Resource List
List all resources, or create a new resource.
GET /api/t/?dataFormatID=%22format_1929%22&format=api
{ "count": 847, "next": "?page=2", "previous": null, "list": [ { "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": "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": [ "2.11.5.0" ], "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" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" }, { "uri": "http://edamontology.org/operation_0324", "term": "Phylogenetic tree analysis" }, { "uri": "http://edamontology.org/operation_3081", "term": "Sequence alignment editing" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1939", "term": "GFF3-seq" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" }, { "uri": "http://edamontology.org/format_1938", "term": "GFF2-seq" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1948", "term": "nbrf/pir" }, { "uri": "http://edamontology.org/format_3774", "term": "BioJSON (Jalview)" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" }, { "uri": "http://edamontology.org/format_3313", "term": "BLC" }, { "uri": "http://edamontology.org/format_3311", "term": "RNAML" }, { "uri": "http://edamontology.org/format_1947", "term": "GCG MSF" }, { "uri": "http://edamontology.org/format_3015", "term": "Pileup" }, { "uri": "http://edamontology.org/format_1477", "term": "mmCIF" }, { "uri": "http://edamontology.org/format_3016", "term": "VCF" }, { "uri": "http://edamontology.org/format_1915", "term": "Format" } ] }, { "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_3464", "term": "JSON" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" }, { "uri": "http://edamontology.org/format_3313", "term": "BLC" }, { "uri": "http://edamontology.org/format_3774", "term": "BioJSON (Jalview)" }, { "uri": "http://edamontology.org/format_1947", "term": "GCG MSF" }, { "uri": "http://edamontology.org/format_3015", "term": "Pileup" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" } ] }, { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [ { "uri": "http://edamontology.org/format_3603", "term": "PNG" }, { "uri": "http://edamontology.org/format_2331", "term": "HTML" }, { "uri": "http://edamontology.org/format_3466", "term": "EPS" }, { "uri": "http://edamontology.org/format_3604", "term": "SVG" }, { "uri": "http://edamontology.org/format_1915", "term": "Format" } ] } ], "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": [ "Linux", "Windows", "Mac" ], "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://source.jalview.org/crucible/browse/jalview", "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" } ], "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": 7499, "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": "2025-09-04T13:26:28.643607Z", "editPermission": { "type": "group", "authors": [ "ben_s", "jimprocter" ] }, "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": [ "v1.11.4" ], "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_1927", "term": "EMBL format" }, { "uri": "http://edamontology.org/format_1975", "term": "GFF3" }, { "uri": "http://edamontology.org/format_3464", "term": "JSON" }, { "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_3603", "term": "PNG" }, { "uri": "http://edamontology.org/format_3604", "term": "SVG" } ] }, { "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": [ "Command-line tool", "Web application" ], "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": { "title": "Bakta: Rapid and standardized annotation of bacterial genomes via alignment-free sequence identification", "abstract": "", "date": "2021-01-01T00:00:00Z", "citationCount": 582, "authors": [], "journal": "Microbial Genomics" } } ], "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": "2025-09-01T07:59:35.735958Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-CZ", "bebatut" ] }, "validated": 0, "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": "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": "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": "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://ccb.jhu.edu/software/kraken2/", "biotoolsID": "kraken2", "biotoolsCURIE": "biotools:kraken2", "version": [ "2.0.8-beta" ], "otherID": [], "relation": [ { "biotoolsID": "kraken", "type": "isNewVersionOf" }, { "biotoolsID": "bracken", "type": "usedBy" } ], "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": [ "C++", "Perl" ], "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": "2025-06-18T12:24:26.657325Z", "editPermission": { "type": "group", "authors": [ "vashokan", "Keiler_Collier" ] }, "validated": 1, "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": "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": "2025-06-18T11:53:52.861712Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-CZ", "Keiler_Collier" ] }, "validated": 1, "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 }, { "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", "1.22" ], "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_2573", "term": "SAM" }, { "uri": "http://edamontology.org/format_2572", "term": "BAM" }, { "uri": "http://edamontology.org/format_3462", "term": "CRAM" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_3498", "term": "Sequence variations" }, "format": [ { "uri": "http://edamontology.org/format_3016", "term": "VCF" }, { "uri": "http://edamontology.org/format_3020", "term": "BCF" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0924", "term": "Sequence trace" }, "format": [ { "uri": "http://edamontology.org/format_2573", "term": "SAM" }, { "uri": "http://edamontology.org/format_2572", "term": "BAM" }, { "uri": "http://edamontology.org/format_3462", "term": "CRAM" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_3498", "term": "Sequence variations" }, "format": [ { "uri": "http://edamontology.org/format_3016", "term": "VCF" }, { "uri": "http://edamontology.org/format_3020", "term": "BCF" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Library" ], "topic": [ { "uri": "http://edamontology.org/topic_3071", "term": "Data management" } ], "operatingSystem": [ "Linux", "Windows", "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": { "title": "HTSlib: C library for reading/writing high-Throughput sequencing data", "abstract": "Background: Since the original publication of the VCF and SAM formats, an explosion of software tools have been created to process these data files. To facilitate this a library was produced out of the original SAMtools implementation, with a focus on performance and robustness. The file formats themselves have become international standards under the jurisdiction of the Global Alliance for Genomics and Health. Findings: We present a software library for providing programmatic access to sequencing alignment and variant formats. It was born out of the widely used SAMtools and BCFtools applications. Considerable improvements have been made to the original code plus many new features including newer access protocols, the addition of the CRAM file format, better indexing and iterators, and better use of threading. Conclusion: Since the original Samtools release, performance has been considerably improved, with a BAM read-write loop running 5 times faster and BAM to SAM conversion 13 times faster (both using 16 threads, compared to Samtools 0.1.19). Widespread adoption has seen HTSlib downloaded >1 million times from GitHub and conda. The C library has been used directly by an estimated 900 GitHub projects and has been incorporated into Perl, Python, Rust, and R, significantly expanding the number of uses via other languages. HTSlib is open source and is freely available from htslib.org under MIT/BSD license.", "date": "2021-02-01T00:00:00Z", "citationCount": 189, "authors": [ { "name": "Bonfield J.K." }, { "name": "Marshall J." }, { "name": "Danecek P." }, { "name": "Li H." }, { "name": "Ohan V." }, { "name": "Whitwham A." }, { "name": "Keane T." } ], "journal": "GigaScience" } } ], "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": "2025-06-03T09:00:20.313887Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics", "smoe" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MuGVRE", "description": "The MuG Virtual Research Environment is an analysis platform for 3D/4D genomics analyses. It integrates genomics tools for chromatin dynamics data.", "homepage": "https://www.multiscalegenomics.eu/", "biotoolsID": "mugvre", "biotoolsCURIE": "biotools:mugvre", "version": [ "1.0" ], "otherID": [], "relation": [ { "biotoolsID": "nucleosome_dynamics", "type": "includes" }, { "biotoolsID": "tadbit", "type": "includes" }, { "biotoolsID": "jbrowse", "type": "includes" }, { "biotoolsID": "ngl", "type": "includes" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" }, { "uri": "http://edamontology.org/operation_3198", "term": "Read mapping" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_3210", "term": "Genome index" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_2572", "term": "BAM" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0475", "term": "Nucleic acid structure prediction" }, { "uri": "http://edamontology.org/operation_2426", "term": "Modelling and simulation" }, { "uri": "http://edamontology.org/operation_0279", "term": "Nucleic acid folding analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" } ] }, { "data": { "uri": "http://edamontology.org/data_1255", "term": "Sequence features" }, "format": [ { "uri": "http://edamontology.org/format_2305", "term": "GFF" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3870", "term": "Trajectory data" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1460", "term": "Protein structure" }, "format": [ { "uri": "http://edamontology.org/format_1476", "term": "PDB" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0478", "term": "Molecular docking" }, { "uri": "http://edamontology.org/operation_3900", "term": "DNA-binding protein prediction" } ], "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_2877", "term": "Protein complex" }, "format": [ { "uri": "http://edamontology.org/format_1476", "term": "PDB" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3222", "term": "Peak calling" }, { "uri": "http://edamontology.org/operation_1781", "term": "Gene regulatory network analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0905", "term": "Protein interaction raw data" }, "format": [ { "uri": "http://edamontology.org/format_2572", "term": "BAM" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1276", "term": "Nucleic acid features" }, "format": [ { "uri": "http://edamontology.org/format_3003", "term": "BED" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3927", "term": "Network analysis" }, { "uri": "http://edamontology.org/operation_0279", "term": "Nucleic acid folding analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0905", "term": "Protein interaction raw data" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3872", "term": "Topology data" }, "format": [ { "uri": "http://edamontology.org/format_4002", "term": "pickle" } ] }, { "data": { "uri": "http://edamontology.org/data_0906", "term": "Protein interaction data" }, "format": [ { "uri": "http://edamontology.org/format_4002", "term": "pickle" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2478", "term": "Nucleic