title": "Detection of New Transposable Element Families in Drosophila melanogaster and Anopheles gambiae Genomes", "abstract": "", "date": "2003-12-29T00:00:00Z", "citationCount": 65, "authors": [], "journal": "Journal of Molecular Evolution" } }, { "doi": "10.1109/JPROC.2016.2590833", "pmid": null, "pmcid": null, "type": [ "Method" ], "version": null, "note": null, "metadata": { "title": "De Novo Annotation of Transposable Elements: Tackling the Fat Genome Issue", "abstract": "", "date": "2017-03-01T00:00:00Z", "citationCount": 18, "authors": [], "journal": "Proceedings of the IEEE" } } ], "credit": [ { "name": "URGI", "email": "urgi-repet@versailles.inrae.fr", "url": "http://urgi.versailles.inrae.fr/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Developer", "Contributor", "Maintainer", "Provider", "Support", "Documentor" ], "note": "This tool has a \"Numero de depot APP\": FR 001 480007 000 R P 2008 000 31 235" } ], "owner": "Institut Francais de Bioinform", "additionDate": "2016-03-24T16:22:28Z", "lastUpdate": "2025-09-09T08:10:41.737859Z", "editPermission": { "type": "group", "authors": [ "vjamilloux", "johann_confais", "raphael.flores", "cmichotey" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "fqcleaner", "description": "Mini workflow for preprocessing fastq files, it includes quality trimming, duplicate and artefacts filters for FASTQ read files.", "homepage": "https://gensoft.pasteur.fr/docs/fqCleanER/21.10/", "biotoolsID": "fqcleaner", "biotoolsCURIE": "biotools:fqcleaner", "version": [ "0.4.1.1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3192", "term": "Sequence trimming" }, { "uri": "http://edamontology.org/operation_3695", "term": "Data filtering" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_1932", "term": "FASTQ-sanger" } ] }, { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_1932", "term": "FASTQ-sanger" } ] }, { "data": { "uri": "http://edamontology.org/data_0006", "term": "Data" }, "format": [ { "uri": "http://edamontology.org/format_1932", "term": "FASTQ-sanger" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_3572", "term": "Data quality management" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [ "galaxyPasteur", "Institut Pasteur", "fqtools" ], "maturity": "Mature", "cost": null, "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://galaxy.pasteur.fr/tool_runner?tool_id=toolshed.pasteur.fr/repos/odoppelt/fqcleaner/fqCleaner/0.4.1.1", "type": [ "Galaxy service" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1093/nar/gkw343", "pmid": null, "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2016 update", "abstract": "High-throughput data production technologies, particularly ‘next-generation’ DNA sequencing, have ushered in widespread and disruptive changes to biomedical research. Making sense of the large datasets produced by these technologies requires sophisticated statistical and computational methods, as well as substantial computational power. This has led to an acute crisis in life sciences, as researchers without informatics training attempt to perform computation-dependent analyses. Since 2005, the Galaxy project has worked to address this problem by providing a framework that makes advanced computational tools usable by non experts. Galaxy seeks to make data-intensive research more accessible, transparent and reproducible by providing a Web-based environment in which users can perform computational analyses and have all of the details automatically tracked for later inspection, publication, or reuse. In this report we highlight recently added features enabling biomedical analyses on a large scale.", "date": "2016-07-08T00:00:00Z", "citationCount": 1477, "authors": [ { "name": "Afgan E." }, { "name": "Baker D." }, { "name": "van den Beek M." }, { "name": "Blankenberg D." }, { "name": "Bouvier D." }, { "name": "Cech M." }, { "name": "Chilton J." }, { "name": "Clements D." }, { "name": "Coraor N." }, { "name": "Eberhard C." }, { "name": "Gruning B." }, { "name": "Guerler A." }, { "name": "Hillman-Jackson J." }, { "name": "Kuster G.V." }, { "name": "Rasche E." }, { "name": "Soranzo N." }, { "name": "Turaga N." }, { "name": "Taylor J." }, { "name": "Nekrutenko A." }, { "name": "Goecks J." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.7490/f1000research.1114334.1", "pmid": null, "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Galaxy Support Team", "email": "galaxy@pasteur.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "hmenager", "additionDate": "2016-12-19T14:27:26Z", "lastUpdate": "2025-08-27T10:47:14.412802Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ETENLNC", "description": "ETENLNC (End-To-End-Novel-NonCoding) is a lncRNA identification and analysis framework", "homepage": "https://github.com/EvolOMICS-TU/ETENLNC", "biotoolsID": "etenlnc", "biotoolsCURIE": "biotools:etenlnc", "version": [ "1.0" ], "otherID": [], "relation": [ { "biotoolsID": "hisat2", "type": "uses" }, { "biotoolsID": "salmon", "type": "uses" }, { "biotoolsID": "fastqc", "type": "uses" }, { "biotoolsID": "fastp", "type": "uses" }, { "biotoolsID": "stringtie", "type": "uses" }, { "biotoolsID": "gffcompare", "type": "uses" }, { "biotoolsID": "cpc2", "type": "uses" }, { "biotoolsID": "ncbi_blast_plus", "type": "uses" }, { "biotoolsID": "tximport", "type": "uses" }, { "biotoolsID": "deseq2", "type": "uses" }, { "biotoolsID": "lnctar", "type": "uses" }, { "biotoolsID": "capsule-lpi", "type": "uses" }, { "biotoolsID": "seekr", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3219", "term": "Read pre-processing" }, { "uri": "http://edamontology.org/operation_3218", "term": "Sequencing quality control" }, { "uri": "http://edamontology.org/operation_3258", "term": "Transcriptome assembly" }, { "uri": "http://edamontology.org/operation_0415", "term": "Nucleic acid feature detection" }, { "uri": "http://edamontology.org/operation_3800", "term": "RNA-Seq quantification" }, { "uri": "http://edamontology.org/operation_3223", "term": "Differential gene expression profiling" }, { "uri": "http://edamontology.org/operation_0531", "term": "Heat map generation" }, { "uri": "http://edamontology.org/operation_0278", "term": "RNA secondary structure prediction" }, { "uri": "http://edamontology.org/operation_3472", "term": "k-mer counting" }, { "uri": "http://edamontology.org/operation_0389", "term": "Protein-nucleic acid interaction analysis" }, { "uri": "http://edamontology.org/operation_3901", "term": "RNA-binding protein prediction" }, { "uri": "http://edamontology.org/operation_2437", "term": "Gene regulatory network prediction" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2603", "term": "Expression data" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1288", "term": "Genome map" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [ { "uri": "http://edamontology.org/format_2306", "term": "GTF" }, { "uri": "http://edamontology.org/format_2305", "term": "GFF" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2887", "term": "Nucleic acid sequence record" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_3112", "term": "Gene expression matrix" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] }, { "data": { "uri": "http://edamontology.org/data_1636", "term": "Heat map" }, "format": [ { "uri": "http://edamontology.org/format_3508", "term": "PDF" } ] }, { "data": { "uri": "http://edamontology.org/data_0906", "term": "Protein interaction data" }, "format": [] } ], "note": "Run ETENLNC on paired-end raw RNA-Seq (.fastq) data", "cmd": "bash ETENLNC_docker.sh" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0659", "term": "Functional, regulatory and non-coding RNA" } ], "operatingSystem": [ "Linux", "Mac", "Windows" ], "language": [], "license": "GPL-3.0", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/EvolOMICS-TU/ETENLNC", "type": [ "Repository" ], "note": "GitHub Repo" } ], "download": [ { "url": "https://zenodo.org/records/14325721?token=eyJhbGciOiJIUzUxMiJ9.eyJpZCI6ImVmYTllNWJkLWE4ODUtNGM3OC05YTAxLWM4ZDk5YTljZDZjMCIsImRhdGEiOnt9LCJyYW5kb20iOiI4M2I1YjBlZDQ4MmUyZTIxNDg2YmI0YTFkMWE5MTI1OCJ9.HeB3WrsPduNzMyXjH4x5HfCgmIp4NzYv0P_11XU9lcXC_ZxEaVndP-kD0LDkxwufHVNlroeAhdK33PR51F6jnw", "type": "Biological data", "note": "Sample/demo data for ETENLNC. A detailed guide on running ETENLNC using the demo data can be found in the ETENLNC manual (supplementary to our publication).", "version": "1.0" } ], "documentation": [ { "url": "https://github.com/EvolOMICS-TU/ETENLNC", "type": [ "Command-line options" ], "note": "A detailed guide on running ETENLNC using the demo data can be found in the ETENLNC manual (supplementary to our publication)" } ], "publication": [ { "doi": "10.1016/j.compbiolchem.2024.108140", "pmid": "38996755", "pmcid": null, "type": [ "Primary" ], "version": ".0", "note": null, "metadata": { "title": "ETENLNC: An end to end lncRNA identification and analysis framework to facilitate construction of known and novel lncRNA regulatory networks", "abstract": "Long non-coding RNAs (lncRNAs) play crucial roles in the regulation of gene expression and maintenance of genomic integrity through various interactions with DNA, RNA, and proteins. The availability of large-scale sequence data from various high-throughput platforms has opened possibilities to identify, predict, and functionally annotate lncRNAs. As a result, there is a growing demand for an integrative computational framework capable of identifying known lncRNAs, predicting novel lncRNAs, and inferring the downstream regulatory interactions of lncRNAs at the genome-scale. We present ETENLNC (End-To-End-Novel-Long-NonCoding), a user-friendly, integrative, open-source, scalable, and modular computational framework for identifying and analyzing lncRNAs from raw RNA-Seq data. ETENLNC employs six stringent filtration steps to identify novel lncRNAs, performs differential expression analysis of mRNA and lncRNA transcripts, and predicts regulatory interactions between lncRNAs, mRNAs, miRNAs, and proteins. We benchmarked ETENLNC against six existing tools and optimized it for desktop workstations and high-performance computing environments using data from three different species. ETENLNC is freely available on GitHub: https://github.com/EvolOMICS-TU/ETENLNC.", "date": "2024-10-01T00:00:00Z", "citationCount": 2, "authors": [ { "name": "Nath P." }, { "name": "Bhuyan K." }, { "name": "Bhattacharyya D.K." }, { "name": "Barah P." } ], "journal": "Computational Biology and Chemistry" } } ], "credit": [ { "name": "Pankaj Barah", "email": "barah@tezu.ernet.in", "url": "https://www.tezu.ernet.in/dmbbt/profile/34", "orcidid": "https://orcid.org/0000-0001-7039-7996", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Maintainer" ], "note": "Assistant Professor at Department of Molecular Biology and Biotechnology, Tezpur University." }, { "name": "Prangan Nath", "email": "prangannathofficial@gmai.com", "url": null, "orcidid": "https://orcid.org/0000-0002-9451-7822", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Maintainer" ], "note": null } ], "owner": "prangannath", "additionDate": "2025-07-23T10:27:57.572501Z", "lastUpdate": "2025-07-23T10:27:57.574879Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "UniversalMer", "description": "UniversalMer is a k-mer counting tool for multiple size of k at once. It is available for DNA, RNA, and protein sequences. The program counts and summarizes the exact frequency of all k-mers from 1-mer to a user-defined maximum length (kmax). Analyzing the k-mer spectrum across multiple values of k can be done in seconds. This program is designed for bioinformatics researchers and scientists.", "homepage": "https://ugrammer.github.io", "biotoolsID": "UniversalMer", "biotoolsCURIE": "biotools:UniversalMer", "version": [ "2.0.