Resource List
List all resources, or create a new resource.
GET /api/t/?dataFormat=%22FASTA%22
{ "count": 916, "next": "?page=2", "previous": null, "list": [ { "name": "DeepARG", "description": "A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes.", "homepage": "https://github.com/gaarangoa/deeparg", "biotoolsID": "deeparg", "biotoolsCURIE": "biotools:deeparg", "version": [ "1.0.4" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3482", "term": "Antimicrobial resistance prediction" } ], "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_3002", "term": "Annotation track" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "Prediction of ARGs from assembled reads (short sequences or long sequences)", "cmd": "deeparg predict \\\n --model LS \\\n -i ./test/ORFs.fa \\\n -o ./test/X \\\n -d /path/to/data/ \\\n --type nucl \\\n --min-prob 0.8 \\\n --arg-alignment-identity 30 \\\n --arg-alignment-evalue 1e-10 \\\n --arg-num-alignments-per-entry 1000" }, { "operation": [ { "uri": "http://edamontology.org/operation_3482", "term": "Antimicrobial resistance prediction" } ], "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_3989", "term": "GZIP format" } ] } ], "output": [], "note": "ARG prediction from raw reads", "cmd": "deeparg short_reads_pipeline \\\n --forward_pe_file ./test/F.fq.gz \\\n --reverse_pe_file ./test/R.fq.gz \\\n --output_file ./test/reads \\\n -d ~/Desktop/darg \\\n --bowtie_16s_identity 100" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "Python" ], "license": "MIT", "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/gaarangoa/deeparg", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [ { "url": "https://github.com/gaarangoa/deeparg?tab=readme-ov-file", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1186/s40168-018-0401-z", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Gustavo Arango-Argoty", "email": "gustavo1@vt.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Primary contact" ], "note": null } ], "community": null, "owner": "hugo-lefeuvre", "additionDate": "2024-10-11T15:08:50.098419Z", "lastUpdate": "2024-10-11T15:08:50.101943Z", "editPermission": { "type": "public", "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 } ], "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 } ], "community": null, "owner": "n.m.palmblad@lumc.nl", "additionDate": "2023-08-30T13:03:57.407598Z", "lastUpdate": "2024-10-02T13:04:01.584365Z", "editPermission": { "type": "group", "authors": [ "VKasalica", "veits@bmb.sdu.dk" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Sage", "description": "Sage is a proteomics database search engine to match tandem mass spectra to peptides. Sage also performs retention time prediction, quantificaiton and FDR control.", "homepage": "https://github.com/lazear/sage", "biotoolsID": "Sage-proteomics", "biotoolsCURIE": "biotools:Sage-proteomics", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3631", "term": "Peptide identification" }, { "uri": "http://edamontology.org/operation_3633", "term": "Retention time prediction" }, { "uri": "http://edamontology.org/operation_2428", "term": "Validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0943", "term": "Mass spectrum" }, "format": [ { "uri": "http://edamontology.org/format_3244", "term": "mzML" } ] }, { "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_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": null } ], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": "MIT", "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://sage-docs.vercel.app/docs", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1021/acs.jproteome.3c00486", "pmid": "37819886", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [], "community": null, "owner": "n.m.palmblad@lumc.nl", "additionDate": "2024-02-13T15:27:57.571212Z", "lastUpdate": "2024-10-02T12:18:34.142607Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MetaMorpheus", "description": "Improved Protein Inference from Multiple Protease Bottom-Up Mass Spectrometry Data | Proteomics search software with integrated calibration, PTM discovery, bottom-up, top-down and LFQ capabilities | MetaMorpheus: Free, Open-Source PTM Discovery | Download the current version here. For first-time Windows users, choose \"MetaMorpheusInstaller.msi\" and install MetaMorpheus. Check out our getting started video on YouTube", "homepage": "https://github.com/smith-chem-wisc/MetaMorpheus", "biotoolsID": "MetaMorpheus", "biotoolsCURIE": "biotools:MetaMorpheus", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3755", "term": "PTM localisation" }, { "uri": "http://edamontology.org/operation_3649", "term": "Target-Decoy" }, { "uri": "http://edamontology.org/operation_3767", "term": "Protein identification" }, { "uri": "http://edamontology.org/operation_3631", "term": "Peptide identification" }, { "uri": "http://edamontology.org/operation_2421", "term": "Database search" }, { "uri": "http://edamontology.org/operation_3629", "term": "Deisotoping" }, { "uri": "http://edamontology.org/operation_3215", "term": "Peak