acid sequence analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1461", "term": "Protein-ligand complex" }, "format": [ { "uri": "http://edamontology.org/format_1476", "term": "PDB" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2084", "term": "Nucleic acid report" }, "format": [] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2476", "term": "Molecular dynamics" }, { "uri": "http://edamontology.org/operation_2481", "term": "Nucleic acid structure analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0883", "term": "Structure" }, "format": [ { "uri": "http://edamontology.org/format_1476", "term": "PDB" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3870", "term": "Trajectory data" }, "format": [] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0432", "term": "Nucleosome position prediction" }, { "uri": "http://edamontology.org/operation_3454", "term": "Phasing" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0905", "term": "Protein interaction raw data" }, "format": [ { "uri": "http://edamontology.org/format_2572", "term": "BAM" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [ { "uri": "http://edamontology.org/format_2305", "term": "GFF" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_0570", "term": "Structure visualisation" }, { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" }, { "uri": "http://edamontology.org/operation_3925", "term": "Network visualisation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2012", "term": "Sequence coordinates" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3869", "term": "Simulation" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_0883", "term": "Structure" }, "format": [] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application", "Workbench" ], "topic": [ { "uri": "http://edamontology.org/topic_3176", "term": "DNA packaging" }, { "uri": "http://edamontology.org/topic_3169", "term": "ChIP-seq" }, { "uri": "http://edamontology.org/topic_0097", "term": "Nucleic acid structure analysis" }, { "uri": "http://edamontology.org/topic_2275", "term": "Molecular modelling" } ], "operatingSystem": [], "language": [ "PHP", "Python" ], "license": "Apache-2.0", "collectionID": [ "RIS3CAT VEIS" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://vre.multiscalegenomics.eu", "type": [ "Service" ], "note": null }, { "url": "https://github.com/Multiscale-Genomics/VRE", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [ { "url": "https://www.multiscalegenomics.eu/MuGVRE/terms-of-use/", "type": [ "Terms of use" ], "note": null }, { "url": "http://vre.multiscalegenomics.eu/help/starting.php", "type": [ "Quick start guide" ], "note": null }, { "url": "https://www.multiscalegenomics.eu/MuGVRE/training/", "type": [ "Training material" ], "note": null } ], "publication": [ { "doi": "10.1101/602474", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": "1.0", "note": null, "metadata": null } ], "credit": [ { "name": "Laia Codó", "email": "laia.codo@bsc.es", "url": null, "orcidid": "https://orcid.org/0000-0002-6797-8746", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Josep Lluís Gelpí", "email": null, "url": null, "orcidid": "http://orcid.org/0000-0002-0566-7723", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Contributor" ], "note": null }, { "name": "Multiscale Complex Genomics Community", "email": "vre@multiscalegenomics.eu", "url": "https://www.multiscalegenomics.eu/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Consortium", "typeRole": [ "Developer" ], "note": null } ], "owner": "lcodo", "additionDate": "2021-01-12T12:02:47Z", "lastUpdate": "2025-05-29T11:46:19.236621Z", "editPermission": { "type": "group", "authors": [ "gelpi@ub.edu" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "SpliceMachine", "description": "Splice site prediction.", "homepage": "http://bioinformatics.psb.ugent.be/software/details/SpliceMachine", "biotoolsID": "splicemachine", "biotoolsCURIE": "biotools:splicemachine", "version": [ "1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0433", "term": "Splice site prediction" } ], "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_2070", "term": "Sequence motif (nucleic acid)" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3511", "term": "Nucleic acid sites, features and motifs" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Java" ], "license": null, "collectionID": [ "BIG N2N", "VIB", "Plant Systems Biology", "UGent" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://bioinformatics.psb.ugent.be/webtools/splicemachine/help/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/bti166", "pmid": "15564294", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "ugent.be", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": "yves.vandepeer@psb.vib-ugent.be", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "Katrijn.Vannerum@ugent.be", "additionDate": "2016-05-17T10:18:56Z", "lastUpdate": "2025-05-13T13:36:17.236762Z", "editPermission": { "type": "group", "authors": [ "Bharathi" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NetGene2", "description": "Neural network predictions of splice sites in human, C. elegans and A. thaliana DNA.", "homepage": "http://cbs.dtu.dk/services/NetGene2/", "biotoolsID": "netgene2", "biotoolsCURIE": "biotools:netgene2", "version": [ "1.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0433", "term": "Splice site prediction" } ], "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": "Neural network predictions of splice sites", "cmd": null } ], "toolType": [ "Command-line tool", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" }, { "uri": "http://edamontology.org/topic_3512", "term": "Gene transcripts" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": "Other", "collectionID": [ "CBS DTU" ], "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/NetGene2/instruct.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/24.17.3439", "pmid": "8811101", "pmcid": "PMC146109", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "Splice site prediction in Arabidopsis thaliana pre-mRNA by combining local and global sequence information", "abstract": "Artificial neural networks have been combined with a rule based system to predict intron splice sites in the dicot plant Arabidopsis thaliana. A two step prediction scheme, where a global prediction of the coding potential regulates a cutoff level for a local prediction of splice sites, is refined by rules based on splice site confidence values, prediction scores, coding context and distances between potential splice sites. In this approach, the prediction of splice sites mutually affect each other in a non-local manner. The combined approach drastically reduces the large amount of false positive splice sites normally haunting splice site prediction. An analysis of the errors made by the networks in the first step of the method revealed a previously unknown feature, a frequent T-tract prolongation containing cryptic acceptor sites in the 5' end of exons. The method presented here has been compared with three other approaches, GeneFinder, GeneMark and Grail. Overall the method presented here is an order of magnitude better. We show that the new method is able to find a donor site in the coding sequence for the jelly fish Green Fluorescent Protein, exactly at the position that was experimentally observed in A.thaliana transformants. Predictions for alternatively spliced genes are also presented, together with examples of genes from other dicots, monocots and algae. The method has been made available through electronic mail.", "date": "1996-01-01T00:00:00Z", "citationCount": 690, "authors": [ { "name": "Hebsgaard S.M." }, { "name": "Korning P.G." }, { "name": "Tolstrup N." }, { "name": "Engelbrecht J." }, { "name": "Rouze P." }, { "name": "Brunak S." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/24.17.3439", "pmid": "8811101", "pmcid": "PMC146109", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "Splice site prediction in Arabidopsis thaliana pre-mRNA by combining local and global sequence information", "abstract": "Artificial neural networks have been combined with a rule based system to predict intron splice sites in the dicot plant Arabidopsis thaliana. A two step prediction scheme, where a global prediction of the coding potential regulates a cutoff level for a local prediction of splice sites, is refined by rules based on splice site confidence values, prediction scores, coding context and distances between potential splice sites. In this approach, the prediction of splice sites mutually affect each other in a non-local manner. The combined approach drastically reduces the large amount of false positive splice sites normally haunting splice site prediction. An analysis of the errors made by the networks in the first step of the method revealed a previously unknown feature, a frequent T-tract prolongation containing cryptic acceptor sites in the 5' end of exons. The method presented here has been compared with three other approaches, GeneFinder, GeneMark and Grail. Overall the method presented here is an order of magnitude better. We show that the new method is able to find a donor site in the coding sequence for the jelly fish Green Fluorescent Protein, exactly at the position that was experimentally observed in A.thaliana transformants. Predictions for alternatively spliced genes are also presented, together with examples of genes from other dicots, monocots and algae. The method has been made available through electronic mail.", "date": "1996-01-01T00:00:00Z", "citationCount": 690, "authors": [ { "name": "Hebsgaard S.M." }, { "name": "Korning P.G." }, { "name": "Tolstrup N." }, { "name": "Engelbrecht J." }, { "name": "Rouze P." }, { "name": "Brunak S." } ], "journal": "Nucleic Acids Research" } } ], "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 } ], "owner": "CBS", "additionDate": "2015-06-29T10:15:39Z", "lastUpdate": "2025-05-13T13:36:16.138281Z", "editPermission": { "type": "group", "authors": [ "Bharathi" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "OpenMS", "description": "Open source library and a collection of tools and interfaces for the analysis of mass spectrometry data. Includes over 200 standalone (TOPP) tools that can be combined to a workflow with the integrated workflow editor TOPPAS. Raw and intermediate mass spectrometry data can be visualised with the included viewer TOPPView.", "homepage": "http://www.openms.de", "biotoolsID": "openms", "biotoolsCURIE": "biotools:openms", "version": [ "2.0.