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3472", "term": "k-mer counting" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" } ] }, { "data": { "uri": "http://edamontology.org/data_3495", "term": "RNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" } ] }, { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1266", "term": "Base word frequencies table" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1265", "term": "Base frequencies table" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3671", "term": "Text" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" }, { "uri": "http://edamontology.org/topic_3473", "term": "Data mining" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Windows", "Mac" ], "language": [ "C++", "C" ], "license": "Freeware", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Tools" ], "elixirNode": [ "UK" ], "elixirCommunity": [], "link": [ { "url": "https://sourceforge.net/projects/universal-mer/", "type": [ "Mirror" ], "note": null } ], "download": [ { "url": "https://sourceforge.net/projects/universal-mer/", "type": "Command-line specification", "note": null, "version": "2.0" } ], "documentation": [], "publication": [], "credit": [], "owner": "Ugrammer", "additionDate": "2025-07-14T08:21:28.942611Z", "lastUpdate": "2025-07-14T08:21:28.944946Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "MirGeneDB", "description": "MirGeneDB is a database of manually curated microRNA genes that have been validated and annotated as initially described in Fromm et al. 2015 , Fromm et al. 2020 and Fromm et al 2022. MirGeneDB 3.0 (Clarke and Hoye et al. 2024 ) includes more than 21,000 microRNA gene entries representing more than 1,700 microRNA families from 114 metazoan species. All microRNAs can be browsed, searched and downloaded.", "homepage": "http://mirgenedb.org/", "biotoolsID": "mirgen", "biotoolsCURIE": "biotools:mirgen", "version": [ "3.0" ], "otherID": [ { "value": "doi:10.25504/FAIRsharing.QXSgvF", "type": "doi", "version": "2.0" } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" }, { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1097", "term": "Sequence accession (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1869", "term": "Organism identifier" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3134", "term": "Gene transcript report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] }, { "data": { "uri": "http://edamontology.org/data_0880", "term": "RNA secondary structure" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": "Data retrieval: curated miRNA. Organism identifier: a specific miRNA identifier or a species for all miRNAs for that species. Gene transcript report: with metadata and visualization. RNA secondary structure: the hairpin loop of the miRNA with bases.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1097", "term": "Sequence accession (nucleic acid)" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3495", "term": "RNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_2012", "term": "Sequence coordinates" }, "format": [ { "uri": "http://edamontology.org/format_2305", "term": "GFF" }, { "uri": "http://edamontology.org/format_3003", "term": "BED" } ] }, { "data": { "uri": "http://edamontology.org/data_3917", "term": "Count matrix" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0659", "term": "Functional, regulatory and non-coding RNA" }, { "uri": "http://edamontology.org/topic_0204", "term": "Gene regulation" }, { "uri": "http://edamontology.org/topic_3299", "term": "Evolutionary biology" }, { "uri": "http://edamontology.org/topic_3500", "term": "Zoology" }, { "uri": "http://edamontology.org/topic_2815", "term": "Human biology" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": "CC0-1.0", "collectionID": [ "UiO tools", "ELIXIR-NO", "ELIXIR-Norway" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "Norway" ], "elixirCommunity": [], "link": [ { "url": "https://elixir.no/helpdesk", "type": [ "Helpdesk" ], "note": null } ], "download": [ { "url": "https://www.mirgenedb.org/download", "type": "Biological data", "note": "Sequence downloads for 75 species", "version": "3.0" } ], "documentation": [ { "url": "https://www.mirgenedb.org/information", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkab1101", "pmid": "34850127", "pmcid": "PMC8728216", "type": [ "Primary" ], "version": "2.1", "note": null, "metadata": { "title": "MirGeneDB 2.1: Toward a complete sampling of all major animal phyla", "abstract": "We describe an update of MirGeneDB, the manually curated microRNA gene database. Adhering to uniform and consistent criteria for microRNA annotation and nomenclature, we substantially expanded MirGeneDB with 30 additional species representing previously missing metazoan phyla such as sponges, jellyfish, rotifers and flatworms. MirGeneDB 2.1 now consists of 75 species spanning over ∼800 million years of animal evolution, and contains a total number of 16 670 microRNAs from 1549 families. Over 6000 microRNAs were added in this update using ∼550 datasets with ∼7.5 billion sequencing reads. By adding new phylogenetically important species, especially those relevant for the study of whole genome duplication events, and through updating evolutionary nodes of origin for many families and genes, we were able to substantially refine our nomenclature system. All changes are traceable in the specifically developed MirGeneDB version tracker. The performance of read-pages is improved and microRNA expression matrices for all tissues and species are now also downloadable. Altogether, this update represents a significant step toward a complete sampling of all major metazoan phyla, and a widely needed foundation for comparative microRNA genomics and transcriptomics studies. MirGeneDB 2.1 is part of RNAcentral and Elixir Norway, publicly and freely available at http://www.mirgenedb.org/.", "date": "2022-01-07T00:00:00Z", "citationCount": 95, "authors": [ { "name": "Fromm B." }, { "name": "Hoye E." }, { "name": "Domanska D." }, { "name": "Zhong X." }, { "name": "Aparicio-Puerta E." }, { "name": "Ovchinnikov V." }, { "name": "Umu S.U." }, { "name": "Chabot P.J." }, { "name": "Kang W." }, { "name": "Aslanzadeh M." }, { "name": "Tarbier M." }, { "name": "Marmol-Sanchez E." }, { "name": "Urgese G." }, { "name": "Johansen M." }, { "name": "Hovig E." }, { "name": "Hackenberg M." }, { "name": "Friedlander M.R." }, { "name": "Peterson K.J." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkz885", "pmid": "31598695", "pmcid": "PMC6943042", "type": [ "Primary" ], "version": "2.0", "note": null, "metadata": { "title": "MirGeneDB 2.0: The metazoan microRNA complement", "abstract": "Small non-coding RNAs have gained substantial attention due to their roles in animal development and human disorders. Among them, microRNAs are special because individual gene sequences are conserved across the animal kingdom. In addition, unique and mechanistically well understood features can clearly distinguish bona fide miRNAs from the myriad other small RNAs generated by cells. However, making this distinction is not a common practice and, thus, not surprisingly, the heterogeneous quality of available miRNA complements has become a major concern in microRNA research. We addressed this by extensively expanding our curated microRNA gene database-MirGeneDB-to 45 organisms, encompassing a wide phylogenetic swath of animal evolution. By consistently annotating and naming 10,899 microRNA genes in these organisms, we show that previous microRNA annotations contained not only many false positives, but surprisingly lacked >2000 bona fide microRNAs. Indeed, curated microRNA complements of closely related organisms are very similar and can be used to reconstruct ancestral miRNA repertoires. MirGeneDB represents a robust platform for microRNA-based research, providing deeper and more significant insights into the biology and evolution of miRNAs as well as biomedical and biomarker research. MirGeneDB is publicly and freely available at http://mirgenedb.org/.", "date": "2020-01-01T00:00:00Z", "citationCount": 178, "authors": [ { "name": "Fromm B." }, { "name": "Domanska D." }, { "name": "Hoye E." }, { "name": "Ovchinnikov V." }, { "name": "Kang W." }, { "name": "Aparicio-Puerta E." }, { "name": "Johansen M." }, { "name": "Flatmark K." }, { "name": "Mathelier A." }, { "name": "Hovig E." }, { "name": "Hackenberg M." }, { "name": "Friedlander M.R." }, { "name": "Peterson K.J." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1146/annurev-genet-120213-092023", "pmid": "26473382", "pmcid": "PMC4743252", "type": [ "Primary" ], "version": "1.0", "note": null, "metadata": { "title": "A Uniform System for the Annotation of Vertebrate microRNA Genes and the Evolution of the Human microRNAome", "abstract": "Although microRNAs (miRNAs) are among the most intensively studied molecules of the past 20 years, determining what is and what is not a miRNA has not been straightforward. Here, we present a uniform system for the annotation and nomenclature of miRNA genes. We show that less than a third of the 1,881 human miRBase entries, and only approximately 16% of the 7,095 metazoan miRBase entries, are robustly supported as miRNA genes. Furthermore, we show that the human repertoire of miRNAs has been shaped by periods of intense miRNA innovation and that mature gene products show a very different tempo and mode of sequence evolution than star products. We establish a new open access database-MirGeneDB (http://mirgenedb.org)-to catalog this set of miRNAs, which complements the efforts of miRBase but differs from it by annotating the mature versus star products and by imposing an evolutionary hierarchy upon this curated and consistently named repertoire.", "date": "2015-11-23T00:00:00Z", "citationCount": 435, "authors": [ { "name": "Fromm B." }, { "name": "Billipp T." }, { "name": "Peck L.E." }, { "name": "Johansen M." }, { "name": "Tarver J.E." }, { "name": "King B.L." }, { "name": "Newcomb J.M." }, { "name": "Sempere L.F." }, { "name": "Flatmark K." }, { "name": "Hovig E." }, { "name": "Peterson K.J." } ], "journal": "Annual Review of Genetics" } }, { "doi": "10.1093/nar/gkae1094", "pmid": "39673268", "pmcid": "PMC11701709", "type": [ "Primary" ], "version": "3.0", "note": null, "metadata": { "title": "MirGeneDB 3.0: Improved taxonomic sampling, uniform nomenclature of novel conserved microRNA families and updated covariance models", "abstract": "We present a major update of MirGeneDB (3.0), the manually curated animal microRNA gene database. Beyond moving to a new server and the creation of a computational mirror, we have expanded the database with the addition of 33 invertebrate species, including representatives of 5 previously unsampled phyla, and 6 mammal species. MirGeneDB now contains entries for 21 822 microRNA genes (5160 of these from the new species) belonging to 1743 microRNA families. The inclusion of these new species allowed us to refine both the evolutionary node of appearance of a number of microRNA genes/families, as well as MirGeneDB's phylogenetically informed nomenclature system. Updated covariance models of all microRNA families, along with all smallRNA read data are now downloadable. These enhanced annotations will allow researchers to analyze microRNA properties such as secondary structure and features of their biogenesis within a robust phylogenetic context and without the database plagued with numerous false positives and false negatives. In light of these improvements, MirGeneDB 3.0 will assume the responsibility for naming conserved novel metazoan microRNAs. MirGeneDB is part of RNAcentral and Elixir Norway and is publicly and freely available at mirgenedb.org.", "date": "2025-01-06T00:00:00Z", "citationCount": 6, "authors": [ { "name": "Clarke A.W." }, { "name": "Hoye E." }, { "name": "Hembrom A.A." }, { "name": "Paynter V.M." }, { "name": "Vinther J." }, { "name": "Wyrozemski L." }, { "name": "Biryukova I." }, { "name": "Formaggioni A." }, { "name": "Ovchinnikov V." }, { "name": "Herlyn H." }, { "name": "Pierce A." }, { "name": "Wu C." }, { "name": "Aslanzadeh M." }, { "name": "Cheneby J." }, { "name": "Martinez P." }, { "name": "Friedlander M.R." }, { "name": "Hovig E." }, { "name": "Hackenberg M." }, { "name": "Umu S.U." }, { "name": "Johansen M." }, { "name": "Peterson K.J." }, { "name": "Fromm B." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Bastian Fromm", "email": "BastianFromm@gmail.com", "url": null, "orcidid": "https://orcid.org/0000-0003-0352-3037", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Developer", "Maintainer", "Support" ], "note": null }, { "name": "Kevin J. Peterson", "email": "kevin.j.peterson@dartmouth.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Maintainer" ], "note": null }, { "name": "The Norwegian Bioinformatics Platform (ELIXIR-Norway) Helpdesk", "email": "support@elixir.no", "url": "https://elixir.no/helpdesk", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Consortium", "typeRole": [ "Support" ], "note": null }, { "name": "University of Oslo", "email": null, "url": "https://www.uio.no/english/index.html", "orcidid": null, "gridid": "grid.5510.1", "rorid": "01xtthb56", "fundrefid": "10.13039/501100005366", "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null } ], "owner": "UiO", "additionDate": "2016-02-09T13:19:44Z", "lastUpdate": "2025-07-05T22:33:30.082420Z", "editPermission": { "type": "group", "authors": [ "eca008" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "RepeatModeler2", "description": "RepeatModeler is a de novo transposable element (TE) family identification and modeling package. At the heart of RepeatModeler are three de-novo repeat finding programs ( RECON, RepeatScout and LtrHarvest/Ltr_retriever ) which employ complementary computational methods for identifying repeat element boundaries and family relationships from sequence data.", "homepage": "https://github.com/Dfam-consortium/RepeatModeler", "biotoolsID": "RepeatModeler2", "biotoolsCURIE": "biotools:RepeatModeler2", "version": [ "2.0.7" ], "otherID": [], "relation": [ { "biotoolsID": "repeatmodeler", "type": "isNewVersionOf" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_3644", "term": "de Novo sequencing" }, { "uri": "http://edamontology.org/operation_0362", "term": "Genome annotation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" }, { "uri": "http://edamontology.org/topic_0157", "term": "Sequence composition, complexity and repeats" }, { "uri": "http://edamontology.org/topic_3673", "term": "Whole genome sequencing" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_0798", "term": "Mobile genetic elements" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "Perl" ], "license": "OSL-2.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/Dfam-consortium/RepeatModeler/blob/master/LICENSE", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1101/856591", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [], "owner": "Pub2Tools", "additionDate": "2020-01-14T08:51:14Z", "lastUpdate": "2025-07-01T04:28:03.302129Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "purge_dups", "description": "Identifying and removing haplotypic duplication in primary genome assemblies | haplotypic duplication identification tool | scripts/pd_config.py: script to generate a configuration file used by run_purge_dups.py | purge haplotigs and overlaps in an assembly based on read depth | Given a primary assembly pri_asm and an alternative assembly hap_asm (optional, if you have one), follow the steps shown below to build your own purge_dups pipeline, steps with same number can be run simultaneously. Among all the steps, although step 4 is optional, we highly recommend our users to do so, because assemblers may produce overrepresented seqeuences. In such a case, The final step 4 can be applied to remove those seqeuences", "homepage": "https://github.com/dfguan/purge_dups", "biotoolsID": "purge_dups", "biotoolsCURIE": "biotools:purge_dups", "version": [ "v.1.2.6" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_3798", "term": "Read binning" }, { "uri": "http://edamontology.org/operation_3216", "term": "Scaffolding" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "Python", "C" ], "license": "MIT", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/dfguan/purge_dups", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/dfguan/purge_dups/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1101/729962", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Dengfeng Guan", "email": null, "url": "https://www.chatlink.com.cn", "orcidid": "https://orcid.org/0000-0002-6376-3940", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "Pub2Tools", "additionDate": "2019-11-14T18:08:10Z", "lastUpdate": "2025-06-30T15:34:51.626796Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "Compleasm", "description": "Compleasm: a faster and more accurate reimplementation of BUSCO.\nIt provides measures for quantitative assessment of genome assembly, gene set, and transcriptome completeness based on evolutionarily informed expectations of gene content from near-universal single-copy orthologs.", "homepage": "https://github.com/huangnengCSU/compleasm", "biotoolsID": "compleasm", "biotoolsCURIE": "biotools:compleasm", "version": [ "v.0.2.5" ], "otherID": [], "relation": [ { "biotoolsID": "busco", "type": "isNewVersionOf" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3180", "term": "Sequence assembly validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [] } ], "note": "Runs compleasm using the BUSCO set corresponding to the lineage given.", "cmd": "compleasm run -l \"$lineage\" -a assembly.fa -o output_prefix" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_3308", "term": "Transcriptomics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [], "language": [ "Python" ], "license": "Apache-2.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/huangnengCSU/compleasm", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/huangnengCSU/compleasm/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://busco.ezlab.org/list_of_lineages.html", "type": [ "Other" ], "note": "List of accepted lineages (taxonomic groups with curated BUSCO sets)" } ], "download": [], "documentation": [ { "url": "https://github.com/huangnengCSU/compleasm/blob/0.2.6/README.md", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btad595", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "compleasm: a faster and more accurate reimplementation of BUSCO", "abstract": "Motivation: Evaluating the gene completeness is critical to measuring the quality of a genome assembly. An incomplete assembly can lead to errors in gene predictions, annotation, and other downstream analyses. Benchmarking Universal Single-Copy Orthologs (BUSCO) is a widely used tool for assessing the completeness of genome assembly by testing the presence of a set of single-copy orthologs conserved across a wide range of taxa. However, BUSCO is slow particularly for large genome assemblies. It is cumbersome to apply BUSCO to a large number of assemblies. Results: Here, we present compleasm, an efficient tool for assessing the completeness of genome assemblies. Compleasm utilizes the miniprot protein-to-genome aligner and the conserved orthologous genes from BUSCO. It is 14 times faster than BUSCO for human assemblies and reports a more accurate completeness of 99.6% than BUSCO's 95.7%, which is in close agreement with the annotation completeness of 99.5% for T2T-CHM13.", "date": "2023-10-01T00:00:00Z", "citationCount": 95, "authors": [ { "name": "Huang N." }, { "name": "Li H." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Neng Huang", "email": "neng@ds.dfci.harvard.edu", "url": null, "orcidid": "https://orcid.org/0000-0001-7187-0749", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "rlibouban", "additionDate": "2024-03-18T14:51:49.667412Z", "lastUpdate": "2025-06-30T15:30:41.266812Z", "editPermission": { "type": "public", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "SILVA rRNA database", "description": "SILVA provides comprehensive, quality checked and regularly updated datasets of aligned small (16S/18S, SSU) and large subunit (23S/28S, LSU) ribosomal RNA (rRNA) sequences for all three domains of life (Bacteria, Archaea and Eukaryota).", "homepage": "https://www.arb-silva.de", "biotoolsID": "silva", "biotoolsCURIE": "biotools:silva", "version": [], "otherID": [ { "value": "RRID:SCR_006423", "type": "rrid", "version": null } ], "relation": [ { "biotoolsID": "silvangs", "type": "usedBy" }, { "biotoolsID": "d3hub", "type": "includedIn" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1097", "term": "Sequence accession (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_1868", "term": "Taxon" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_1046", "term": "Strain name" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_1088", "term": "Article ID" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] }, { "data": { "uri": "http://edamontology.org/data_1383", "term": "Sequence alignment (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_3830", "term": "ARB" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] }, { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_3830", "term": "ARB" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] } ], "note": "The search and retrieval functions of the SILVA website can be used to build custom subsets of sequences. In addition to simple searches e.g. for accession numbers, organism names, taxonomic entities, or publication DOI/PubMed IDs, complex queries over several database fields using constraints such as sequence length or quality values are possible. The results can be sorted according to accession numbers, organism names, sequence length, sequence and alignment quality and Pintail values. The search results show accession number, organism name, sequence length, sequence quality values, taxonomic classifications, and links to view the full sequence record on SILVA and on ENA. Sequences found via search and added to download cart can be downloaded as FASTA and ARB files.