detection" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2536", "term": "Mass spectrometry data" }, "format": [ { "uri": "http://edamontology.org/format_3651", "term": "MGF" }, { "uri": "http://edamontology.org/format_3712", "term": "Thermo RAW" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" } ] }, { "data": { "uri": "http://edamontology.org/data_2976", "term": "Protein sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_3770", "term": "UniProtKB XML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0945", "term": "Peptide identification" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" }, { "uri": "http://edamontology.org/format_3247", "term": "mzIdentML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" }, { "uri": "http://edamontology.org/topic_3520", "term": "Proteomics experiment" }, { "uri": "http://edamontology.org/topic_0601", "term": "Protein modifications" }, { "uri": "http://edamontology.org/topic_3922", "term": "Proteogenomics" }, { "uri": "http://edamontology.org/topic_0154", "term": "Small molecules" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [], "language": [ "C#" ], "license": "MIT", "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1021/ACS.JPROTEOME.9B00330", "pmid": "31378069", "pmcid": "PMC6733628", "type": [], "version": null, "note": null, "metadata": { "title": "Improved Protein Inference from Multiple Protease Bottom-Up Mass Spectrometry Data", "abstract": "Peptides detected by tandem mass spectrometry (MS/MS) in bottom-up proteomics serve as proxies for the proteins expressed in the sample. Protein inference is a process routinely applied to these peptides to generate a plausible list of candidate protein identifications. The use of multiple proteases for parallel protein digestions expands sequence coverage, provides additional peptide identifications, and increases the probability of identifying peptides that are unique to a single protein, which are all valuable for protein inference. We have developed and implemented a multi-protease protein inference algorithm in MetaMorpheus, a bottom-up search software program, which incorporates the calculation of protease-specific q-values and preserves the association of peptide sequences and their protease of origin. This integrated multi-protease protein inference algorithm provides more accurate results than either the aggregation of results from the separate analysis of the peptide identifications produced by each protease (separate approach) in MetaMorpheus, or results that are obtained using Fido, ProteinProphet, or DTASelect2. MetaMorpheus' integrated multi-protease data analysis decreases the ambiguity of the protein group list, reduces the frequency of erroneous identifications, and increases the number of post-translational modifications identified, while combining multi-protease search and protein inference into a single software program.", "date": "2019-09-06T00:00:00Z", "citationCount": 32, "authors": [ { "name": "Miller R.M." }, { "name": "Millikin R.J." }, { "name": "Hoffmann C.V." }, { "name": "Solntsev S.K." }, { "name": "Sheynkman G.M." }, { "name": "Shortreed M.R." }, { "name": "Smith L.M." } ], "journal": "Journal of Proteome Research" } }, { "doi": "10.1021/ACS.JPROTEOME.0C00838", "pmid": "33683901", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Binary Classifier for Computing Posterior Error Probabilities in MetaMorpheus", "abstract": "MetaMorpheus is a free, open-source software program for the identification of peptides and proteoforms from data-dependent acquisition tandem MS experiments. There is inherent uncertainty in these assignments for several reasons, including the limited overlap between experimental and theoretical peaks, the m/z uncertainty, and noise peaks or peaks from coisolated peptides that produce false matches. False discovery rates provide only a set-wise approximation for incorrect spectrum matches. Here we implemented a binary decision tree calculation within MetaMorpheus to compute a posterior error probability, which provides a measure of uncertainty for each peptide-spectrum match. We demonstrate its utility for increasing identifications and resolving ambiguities in bottom-up, top-down, proteogenomic, and nonspecific digestion searches.", "date": "2021-04-02T00:00:00Z", "citationCount": 1, "authors": [ { "name": "Shortreed M.R." }, { "name": "Millikin R.J." }, { "name": "Liu L." }, { "name": "Rolfs Z." }, { "name": "Miller R.M." }, { "name": "Schaffer L.V." }, { "name": "Frey B.L." }, { "name": "Smith L.M." } ], "journal": "Journal of Proteome Research" } } ], "credit": [ { "name": "Lloyd M. Smith", "email": "smith@chem.wisc.