Resource List
List all resources, or create a new resource.
GET /api/t/?dataFormatID=%22format_1929%22
{ "count": 833, "next": "?page=2", "previous": null, "list": [ { "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" }, { "name": "MeSS", "description": "Snakemake pipeline for simulating shotgun metagenomic samples", "homepage": "https://github.com/metagenlab/MeSS", "biotoolsID": "mess", "biotoolsCURIE": "biotools:mess", "version": [], "otherID": [], "relation": [ { "biotoolsID": "assembly_finder", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2426", "term": "Modelling and simulation" } ], "input": [ { "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_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_2572", "term": "BAM" } ] }, { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "Simulate sequencing reads from taxonomic profile abundances and fasta files", "cmd": "`mess simulate -i taxonomic_profile.tsv --fasta fastas/ -o output/ `" } ], "toolType": [ "Command-line tool", "Workflow" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" }, { "uri": "http://edamontology.org/topic_3837", "term": "Metagenomic sequencing" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Python" ], "license": "MIT", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/metagenlab/MeSS", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/metagenlab/MeSS/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "https://github.com/metagenlab/MeSS/releases", "type": "Source code", "note": null, "version": null }, { "url": "https://bioconda.github.io/recipes/mess/README.html", "type": "Software package", "note": "Bioconda package", "version": null }, { "url": "https://github.com/metagenlab/MeSS/pkgs/container/mess", "type": "Container file", "note": null, "version": null } ], "documentation": [ { "url": "https://metagenlab.github.io/MeSS/", "type": [ "General" ], "note": null }, { "url": "https://metagenlab.github.io/MeSS/install/", "type": [ "Installation instructions" ], "note": null }, { "url": "https://metagenlab.github.io/MeSS/commands/", "type": [ "Command-line options" ], "note": null } ], "publication": [], "credit": [ { "name": "Farid Chaabane", "email": "farid.chaabane@chuv.ch", "url": null, "orcidid": "https://orcid.org/0009-0007-9322-1281", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Developer" ], "note": null } ], "community": null, "owner": "farchaab", "additionDate": "2024-08-08T09:43:23.658886Z", "lastUpdate": "2024-08-30T13:01:30.910222Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Sigma70Pred", "description": "A highly accurate method for predicting sigma70 promoter in prokaryotic genome.", "homepage": "https://webs.iiitd.edu.in/raghava/sigma70pred/", "biotoolsID": "sigma70pred", "biotoolsCURIE": "biotools:sigma70pred", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0440", "term": "Promoter prediction" }, { "uri": "http://edamontology.org/operation_2575", "term": "Binding site prediction" }, { "uri": "http://edamontology.org/operation_0441", "term": "cis-regulatory element prediction" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0749", "term": "Transcription factors and regulatory sites" }, { "uri": "http://edamontology.org/topic_3512", "term": "Gene transcripts" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://webs.iiitd.edu.in/raghava/sigma70pred/help.html#pred", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1101/2021.06.29.450448", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Gajendra P.S. Raghava", "email": "raghava@iiitd.ac.in", "url": null, "orcidid": "https://orcid.org/0000-0002-8902-2876", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Dhawal Singh Pundir", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Mohd. Zartab Ali", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Nitindeep Singh", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null }, { "name": "Sumeet Patiyal", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0003-1358-292X", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "community": null, "owner": "raghavagps", "additionDate": "2021-11-20T21:57:19.005718Z", "lastUpdate": "2024-08-21T09:41:30.194762Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "assembly_finder", "description": "snakemake-powered cli to download genomes using NCBI datasets", "homepage": "https://github.com/metagenlab/assembly_finder", "biotoolsID": "assembly_finder", "biotoolsCURIE": "biotools:assembly_finder", "version": [], "otherID": [], "relation": [ { "biotoolsID": "ncbi_datasets", "type": "uses" }, { "biotoolsID": "mess", "type": "usedBy" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1179", "term": "NCBI taxonomy ID" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" }, { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" }, { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_3266", "term": "Sequence assembly ID" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" }, { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] } ], "output": [ { "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_3181", "term": "Sequence