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3767", "term": "Protein identification" }, { "uri": "http://edamontology.org/operation_1812", "term": "Parsing" }, { "uri": "http://edamontology.org/operation_2409", "term": "Data handling" }, { "uri": "http://edamontology.org/operation_3628", "term": "Chromatographic alignment" }, { "uri": "http://edamontology.org/operation_3627", "term": "Mass spectra calibration" }, { "uri": "http://edamontology.org/operation_0335", "term": "Formatting" }, { "uri": "http://edamontology.org/operation_3630", "term": "Protein quantification" }, { "uri": "http://edamontology.org/operation_3633", "term": "Retention time prediction" }, { "uri": "http://edamontology.org/operation_0226", "term": "Annotation" }, { "uri": "http://edamontology.org/operation_3092", "term": "Protein feature detection" }, { "uri": "http://edamontology.org/operation_3705", "term": "Isotope-coded protein label" }, { "uri": "http://edamontology.org/operation_3634", "term": "Label-free quantification" }, { "uri": "http://edamontology.org/operation_3639", "term": "iTRAQ" }, { "uri": "http://edamontology.org/operation_3631", "term": "Peptide identification" }, { "uri": "http://edamontology.org/operation_3215", "term": "Peak detection" }, { "uri": "http://edamontology.org/operation_3694", "term": "Mass spectrum visualisation" }, { "uri": "http://edamontology.org/operation_3635", "term": "Labeled quantification" }, { "uri": "http://edamontology.org/operation_3359", "term": "Splitting" }, { "uri": "http://edamontology.org/operation_3214", "term": "Spectral analysis" }, { "uri": "http://edamontology.org/operation_3629", "term": "Deisotoping" }, { "uri": "http://edamontology.org/operation_3649", "term": "Target-Decoy" }, { "uri": "http://edamontology.org/operation_3023", "term": "Prediction and recognition (protein)" }, { "uri": "http://edamontology.org/operation_2424", "term": "Comparison" }, { "uri": "http://edamontology.org/operation_3435", "term": "Standardisation and normalisation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2536", "term": "Mass spectrometry data" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" }, { "uri": "http://edamontology.org/format_3248", "term": "mzQuantML" }, { "uri": "http://edamontology.org/format_3652", "term": "dta" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_3747", "term": "protXML" }, { "uri": "http://edamontology.org/format_3764", "term": "idXML" }, { "uri": "http://edamontology.org/format_2549", "term": "OBO" }, { "uri": "http://edamontology.org/format_2332", "term": "XML" }, { "uri": "http://edamontology.org/format_3246", "term": "TraML" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" }, { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" }, { "uri": "http://edamontology.org/format_3654", "term": "mzXML" }, { "uri": "http://edamontology.org/format_3651", "term": "MGF" }, { "uri": "http://edamontology.org/format_3683", "term": "qcML" } ] }, { "data": { "uri": "http://edamontology.org/data_0849", "term": "Sequence record" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" }, { "uri": "http://edamontology.org/format_3248", "term": "mzQuantML" }, { "uri": "http://edamontology.org/format_3652", "term": "dta" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_3747", "term": "protXML" }, { "uri": "http://edamontology.org/format_3764", "term": "idXML" }, { "uri": "http://edamontology.org/format_2549", "term": "OBO" }, { "uri": "http://edamontology.org/format_2332", "term": "XML" }, { "uri": "http://edamontology.org/format_3246", "term": "TraML" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" }, { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" }, { "uri": "http://edamontology.org/format_3654", "term": "mzXML" }, { "uri": "http://edamontology.org/format_3651", "term": "MGF" }, { "uri": "http://edamontology.org/format_3683", "term": "qcML" } ] }, { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" }, { "uri": "http://edamontology.org/format_3248", "term": "mzQuantML" }, { "uri": "http://edamontology.org/format_3652", "term": "dta" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_3747", "term": "protXML" }, { "uri": "http://edamontology.org/format_3764", "term": "idXML" }, { "uri": "http://edamontology.org/format_2549", "term": "OBO" }, { "uri": "http://edamontology.org/format_2332", "term": "XML" }, { "uri": "http://edamontology.org/format_3246", "term": "TraML" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" }, { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" }, { "uri": "http://edamontology.org/format_3654", "term": "mzXML" }, { "uri": "http://edamontology.org/format_3651", "term": "MGF" }, { "uri": "http://edamontology.org/format_3683", "term": "qcML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" }, { "uri": "http://edamontology.org/format_3248", "term": "mzQuantML" }, { "uri": "http://edamontology.org/format_3652", "term": "dta" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_3764", "term": "idXML" }, { "uri": "http://edamontology.org/format_3654", "term": "mzXML" }, { "uri": "http://edamontology.org/format_3246", "term": "TraML" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" }, { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" }, { "uri": "http://edamontology.org/format_3651", "term": "MGF" }, { "uri": "http://edamontology.org/format_3683", "term": "qcML" } ] }, { "data": { "uri": "http://edamontology.org/data_2603", "term": "Expression data" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" }, { "uri": "http://edamontology.org/format_3248", "term": "mzQuantML" }, { "uri": "http://edamontology.org/format_3652", "term": "dta" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_3764", "term": "idXML" }, { "uri": "http://edamontology.org/format_3654", "term": "mzXML" }, { "uri": "http://edamontology.org/format_3246", "term": "TraML" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" }, { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" }, { "uri": "http://edamontology.org/format_3651", "term": "MGF" }, { "uri": "http://edamontology.org/format_3683", "term": "qcML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Library", "Workbench" ], "topic": [ { "uri": "http://edamontology.org/topic_3520", "term": "Proteomics experiment" }, { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" }, { "uri": "http://edamontology.org/topic_3172", "term": "Metabolomics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "C++" ], "license": "BSD-3-Clause", "collectionID": [ "KNIME", "de.NBI", "Proteomics", "OpenMS" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/OpenMS/OpenMS", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://github.com/OpenMS/OpenMS", "type": "Source code", "note": null, "version": null }, { "url": "http://sourceforge.net/projects/open-ms/files/OpenMS/OpenMS-2.0/", "type": "Binaries", "note": null, "version": null }, { "url": "https://github.com/OpenMS/OpenMS", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "http://ftp.mi.fu-berlin.de/pub/OpenMS/release-documentation/html/index.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1038/nmeth.3959", "pmid": "27575624", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "OpenMS: A flexible open-source software platform for mass spectrometry data analysis", "abstract": "© 2016 Nature America, Inc. All rights reserved.High-resolution mass spectrometry (MS) has become an important tool in the life sciences, contributing to the diagnosis and understanding of human diseases, elucidating biomolecular structural information and characterizing cellular signaling networks. However, the rapid growth in the volume and complexity of MS data makes transparent, accurate and reproducible analysis difficult. We present OpenMS 2.0 (http://www.openms.de), a robust, open-source, cross-platform software specifically designed for the flexible and reproducible analysis of high-throughput MS data. The extensible OpenMS software implements common mass spectrometric data processing tasks through a well-defined application programming interface in C++ and Python and through standardized open data formats. OpenMS additionally provides a set of 185 tools and ready-made workflows for common mass spectrometric data processing tasks, which enable users to perform complex quantitative mass spectrometric analyses with ease.", "date": "2016-08-30T00:00:00Z", "citationCount": 246, "authors": [ { "name": "Rost H.L." }, { "name": "Sachsenberg T." }, { "name": "Aiche S." }, { "name": "Bielow C." }, { "name": "Weisser H." }, { "name": "Aicheler F." }, { "name": "Andreotti S." }, { "name": "Ehrlich H.-C." }, { "name": "Gutenbrunner P." }, { "name": "Kenar E." }, { "name": "Liang X." }, { "name": "Nahnsen S." }, { "name": "Nilse L." }, { "name": "Pfeuffer J." }, { "name": "Rosenberger G." }, { "name": "Rurik M." }, { "name": "Schmitt U." }, { "name": "Veit J." }, { "name": "Walzer M." }, { "name": "Wojnar D." }, { "name": "Wolski W.E." }, { "name": "Schilling O." }, { "name": "Choudhary J.S." }, { "name": "Malmstrom L." }, { "name": "Aebersold R." }, { "name": "Reinert K." }, { "name": "Kohlbacher O." } ], "journal": "Nature Methods" } }, { "doi": "10.1007/978-1-60761-987-1_23", "pmid": null, "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "OpenMS and TOPP: open source software for LC-MS data analysis.", "abstract": "Proteomics experiments based on state-of-the-art mass spectrometry produce vast amounts of data, which cannot be analyzed manually. Hence, software is needed which is able to analyze the data in an automated fashion. The need for robust and reusable software tools triggered the development of libraries implementing different algorithms for the various analysis steps. OpenMS is such a software library and provides a wealth of data structures and algorithms for the analysis of mass spectrometric data. For users unfamiliar with programming, TOPP (\"The OpenMS Proteomics Pipeline\") offers a wide range of already implemented tools sharing the same interface and designed for a specific analysis task each. TOPP thus makes the sophisticated algorithms of OpenMS accessible to nonprogrammers. The individual TOPP tools can be strung together into pipelines for analyzing mass spectrometry-based experiments starting from the raw output of the mass spectrometer. These analysis pipelines can be constructed using a graphical editor. Even complex analytical workflows can thus be analyzed with ease.", "date": "2011-01-01T00:00:00Z", "citationCount": 65, "authors": [ { "name": "Bertsch A." }, { "name": "Gropl C." }, { "name": "Reinert K." }, { "name": "Kohlbacher O." } ], "journal": "Methods in molecular biology (Clifton, N.J.)" } } ], "credit": [ { "name": "ETH Zürich", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Eberhard-Karls-Universität Tübingen", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Freie Universität Berlin", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Center for Integrative Bioinformatics (CiBi)", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Consortium", "typeRole": [], "note": null }, { "name": "cibi", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "General Mailinglist", "email": "open-ms-general@lists.sourceforge.net", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Support" ], "note": null }, { "name": "General Mailinglist", "email": "open-ms-general@lists.sourceforge.net", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Hannes Röst", "email": null, "url": null, "orcidid": "http://orcid.org/0000-0003-0990-7488", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Contributor" ], "note": null } ], "owner": "samwein", "additionDate": "2016-01-19T16:39:56Z", "lastUpdate": "2025-04-30T11:39:30.251890Z", "editPermission": { "type": "group", "authors": [ "proteomics.bio.tools" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "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": [], "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" }, { "uri": "http://edamontology.org/format_2573", "term": "SAM" } ] } ], "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", "Windows", "Mac" ], "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": { "title": "Metagenomic microbial community profiling using unique clade-specific marker genes", "abstract": "Metagenomic shotgun sequencing data can identify microbes populating a microbial community and their proportions, but existing taxonomic profiling methods are inefficient for increasingly large data sets. We present an approach that uses clade-specific marker genes to unambiguously assign reads to microbial clades more accurately and >50Ã-faster than current approaches. We validated our metagenomic phylogenetic analysis tool, MetaPhlAn, on terabases of short reads and provide the largest metagenomic profiling to date of the human gut. It can be accessed at http://huttenhower.sph.harvard.edu/ metaphlan/. © 2012 Nature America, Inc. All rights reserved.", "date": "2012-08-01T00:00:00Z", "citationCount": 1300, "authors": [ { "name": "Segata N." }, { "name": "Waldron L." }, { "name": "Ballarini A." }, { "name": "Narasimhan V." }, { "name": "Jousson O." }, { "name": "Huttenhower C." } ], "journal": "Nature Methods" } } ], "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": "2025-04-22T12:44:24.859435Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics", "ELIXIR-CZ", "bebatut", "vashokan" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NetPicoRNA", "description": "Neural network predictions of cleavage sites of picornaviral proteases.", "homepage": "http://cbs.dtu.dk/services/NetPicoRNA/", "biotoolsID": "netpicorna", "biotoolsCURIE": "biotools:netpicorna", "version": [ "1.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0422", "term": "Protein cleavage site prediction" } ], "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 of cleavage sites of picornaviral proteases", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3510", "term": "Protein sites, features and motifs" }, { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" } ], "operatingSystem": [ "Linux" ], "language": [], "license": "Other", "collectionID": [], "maturity": "Legacy", "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/NetPicoRNA/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1002/pro.5560051107", "pmid": "8931139", "pmcid": "PMC2143287", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Cleavage site analysis in picornaviral polyproteins: Discovering cellular targets by neural networks", "abstract": "Picornaviral proteinases are responsible for maturation cleavages of the viral polyprotein, but also catalyze the degradation of cellular targets. Using graphical visualization techniques and neural network algorithms, we have investigated the sequence specificity of the two proteinases 2A(pro) and 3C(pro). The cleavage of VP0 (giving rise to VP2 and VP4), which is carried out by a so-far unknown proteinase, was also examined. In combination with a novel surface exposure prediction algorithm, our neural network approach successfully distinguishes known cleavage sites from noncleavage sites and yields a more consistent definition of features common to these sites. The method is able to predict experimentally determined cleavage sites in cellular proteins. We present a list of mammalian and other proteins that are predicted to be possible targets for the vital proteinases. Whether these proteins are indeed cleaved awaits experimental verification. Additionally, we report several errors detected in the protein databases.", "date": "1996-01-01T00:00:00Z", "citationCount": 204, "authors": [ { "name": "Blom N." }, { "name": "Hansen J." }, { "name": "Blaas D." }, { "name": "Brunak S." } ], "journal": "Protein Science" } } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Nikolaj Sorgenfrei Blom", "email": "nikob@cbs.dtu.dk", "url": null, "orcidid": "https://orcid.org/0000-0001-7787-7853", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "powehi", "additionDate": "2015-06-29T10:14:28Z", "lastUpdate": "2025-04-21T12:49:56.070719Z", "editPermission": { "type": "group", "authors": [ "powehi" ] }, "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_3508", "term": "PDF" }, { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "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": [], "version": "0.0.6", "note": null, "metadata": { "title": "prolfquapp ─ A User-Friendly Command-Line Tool Simplifying Differential Expression Analysis in Quantitative Proteomics", "abstract": "Mass spectrometry is a cornerstone of quantitative proteomics, enabling relative protein quantification and differential expression analysis (DEA) of proteins. As experiments grow in complexity, involving more samples, groups, and identified proteins, interactive differential expression analysis tools become impractical. The prolfquapp addresses this challenge by providing a command-line interface that simplifies DEA, making it accessible to nonprogrammers and seamlessly integrating it into workflow management systems. Prolfquapp streamlines data processing and result visualization by generating dynamic HTML reports that facilitate the exploration of differential expression results. These reports allow for investigating complex experiments, such as those involving repeated measurements or multiple explanatory variables. Additionally, prolfquapp supports various output formats, including XLSX files, SummarizedExperiment objects and rank files, for further interactive analysis using spreadsheet software, the exploreDE Shiny application, or gene set enrichment analysis software, respectively. By leveraging advanced statistical models from the prolfqua R package, prolfquapp offers a user-friendly, integrated solution for large-scale quantitative proteomics studies, combining efficient data processing with insightful, publication-ready outputs.", "date": "2025-02-07T00:00:00Z", "citationCount": 0, "authors": [ { "name": "Wolski W.E." }, { "name": "Grossmann J." }, { "name": "Schwarz L." }, { "name": "Leary P." }, { "name": "Turker C." }, { "name": "Nanni P." }, { "name": "Schlapbach R." }, { "name": "Panse C." } ], "journal": "Journal of Proteome Research" } } ], "credit": [], "owner": "n.m.palmblad@lumc.nl", "additionDate": "2025-02-28T15:04:33.594183Z", "lastUpdate": "2025-03-28T10:18:25.715685Z", "editPermission": { "type": "group", "authors": [ "thatmariia" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ProteoMaker", "description": "ProteoMaker is a platform for the generation of an in-silico bottom-up proteomics data set with a ground truth on the level of proteoforms.", "homepage": "https://github.com/computproteomics/ProteoMaker", "biotoolsID": "proteomaker", "biotoolsCURIE": "biotools:proteomaker", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3566", "term": "Simulated gene expression data generation" }, { "uri": "http://edamontology.org/operation_2238", "term": "Statistical calculation" } ], "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_3112", "term": "Gene expression matrix" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] }, { "data": { "uri": "http://edamontology.org/data_1238", "term": "Proteolytic digest" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] }, { "data": { "uri": "http://edamontology.org/data_3914", "term": "Quality control report" }, "format": [ { "uri": "http://edamontology.org/format_3750", "term": "YAML" } ] }, { "data": { "uri": "http://edamontology.org/data_0951", "term": "Statistical estimate score" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Library", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" }, { "uri": "http://edamontology.org/topic_3520", "term": "Proteomics experiment" }, { "uri": "http://edamontology.org/topic_3524", "term": "Simulation experiment" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "R" ], "license": "MIT", "collectionID": [ "Proteomics" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://computproteomics.bmb.sdu.dk/app_direct/ProteoMaker", "type": [ "Service" ], "note": "Web application" } ], "download": [ { "url": "https://github.com/computproteomics/ProteoMaker", "type": "Source code", "note": null, "version": null } ], "documentation": [], "publication": [], "credit": [], "owner": "veitveit11", "additionDate": "2025-01-31T17:19:47.094256Z", "lastUpdate": "2025-01-31T17:19:47.096981Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "shic", "description": "shic is a collection of shims for use in automated workflow composition", "homepage": "https://github.com/magnuspalmblad/shic", "biotoolsID": "shic", "biotoolsCURIE": "biotools:shic", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_3747", "term": "protXML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2872", "term": "ID list" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "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_2536", "term": "Mass spectrometry data" }, "format": [ { "uri": "http://edamontology.org/format_3651", "term": "MGF" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0870", "term": "Sequence distance matrix" }, "format": [ { "uri": "http://edamontology.org/format_1912", "term": "Nexus format" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0870", "term": "Sequence distance matrix" }, "format": [ { "uri": "http://edamontology.org/format_1991", "term": "mega" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "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_3021", "term": "UniProt accession" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0972", "term": "Text mining report" }, "format": [ { "uri": "http://edamontology.org/format_2332", "term": "XML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1174", "term": "ChEBI ID" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2872", "term": "ID list" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1009", "term": "Protein name" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3655", "term": "pepXML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2764", "term": "Protein name (UniProt)" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Script" ], "topic": [], "operatingSystem": [], "language": [], "license": "MIT", "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [ "Proteomics", "Galaxy", "Metabolomics" ], "link": [ { "url": "https://github.com/magnuspalmblad/shic", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [ { "url": "https://github.com/magnuspalmblad/shic/README.md", "type": [ "General" ], "note": null } ], "publication": [], "credit": [ { "name": "Magnus Palmblad", "email": "magnus.palmblad@gmail.com", "url": null, "orcidid": "https://orcid.org/0000-0002-5865-8994", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Primary contact" ], "note": null }, { "name": "Veit Schwämmle", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0002-9708-6722", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Dirk Winkelhardt", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0001-8770-2221", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Vedran Kasalica", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0002-0097-1056", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Anna-Lena