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "community": null, "owner": "Pub2Tools", "additionDate": "2019-11-14T18:33:05Z", "lastUpdate": "2024-09-30T08:48:29.824928Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "MetaPathways", "description": "MetaPathways is a meta’omic analysis pipeline for the annotation and analysis for environmental sequence information. MetaPathways include metagenomic or metatranscriptomic sequence data. The pipeline consists of four operational stages including: Quality Control, Feature Prediction, Functional Annotation, Pathway Inference.", "homepage": "https://metapathways.readthedocs.io/en/dev/index.html", "biotoolsID": "metapathways", "biotoolsCURIE": "biotools:metapathways", "version": [ "3.5" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3672", "term": "Gene functional annotation" }, { "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": [ { "data": { "uri": "http://edamontology.org/data_3779", "term": "Annotated text" }, "format": [ { "uri": "http://edamontology.org/format_3751", "term": "DSV" } ] } ], "note": "Use MetaPathways to annotate a metagenome.", "cmd": "metapathways run \\\n -i $[input_metagenome.fa] \\\n -d ${path/to/save/reference_databases} \\\n -o ${path/to/output} \\\n -t ${threads}" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" }, { "uri": "http://edamontology.org/topic_3796", "term": "Population genomics" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": "MPL-2.0", "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://metapathways.readthedocs.io/en/dev/index.html", "type": [ "Other" ], "note": null } ], "download": [ { "url": "https://anaconda.org/Hallamlab/metapathways", "type": "Tool wrapper (Other)", "note": null, "version": "3.5" }, { "url": "https://quay.io/repository/hallamlab/metapathways", "type": "Container file", "note": null, "version": "3.5" }, { "url": "https://bitbucket.org/BCB2/metapathways/src/dev/", "type": "Source code", "note": null, "version": "3.5" } ], "documentation": [ { "url": "https://metapathways.readthedocs.io/en/dev/index.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1101/2024.06.04.597460", "pmid": null, "pmcid": null, "type": [], "version": "3.5", "note": null, "metadata": null }, { "doi": "10.1093/bioinformatics/btv361", "pmid": null, "pmcid": null, "type": [], "version": "2.5", "note": null, "metadata": { "title": "MetaPathways v2.5: Quantitative functional, taxonomic and usability improvements", "abstract": "Next-generation sequencing is producing vast amounts of sequence information from natural and engineered ecosystems. Although this data deluge has an enormous potential to transform our lives, knowledge creation and translation need software applications that scale with increasing data processing and analysis requirements. Here, we present improvements to MetaPathways, an annotation and analysis pipeline for environmental sequence information that expedites this transformation. We specifically address pathway prediction hazards through integration of a weighted taxonomic distance and enable quantitative comparison of assembled annotations through a normalized read-mapping measure. Additionally, we improve LAST homology searches through BLAST-equivalent E-values and output formats that are natively compatible with prevailing software applications. Finally, an updated graphical user interface allows for keyword annotation query and projection onto user-defined functional gene hierarchies, including the Carbohydrate-Active Enzyme database.", "date": "2015-03-25T00:00:00Z", "citationCount": 40, "authors": [ { "name": "Konwar K.M." }, { "name": "Hanson N.W." }, { "name": "Bhatia M.P." }, { "name": "Kim D." }, { "name": "Wu S.-J." }, { "name": "Hahn A.S." }, { "name": "Morgan-Lang C." }, { "name": "Cheung H.K." }, { "name": "Hallam S.J." } ], "journal": "Bioinformatics" } }, { "doi": "10.1186/1471-2105-14-202", "pmid": null, "pmcid": null, "type": [], "version": "1.0", "note": null, "metadata": { "title": "MetaPathways: A modular pipeline for constructing pathway/genome databases from environmental sequence information", "abstract": "Background: A central challenge to understanding the ecological and biogeochemical roles of microorganisms in natural and human engineered ecosystems is the reconstruction of metabolic interaction networks from environmental sequence information. The dominant paradigm in metabolic reconstruction is to assign functional annotations using BLAST. Functional annotations are then projected onto symbolic representations of metabolism in the form of KEGG pathways or SEED subsystems.Results: Here we present MetaPathways, an open source pipeline for pathway inference that uses the PathoLogic algorithm to map functional annotations onto the MetaCyc collection of reactions and pathways, and construct environmental Pathway/Genome Databases (ePGDBs) compatible with the editing and navigation features of Pathway Tools. The pipeline accepts assembled or unassembled nucleotide sequences, performs quality assessment and control, predicts and annotates noncoding genes and open reading frames, and produces inputs to PathoLogic. In addition to constructing ePGDBs, MetaPathways uses MLTreeMap to build phylogenetic trees for selected taxonomic anchor and functional gene markers, converts General Feature Format (GFF) files into concatenated GenBank files for ePGDB construction based on third-party annotations, and generates useful file formats including Sequin files for direct GenBank submission and gene feature