assembly report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": "`assembly_finder -i staphylococcus_aureus -nb 1`" } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_3077", "term": "Data acquisition" }, { "uri": "http://edamontology.org/topic_3071", "term": "Biological databases" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Python" ], "license": "MIT", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/metagenlab/assembly_finder", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/metagenlab/assembly_finder/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "https://github.com/metagenlab/assembly_finder/releases", "type": "Source code", "note": null, "version": null }, { "url": "https://bioconda.github.io/recipes/assembly_finder/README.html", "type": "Software package", "note": "Bioconda package", "version": null }, { "url": "https://github.com/metagenlab/assembly_finder/pkgs/container/assembly_finder", "type": "Container file", "note": null, "version": null } ], "documentation": [ { "url": "https://metagenlab.github.io/assembly_finder/", "type": [ "General" ], "note": null }, { "url": "https://metagenlab.github.io/assembly_finder/#installation", "type": [ "Installation instructions" ], "note": null }, { "url": "https://metagenlab.github.io/assembly_finder/#usage", "type": [ "Command-line options" ], "note": null } ], "publication": [], "credit": [ { "name": "Farid Chaabane", "email": "farid.chaabane@chuv.ch", "url": null, "orcidid": "https://orcid.org/0009-0007-9322-1281", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "community": null, "owner": "farchaab", "additionDate": "2024-08-08T10:55:20.712595Z", "lastUpdate": "2024-08-09T08:57:49.651562Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "varVAMP", "description": "variable VirusAMPlicons (varVAMP) is a tool to design primers for highly diverse viruses. The input is an alignment of your viral (full-genome) sequences.", "homepage": "https://github.com/jonas-fuchs/varVAMP", "biotoolsID": "varvamp", "biotoolsCURIE": "biotools:varvamp", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0308", "term": "PCR primer design" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0781", "term": "Virology" }, { "uri": "http://edamontology.org/topic_0632", "term": "Probes and primers" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [], "license": "GPL-3.0", "collectionID": [], "maturity": "Mature", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [ { "name": "Jonas Fuchs", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "community": null, "owner": "wm75", "additionDate": "2024-01-26T16:34:11.694040Z", "lastUpdate": "2024-08-07T20:48:46.925581Z", "editPermission": { "type": "public", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MacSyFinder", "description": "Program to model and detect macromolecular systems, genetic pathways... in protein datasets. In prokaryotes, these systems have often evolutionarily conserved properties: they are made of conserved components, and are encoded in compact loci (conserved genetic architecture). The user models these systems to reflect these conserved features, and to allow their efficient detection.", "homepage": "https://github.com/gem-pasteur/macsyfinder", "biotoolsID": "macsyfinder", "biotoolsCURIE": "biotools:macsyfinder", "version": [ "1.0.2", "2.0", "2.1.1", "2.1.2", "2.1.3", "2.1.4" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3672", "term": "Gene functional annotation" }, { "uri": "http://edamontology.org/operation_1777", "term": "Protein function prediction" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2886", "term": "Protein sequence record" }, "format": [ { "uri": "http://edamontology.org/format_2200", "term": "FASTA-like (text)" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_0869", "term": "Sequence-profile alignment" }, "format": [ { "uri": "http://edamontology.org/format_3329", "term": "HMMER3" } ] }, { "data": { "uri": "http://edamontology.org/data_2337", "term": "Resource metadata" }, "format": [ { "uri": "http://edamontology.org/format_2332", "term": "XML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] }, { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": "Detection of macromolecular systems in protein datasets using systems modelling and similarity search.", "cmd": null } ], "toolType": [ "Command-line tool", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0085", "term": "Functional genomics" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [ "GEM Pasteur" ], "maturity": "Mature", "cost": null, "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "France" ], "elixirCommunity": [], "link": [ { "url": "https://github.com/gem-pasteur/macsyfinder", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://github.com/gem-pasteur/macsyfinder", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0110726", "type": [ "Citation instructions" ], "note": "For MacSyFinder v1" }, { "url": "https://macsyfinder.readthedocs.io/en/latest/", "type": [ "General" ], "note": null }, { "url": "https://macsyfinder.readthedocs.io/en/latest/user_guide/index.html", "type": [ "User manual" ], "note": null }, { "url": "https://macsyfinder.readthedocs.io/en/latest/developer_guide/index.html", "type": [ "API documentation" ], "note": null }, { "url": "https://peercommunityjournal.org/articles/10.24072/pcjournal.250/", "type": [ "Citation instructions" ], "note": "For MacSyFinder v2" } ], "publication": [ { "doi": "10.1371/journal.pone.0110726", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": "1", "note": null, "metadata": { "title": "MacSyFinder: A program to mine genomes for molecular systems with an application to CRISPR-Cas systems", "abstract": "Motivation: Biologists often wish to use their knowledge on a few experimental models of a given molecular system to identify homologs in genomic data. We developed a generic tool for this purpose. Results: Macromolecular System Finder (MacSyFinder) provides a flexible framework to model the properties of molecular systems (cellular machinery or pathway) including their components, evolutionary associations with other systems and genetic architecture. Modelled features also include functional analogs, and the multiple uses of a same component by different systems. Models are used to search for molecular systems in complete genomes or in unstructured data like metagenomes. The components of the systems are searched by sequence similarity using Hidden Markov model (HMM) protein profiles. The assignment of hits to a given system is decided based on compliance with the content and organization of the system model. A graphical interface, MacSyView, facilitates the analysis of the results by showing overviews of component content and genomic context. To exemplify the use of MacSyFinder we built models to detect and class CRISPR-Cas systems following a previously established classification. We show that MacSyFinder allows to easily define an accurate \"Cas-finder\" using publicly available protein profiles. Availability and Implementation: MacSyFinder is a standalone application implemented in Python. It requires Python 2.7, Hmmer and makeblastdb (version 2.2.28 or higher). It is freely available with its source code under a GPLv3 license at https://github.com/gem-pasteur/macsyfinder. It is compatible with all platforms supporting Python and Hmmer/ makeblastdb. The \"Cas-finder\" (models and HMM profiles) is distributed as a compressed tarball archive as Supporting Information.", "date": "2014-10-17T00:00:00Z", "citationCount": 220, "authors": [ { "name": "Abby S.S." }, { "name": "Neron B." }, { "name": "Menager H." }, { "name": "Touchon M." }, { "name": "Rocha E.P.C." } ], "journal": "PLoS ONE" } }, { "doi": "10.24072/pcjournal.250", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": "2", "note": null, "metadata": { "title": "MacSyFinder v2: Improved modelling and search engine to identify molecular systems in genomes", "abstract": "Complex cellular functions are usually encoded by a set of genes in one or a few orga-nized genetic loci in microbial genomes. Macromolecular System Finder (MacSyFinder) is a program that uses these properties to model and then annotate cellular functions in microbial genomes. This is done by integrating the identification of each individual gene at the level of the molecular system. We hereby present a major release of MacSyFinder (version 2) coded in Python 3. The code was improved and rationalized to facilitate future maintainability. Several new features were added to allow more flexible modelling of the systems. We introduce a more intuitive and comprehensive search engine to identify all the best candidate systems and sub-optimal ones that respect the models’ constraints. We also introduce the novel macsydata companion tool that enables the easy installation and broad distribution of the models developed for MacSyFinder (macsy-models) from GitHub repositories. Finally, we have updated and improved MacSyFinder popular mod-els: TXSScan to identify protein secretion systems, TFFscan to identify type IV filaments, CONJscan to identify conjugative systems, and CasFinder to identify CRISPR associated proteins. MacSyFinder and the updated models are available at: https://github.com/gem-pasteur/macsyfinder.", "date": "2023-01-01T00:00:00Z", "citationCount": 13, "authors": [ { "name": "Neron B." }, { "name": "Denise R." }, { "name": "Coluzzi C." }, { "name": "Touchon M." }, { "name": "Rocha E.P.C." }, { "name": "Abby S.S." } ], "journal": "Peer Community Journal" } } ], "credit": [ { "name": "Institut Pasteur", "email": null, "url": "https://research.pasteur.fr", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Bioinformatics and Biostatistics HUB", "email": null, "url": "https://research.pasteur.fr/en/team/bioinformatics-and-biostatistics-hub/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Division", "typeRole": [], "note": null }, { "name": "Microbial Evolutionary Genomics Unit", "email": null, "url": "https://research.pasteur.fr/en/team/microbial-evolutionary-genomics/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Division", "typeRole": [ "Provider" ], "note": "CNRS - UMR 352" }, { "name": "Bertrand Néron", "email": "bneron@pasteur.fr", "url": "https://research.pasteur.fr/en/member/bertrand-neron/", "orcidid": "https://orcid.org/0000-0002-0220-0482", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Developer" ], "note": null }, { "name": "Eduardo Rocha", "email": "eduardo.rocha@pasteur.fr", "url": "https://research.pasteur.fr/fr/member/eduardo-rocha/", "orcidid": "https://orcid.org/0000-0001-7704-822X", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Bertrand Néron", "email": "bneron@pasteur.