Lamprecht", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0003-1953-5606", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "owner": "n.m.palmblad@lumc.nl", "additionDate": "2023-08-30T13:03:57.407598Z", "lastUpdate": "2025-01-16T16:39:33.218764Z", "editPermission": { "type": "group", "authors": [ "VKasalica", "veits@bmb.sdu.dk" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "PHIEmbed", "description": "PHIEmbed is a phage-host interaction prediction tool that uses protein language models to represent the receptor-binding proteins of phages. It presents improvements over using handcrafted (manually feature-engineered) sequence properties and eliminates the need to manually extract and select features from phage sequences.", "homepage": "https://github.com/bioinfodlsu/phage-host-prediction", "biotoolsID": "phiembed", "biotoolsCURIE": "biotools:phiembed", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2423", "term": "Prediction and recognition" } ], "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_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] } ], "note": "Predicts the host genus of a phage given its receptor-binding protein sequences", "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3474", "term": "Machine learning" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0078", "term": "Proteins" }, { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" }, { "uri": "http://edamontology.org/topic_3307", "term": "Computational biology" }, { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" }, { "uri": "http://edamontology.org/topic_0781", "term": "Virology" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "Python" ], "license": "MIT", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/bioinfodlsu/phage-host-prediction", "type": [ "Repository" ], "note": null }, { "url": "http://phiembed.bioinfodlsu.com/", "type": [ "Service" ], "note": null } ], "download": [ { "url": "https://github.com/bioinfodlsu/phage-host-prediction", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "https://github.com/bioinfodlsu/phage-host-prediction", "type": [ "Installation instructions", "Quick start guide", "Citation instructions", "Command-line options" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pone.0289030", "pmid": "37486915", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Protein embeddings improve phage-host interaction prediction", "abstract": "With the growing interest in using phages to combat antimicrobial resistance, computational methods for predicting phage-host interactions have been explored to help shortlist candidate phages. Most existing models consider entire proteomes and rely on manual feature engineering, which poses difficulty in selecting the most informative sequence properties to serve as input to the model. In this paper, we framed phage-host interaction prediction as a multiclass classification problem that takes as input the embeddings of a phage’s receptor-binding proteins, which are known to be the key machinery for host recognition, and predicts the host genus. We explored different protein language models to automatically encode these protein sequences into dense embeddings without the need for additional alignment or structural information. We show that the use of embeddings of receptor-binding proteins presents improvements over handcrafted genomic and protein sequence features. The highest performance was obtained using the transformer-based protein language model ProtT5, resulting in a 3% to 4% increase in weighted F1 and recall scores across different prediction confidence thresholds, compared to using selected handcrafted sequence features.", "date": "2023-07-01T00:00:00Z", "citationCount": 2, "authors": [ { "name": "Gonzales M.E.M." }, { "name": "Ureta J.C." }, { "name": "Shrestha A.M.S." } ], "journal": "PLoS ONE" } } ], "credit": [ { "name": "Mark Edward M. Gonzales", "email": "gonzales.markedward@gmail.com", "url": "https://github.com/memgonzales", "orcidid": "https://orcid.org/0000-0001-5050-3157", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": "Research Assistant, Bioinformatics Lab, Advanced Research Institute for Informatics, Computing and Networking, De La Salle University, Manila, Philippines" }, { "name": "Jennifer C. Ureta", "email": "jennifer.ureta@gmail.com", "url": "https://scholar.google.com/citations?user=v0Tf_u4AAAAJ&hl=en", "orcidid": "https://orcid.org/0000-0003-0427-5311", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Contributor" ], "note": "Faculty, Bioinformatics Lab, Advanced Research Institute for Informatics, Computing and Networking, De La Salle University, Manila, Philippines" }, { "name": "Anish M.S. Shrestha", "email": "anish.shrestha@dlsu.edu.ph", "url": "https://a-transposable-element.com/", "orcidid": "https://orcid.org/0000-0002-9192-9709", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": "Head, Bioinformatics Lab, Advanced Research Institute for Informatics, Computing and Networking, De La Salle University, Manila, Philippines" } ], "owner": "memgonzales", "additionDate": "2024-05-05T10:53:14.688391Z", "lastUpdate": "2025-01-14T09:13:55.932761Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "DynaMine", "description": "Protein backbone dynamics prediction from sequence.", "homepage": "http://dynamine.ibsquare.be/", "biotoolsID": "dynamine", "biotoolsCURIE": "biotools:dynamine", "version": [ "1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2423", "term": "Prediction and recognition" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2974", "term": "Protein sequence (raw)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1277", "term": "Protein features" }, "format": [] } ], "note": "Protein backbone dynamics prediction from sequence File containing one value per amino acid in each protein sequence", "cmd": null } ], "toolType": [ "Web API", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3306", "term": "Biophysics" }, { "uri": "http://edamontology.org/topic_0123", "term": "Protein properties" }, { "uri": "http://edamontology.org/topic_3538", "term": "Protein disordered structure" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://dynamine.ibsquare.be/help/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1038/ncomms3741", "pmid": "24225580", "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": null }, { "doi": "10.1093/nar/gku270", "pmid": "24728994", "pmcid": "PMC4086073", "type": [ "Other" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "vub.ac.be", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Wim Vranken", "email": "wvranken@vub.ac.be", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Support" ], "note": null }, { "name": "Wim Vranken", "email": "wvranken@vub.ac.be", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "wvranken@vub.ac.be", "additionDate": "2016-05-31T11:29:42Z", "lastUpdate": "2025-01-08T15:03:40.105084Z", "editPermission": { "type": "group", "authors": [ "tanish" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "TREND Protein Evolution Function", "description": "TREND is a platform that allows researchers to explore protein function and evolution identifying protein features, gene neighborhoods and operons, clustering neighboring genes, and integrating all these data into phylogenomic context and cross-referencing with RefSeq, Pfam, CDD and MiST databases. The platform provides ample opportunities for adjusting each step of the analysis.", "homepage": "http://trend.evobionet.com/", "biotoolsID": "trend_protein_evolution_function", "biotoolsCURIE": "biotools:trend_protein_evolution_function", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0492", "term": "Multiple sequence alignment" }, { "uri": "http://edamontology.org/operation_0323", "term": "Phylogenetic inference" }, { "uri": "http://edamontology.org/operation_0291", "term": "Sequence clustering" }, { "uri": "http://edamontology.org/operation_2995", "term": "Sequence classification" }, { "uri": "http://edamontology.org/operation_0246", "term": "Protein domain recognition" }, { "uri": "http://edamontology.org/operation_3092", "term": "Protein feature detection" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1384", "term": "Protein sequence alignment" }, "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_0872", "term": "Phylogenetic tree" }, "format": [ { "uri": "http://edamontology.org/format_1910", "term": "newick" } ] }, { "data": { "uri": "http://edamontology.org/data_1900", "term": "NCBI locus tag" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] }, { "data": { "uri": "http://edamontology.org/data_2385", "term": "RefSeq accession (protein)" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1384", "term": "Protein sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "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_1277", "term": "Protein features" }, "format": [ { "uri": "http://edamontology.org/format_3464", "term": "JSON" } ] }, { "data": { "uri": "http://edamontology.org/data_2968", "term": "Image" }, "format": [ { "uri": "http://edamontology.org/format_3604", "term": "SVG" } ] }, { "data": { "uri": "http://edamontology.org/data_1245", "term": "Sequence cluster (protein)" }, "format": [ { "uri": "http://edamontology.org/format_3464", "term": "JSON" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Web service" ], "topic": [ { "uri": "http://edamontology.org/topic_3299", "term": "Evolutionary biology" }, { "uri": "http://edamontology.org/topic_0084", "term": "Phylogeny" }, { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" }, { "uri": "http://edamontology.org/topic_3510", "term": "Protein sites, features and motifs" }, { "uri": "http://edamontology.org/topic_0085", "term": "Functional genomics" }, { "uri": "http://edamontology.org/topic_0194", "term": "Phylogenomics" }, { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://trend.evobionet.com/help", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkaa243", "pmid": "32282909", "pmcid": "PMC7319448", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "TREND: a platform for exploring protein function in prokaryotes based on phylogenetic, domain architecture and gene neighborhood analyses", "abstract": "Key steps in a computational study of protein function involve analysis of (i) relationships between homologous proteins, (ii) protein domain architecture and (iii) gene neighborhoods the corresponding proteins are encoded in. Each of these steps requires a separate computational task and sets of tools. Currently in order to relate protein features and gene neighborhoods information to phylogeny, researchers need to prepare all the necessary data and combine them by hand, which is time-consuming and error-prone. Here, we present a new platform, TREND (tree-based exploration of neighborhoods and domains), which can perform all the necessary steps in automated fashion and put the derived information into phylogenomic context, thus making evolutionary based protein function analysis more efficient. A rich set of adjustable components allows a user to run the computational steps specific to his task. TREND is freely available at http://trend.zhulinlab.org.", "date": "2021-01-01T00:00:00Z", "citationCount": 33, "authors": [ { "name": "Gumerov V.M." }, { "name": "Zhulin I.B." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkac034", "pmid": "35100406", "pmcid": "PMC8860576", "type": [ "Other" ], "version": null, "note": "Can be also accessed at this URL: https://academic.oup.com/nar/advance-article/doi/10.1093/nar/gkac034/6517937", "metadata": { "title": "Erratum: TREND: A platform for exploring protein function in prokaryotes based on phylogenetic, domain architecture and gene neighborhood analyses (Nucleic Acids Research DOI: 10.1093/nar/gkaa243)", "abstract": "TheURL address of the web server published in this article has been changed fromhttp://trend.zhulinlab.org to http://trend. evobionet.com/.", "date": "2022-02-22T00:00:00Z", "citationCount": 6, "authors": [ { "name": "Gumerov V.M." }, { "name": "Zhulin I.B." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Vadim Gumerov", "email": "gumerov.1@osu.edu", "url": null, "orcidid": "https://orcid.org/0000-0003-1670-7679", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "owner": "vadim", "additionDate": "2020-11-09T21:38:53Z", "lastUpdate": "2024-12-17T20:42:49.942166Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Cofactory", "description": "Identification of Rossmann folds and prediction of FAD, NAD and NADP specificity.", "homepage": "http://cbs.dtu.dk/services/Cofactory/", "biotoolsID": "cofactory", "biotoolsCURIE": "biotools:cofactory", "version": [ "2.1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2423", "term": "Prediction and recognition" } ], "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" } ] } ], "note": "identifies Rossmann fold sequence domains and predicts their specificity for the cofactors FAD, NAD or NADP", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3510", "term": "Protein sites, features and motifs" } ], "operatingSystem": [ "Linux" ], "language": [], "license": "Other", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge (with restrictions)", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.cbs.dtu.dk/services/doc/cofactory-1.0.readme", "type": [ "Repository" ], "note": null }, { "url": "http://cbs.dtu.dk/services", "type": [ "Software catalogue" ], "note": null } ], "download": [ { "url": "http://www.cbs.dtu.dk/services/doc/cofactory-1.0.readme", "type": "Source code", "note": null, "version": null }, { "url": "http://www.cbs.dtu.dk/services/doc/cofactory-1.0.readme", "type": "Binaries", "note": null, "version": null } ], "documentation": [ { "url": "http://www.cbs.dtu.dk/services/Cofactory/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1002/prot.24536", "pmid": "24523134", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Thomas Nordahl Petersen", "email": "tnp@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-08-24T10:00:36Z", "lastUpdate": "2024-11-25T16:22:09.216410Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "msa", "description": "Display multiple-sequence alignment. The tool is also available as R/BioConductor interface to the multiple sequence alignment algorithms ClustalW, ClustalOmega, and Muscle. All three algorithms are integrated in the package, therefore, they do not depend on any external software tools and are available for all major platforms.", "homepage": "http://msa.biojs.net", "biotoolsID": "msa", "biotoolsCURIE": "biotools:msa", "version": [ "1.0.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "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_1982", "term": "ClustalW format" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] }, { "data": { "uri": "http://edamontology.org/data_1711", "term": "Sequence alignment image" }, "format": [ { "uri": "http://edamontology.org/format_3547", "term": "Image format" } ] }, { "data": { "uri": "http://edamontology.org/data_0850", "term": "Sequence set" }, "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_2305", "term": "GFF" } ] } ], "note": "Visualizes multiple sequence alignment, calculates conservation, shows sequence logo, applies multiple color schemes A multiple sequence alignment (ClustalW, FASTA, ...) Exports selected sequences and regions from the alignment Images are exported in PNG Export sequences in FASTA format Export features in GFF\nNOTE: Actually, all these output types of data should instead be under separate \"constant\" operations, while the visualisation should be an unary operation, perhaps without an output.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0492", "term": "Multiple sequence alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1948", "term": "nbrf/pir" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1935", "term": "GCG" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" }, { "uri": "http://edamontology.org/format_1927", "term": "EMBL format" }, { "uri": "http://edamontology.org/format_1936", "term": "GenBank format" } ] }, { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_1948", "term": "nbrf/pir" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1935", "term": "GCG" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" }, { "uri": "http://edamontology.org/format_1927", "term": "EMBL format" }, { "uri": "http://edamontology.org/format_1936", "term": "GenBank format" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0867", "term": "Sequence alignment report" }, "format": [ { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1997", "term": "PHYLIP format" }, { "uri": "http://edamontology.org/format_3508", "term": "PDF" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Library" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" }, { "uri": "http://edamontology.org/topic_3293", "term": "Phylogenetics" }, { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "JavaScript" ], "license": "Apache-2.0", "collectionID": [ "Rostlab tools", "Bioconductor", "BioJS" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/wilzbach/msa", "type": [ "Repository" ], "note": null }, { "url": "http://biojs.io/", "type": [ "Software catalogue" ], "note": null }, { "url": "http://github.com/wilzbach/msa", "type": [ "Helpdesk" ], "note": null }, { "url": "http://www.bioinf.jku.at/software/msa/", "type": [ "Mirror" ], "note": null } ], "download": [ { "url": "https://github.com/wilzbach/msa", "type": "Source code", "note": null, "version": null }, { "url": "https://cdn.bio.sh/", "type": "Binaries", "note": null, "version": null } ], "documentation": [ { "url": "https://github.com/wilzbach/msa/blob/master/LICENSE", "type": [ "Terms of use" ], "note": null }, { "url": "http://msa.biojs.net", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btw474", "pmid": "27412096", "pmcid": "PMC5181560", "type": [ "Primary" ], "version": null, "note": null, "metadata": null }, { "doi": "10.1093/bioinformatics/btv494", "pmid": "26315911", "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Sebastian Wilzbach", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Ian Sillitoe", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor" ], "note": null }, { "name": "Guy Yachdav", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor" ], "note": null }, { "name": "Benedikt Rauscher", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor" ], "note": null }, { "name": "Tatyana Goldberg", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor" ], "note": null }, { "name": "Technische Universität München", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Google Summer of Code (GSoC) 2014", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Funding agency", "typeRole": [ "Contributor" ], "note": null }, { "name": "BioJS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": null, "url": "http://github.com/wilzbach/msa", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Ulrich Bodenhofer", "email": "bodenhofer@bioinf.jku.at", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "BioJS", "additionDate": "2016-06-02T02:47:10Z", "lastUpdate": "2024-11-25T16:17:03.898741Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Crispi", "description": "A CRISPR Interactive database.", "homepage": "http://crispi.genouest.org/", "biotoolsID": "crispi", "biotoolsCURIE": "biotools:crispi", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0338", "term": "Sequence database search" } ], "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_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "A CRISPR Interactive database", "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://genoweb1.irisa.fr/Serveur-GPO/outils/repeatsAnalysis/CRISPR/help/crispri.pdf", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btp586", "pmid": "19846435", "pmcid": "PMC2788928", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "GenOuest", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "GenOuest platform", "email": "support@genouest.org", "url": "http://www.genouest.org", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "GenOuest", "additionDate": "2015-01-21T15:12:23Z", "lastUpdate": "2024-11-25T16:06:25.068541Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Plast", "description": "Parallel Local Alignment Search Tool for Database Comparison.", "homepage": "http://www.irisa.fr/symbiose/projects/plast/", "biotoolsID": "plast", "biotoolsCURIE": "biotools:plast", "version": [ "1.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0495", "term": "Local alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "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_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "Sequence alignment", "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": "CECILL-2.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://plast.inria.fr/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-10-329", "pmid": "19821978", "pmcid": "PMC2770072", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "GenOuest", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Dominique Lavenier", "email": "lavenier@irisa.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "GenOuest", "additionDate": "2015-01-21T15:12:23Z", "lastUpdate": "2024-11-25T16:06:23.702130Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Mapsembler", "description": "A targeted assembly software.", "homepage": "https://colibread.inria.fr/mapsembler2/", "biotoolsID": "mapsembler", "biotoolsCURIE": "biotools:mapsembler", "version": [ "2.2.4" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3183", "term": "Localised reassembly" } ], "input": [ { "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_2975", "term": "Nucleic acid sequence (raw)" }, "format": [ { "uri": "http://edamontology.org/format_2182", "term": "FASTQ-like format (text)" } ] } ], "output": [ { "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_2600", "term": "Pathway or network" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "Targeted sequence assembly", "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Linux" ], "language": [], "license": "AGPL-3.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://colibread.inria.fr/software/mapsembler2/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-13-48", "pmid": "22443449", "pmcid": "PMC3514201", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "GenOuest", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Pierre Peterlongo", "email": "pierre.peterlongo@inria.