tables summarizing annotations, MLTreeMap trees, and ePGDB pathway coverage summaries for statistical comparisons.Conclusions: MetaPathways provides users with a modular annotation and analysis pipeline for predicting metabolic interaction networks from environmental sequence information using an alternative to KEGG pathways and SEED subsystems mapping. It is extensible to genomic and transcriptomic datasets from a wide range of sequencing platforms, and generates useful data products for microbial community structure and function analysis. The MetaPathways software package, installation instructions, and example data can be obtained from http://hallam.microbiology.ubc.ca/MetaPathways. © 2013 Konwar et al.; licensee BioMed Central Ltd.", "date": "2013-06-21T00:00:00Z", "citationCount": 82, "authors": [ { "name": "Konwar K.M." }, { "name": "Hanson N.W." }, { "name": "Page A.P." }, { "name": "Hallam S.J." } ], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": null, "email": "shallam@mail.ubc.ca", "url": "https://hallam.microbiology.ubc.ca/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "community": null, "owner": "mbs_import", "additionDate": "2017-08-03T18:51:07Z", "lastUpdate": "2024-09-24T13:45:50.534200Z", "editPermission": { "type": "group", "authors": [ "mclaughlinr2" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "iPHoP", "description": "An automated command-line pipeline for predicting host genus of novel bacteriophages and archaeoviruses based on their genome sequences.", "homepage": "https://bitbucket.org/srouxjgi/iphop/", "biotoolsID": "iphop", "biotoolsCURIE": "biotools:iphop", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3731", "term": "Sample comparison" } ], "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": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1371/journal.pbio.3002083", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "iPHoP: An integrated machine learning framework to maximize host prediction for metagenome-derived viruses of archaea and bacteria", "abstract": "The extraordinary diversity of viruses infecting bacteria and archaea is now primarily studied through metagenomics. While metagenomes enable high-throughput exploration of the viral sequence space, metagenome-derived sequences lack key information compared to isolated viruses, in particular host association. Different computational approaches are available to predict the host(s) of uncultivated viruses based on their genome sequences, but thus far individual approaches are limited either in precision or in recall, i.e., for a number of viruses they yield erroneous predictions or no prediction at all. Here, we describe iPHoP, a two-step framework that integrates multiple methods to reliably predict host taxonomy at the genus rank for a broad range of viruses infecting bacteria and archaea, while retaining a low false discovery rate. Based on a large dataset of metagenome-derived virus genomes from the IMG/VR database, we illustrate how iPHoP can provide extensive host prediction and guide further characterization of uncultivated viruses.", "date": "2023-04-01T00:00:00Z", "citationCount": 65, "authors": [ { "name": "Roux S." }, { "name": "Camargo A.P." }, { "name": "Coutinho F.H." }, { "name": "Dabdoub S.M." }, { "name": "Dutilh B.E." }, { "name": "Nayfach S." }, { "name": "Tritt A." } ], "journal": "PLoS Biology" } } ], "credit": [], "community": null, "owner": "m.bernt", "additionDate": "2024-09-20T07:18:14.102477Z", "lastUpdate": "2024-09-20T07:30:58.461443Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Jalview", "description": "Jalview is a free program for multiple sequence alignment editing, visualisation and analysis. Use it to 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": [ "2.11.4.0" ], "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" ], "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": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Jalview Version 2-A multiple sequence alignment editor and analysis workbench", "abstract": "Summary: Jalview Version 2 is a system for interactive WYSIWYG editing, analysis and annotation of multiple sequence alignments. Core features include keyboard and mouse-based editing, multiple views and alignment overviews, and linked structure display with Jmol. Jalview 2 is available in two forms: a lightweight Java applet for use in web applications, and a powerful desktop application that employs web services for sequence alignment, secondary structure prediction and the retrieval of alignments, sequences, annotation and structures from public databases and any DAS 1.53 compliant sequence or annotation server. © 2009 The Author(s).", "date": "2009-05-07T00:00:00Z", "citationCount": 6801, "authors": [ { "name": "Waterhouse A.M." }, { "name": "Procter J.B." }, { "name": "Martin D.M.A." }, { "name": "Clamp M." }, { "name": "Barton G.J." } ], "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 } ], "community": null, "owner": "ben_s", "additionDate": "2019-02-13T17:01:40Z", "lastUpdate": "2024-09-19T12:50:26.798483Z", "editPermission": { "type": "group", "authors": [ "ben_s", "jimprocter" ] }, "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" ], "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": 143, "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 } ], "community": null, "owner": "awhitwham", "additionDate": "2017-08-20T16:07:58Z", "lastUpdate": "2024-09-13T13:57:13.745910Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics", "smoe" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "SQUARNA", "description": "SQUARNA is a tool for RNA secondary structure prediction. With a single RNA sequence as input, SQUARNA annotates and scores potential stems (stretches of consecutive canonical base pairs) and selects them one by one. SQUARNA handles pseudoknots and is able to predict alternative secondary structures. With a multiple sequence alignment input SQUARNA calculates the total matrix of stem scores and derives the most conserved base pairs. SQUARNA allows structural restraints and chemical probing data as additional input and is available at https://github.com/febos/SQUARNA.", "homepage": "https://github.com/febos/SQUARNA", "biotoolsID": "squarna", "biotoolsCURIE": "biotools:squarna", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0278", "term": "RNA secondary structure prediction" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3495", "term": "RNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" } ] }, { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1961", "term": "Stockholm format" }, { "uri": "http://edamontology.org/format_1982", "term": "ClustalW format" } ] }, { "data": { "uri": "http://edamontology.org/data_0889", "term": "Structural profile" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0880", "term": "RNA secondary structure" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" } ] }, { "data": { "uri": "http://edamontology.org/data_1772", "term": "Score" }, "format": [] } ], "note": "Input can be a single or several RNA sequences or an alignment of RNA sequences along with structural restraints and/or chemical probing data on base reactivities", "cmd": "python3 pathto/SQUARNA.py i=inputfile [OPTIONS]" } ], "toolType": [ "Command-line tool", "Script" ], "topic": [ { "uri": "http://edamontology.org/topic_3307", "term": "Computational biology" }, { "uri": "http://edamontology.org/topic_0077", "term": "Nucleic acids" }, { "uri": "http://edamontology.org/topic_0081", "term": "Structure analysis" }, { "uri": "http://edamontology.org/topic_0097", "term": "Nucleic acid structure analysis" }, { "uri": "http://edamontology.org/topic_0082", "term": "Structure prediction" }, { "uri": "http://edamontology.org/topic_0099", "term": "RNA" }, { "uri": "http://edamontology.org/topic_0659", "term": "Functional, regulatory and non-coding RNA" }, { "uri": "http://edamontology.org/topic_3511", "term": "Nucleic acid sites, features and motifs" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "Python" ], "license": "Apache-2.0", "collectionID": [ "3D-BioInfo-Nucleic-Acid" ], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/febos/SQUARNA", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://doi.org/10.5281/zenodo.8292326", "type": "Software package", "note": null, "version": "ver0.9" } ], "documentation": [ { "url": "https://github.com/febos/SQUARNA/blob/main/README.md", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1101/2023.08.28.555103", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Eugene F Baulin", "email": "efbaulin@gmail.com", "url": "https://scholar.google.com/citations?user=sjfDaUwAAAAJ&hl=en", "orcidid": "https://orcid.org/0000-0003-4694-9783", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Developer", "Primary contact", "Support" ], "note": null } ], "community": null, "owner": "febos", "additionDate": "2023-09-05T09:39:45.613658Z", "lastUpdate": "2024-09-09T10:19:24.216814Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "REPET", "description": "The REPET package integrates bioinformatics pipelines dedicated to detect, annotate and analyze transposable elements (TEs) in genomic sequences. The main pipelines are (i) TEdenovo, which search for interspersed repeats, build consensus sequences and classify them according to TE features, and (ii)\n TEannot, which mines a genome with a library of TE sequences, for instance the one produced by the TEdenovo pipeline, to provide TE annotations exported into GFF3 files.", "homepage": "https://urgi.versailles.inrae.fr/Tools/REPET", "biotoolsID": "repet", "biotoolsCURIE": "biotools:repet", "version": [ "v3.