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Sophie Abby", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0002-5231-3346", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "community": null, "owner": "bneron", "additionDate": "2016-12-04T05:58:15Z", "lastUpdate": "2024-08-06T11:28:15.223552Z", "editPermission": { "type": "group", "authors": [ "hmenager", "khillion" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "decontaminator", "description": "Decontaminator is a deep learning helping tool that filters out phage or fungi contigs from plant virome RNAseq assemblies.", "homepage": "https://github.com/cbib/decontaminator", "biotoolsID": "decontaminator", "biotoolsCURIE": "biotools:decontaminator", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3695", "term": "Filtering" } ], "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_1984", "term": "FASTA-aln" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" } ], "operatingSystem": [], "language": [ "Python" ], "license": "MIT", "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "community": null, "owner": "m.bernt", "additionDate": "2024-07-27T11:59:04.572880Z", "lastUpdate": "2024-07-27T12:05:32.493883Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Stitch", "description": "Stitch is a software tool that performs template-based assembly of proteomics short reads for de novo antibody sequencing and repertoire profiling.", "homepage": "https://github.com/snijderlab/stitch", "biotoolsID": "stitch-snijderlab", "biotoolsCURIE": "biotools:stitch-snijderlab", "version": [ "1.5.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0310", "term": "Sequence assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1233", "term": "Sequence set (protein)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" }, { "uri": "http://edamontology.org/format_3752", "term": "CSV" }, { "uri": "http://edamontology.org/format_1477", "term": "mmCIF" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1233", "term": "Sequence set (protein)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_2331", "term": "HTML" }, { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] } ], "note": "Assembles de novo peptide sequences against known antibody gene segments to reconstruct complete antibody sequences.\nFor batch file (job file) specifications, see https://github.com/snijderlab/stitch/blob/master/BatchFiles.md.\nOptions:\n--expect - The expected result(s) of the run as the final sequence(s) by separated commas, used for automated testing;\n--open - Open the HTML report (if available) automatically in the browser;\n--live - Prepare the HTML report for use with VS Code Live Server on the given port, -1 turns it off;\n--quiet - Turns off any output on the command line in normal operation.", "cmd": "stitch run [OPTIONS] <batchfile>" }, { "operation": [ { "uri": "http://edamontology.org/operation_2425", "term": "Optimisation and refinement" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0943", "term": "Mass spectrum" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0943", "term": "Mass spectrum" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" } ] } ], "note": "Utilizes a mass-based alignment algorithm to handle mass coincidence errors and differentiates between isoleucine and leucine residues using secondary fragments. Generates two CSV files: one with refined reads and another with positional information.\nOptions:\n--output - The filename of the refined reads, the extension will be added automatically;\n--peaks-version - The version of the Peaks file format to use.", "cmd": "stitch refine [OPTIONS] <input> <raw-data-dir>" }, { "operation": [ { "uri": "http://edamontology.org/operation_1812", "term": "Parsing" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1233", "term": "Sequence set (protein)" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1233", "term": "Sequence set (protein)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": "Parses the sequences from an IMGT HTML file and creates annotated fasta files (also cleans data).