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2419", "term": "Primer and probe design" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1207", "term": "nucleotide" } ] }, { "data": { "uri": "http://edamontology.org/data_1240", "term": "PCR primers" }, "format": [ { "uri": "http://edamontology.org/format_1207", "term": "nucleotide" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" }, { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] }, { "data": { "uri": "http://edamontology.org/data_0850", "term": "Sequence set" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] }, { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_3830", "term": "ARB" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] }, { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_3830", "term": "ARB" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] } ], "note": "The SILVA Probe Match and Evaluation Tool detects and displays all occurrences of a given probe or primer sequence in the SILVA datasets. \n\nTestPrime allows you to evaluate the performance of primer pairs by running an in silico PCR on the SILVA databases. From the results of the PCR, TestPrime computes coverages for each taxonomic group in all of the taxonomies offered by SILVA.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0492", "term": "Multiple sequence alignment" }, { "uri": "http://edamontology.org/operation_0496", "term": "Global alignment" }, { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" }, { "uri": "http://edamontology.org/operation_0547", "term": "Phylogenetic inference (maximum likelihood and Bayesian methods)" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_3830", "term": "ARB" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] }, { "data": { "uri": "http://edamontology.org/data_0867", "term": "Sequence alignment report" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" }, { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] }, { "data": { "uri": "http://edamontology.org/data_0872", "term": "Phylogenetic tree" }, "format": [ { "uri": "http://edamontology.org/format_1910", "term": "newick" } ] }, { "data": { "uri": "http://edamontology.org/data_1872", "term": "Taxonomic classification" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] } ], "note": "The Alignment, Classification and Tree Service (ACT) of SILVA allows to align and optionally classify sequences using the SILVA Incremental Aligner (SINA). From aligned sequences, (optionally) phylogenetic trees can be inferred using FastTree or RAxML.", "cmd": null } ], "toolType": [ "Web application", "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0659", "term": "Functional, regulatory and non-coding RNA" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_3293", "term": "Phylogenetics" }, { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" }, { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" }, { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" }, { "uri": "http://edamontology.org/topic_0632", "term": "Probes and primers" } ], "operatingSystem": [], "language": [], "license": "CC-BY-4.0", "collectionID": [ "de.NBI", "de.NBI-biodata", "DSMZ Digital Diversity" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Data" ], "elixirNode": [ "Germany" ], "elixirCommunity": [], "link": [ { "url": "https://www.arb-silva.de/browser/", "type": [ "Service" ], "note": "SILVA Taxonomy Browser" }, { "url": "https://www.arb-silva.de/search/", "type": [ "Service" ], "note": "SILVA metadata search" }, { "url": "https://www.arb-silva.de/aligner/", "type": [ "Service" ], "note": "ACT: Alignment, Classification and Tree Service" }, { "url": "https://www.arb-silva.de/search/testprobe/", "type": [ "Service" ], "note": "SILVA Probe Match and Evaluation Tool" }, { "url": "https://www.arb-silva.de/search/testprime/", "type": [ "Service" ], "note": "SILVA Primer Evaluation Tool" }, { "url": "https://treeviewer.arb-silva.de/", "type": [ "Service" ], "note": "Web-based viewer for the SILVA guide trees" } ], "download": [ { "url": "https://www.arb-silva.de/download/archive/", "type": "Downloads page", "note": "SILVA dataset archive", "version": null } ], "documentation": [ { "url": "https://www.arb-silva.de/silva-license-information/", "type": [ "Terms of use" ], "note": null }, { "url": "https://www.arb-silva.de/contact/", "type": [ "Citation instructions" ], "note": null }, { "url": "https://www.arb-silva.de/documentation/", "type": [ "General" ], "note": null }, { "url": "https://www.arb-silva.de/documentation/faqs/", "type": [ "FAQ" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gks1219", "pmid": "23193283", "pmcid": "PMC3531112", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The SILVA ribosomal RNA gene database project: Improved data processing and web-based tools", "abstract": "SILVA (from Latin silva, forest, http://www.arb-silva.de) is a comprehensive web resource for up to date, quality-controlled databases of aligned ribosomal RNA (rRNA) gene sequences from the Bacteria, Archaea and Eukaryota domains and supplementary online services. The referred database release 111 (July 2012) contains 3194 778 small subunit and 288717 large subunit rRNA gene sequences. Since the initial description of the project, substantial new features have been introduced, including advanced quality control procedures, an improved rRNA gene aligner, online tools for probe and primer evaluation and optimized browsing, searching and downloading on the website. Furthermore, the extensively curated SILVA taxonomy and the new non-redundant SILVA datasets provide an ideal reference for high-throughput classification of data from next-generation sequencing approaches. © The Author(s) 2012.", "date": "2013-01-01T00:00:00Z", "citationCount": 22633, "authors": [ { "name": "Quast C." }, { "name": "Pruesse E." }, { "name": "Yilmaz P." }, { "name": "Gerken J." }, { "name": "Schweer T." }, { "name": "Yarza P." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkt1209", "pmid": "24293649", "pmcid": "PMC3965112", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "The SILVA and \"all-species Living Tree Project (LTP)\" taxonomic frameworks", "abstract": "SILVA (from Latin silva, forest, http://www.arb-silva.de) is a comprehensive resource for up-to-date quality-controlled databases of aligned ribosomal RNA (rRNA) gene sequences from the Bacteria, Archaea and Eukaryota domains and supplementary online services. SILVA provides a manually curated taxonomy for all three domains of life, based on representative phylogenetic trees for the small- and large-subunit rRNA genes. This article describes the improvements the SILVA taxonomy has undergone in the last 3 years. Specifically we are focusing on the curation process, the various resources used for curation and the comparison of the SILVA taxonomy with Greengenes and RDP-II taxonomies. Our comparisons not only revealed a reasonable overlap between the taxa names, but also points to significant differences in both names and numbers of taxa between the three resources. © 2013 The Author(s). Published by Oxford University Press.", "date": "2014-01-01T00:00:00Z", "citationCount": 2590, "authors": [ { "name": "Yilmaz P." }, { "name": "Parfrey L.W." }, { "name": "Yarza P." }, { "name": "Gerken J." }, { "name": "Pruesse E." }, { "name": "Quast C." }, { "name": "Schweer T." }, { "name": "Peplies J." }, { "name": "Ludwig W." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkm864", "pmid": "17947321", "pmcid": "PMC2175337", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "SILVA: A comprehensive online resource for quality checked and aligned ribosomal RNA sequence data compatible with ARB", "abstract": "Sequencing ribosomal RNA (rRNA) genes is currently the method of choice for phylogenetic reconstruction, nucleic acid based detection and quantification of microbial diversity. The ARB software suite with its corresponding rRNA datasets has been accepted by researchers worldwide as a standard tool for large scale rRNA analysis. However, the rapid increase of publicly available rRNA sequence data has recently hampered the maintenance of comprehensive and curated rRNA knowledge databases. A new system, SILVA (from Latin silva, forest), was implemented to provide a central comprehensive web resource for up to date, quality controlled databases of aligned rRNA sequences from the Bacteria, Archaea and Eukarya domains. All sequences are checked for anomalies, carry a rich set of sequence associated contextual information, have multiple taxonomic classifications, and the latest validly described nomenclature. Furthermore, two precompiled sequence datasets compatible with ARB are offered for download on the SILVA website: (i) the reference (Ref) datasets, comprising only high quality, nearly full length sequences suitable for in-depth phylogenetic analysis and probe design and (ii) the comprehensive Parc datasets with all publicly available rRNA sequences longer than 300 nucleotides suitable for biodiversity analyses. The latest publicly available database release 91 (August 2007) hosts 547 521 sequences split into 461 823 small subunit and 85 689 large subunit rRNAs. © 2007 The Author(s).", "date": "2007-12-01T00:00:00Z", "citationCount": 5291, "authors": [ { "name": "Pruesse E." }, { "name": "Quast C." }, { "name": "Knittel K." }, { "name": "Fuchs B.M." }, { "name": "Ludwig W." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/bioinformatics/bts252", "pmid": "22556368", "pmcid": "PMC3389763", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "SINA: Accurate high-throughput multiple sequence alignment of ribosomal RNA genes", "abstract": "Motivation: In the analysis of homologous sequences, computation of multiple sequence alignments (MSAs) has become a bottleneck. This is especially troublesome for marker genes like the ribosomal RNA (rRNA) where already millions of sequences are publicly available and individual studies can easily produce hundreds of thousands of new sequences. Methods have been developed to cope with such numbers, but further improvements are needed to meet accuracy requirements.Results: In this study, we present the SILVA Incremental Aligner (SINA) used to align the rRNA gene databases provided by the SILVA ribosomal RNA project. SINA uses a combination of k-mer searching and partial order alignment (POA) to maintain very high alignment accuracy while satisfying high throughput performance demands. SINA was evaluated in comparison with the commonly used high throughput MSA programs PyNAST and mothur. The three BRAliBase III benchmark MSAs could be reproduced with 99.3, 97.6 and 96.1 accuracy. A larger benchmark MSA comprising 38 772 sequences could be reproduced with 98.9 and 99.3% accuracy using reference MSAs comprising 1000 and 5000 sequences. SINA was able to achieve higher accuracy than PyNAST and mothur in all performed benchmarks. © The Author(s) 2012. Published by Oxford University Press.", "date": "2012-07-01T00:00:00Z", "citationCount": 2408, "authors": [ { "name": "Pruesse E." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Bioinformatics" } }, { "doi": "10.1016/j.jbiotec.2017.06.1198", "pmid": "28648396", "pmcid": null, "type": [ "Review" ], "version": null, "note": null, "metadata": { "title": "25 years of serving the community with ribosomal RNA gene reference databases and tools", "abstract": "SILVA (lat. forest) is a comprehensive web resource, providing services around up to date, high-quality datasets of aligned ribosomal RNA gene (rDNA) sequences from the Bacteria, Archaea, and Eukaryota domains. SILVA dates back to the year 1991 when Dr. Wolfgang Ludwig from the Technical University Munich started the integrated software workbench ARB (lat. tree) to support high-quality phylogenetic inference and taxonomy based on the SSU and LSU rDNA marker genes. At that time, the ARB project maintained both, the sequence reference datasets and the software package for data analysis. In 2005, with the massive increase of DNA sequence data, the maintenance of the software system ARB and the corresponding rRNA databases SILVA was split between Munich and the Microbial Genomics and Bioinformatics Research Group in Bremen. ARB has been continuously developed to include new features and improve the usability of the workbench. Thousands of users worldwide appreciate the seamless integration of common analysis tools under a central graphical user interface, in combination with its versatility. The first SILVA release was deployed in February 2007 based on the EMBL-EBI/ENA release 89. Since then, full SILVA releases offering the database content in various flavours are published at least annually, complemented by intermediate web-releases where only the SILVA web dataset is updated. SILVA is the only rDNA database project worldwide where special emphasis is given to the consistent naming of clades of uncultivated (environmental) sequences, where no validly described cultivated representatives are available. Also exclusive for SILVA is the maintenance of both comprehensive aligned 16S/18S rDNA and 23S/28S rDNA sequence datasets. Furthermore, the SILVA alignments and trees were designed to include Eukaryota, another unique feature among rDNA databases. With the termination of the European Ribosomal RNA Database Project in 2007, the SILVA database has become the authoritative rDNA database project for Europe. The application spectrum of ARB and SILVA ranges from biodiversity analysis, medical diagnostics, to biotechnology and quality control for academia and industry.", "date": "2017-11-10T00:00:00Z", "citationCount": 635, "authors": [ { "name": "Glockner F.O." }, { "name": "Yilmaz P." }, { "name": "Quast C." }, { "name": "Gerken J." }, { "name": "Beccati A." }, { "name": "Ciuprina A." }, { "name": "Bruns G." }, { "name": "Yarza P." }, { "name": "Peplies J." }, { "name": "Westram R." }, { "name": "Ludwig W." } ], "journal": "Journal of Biotechnology" } }, { "doi": "10.1186/s12859-017-1841-3", "pmid": null, "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "SILVA tree viewer: Interactive web browsing of the SILVA phylogenetic guide trees", "abstract": "Background: Phylogenetic trees are an important tool to study the evolutionary relationships among organisms. The huge amount of available taxa poses difficulties in their interactive visualization. This hampers the interaction with the users to provide feedback for the further improvement of the taxonomic framework. Results: The SILVA Tree Viewer is a web application designed for visualizing large phylogenetic trees without requiring the download of any software tool or data files. The SILVA Tree Viewer is based on Web Geographic Information Systems (Web-GIS) technology with a PostgreSQL backend. It enables zoom and pan functionalities similar to Google Maps. The SILVA Tree Viewer enables access to two phylogenetic (guide) trees provided by the SILVA database: the SSU Ref NR99 inferred from high-quality, full-length small subunit sequences, clustered at 99% sequence identity and the LSU Ref inferred from high-quality, full-length large subunit sequences. Conclusions: The Tree Viewer provides tree navigation, search and browse tools as well as an interactive feedback system to collect any kinds of requests ranging from taxonomy to data curation and improving the tool itself.", "date": "2017-09-30T00:00:00Z", "citationCount": 29, "authors": [ { "name": "Beccati A." }, { "name": "Gerken J." }, { "name": "Quast C." }, { "name": "Yilmaz P." }, { "name": "Glockner F.O." } ], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": "Leibniz Institute DSMZ-German Collection of Microorganisms and Cell Cultures", "email": "hub@dsmz.de", "url": "https://www.dsmz.de", "orcidid": null, "gridid": "grid.420081.f", "rorid": "02tyer376", "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "SILVA Team", "email": "contact@arb-silva.de", "url": "https://www.arb-silva.de/contact/team/", "orcidid": null, "gridid": "grid.507782.f", "rorid": "027z9pz32", "fundrefid": null, "typeEntity": "Division", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "silva", "additionDate": "2016-09-30T15:59:05Z", "lastUpdate": "2025-06-30T13:26:42.882897Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "SILVAngs", "description": "SILVAngs is a data analysis service for ribosomal RNA gene (rDNA) amplicon reads from high-throughput sequencing (next-generation sequencing (NGS)) approaches based on an automatic software pipeline. It uses the SILVA rDNA databases, taxonomies, and alignments as a reference. It facilitates the classification of rDNA reads and provides a wealth of results (tables, graphs and sequence files) for download.", "homepage": "https://ngs.arb-silva.de", "biotoolsID": "silvangs", "biotoolsCURIE": "biotools:silvangs", "version": [ "1.9.10" ], "otherID": [], "relation": [ { "biotoolsID": "silva", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_2238", "term": "Statistical calculation" }, { "uri": "http://edamontology.org/operation_2478", "term": "Nucleic acid sequence analysis" }, { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" }, { "uri": "http://edamontology.org/operation_2428", "term": "Validation" }, { "uri": "http://edamontology.org/operation_0291", "term": "Sequence clustering" }, { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2082", "term": "Matrix" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_3508", "term": "PDF" } ] }, { "data": { "uri": "http://edamontology.org/data_1246", "term": "Sequence cluster (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] }, { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_3830", "term": "ARB" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] } ], "note": "The pipeline accepts input data in Multi-Fasta format with each input file representing one sample. Samples that belong to one project (a transect, timeseries etc.) should be uploaded as a single SILVAngs project.", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" }, { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" }, { "uri": "http://edamontology.org/topic_0659", "term": "Functional, regulatory and non-coding RNA" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [ "de.NBI", "de.NBI-biodata", "DSMZ Digital Diversity" ], "maturity": "Mature", "cost": "Free of charge (with restrictions)", "accessibility": null, "elixirPlatform": [ "Data" ], "elixirNode": [ "Germany" ], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://www.arb-silva.de/fileadmin/silva_databases/sngs/SILVAngs_User_Guide.pdf", "type": [ "User manual" ], "note": null }, { "url": "https://www.arb-silva.de/documentation/silvangs/userfaq/", "type": [ "FAQ" ], "note": null }, { "url": "https://www.arb-silva.de/footer/sngs-termsofuse", "type": [ "Terms of use" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gks1219", "pmid": "23193283", "pmcid": "PMC3531112", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The SILVA ribosomal RNA gene database project: Improved data processing and web-based tools", "abstract": "SILVA (from Latin silva, forest, http://www.arb-silva.de) is a comprehensive web resource for up to date, quality-controlled databases of aligned ribosomal RNA (rRNA) gene sequences from the Bacteria, Archaea and Eukaryota domains and supplementary online services. The referred database release 111 (July 2012) contains 3194 778 small subunit and 288717 large subunit rRNA gene sequences. Since the initial description of the project, substantial new features have been introduced, including advanced quality control procedures, an improved rRNA gene aligner, online tools for probe and primer evaluation and optimized browsing, searching and downloading on the website. Furthermore, the extensively curated SILVA taxonomy and the new non-redundant SILVA datasets provide an ideal reference for high-throughput classification of data from next-generation sequencing approaches. © The Author(s) 2012.", "date": "2013-01-01T00:00:00Z", "citationCount": 22633, "authors": [ { "name": "Quast C." }, { "name": "Pruesse E." }, { "name": "Yilmaz P." }, { "name": "Gerken J." }, { "name": "Schweer T." }, { "name": "Yarza P." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkt1209", "pmid": "24293649", "pmcid": "PMC3965112", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The SILVA and \"all-species Living Tree Project (LTP)\" taxonomic frameworks", "abstract": "SILVA (from Latin silva, forest, http://www.arb-silva.de) is a comprehensive resource for up-to-date quality-controlled databases of aligned ribosomal RNA (rRNA) gene sequences from the Bacteria, Archaea and Eukaryota domains and supplementary online services. SILVA provides a manually curated taxonomy for all three domains of life, based on representative phylogenetic trees for the small- and large-subunit rRNA genes. This article describes the improvements the SILVA taxonomy has undergone in the last 3 years. Specifically we are focusing on the curation process, the various resources used for curation and the comparison of the SILVA taxonomy with Greengenes and RDP-II taxonomies. Our comparisons not only revealed a reasonable overlap between the taxa names, but also points to significant differences in both names and numbers of taxa between the three resources. © 2013 The Author(s). Published by Oxford University Press.", "date": "2014-01-01T00:00:00Z", "citationCount": 2590, "authors": [ { "name": "Yilmaz P." }, { "name": "Parfrey L.W." }, { "name": "Yarza P." }, { "name": "Gerken J." }, { "name": "Pruesse E." }, { "name": "Quast C." }, { "name": "Schweer T." }, { "name": "Peplies J." }, { "name": "Ludwig W." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/bioinformatics/bts252", "pmid": "22556368", "pmcid": "PMC3389763", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "SINA: Accurate high-throughput multiple sequence alignment of ribosomal RNA genes", "abstract": "Motivation: In the analysis of homologous sequences, computation of multiple sequence alignments (MSAs) has become a bottleneck. This is especially troublesome for marker genes like the ribosomal RNA (rRNA) where already millions of sequences are publicly available and individual studies can easily produce hundreds of thousands of new sequences. Methods have been developed to cope with such numbers, but further improvements are needed to meet accuracy requirements.Results: In this study, we present the SILVA Incremental Aligner (SINA) used to align the rRNA gene databases provided by the SILVA ribosomal RNA project. SINA uses a combination of k-mer searching and partial order alignment (POA) to maintain very high alignment accuracy while satisfying high throughput performance demands. SINA was evaluated in comparison with the commonly used high throughput MSA programs PyNAST and mothur. The three BRAliBase III benchmark MSAs could be reproduced with 99.3, 97.6 and 96.1 accuracy. A larger benchmark MSA comprising 38 772 sequences could be reproduced with 98.9 and 99.3% accuracy using reference MSAs comprising 1000 and 5000 sequences. SINA was able to achieve higher accuracy than PyNAST and mothur in all performed benchmarks. © The Author(s) 2012. Published by Oxford University Press.", "date": "2012-07-01T00:00:00Z", "citationCount": 2408, "authors": [ { "name": "Pruesse E." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "SILVA Team", "email": "ngs-contact@arb-silva.de", "url": "https://www.arb-silva.de/contact/team/", "orcidid": null, "gridid": "grid.507782.f", "rorid": "027z9pz32", "fundrefid": null, "typeEntity": "Division", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Leibniz Institute DSMZ-German Collection of Microorganisms and Cell Cultures", "email": "hub@dsmz.de", "url": "https://www.dsmz.de", "orcidid": null, "gridid": "grid.420081.f", "rorid": "02tyer376", "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null } ], "owner": "silva", "additionDate": "2016-09-30T07:30:11Z", "lastUpdate": "2025-06-30T13:26:39.251875Z", "editPermission": { "type": "group", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "DeepSig", "description": "Prediction of secretory signal peptides in protein sequences", "homepage": "https://busca.biocomp.unibo.it/deepsig/", "biotoolsID": "deepsig", "biotoolsCURIE": "biotools:deepsig", "version": [ "1.2.5" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0418", "term": "Protein signal peptide detection" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2974", "term": "Protein sequence (raw)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Web application", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3307", "term": "Computational biology" }, { "uri": "http://edamontology.org/topic_3510", "term": "Protein sites, features and motifs" }, { "uri": "http://edamontology.org/topic_0123", "term": "Protein properties" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Python", "C++" ], "license": "GPL-3.0", "collectionID": [ "Bologna Biocomputing Group" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "Italy" ], "elixirCommunity": [], "link": [], "download": [ { "url": "https://github.com/BolognaBiocomp/deepsig", "type": "Source code", "note": null, "version": "1.2.5" }, { "url": "https://hub.docker.com/r/bolognabiocomp/deepsig", "type": "Container file", "note": null, "version": "1.2.5" } ], "documentation": [ { "url": "https://github.com/BolognaBiocomp/deepsig", "type": [ "Command-line options" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btx818", "pmid": "29280997", "pmcid": "PMC5946842", "type": [ "Primary" ], "version": "1.0", "note": null, "metadata": { "title": "DeepSig: Deep learning improves signal peptide detection in proteins", "abstract": "Motivation The identification of signal peptides in protein sequences is an important step toward protein localization and function characterization. Results Here, we present DeepSig, an improved approach for signal peptide detection and cleavage-site prediction based on deep learning methods. Comparative benchmarks performed on an updated independent dataset of proteins show that DeepSig is the current best performing method, scoring better than other available state-of-the-art approaches on both signal peptide detection and precise cleavage-site identification. Availability and implementation DeepSig is available as both standalone program and web server at https://deepsig.biocomp.unibo.it. All datasets used in this study can be obtained from the same website.", "date": "2018-05-15T00:00:00Z", "citationCount": 96, "authors": [ { "name": "Savojardo C." }, { "name": "Martelli P.L." }, { "name": "Fariselli P." }, { "name": "Casadio R." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "ELIXIR-ITA-BOLOGNA", "email": null, "url": "http://biocomp.unibo.it", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Castrense Savojardo", "email": "castrense.savojardo2@unibo.it", "url": null, "orcidid": "https://orcid.org/0000-0002-7359-0633", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Primary contact" ], "note": null }, { "name": "Pier Luigi Martelli", "email": "pierluigi.martelli@unibo.it", "url": "http://biocomp.unibo.it", "orcidid": "https://orcid.org/0000-0002-0274-5669", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-ITA-BOLOGNA", "additionDate": "2018-05-28T14:50:09Z", "lastUpdate": "2025-06-19T11:55:09.017105Z", "editPermission": { "type": "group", "authors": [ "savo", "ELIXIR-ITA-BOLOGNA" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "NanoPlot", "description": "NanoPlot is a tool with various visualizations of sequencing data in bam, cram, fastq, fasta or platform-specific TSV summaries, mainly intended for long-read sequencing from Oxford Nanopore Technologies and Pacific Biosciences", "homepage": "https://github.com/wdecoster/NanoPlot", "biotoolsID": "nanoplot", "biotoolsCURIE": "biotools:nanoplot", "version": [ "v.1.42.0" ], "otherID": [], "relation": [ { "biotoolsID": "nanopack", "type": "includedIn" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2940", "term": "Scatter plot plotting" }, { "uri": "http://edamontology.org/operation_2943", "term": "Box-Whisker plot plotting" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" }, { "uri": "http://edamontology.org/format_1207", "term": "nucleotide" } ] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge (with restrictions)", "accessibility": "Open access (with restrictions)", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/wdecoster/NanoPlot", "type": [ "Repository" ], "note": "Issue tracker and most up to date software version" }, { "url": "http://nanoplot.bioinf.be/", "type": [ "Service" ], "note": "Web service with more limited options compared to the command line tool" } ], "download": [ { "url": "https://anaconda.org/bioconda/nanoplot", "type": "Command-line specification", "note": null, "version": null }, { "url": "https://pypi.org/project/NanoPlot/", "type": "Command-line specification", "note": null, "version": null } ], "documentation": [ { "url": "https://github.com/wdecoster/NanoPlot", "type": [ "Command-line options" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/bty149", "pmid": "29547981", "pmcid": "PMC6061794", "type": [ "Method" ], "version": null, "note": null, "metadata": { "title": "NanoPack: Visualizing and processing long-read sequencing data", "abstract": "Summary: Here we describe NanoPack, a set of tools developed for visualization and processing of long-read sequencing data from Oxford Nanopore Technologies and Pacific Biosciences. Availability and implementation: The NanoPack tools are written in Python3 and released under the GNU GPL3.0 License. The source code can be found at https://github.com/wdecoster/nanopack, together with links to separate scripts and their documentation. The scripts are compatible with Linux, Mac OS and the MS Windows 10 subsystem for Linux and are available as a graphical user interface, a web service at http://nanoplot.bioinf.be and command line tools.", "date": "2018-08-01T00:00:00Z", "citationCount": 1840, "authors": [ { "name": "De Coster W." }, { "name": "D'Hert S." }, { "name": "Schultz D.T." }, { "name": "Cruts M." }, { "name": "Van Broeckhoven C." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Wouter De Coster", "email": null, "url": "https://gigabaseorgigabyte.wordpress.com/", "orcidid": "https://orcid.org/0000-0002-5248-8197", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "wdecoster", "additionDate": "2021-07-06T20:27:27Z", "lastUpdate": "2025-06-18T12:31:48.762608Z", "editPermission": { "type": "public", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NextDenovo", "description": "NextDenovo is a string graph-based de novo assembler for long reads (CLR, HiFi and ONT). It uses a \"correct-then-assemble\" strategy similar to canu (no correction step for PacBio Hifi reads), but requires significantly less computing resources and storages.", "homepage": "https://github.com/Nextomics/NextDenovo", "biotoolsID": "nextdenovo", "biotoolsCURIE": "biotools:nextdenovo", "version": [ "v.2.5.2" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0524", "term": "De-novo assembly" }, { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0924", "term": "Sequence trace" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0925", "term": "Sequence assembly" }, "format": [ { "uri": "http://edamontology.org/format_2561", "term": "Sequence assembly format (text)" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [], "language": [ "Python", "C" ], "license": "GPL-3.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/Nextomics/NextDenovo/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "https://github.com/Nextomics/NextDenovo/releases/tag/2.5.2", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "https://nextdenovo.readthedocs.io/en/latest/", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1101/2023.03.09.531669.", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Nextomics", "email": "support@nextomics.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "Kigaard", "additionDate": "2021-05-26T21:13:32Z", "lastUpdate": "2025-06-18T12:20:23.607241Z", "editPermission": { "type": "group", "authors": [ "jw", "ELIXIR-CZ", "Keiler_Collier" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "quickmerge", "description": "Quickmerge is a program that uses complementary information from genomes assembled with long reads in order to improve contiguity, and works with assemblies derived from both Pacific Biosciences or Oxford Nanopore. Quickmerge will even work with hybrid assemblies made by combining long reads and Illumina short reads.", "homepage": "https://github.com/mahulchak/quickmerge", "biotoolsID": "quickmerge", "biotoolsCURIE": "biotools:quickmerge", "version": [ "v.0.3" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_3216", "term": "Scaffolding" }, { "uri": "http://edamontology.org/operation_0524", "term": "De-novo assembly" }, { "uri": "http://edamontology.org/operation_3196", "term": "Genotyping" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": "Runs whole merge process on an input assembly.