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0379", "term": "Repeat sequence detection" }, { "uri": "http://edamontology.org/operation_0237", "term": "Repeat sequence analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_1270", "term": "Feature table" }, "format": [ { "uri": "http://edamontology.org/format_2206", "term": "Sequence feature table format (text)" } ] }, { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [ { "uri": "http://edamontology.org/format_1939", "term": "GFF3-seq" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0157", "term": "Sequence composition, complexity and repeats" }, { "uri": "http://edamontology.org/topic_0654", "term": "DNA" }, { "uri": "http://edamontology.org/topic_0097", "term": "Nucleic acid structure analysis" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "C++", "Python" ], "license": "CECILL-2.0", "collectionID": [ "REPET", "elixir-fr-sdp-2019", "PlantBioinfoPF", "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": "Summary: The classification of transposable elements (TEs) is key step towards deciphering their potential impact on the genome. However, this process is often based on manual sequence inspection by TE experts. With the wealth of genomic sequences now available, this task requires automation, making it accessible to most scientists. We propose a new tool, PASTEC, which classifies TEs by searching for structural features and similarities. This tool outperforms currently available software for TE classification. The main innovation of PASTEC is the search for HMM profiles, which is useful for inferring the classification of unknown TE on the basis of conserved functional domains of the proteins. In addition, PASTEC is the only tool providing an exhaustive spectrum of possible classifications to the order level of the Wicker hierarchical TE classification system. It can also automatically classify other repeated elements, such as SSR (Simple Sequence Repeats), rDNA or potential repeated host genes. Finally, the output of this new tool is designed to facilitate manual curation by providing to biologists with all the evidence accumulated for each TE consensus. Availability: PASTEC is available as a REPET module or standalone software (http://urgi.versailles.inra.fr/download/repet/REPET-linux-x64-2.2.tar. gz). It requires a Unix-like system. There are two standalone versions: one of which is parallelized (requiring Sun grid Engine or Torque), and the other of which is not. © 2014 Hoede et al.", "date": "2014-05-02T00:00:00Z", "citationCount": 203, "authors": [ { "name": "Hoede C." }, { "name": "Arnoux S." }, { "name": "Moisset M." }, { "name": "Chaumier T." }, { "name": "Inizan O." }, { "name": "Jamilloux V." }, { "name": "Quesneville H." } ], "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": "Transposable elements (TEs) are mobile, repetitive DNA sequences that are almost ubiquitous in prokaryotic and eukaryotic genomes. They have a large impact on genome structure, function and evolution. With the recent development of highthroughput sequencing methods, many genome sequences have become available, making possible comparative studies of TE dynamics at an unprecedented scale. Several methods have been proposed for the de novo identification of TEs in sequenced genomes. Most begin with the detection of genomic repeats, but the subsequent steps for defining TE families differ. High-quality TE annotations are available for the Drosophila melanogaster and Arabidopsis thaliana genome sequences, providing a solid basis for the benchmarking of such methods. We compared the performance of specific algorithms for the clustering of interspersed repeats and found that only a particular combination of algorithms detected TE families with good recovery of the reference sequences. We then applied a new procedure for reconciling the different clustering results and classifying TE sequences. The whole approach was implemented in a pipeline using the REPET package. Finally, we show that our combined approach highlights the dynamics of well defined TE families by making it possible to identify structural variations among their copies. This approach makes it possible to annotate TE families and to study their diversification in a single analysis, improving our understanding of TE dynamics at the whole-genome scale and for diverse species. © 2011 Flutre et al.", "date": "2011-02-09T00:00:00Z", "citationCount": 330, "authors": [ { "name": "Flutre T." }, { "name": "Duprat E." }, { "name": "Feuillet C." }, { "name": "Quesneville H." } ], "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": "Transposable elements (TEs) are mobile, repetitive sequences that make up significant fractions of metazoan genomes. Despite their near ubiquity and importance in genome and chromosome biology, most efforts to annotate TEs in genome sequences rely on the results of a single computational program, RepeatMasker. In contrast, recent advances in gene annotation indicate that high-quality gene models can be produced from combining multiple independent sources of computational evidence. To elevate the quality of TE annotations to a level comparable to that of gene models, we have developed a combined evidence-model TE annotation pipeline, analogous to systems used for gene annotation, by integrating results from multiple homology-based and de novo TE identification methods. As proof of principle, we have annotated \"TE models\" in Drosophila melanogaster Release 4 genomic sequences using the combined computational evidence derived from