\nOptions:\n--output - The output file name, if missing will overwrite the input file.", "cmd": "stitch annotate [OPTIONS] <input>" }, { "operation": [ { "uri": "http://edamontology.org/operation_2409", "term": "Data handling" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1233", "term": "Sequence set (protein)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1233", "term": "Sequence set (protein)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": "Removes duplicates and incomplete sequences from fasta. \nOptions: \n--output - The output file name, if missing will overwrite the input file.", "cmd": "stitch clean [OPTIONS] <input>" } ], "toolType": [ "Command-line tool" ], "topic": [], "operatingSystem": [ "Windows", "Linux", "Mac" ], "language": [ "C#" ], "license": "MIT", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/snijderlab/stitch", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "https://github.com/snijderlab/stitch/releases/tag/v1.5.0", "type": "Downloads page", "note": null, "version": "1.5.0" } ], "documentation": [], "publication": [ { "doi": "10.1021/acs.jproteome.4c00188", "pmid": "38932690", "pmcid": null, "type": [], "version": "1.5.0", "note": null, "metadata": { "title": "A Handle on Mass Coincidence Errors in De Novo Sequencing of Antibodies by Bottom-up Proteomics", "abstract": "Antibody sequences can be determined at 99% accuracy directly from the polypeptide product by using bottom-up proteomics techniques. Sequencing accuracy at the peptide level is limited by the isobaric residues leucine and isoleucine, incomplete fragmentation spectra in which the order of two or more residues remains ambiguous due to lacking fragment ions for the intermediate positions, and isobaric combinations of amino acids, of potentially different lengths, for example, GG = N and GA = Q. Here, we present several updates to Stitch (v1.5), which performs template-based assembly of de novo peptides to reconstruct antibody sequences. This version introduces a mass-based alignment algorithm that explicitly accounts for mass coincidence errors. In addition, it incorporates a postprocessing procedure to assign I/L residues based on secondary fragments (satellite ions, i.e., w-ions). Moreover, evidence for sequence assignments can now be directly evaluated with the addition of an integrated spectrum viewer. Lastly, input data from a wider selection of de novo peptide sequencing algorithms are allowed, now including Casanovo, PEAKS, Novor.Cloud, pNovo, and MaxNovo, in addition to flat text and FASTA. Combined, these changes make Stitch compatible with a larger range of data processing pipelines and improve its tolerance to peptide-level sequencing errors.", "date": "2024-01-01T00:00:00Z", "citationCount": 0, "authors": [ { "name": "Schulte D." }, { "name": "Snijder J." } ], "journal": "Journal of Proteome Research" } } ], "credit": [ { "name": "Douwe Schulte", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0003-0594-0993", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": "Software Engineer" }, { "name": "Joost Snijder", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0002-9310-8226", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": "Principal Investigator" }, { "name": "Bastiaan de Graaf", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": "Code Reviews" }, { "name": "Wei Wei Peng", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": "Testing and Analysis" }, { "name": "Biomolecular Mass Spectrometry and Proteomics", "email": null, "url": "https://www.uu.nl/en/research/biomolecular-mass-spectrometry-and-proteomics", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Division", "typeRole": [], "note": "Group at Utrecht University" } ], "community": null, "owner": "thatmariia", "additionDate": "2024-07-17T13:27:56.256529Z", "lastUpdate": "2024-07-18T14:56:47.152424Z", "editPermission": { "type": "public", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "metabuli", "description": "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid", "homepage": "https://metabuli.steineggerlab.com", "biotoolsID": "metabuli", "biotoolsCURIE": "biotools:metabuli", "version": [], "otherID": [], "relation": [ { "biotoolsID": "mmseqs2", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "C++" ], "license": "GPL-3.0", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/steineggerlab/Metabuli/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1038/s41592-024-02273-y", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Metabuli: sensitive and specific metagenomic classification via joint analysis of amino acid and DNA", "abstract": "Metagenomic taxonomic classifiers analyze either DNA or amino acid (AA) sequences. Metabuli (https://metabuli.steineggerlab.com), however, jointly analyzes both DNA and AA to leverage AA conservation for sensitive homology detection and DNA mutations for specific differentiation of closely related taxa. In the Critical Assessment of Metagenome Interpretation 2 plant-associated dataset, Metabuli covered 99% and 98% of classifications of state-of-the-art DNA- and AA-based classifiers, respectively.", "date": "2024-06-01T00:00:00Z", "citationCount": 1, "authors": [ { "name": "Kim J." }, { "name": "Steinegger M." } ], "journal": "Nature Methods" } }, { "doi": "10.1101/2023.05.31.543018", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [], "community": null, "owner": "milot-mirdita", "additionDate": "2023-06-07T03:22:25.847061Z", "lastUpdate": "2024-07-11T05:05:57.102135Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null } ] }