\nAssembly 2 will be used to fill gaps in assembly 1.", "cmd": "merge_wrapper.py -pre output_prefix assembly_1.fa assembly_2.fa" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3175", "term": "Structural variation" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_2885", "term": "DNA polymorphism" }, { "uri": "http://edamontology.org/topic_3673", "term": "Whole genome sequencing" }, { "uri": "http://edamontology.org/topic_0625", "term": "Genotype and phenotype" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "C++", "C" ], "license": "GPL-3.0", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/mahulchak/quickmerge/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/mahulchak/quickmerge", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1534/g3.118.200162", "pmid": "30018084", "pmcid": "PMC6169397", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Rapid low-cost assembly of the drosophila melanogaster reference genome using low-coverage, long-read sequencing", "abstract": "Accurate and comprehensive characterization of genetic variation is essential for deciphering the genetic basis of diseases and other phenotypes. A vast amount of genetic variation stems from largescale sequence changes arising from the duplication, deletion, inversion, and translocation of sequences. In the past 10 years, high-throughput short reads have greatly expanded our ability to assay sequence variation due to single nucleotide polymorphisms. However, a recent de novo assembly of a second Drosophila melanogaster reference genome has revealed that short read genotyping methods miss hundreds of structural variants, including those affecting phenotypes. While genomes assembled using highcoverage long reads can achieve high levels of contiguity and completeness, concerns about cost, errors, and low yield have limited widespread adoption of such sequencing approaches. Here we resequenced the reference strain of D. melanogaster (ISO1) on a single Oxford Nanopore MinION flow cell run for 24 hr. Using only reads longer than 1 kb or with at least 30x coverage, we assembled a highly contiguous de novo genome. The addition of inexpensive paired reads and subsequent scaffolding using an optical map technology achieved an assembly with completeness and contiguity comparable to the D. melanogaster reference assembly. Comparison of our assembly to the reference assembly of ISO1 uncovered a number of structural variants (SVs), including novel LTR transposable element insertions and duplications affecting genes with developmental, behavioral, and metabolic functions. Collectively, these SVs provide a snapshot of the dynamics of genome evolution. Furthermore, our assembly and comparison to the D. melanogaster reference genome demonstrates that high-quality de novo assembly of reference genomes and comprehensive variant discovery using such assemblies are now possible by a single lab for under $1,000 (USD).", "date": "2018-10-01T00:00:00Z", "citationCount": 70, "authors": [ { "name": "Solares E.A." }, { "name": "Chakraborty M." }, { "name": "Miller D.E." }, { "name": "Kalsow S." }, { "name": "Hall K." }, { "name": "Perera A.G." }, { "name": "Emerson J.J." }, { "name": "Scott Hawley R." } ], "journal": "G3: Genes, Genomes, Genetics" } } ], "credit": [ { "name": "Mahul Chakraborty", "email": null, "url": "https://mahulchakraborty.wordpress.com/", "orcidid": "https://orcid.org/0000-0003-2414-9187", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "Kigaard", "additionDate": "2021-05-27T09:04:45Z", "lastUpdate": "2025-06-18T12:17:20.983962Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-CZ", "Keiler_Collier" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Racon", "description": "Consensus module for raw de novo DNA assembly of long uncorrected reads\n\nRacon is intended as a standalone consensus module to correct raw contigs generated by rapid assembly methods which do not include a consensus step. The goal of Racon is to generate genomic consensus which is of similar or better quality compared to the output generated by assembly methods which employ both error correction and consensus steps, while providing a speedup of several times compared to those methods. It supports data produced by both Pacific Biosciences and Oxford Nanopore Technologies.", "homepage": "https://github.com/isovic/racon", "biotoolsID": "Racon", "biotoolsCURIE": "biotools:Racon", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_0523", "term": "Mapping assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_2572", "term": "BAM" }, { "uri": "http://edamontology.org/format_2573", "term": "SAM" } ] }, { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": "# The mapping file can be generated with any mapping program - eg, bwa-mem or minimap2.\n# The following is an example using minimap2 with ONT data\nminimap2 assembly.fa-ax map-ont reads.fa > mapped_reads.sam", "cmd": "racon -u reads.fa mapped_reads.sam assembly.fa > assembly_racon.fa" } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_3673", "term": "Whole genome sequencing" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "C++", "Python" ], "license": "MIT", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/isovic/racon", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/isovic/racon/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.3390/plants8080270", "pmid": "31390788", "pmcid": "PMC6724115", "type": [], "version": null, "note": null, "metadata": { "title": "Constructing a reference genome in a single lab: The possibility to use oxford nanopore technology", "abstract": "The whole genome sequencing (WGS) has become a crucial tool in understanding genome structure and genetic variation. The MinION sequencing of Oxford Nanopore Technologies (ONT) is an excellent approach for performing WGS and it has advantages in comparison with other Next-Generation Sequencing (NGS): It is relatively inexpensive, portable, has simple library preparation, can be monitored in real-time, and has no theoretical limits on reading length. Sorghum bicolor (L.) Moench is diploid (2n = 2x = 20) with a genome size of about 730 Mb, and its genome sequence information is released in the Phytozome database. Therefore, sorghum can be used as a good reference. However, plant species have complex and large genomes when compared to animals or microorganisms. As a result, complete genome sequencing is difficult for plant species. MinION sequencing that produces long-reads can be an excellent tool for overcoming the weak assembly of short-reads generated from NGS by minimizing the generation of gaps or covering the repetitive sequence that appears on the plant genome. Here, we conducted the genome sequencing for S. bicolor cv. BTx623 while using the MinION platform and obtained 895,678 reads and 17.9 gigabytes (Gb) (ca. 25× coverage of reference) from long-read sequence data. A total of 6124 contigs (covering 45.9%) were generated from Canu, and a total of 2661 contigs (covering 50%) were generated from Minimap and Miniasm with a Racon through a de novo assembly using two different tools and mapped assembled contigs against the sorghum reference genome. Our results provide an optimal series of long-read sequencing analysis for plant species while using the MinION platform and a clue to determine the total sequencing scale for optimal coverage that is based on various genome sizes.", "date": "2019-08-01T00:00:00Z", "citationCount": 13, "authors": [ { "name": "Lee Y.G." }, { "name": "Choi S.C." }, { "name": "Kang Y." }, { "name": "Kim K.M." }, { "name": "Kang C.-S." }, { "name": "Kim C." } ], "journal": "Plants" } } ], "credit": [ { "name": "Chon-Sik Kang", "email": "cskang@korea.kr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Changsoo Kim", "email": "changsookim@cnu.ac.kr", "url": null, "orcidid": "https://orcid.org/0000-0002-3596-2934", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "Pub2Tools", "additionDate": "2019-11-14T18:44:38Z", "lastUpdate": "2025-06-18T11:42:42.378216Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "Flye", "description": "Flye is a de novo assembler for single molecule sequencing reads, such as those produced by PacBio and Oxford Nanopore Technologies. It is designed for a wide range of datasets, from small bacterial projects to large mammalian-scale assemblies. The package represents a complete pipeline: it takes raw PB / ONT reads as input and outputs polished contigs.", "homepage": "https://github.com/fenderglass/Flye", "biotoolsID": "Flye", "biotoolsCURIE": "biotools:Flye", "version": [ "2.9.6" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_0524", "term": "De-novo assembly" }, { "uri": "http://edamontology.org/operation_0523", "term": "Mapping assembly" }, { "uri": "http://edamontology.org/operation_3730", "term": "Cross-assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Workflow" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_3673", "term": "Whole genome sequencing" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "C++", "Python", "C" ], "license": "BSD-3-Clause", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/fenderglass/Flye/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/mikolmogorov/Flye", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1099/mgen.0.000294", "pmid": "31483244", "pmcid": "PMC6807382", "type": [ "Usage" ], "version": null, "note": null, "metadata": { "title": "Comparison of long-read sequencing technologies in the hybrid assembly of complex bacterial genomes", "abstract": "Illumina sequencing allows rapid, cheap and accurate whole genome bacterial analyses, but short reads (<300 bp) do not usually enable complete genome assembly. Long-read sequencing greatly assists with resolving complex bacterial genomes, particularly when combined with short-read Illumina data (hybrid assembly). However, it is not clear how different long-read sequencing methods affect hybrid assembly accuracy. Relative automation of the assembly process is also crucial to facilitating high-throughput complete bacterial genome reconstruction, avoiding multiple bespoke filtering and data manipulation steps. In this study, we compared hybrid assemblies for 20 bacterial isolates, including two reference strains, using Illumina sequencing and long reads from either Oxford Nanopore Technologies (ONT) or SMRT Pacific Biosciences (PacBio) sequencing platforms. We chose isolates from the family Enterobacteriaceae, as these frequently have highly plastic, repetitive genetic structures, and complete genome reconstruction for these species is relevant for a precise understanding of the epidemiology of antimicrobial resistance. We de novo assembled genomes using the hybrid assembler Unicycler and compared different read processing strategies, as well as comparing to long-read-only assembly with Flye followed by short-read polishing with Pilon. Hybrid assembly with either PacBio or ONT reads facilitated high-quality genome reconstruction, and was superior to the longread assembly and polishing approach evaluated with respect to accuracy and completeness. Combining ONT and Illumina reads fully resolved most genomes without additional manual steps, and at a lower consumables cost per isolate in our setting. Automated hybrid assembly is a powerful tool for complete and accurate bacterial genome assembly.", "date": "2019-01-01T00:00:00Z", "citationCount": 166, "authors": [ { "name": "De Maio N." }, { "name": "Shaw L.P." }, { "name": "Hubbard A." }, { "name": "George S." }, { "name": "Sanderson N.D." }, { "name": "Swann J." }, { "name": "Wick R." }, { "name": "Oun M.A." }, { "name": "Stubberfield E." }, { "name": "Hoosdally S.J." }, { "name": "Crook D.W." }, { "name": "Peto T.E.A." }, { "name": "Sheppard A.E." }, { "name": "Bailey M.J." }, { "name": "Read D.S." }, { "name": "Anjum M.F." }, { "name": "Sarah Walker