RepeatMasker, BLASTER, TBLASTX, all-by-all BLASTN, RECON, TE-HMM and the previous Release 3.1 annotation. Our system is designed for use with the Apollo genome annotation tool, allowing automatic results to be curated manually to produce reliable annotations. The euchromatic TE fraction of D. melanogaster is now estimated at 5.3% (cf. 3.86% in Release 3.1), and we found a substantially higher number of TEs (n = 6,013) than previously identified (n = 1,572). Most of the new TEs derive from small fragments of a few hundred nucleotides long and highly abundant families not previously annotated (e.g., INE-1). We also estimated that 518 TE copies (8.6%) are inserted into at least one other TE, forming a nest of elements. The pipeline allows rapid and thorough annotation of even the most complex TE models, including highly deleted and/or nested elements such as those often found in heterochromatic sequences. Our pipeline can be easily adapted to other genome sequences, such as those of the D. melanogaster heterochromatin or other species in the genus Drosophila. © 2005 Quesneville et al.", "date": "2005-01-01T00:00:00Z", "citationCount": 262, "authors": [ { "name": "Quesneville H." }, { "name": "Bergman C.M." }, { "name": "Andrieu O." }, { "name": "Autard D." }, { "name": "Nouaud D." }, { "name": "Ashburner M." }, { "name": "Anxolabehere D." } ], "journal": "PLoS Computational Biology" } }, { "doi": "10.1007/s00239-003-0007-2", "pmid": "15008403", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Detection of New Transposable Element Families in Drosophila melanogaster and Anopheles gambiae Genomes", "abstract": "The techniques that are usually used to detect transposable elements (TEs) in nucleic acid sequences rely on sequence similarity with previously characterized elements. However, these methods are likely to miss many elements in various organisms. We tested two strategies for the detection of unknown elements. The first, which we call \"TBLASTX strategy,\" searches for TE sequences by comparing the six-frame translations of the nucleic acid sequences of known TEs with the genomic sequence of interest. The second, \"repeat-based strategy,\" searches genomic sequences for long repeats and clusters them in groups of similar sequences. TE copies from a given family are expected to cluster together. We tested the Drosophila melanogaster genomic sequence and the recently sequenced Anopheles gambiae genome in which most TEs remain unknown. We showed that the \"TBLASTX strategy\" is very efficient as it detected at least 332 new TE families in D. melanogaster and 400 in A. gambiae. This was unexpected in Drosophila as TEs of this organism have been extensively studied. The \"repeat-based strategy\" appeared to be very inefficient because of two problems: (i) TE copies are heavily deleted and few copies share homologous regions, and (ii) segmental duplications are frequent and it is not easy to distinguish them from TE copies.", "date": "2003-12-29T00:00:00Z", "citationCount": 62, "authors": [ { "name": "Quesneville H." }, { "name": "Nouaud D." }, { "name": "Anxolabehere D." } ], "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": "Transposable elements (TEs) constitute the most dynamic and the largest component of large plant genomes: for example, 80% to 90% of the maize genome and the wheat genome may be TEs. De novo TE annotation is therefore a computational challenge, and we investigated, using current tools in the REPET package, new strategies to overcome the difficulties. We tested our methodological developments on the sequence of the chromosome 3B of the hexaploid wheat; this chromosome is ~1 Gb, one of the 'fattest' genomes ever sequenced. We successfully established various strategies for annotating TEs in such a complex dataset. Our analyses show that all of our strategies can overcome the current limitations for de novo TE discovery in large plant genomes. Relative to annotation based on a library of known TEs, our de novo approaches improved genome coverage (from 84% to 90%), and the number of full length annotated copies from 14 830 to 15 905. We also developed two new metrics for qualifying TE annotation: NTE50 involves measuring the number, and LTE50 the smallest sizes of annotations that cover 50% of the genome. NTE50 decreased the number of annotations from 124 868 to 93 633 and LTE50 increased it from 1839 to 2659. This work shows how to obtain comprehensive and high-quality automatic TE annotation for a number of economically and agronomically important species.", "date": "2017-03-01T00:00:00Z", "citationCount": 15, "authors": [ { "name": "Jamilloux V." }, { "name": "Daron J." }, { "name": "Choulet F." }, { "name": "Quesneville H." } ], "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" } ], "community": null, "owner": "Institut Francais de Bioinform", "additionDate": "2016-03-24T16:22:28Z", "lastUpdate": "2024-09-06T17:39:57.162017Z", "editPermission": { "type": "group", "authors": [ "vjamilloux", "johann_confais", "raphael.flores" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" } ] }