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "GenOuest", "additionDate": "2015-01-21T15:12:22Z", "lastUpdate": "2024-11-25T16:06:22.558427Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "CyanoLyase", "description": "Manually curated sequence and amino acid motif database gathering all the different phycobilin lyases and related protein sequences available in public databases.", "homepage": "http://cyanolyase.genouest.org/", "biotoolsID": "cyanolyase", "biotoolsCURIE": "biotools:cyanolyase", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0253", "term": "Sequence 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_0858", "term": "Sequence signature matches" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "Motif occurence detection in protein sequences", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0338", "term": "Sequence database search" } ], "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_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1333", "term": "BLAST results" } ] } ], "note": "Protein sequence alignment against known family members", "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0623", "term": "Gene and protein families" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://cyanolyase.genouest.org/help", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gks1091", "pmid": "23175607", "pmcid": "PMC3531064", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "GenOuest", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "GenOuest", "email": "support@genouest.org", "url": "http://www.genouest.org", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "GenOuest", "additionDate": "2015-01-21T15:12:20Z", "lastUpdate": "2024-11-25T16:06:21.263559Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "SigniSite", "description": "Identification of residue level genotype phenotype correlation in protein multiple sequence alignments by identifying amino acid residues significantly associated with the phenotype of the data set.", "homepage": "http://cbs.dtu.dk/services/SigniSite/", "biotoolsID": "signisite", "biotoolsCURIE": "biotools:signisite", "version": [ "2.1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2479", "term": "Protein sequence analysis" } ], "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_2333", "term": "Binary format" } ] } ], "note": "performs residue level genotype phenotype correlation in protein multiple sequence alignments", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0625", "term": "Genotype and phenotype" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux" ], "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/SigniSite/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkt497", "pmid": "23761454", "pmcid": "PMC3692133", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "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": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-06-29T10:22:56Z", "lastUpdate": "2024-11-25T16:03:57.599680Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "OligoWiz", "description": "Intelligent design of oligonucleotides for DNA microarrays.", "homepage": "http://cbs.dtu.dk/services/OligoWiz/", "biotoolsID": "oligowiz", "biotoolsCURIE": "biotools:oligowiz", "version": [ "2" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0309", "term": "Microarray probe design" } ], "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_2955", "term": "Sequence report" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] } ], "note": "Intelligent design of oligonucleotides for DNA microarrays", "cmd": null } ], "toolType": [ "Command-line tool", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3365", "term": "Data architecture, analysis and design" } ], "operatingSystem": [ "Linux" ], "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/OligoWiz/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gki399", "pmid": "15980547", "pmcid": "PMC1160160", "type": [ "Primary" ], "version": null, "note": null, "metadata": null }, { "doi": "10.1093/nar/gkg622", "pmid": "12824351", "pmcid": "PMC169028", "type": [ "Other" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Henrik Bjorn Nielsen", "email": "oligowiz@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-06-29T10:19:43Z", "lastUpdate": "2024-11-25T16:03:55.687345Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NetSurfP", "description": "Protein Surface Accessibility and Secondary Structure Predictions.", "homepage": "http://cbs.dtu.dk/services/NetSurfP/", "biotoolsID": "netsurfp", "biotoolsCURIE": "biotools:netsurfp", "version": [ "1.1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0267", "term": "Protein secondary structure prediction" } ], "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_2085", "term": "Structure report" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "predicts the surface accessibility and secondary structure of amino acids in an amino acid sequence", "cmd": null } ], "toolType": [ "Command-line tool", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0082", "term": "Structure prediction" } ], "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/NetSurfP/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1472-6807-9-51", "pmid": "19646261", "pmcid": "PMC2725087", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Bent Petersen", "email": "bent@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-06-29T10:13:50Z", "lastUpdate": "2024-11-25T16:03:43.260644Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "FeatureP", "description": "Comparative analysis of protein sequences derived from the same transcript by alternative splicing, genome variation data (SNPs) or protein families from one or more organisms.", "homepage": "http://cbs.dtu.dk/services/EPipe/", "biotoolsID": "featurep", "biotoolsCURIE": "biotools:featurep", "version": [ "0.983" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2451", "term": "Sequence comparison" } ], "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": [] } ], "note": null, "cmd": null } ], "toolType": [ "Web application", "Web service" ], "topic": [ { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" } ], "operatingSystem": [ "Linux" ], "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/EPipe/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1016/j.sbi.2010.03.008", "pmid": "20403684", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Henrik Nielsen", "email": "hnielsen@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-05-04T12:18:09Z", "lastUpdate": "2024-11-25T16:03:40.141479Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Tapir", "description": "This service is like a DNA search engine.", "homepage": "http://bioinformatics.psb.ugent.be/webtools/tapir/", "biotoolsID": "tapir_cbs", "biotoolsCURIE": "biotools:tapir_cbs", "version": [ "1.9" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2423", "term": "Prediction and recognition" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "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_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1212", "term": "dna" } ] } ], "note": "Fast DNA search", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": "Emerging", "cost": "Free of charge (with restrictions)", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.cbs.dtu.dk/services", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://bioinformatics.psb.ugent.be/webtools/tapir/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pone.0083784", "pmid": "24391826", "pmcid": "PMC3877093", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Laurent Gautier", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Ole Lund", "email": "lund@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-01-21T13:29:29Z", "lastUpdate": "2024-11-25T16:03:38.991887Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "VarDom", "description": "Composition and classification analysis of the malaria antigen family PfEMP1.", "homepage": "http://cbs.dtu.dk/services/VarDom/", "biotoolsID": "vardom", "biotoolsCURIE": "biotools:vardom", "version": [ "1.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2995", "term": "Sequence classification" }, { "uri": "http://edamontology.org/operation_2421", "term": "Database search" } ], "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_2955", "term": "Sequence report" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" } ] } ], "note": "predicts PfEMP1 domains and homology blocks", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux" ], "language": [], "license": "Other", "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://toolname.org/docs", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pcbi.1000933", "pmid": "20862303", "pmcid": "PMC2940729", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Anders Gorm Pedersen", "email": "gorm@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-01-21T13:29:26Z", "lastUpdate": "2024-11-25T16:03:37.894701Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "RNAmmer", "description": "Prediction of 5S/8S, 16S/18S, and 23S/28S ribosomal RNA in full genome sequences.", "homepage": "http://cbs.dtu.dk/services/RNAmmer/", "biotoolsID": "rnammer", "biotoolsCURIE": "biotools:rnammer", "version": [ "1.2" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0415", "term": "Nucleic acid 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_2305", "term": "GFF" } ] } ], "note": "predicts 5s/8s, 16s/18s, and 23s/28s ribosomal RNA in full genome sequences", "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" ], "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/RNAmmer/instructions.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkm160", "pmid": "17452365", "pmcid": "PMC1888812", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Hans-Henrik Staerfeldt", "email": "hhs@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-01-21T13:29:23Z", "lastUpdate": "2024-11-25T16:03:36.719331Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NetTurnP", "description": "Prediction whether an amino acid is located in a Beta-turn or not.", "homepage": "http://cbs.dtu.dk/services/NetTurnP/", "biotoolsID": "netturnp", "biotoolsCURIE": "biotools:netturnp", "version": [ "1.