A." }, { "name": "Stoesser N." } ], "journal": "Microbial Genomics" } }, { "doi": "10.1038/s41587-019-0072-8", "pmid": "30936562", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Assembly of long, error-prone reads using repeat graphs", "abstract": "Accurate genome assembly is hampered by repetitive regions. Although long single molecule sequencing reads are better able to resolve genomic repeats than short-read data, most long-read assembly algorithms do not provide the repeat characterization necessary for producing optimal assemblies. Here, we present Flye, a long-read assembly algorithm that generates arbitrary paths in an unknown repeat graph, called disjointigs, and constructs an accurate repeat graph from these error-riddled disjointigs. We benchmark Flye against five state-of-the-art assemblers and show that it generates better or comparable assemblies, while being an order of magnitude faster. Flye nearly doubled the contiguity of the human genome assembly (as measured by the NGA50 assembly quality metric) compared with existing assemblers.", "date": "2019-05-01T00:00:00Z", "citationCount": 3077, "authors": [ { "name": "Kolmogorov M." }, { "name": "Yuan J." }, { "name": "Lin Y." }, { "name": "Pevzner P.A." } ], "journal": "Nature Biotechnology" } }, { "doi": "10.1038/s41592-020-00971-x", "pmid": "33020656", "pmcid": "PMC10699202", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "metaFlye: scalable long-read metagenome assembly using repeat graphs", "abstract": "Long-read sequencing technologies have substantially improved the assemblies of many isolate bacterial genomes as compared to fragmented short-read assemblies. However, assembling complex metagenomic datasets remains difficult even for state-of-the-art long-read assemblers. Here we present metaFlye, which addresses important long-read metagenomic assembly challenges, such as uneven bacterial composition and intra-species heterogeneity. First, we benchmarked metaFlye using simulated and mock bacterial communities and show that it consistently produces assemblies with better completeness and contiguity than state-of-the-art long-read assemblers. Second, we performed long-read sequencing of the sheep microbiome and applied metaFlye to reconstruct 63 complete or nearly complete bacterial genomes within single contigs. Finally, we show that long-read assembly of human microbiomes enables the discovery of full-length biosynthetic gene clusters that encode biomedically important natural products.", "date": "2020-11-01T00:00:00Z", "citationCount": 511, "authors": [ { "name": "Kolmogorov M." }, { "name": "Bickhart D.M." }, { "name": "Behsaz B." }, { "name": "Gurevich A." }, { "name": "Rayko M." }, { "name": "Shin S.B." }, { "name": "Kuhn K." }, { "name": "Yuan J." }, { "name": "Polevikov E." }, { "name": "Smith T.P.L." }, { "name": "Pevzner P.A." } ], "journal": "Nature Methods" } } ], "credit": [ { "name": "Mikhail Kolmogorov", "email": "fenderglass@gmail.com", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Support" ], "note": null }, { "name": "Yu Lin", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Jeffrey Yuan", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "Pub2Tools", "additionDate": "2019-11-14T20:08:20Z", "lastUpdate": "2025-06-18T10:20:03.775603Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "BUSCO", "description": "Provides measures for quantitative assessment of genome assembly, gene set, and transcriptome completeness based on evolutionarily informed expectations of gene content from near-universal single-copy orthologs.", "homepage": "https://busco.ezlab.org/", "biotoolsID": "busco", "biotoolsCURIE": "biotools:busco", "version": [ "1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3180", "term": "Sequence assembly validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_3308", "term": "Transcriptomics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [ "Tools" ], "elixirNode": [ "Switzerland" ], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://busco.ezlab.org/busco_userguide.html", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btv351", "pmid": "26059717", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO: Assessing genome assembly and annotation completeness with single-copy orthologs", "abstract": "Motivation: Genomics has revolutionized biological research, but quality assessment of the resulting assembled sequences is complicated and remains mostly limited to technical measures like N50. Results: We propose a measure for quantitative assessment of genome assembly and annotation completeness based on evolutionarily informed expectations of gene content. We implemented the assessment procedure in open-source software, with sets of Benchmarking Universal Single-Copy Orthologs, named BUSCO.", "date": "2015-10-01T00:00:00Z", "citationCount": 8766, "authors": [ { "name": "Simao F.A." }, { "name": "Waterhouse R.M." }, { "name": "Ioannidis P." }, { "name": "Kriventseva E.V." }, { "name": "Zdobnov E.M." } ], "journal": "Bioinformatics" } }, { "doi": "10.1002/cpz1.323", "pmid": "34936221", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO: Assessing Genomic Data Quality and Beyond", "abstract": "Evaluation of the quality of genomic “data products” such as genome assemblies or gene sets is of critical importance in order to recognize possible issues and correct them during the generation of new data. It is equally essential to guide subsequent or comparative analyses with existing data, as the correct interpretation of the results necessarily requires knowledge about the quality level and reliability of the inputs. Using datasets of near universal single-copy orthologs derived from OrthoDB, BUSCO can estimate the completeness and redundancy of genomic data by providing biologically meaningful metrics based on expected gene content. These can complement technical metrics such as contiguity measures (e.g., number of contigs/scaffolds, and N50 values). Here, we describe the use of the BUSCO tool suite to assess different data types that can range from genome assemblies of single isolates and assembled transcriptomes and annotated gene sets to metagenome-assembled genomes where the taxonomic origin of the species is unknown. BUSCO is the only tool capable of assessing all these types of sequences from both eukaryotic and prokaryotic species. The protocols detail the various BUSCO running modes and the novel workflows introduced in versions 4 and 5, including the batch analysis on multiple inputs, the auto-lineage workflow to run assessments without specifying a dataset, and a workflow for the evaluation of (large) eukaryotic genomes. The protocols further cover the BUSCO setup, guidelines to interpret the results, and BUSCO “plugin” workflows for performing common operations in genomics using BUSCO results, such as building phylogenomic trees and visualizing syntenies. © 2021 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Assessing an input sequence with a BUSCO dataset specified manually. Basic Protocol 2: Assessing an input sequence with a dataset automatically selected by BUSCO. Basic Protocol 3: Assessing multiple inputs. Alternate Protocol: Decreasing analysis runtime when assessing a large number of small genomes with BUSCO auto-lineage workflow and Snakemake. Support Protocol 1: BUSCO setup. Support Protocol 2: Visualizing BUSCO results. Support Protocol 3: Building phylogenomic trees.", "date": "2021-12-01T00:00:00Z", "citationCount": 566, "authors": [ { "name": "Manni M." }, { "name": "Berkeley M.R." }, { "name": "Seppey M." }, { "name": "Zdobnov E.M." } ], "journal": "Current Protocols" } }, { "doi": "10.1093/molbev/msx319", "pmid": "29220515", "pmcid": "PMC5850278", "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO applications from quality assessments to gene prediction and phylogenomics", "abstract": "Genomics promises comprehensive surveying of genomes and metagenomes, but rapidly changing technologies and expanding data volumes make evaluation of completeness a challenging task. Technical sequencing quality metrics can be complemented by quantifying completeness of genomic data sets in terms of the expected gene content of Benchmarking Universal Single-Copy Orthologs (BUSCO, http://busco.ezlab.org) The latest software release implements a complete refactoring of the code tomake itmore flexible and extendable to facilitate high-Throughput assessments. The original six lineage assessment data sets have been updated with improved species sampling, 34 new subsets have been built for vertebrates, arthropods, fungi, and prokaryotes that greatly enhance resolution, and data sets are now also available for nematodes, protists, and plants. Here, we present BUSCO v3 with example analyses that highlight the wideranging utility of BUSCO assessments, which extend beyond quality control of genomics data sets to applications in comparative genomics analyses, gene predictor training, metagenomics, and phylogenomics.", "date": "2018-03-01T00:00:00Z", "citationCount": 1508, "authors": [ { "name": "Waterhouse R.M." }, { "name": "Seppey M." }, { "name": "Simao F.A." }, { "name": "Manni M." }, { "name": "Ioannidis P." }, { "name": "Klioutchnikov G." }, { "name": "Kriventseva E.V." }, { "name": "Zdobnov E.M." } ], "journal": "Molecular Biology and Evolution" } }, { "doi": "10.1093/molbev/msab199", "pmid": "34320186", "pmcid": "PMC8476166", "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO Update: Novel and Streamlined Workflows along with Broader and Deeper Phylogenetic Coverage for Scoring of Eukaryotic, Prokaryotic, and Viral Genomes", "abstract": "Methods for evaluating the quality of genomic and metagenomic data are essential to aid genome assembly procedures and to correctly interpret the results of subsequent analyses. BUSCO estimates the completeness and redundancy of processed genomic data based on universal single-copy orthologs. Here, we present new functionalities and major improvements of the BUSCO software, as well as the renewal and expansion of the underlying data sets in sync with the OrthoDB v10 release. Among the major novelties, BUSCO now enables phylogenetic placement of the input sequence to automatically select the most appropriate BUSCO data set for the assessment, allowing the analysis of metagenome-Assembled genomes of unknown origin. A newly introduced genome workflow increases the efficiency and runtimes especially on large eukaryotic genomes. BUSCO is the only tool capable of assessing both eukaryotic and prokaryotic species, and can be applied to various data types, from genome assemblies and metagenomic bins, to transcriptomes and gene sets.", "date": "2021-10-01T00:00:00Z", "citationCount": 2710, "authors": [ { "name": "Manni M." }, { "name": "Berkeley M.R." }, { "name": "Seppey M." }, { "name": "Simao F.A." }, { "name": "Zdobnov E.M." } ], "journal": "Molecular Biology and Evolution" } } ], "credit": [ { "name": "SIB Swiss Institute of Bioinformatics", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": "evgeny.zdobnov@unige.ch", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "SIB", "additionDate": "2016-10-10T07:21:30Z", "lastUpdate": "2025-06-17T15:10:57.224896Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null } ] }