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0474", "term": "Protein structure prediction" } ], "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_2085", "term": "Structure report" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "predicts whether an amino acid is located in a Beta-turn or not;predicts the nine Beta-turn subtypes", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0082", "term": "Structure prediction" } ], "operatingSystem": [ "Linux" ], "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/NetTurnP/instructions.php", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pone.0015079", "pmid": "21152409", "pmcid": "PMC2994801", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "CBS", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Bent Petersen", "email": "bent@cbs.dtu.dk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "CBS", "additionDate": "2015-01-21T13:29:20Z", "lastUpdate": "2024-11-25T16:03:35.430796Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "TAPIR", "description": "A web server for the prediction of plant microRNA targets, including target mimics.", "homepage": "http://bioinformatics.psb.ugent.be/webtools/tapir/", "biotoolsID": "tapir", "biotoolsCURIE": "biotools:tapir", "version": [ "1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3439", "term": "Pathway or network prediction" } ], "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_1276", "term": "Nucleic acid features" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [ "BIG N2N", "VIB", "Plant Systems Biology", "UGent" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://bioinformatics.psb.ugent.be/webtools/tapir/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btq233", "pmid": "20430753", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "PSB", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": "yves.vandepeer@psb.vib-ugent.be", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "PSB", "additionDate": "2016-01-31T16:35:00Z", "lastUpdate": "2024-11-25T16:01:46.178446Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "webPRANK", "description": "Multiple sequence alignment tool.", "homepage": "http://www.ebi.ac.uk/goldman-srv/webprank/", "biotoolsID": "webprank", "biotoolsCURIE": "biotools:webprank", "version": [ "1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0492", "term": "Multiple sequence alignment" } ], "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_0863", "term": "Sequence alignment" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [ "Goldman Tools", "EBI Tools" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://www.ebi.ac.uk/about/terms-of-use", "type": [ "Terms of use" ], "note": null }, { "url": "http://www.ebi.ac.uk/goldman-srv/webprank/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-11-579", "pmid": "21110866", "pmcid": "PMC3009689", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Goldman group", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Ari Loytynoja", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Nick Goldman", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor" ], "note": null }, { "name": "EMBL-EBI", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": "ari@ebi.ac.uk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Ari Loytynoja", "email": "ari.loytynoja@helsinki.fi", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "EMBL-EBI", "additionDate": "2015-01-29T15:47:27Z", "lastUpdate": "2024-11-25T15:57:33.319602Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Weeder", "description": "De novo motif (transcription factor binding sites) discovery in sequences from coregulated genes of a single species. This is a new release rewritten to be faster and optimized for large ChIP-Seq data.", "homepage": "http://www.beaconlab.it/modtools", "biotoolsID": "weeder", "biotoolsCURIE": "biotools:weeder", "version": [ "2.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0238", "term": "Sequence motif discovery" } ], "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_2070", "term": "Sequence motif (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" }, { "uri": "http://edamontology.org/format_3033", "term": "Matrix format" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0160", "term": "Sequence sites, features and motifs" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "C++" ], "license": "GPL-3.0", "collectionID": [ "MoD Tools" ], "maturity": "Mature", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://159.149.160.51/modtools/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1002/0471250953.bi0211s47", "pmid": "25199791", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "ELIXIR-ITA-MILANO", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Giulio Pavesi", "email": "giulio.pavesi@unimi.it", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Federico Zambelli", "email": "federico.zambelli@unimi.it", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-ITA-MILANO", "additionDate": "2015-01-22T11:35:48Z", "lastUpdate": "2024-11-25T15:54:28.466209Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "leBIBIpqp", "description": "The BioInformatics Prokaryotes Quick Phylogeny is designed to reconstruct the phylogeny of an Archaea or a Bacteria from its nucleic acid sequence. It is also giving the useful informations if species identification is needed.", "homepage": "https://umr5558-bibiserv.univ-lyon1.fr/lebibi/lebibi.cgi", "biotoolsID": "lebibipqp", "biotoolsCURIE": "biotools:lebibipqp", "version": [ "6.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0567", "term": "Phylogenetic tree visualisation" }, { "uri": "http://edamontology.org/operation_0258", "term": "Sequence alignment analysis" }, { "uri": "http://edamontology.org/operation_0338", "term": "Sequence database search" }, { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2044", "term": "Sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1056", "term": "Database name" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] }, { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] }, { "data": { "uri": "http://edamontology.org/data_3272", "term": "Species tree" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_0857", "term": "Sequence search results" }, "format": [ { "uri": "http://edamontology.org/format_1333", "term": "BLAST results" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0084", "term": "Phylogeny" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://umr5558-bibiserv.univ-lyon1.fr/BIBIDOCNEW/index.html#lebibi-qbpp-documentation", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/s12859-015-0692-z", "pmid": "26264559", "pmcid": "PMC4531848", "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "IFB ELIXIR-FR", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Jean-Pierre Flandrois", "email": "jean-pierre.flandrois@univ-lyon1.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-FR", "additionDate": "2015-01-22T11:28:32Z", "lastUpdate": "2024-11-25T15:53:39.526130Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MACSIMS", "description": "Multiple alignment-based information management system that combines the advantages of both knowledge-based and ab initio sequence analysis methods.", "homepage": "http://www.lbgi.fr/~julie/MACSIMS/", "biotoolsID": "macsims", "biotoolsCURIE": "biotools:macsims", "version": [ "MACSIMS" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" }, { "uri": "http://edamontology.org/operation_0361", "term": "Sequence annotation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0863", "term": "Sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" }, { "uri": "http://edamontology.org/format_1947", "term": "GCG MSF" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [] } ], "note": "This function mines automatically structural and functional informations from the public databases. It identifies homologous regions and evaluates and propagates mined data from known to unknown sequences with these reliable regions.", "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0092", "term": "Data visualisation" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.lbgi.fr/~julie/MACSIMS/", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://www.lbgi.fr/~julie/MACSIMS/Documentation/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-7-318", "pmid": "16792820", "pmcid": "PMC1539025", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "IFB ELIXIR-FR", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Julie Thompson", "email": "julie@igbmc.u-strasbg.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-FR", "additionDate": "2015-01-22T11:28:31Z", "lastUpdate": "2024-11-25T15:53:38.069848Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "LocTree3", "description": "Prediction of protein subcellular localization in 18 classes for eukaryota, 6 for bacteria and 3 for archaea.", "homepage": "https://rostlab.org/services/loctree3/", "biotoolsID": "loctree3", "biotoolsCURIE": "biotools:loctree3", "version": [ "1.0.8" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2489", "term": "Protein subcellular localisation prediction" } ], "input": [ { "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_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "Prediction of protein sucellular localization in 18 classes for eukaryota, 6 classes for bacteria and 3 for archaea using homology searches (PSI-BLAST) and machine learning (SVM) User can provide one or more sequences in FASTA format The prediction output contains: prediction score, from 1 (weak prediction) to 100 (strong prediction); one of 18 localization classes for eukaryota, 6 for bacteria and 3 for archaea; GO identifier; GO term; prediction source (PSI-BLAST or SVM)", "cmd": null } ], "toolType": [ "Command-line tool", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0123", "term": "Protein properties" }, { "uri": "http://edamontology.org/topic_2229", "term": "Cell biology" } ], "operatingSystem": [ "Linux" ], "language": [ "PHP", "Java", "Perl", "JavaScript" ], "license": "GPL-3.0", "collectionID": [ "Rostlab tools", "PredictProtein" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://rostlab.org/owiki/index.php/Packages", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://rostlab.org/owiki/index.php/Packages", "type": "Source code", "note": null, "version": null }, { "url": "https://rostlab.org/owiki/index.php/Packages", "type": "Binaries", "note": null, "version": null } ], "documentation": [ { "url": "https://rostlab.org/owiki/index.php/Loctree3", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gku396", "pmid": "24848019", "pmcid": "PMC4086075", "type": [ "Primary" ], "version": null, "note": null, "metadata": null }, { "doi": "10.1093/bioinformatics/bts390", "pmid": "22962467", "pmcid": "PMC3436817", "type": [ "Other" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Maximilian Hecht", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Guy Yachdav", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Timothy Karl", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Tobias Hamp", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Tatyana Goldberg", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Burkhard Rost", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor" ], "note": null }, { "name": "Henrik Nielsen", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor" ], "note": null }, { "name": "Technische Universität München", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Alexander von Humboldt Foundation through German Federal Ministry for Education and Research", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Funding agency", "typeRole": [ "Contributor" ], "note": null }, { "name": "Ernst Ludwig Ehrlich Studienwerk", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Funding agency", "typeRole": [ "Contributor" ], "note": null }, { "name": "RostLab", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": "localization@rostlab.org", "url": "https://rostlab.org/services/loctree3/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "RostLab", "additionDate": "2015-10-01T21:33:09Z", "lastUpdate": "2024-11-25T15:45:41.322065Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null } ] }
