Resource List
List all resources, or create a new resource.
GET /api/t/?otherIDType=RRID
http://bioinf.cs.ucl.ac.uk/psipred/", "biotoolsID": "psipred", "biotoolsCURIE": "biotools:psipred", "version": [], "otherID": [ { "value": "RRID:SCR_018546", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0469", "term": "Protein secondary structure prediction (turns)" }, { "uri": "http://edamontology.org/operation_0303", "term": "Protein fold recognition" }, { "uri": "http://edamontology.org/operation_0267", "term": "Protein secondary structure prediction" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0082", "term": "Structure prediction" }, { "uri": "http://edamontology.org/topic_0736", "term": "Protein folds and structural domains" }, { "uri": "http://edamontology.org/topic_3542", "term": "Protein secondary structure" }, { "uri": "http://edamontology.org/topic_0130", "term": "Protein folding, stability and design" }, { "uri": "http://edamontology.org/topic_2814", "term": "Protein structure analysis" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://bioinf.cs.ucl.ac.uk/index.php?id=779", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/16.4.404", "pmid": "10869041", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "The PSIPRED protein structure prediction server", "abstract": "The PSIPRED protein structure prediction server allows users to submit a protein sequence, perform a prediction of their choice and receive the results of the prediction both textually via e-mail and graphically via the web. The user may select one of three prediction methods to apply to their sequence: PSIPRED, a highly accurate secondary structure prediction method; MEMSAT 2, a new version of a widely used transmembrane topology prediction method; or GenTHREADER, a sequence profile based fold recognition method. Availability: Freely available to non-commercial users at http://globin.bio.warwick.ac.uk/psipred/.", "date": "2000-01-01T00:00:00Z", "citationCount": 3053, "authors": [ { "name": "McGuffin L.J." }, { "name": "Bryson K." }, { "name": "Jones D.T." } ], "journal": "Bioinformatics" } }, { "doi": "10.1006/jmbi.1999.3091", "pmid": "10493868", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Protein secondary structure prediction based on position-specific scoring matrices", "abstract": "A two-stage neural network has been used to predict protein secondary structure based on the position specific scoring matrices generated by PSI-BLAST. Despite the simplicity and convenience of the approach used, the results are found to be superior to those produced by other methods, including the popular PHD method according to our own benchmarking results and the results from the recent Critical Assessment of Techniques for Protein Structure Prediction experiment (CASP3), where the method was evaluated by stringent blind testing. Using a new testing set based on a set of 187 unique folds, and three-way cross-validation based on structural similarity criteria rather than sequence similarity criteria used previously (no similar folds were present in both the testing and training sets) the method presented here (PSIPRED) achieved an average Q3 score of between 76.5% to 78.3% depending on the precise definition of observed secondary structure used, which is the highest published score for any method to date. Given the success of the method in CASP3, it is reasonable to be confident that the evaluation presented here gives a fair indication of the performance of the method in general.", "date": "1999-09-17T00:00:00Z", "citationCount": 4685, "authors": [ { "name": "Jones D.T." } ], "journal": "Journal of Molecular Biology" } }, { "doi": "10.1093/nar/gkt381", "pmid": "23748958", "pmcid": "PMC3692098", "type": [], "version": null, "note": null, "metadata": { "title": "Scalable web services for the PSIPRED Protein Analysis Workbench.", "abstract": "Here, we present the new UCL Bioinformatics Group's PSIPRED Protein Analysis Workbench. The Workbench unites all of our previously available analysis methods into a single web-based framework. The new web portal provides a greatly streamlined user interface with a number of new features to allow users to better explore their results. We offer a number of additional services to enable computationally scalable execution of our prediction methods; these include SOAP and XML-RPC web server access and new HADOOP packages. All software and services are available via the UCL Bioinformatics Group website at http://bioinf.cs.ucl.ac.uk/.", "date": "2013-01-01T00:00:00Z", "citationCount": 1109, "authors": [ { "name": "Buchan D.W." }, { "name": "Minneci F." }, { "name": "Nugent T.C." }, { "name": "Bryson K." }, { "name": "Jones D.T." } ], "journal": "Nucleic acids research" } } ], "credit": [ { "name": "psipred team", "email": "psipred@cs.ucl.ac.uk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "Bijay", "additionDate": "2017-03-25T16:29:49Z", "lastUpdate": "2025-04-03T08:22:35.616168Z", "editPermission": { "type": "group", "authors": [ "zhouwj", "Bijay", "Yunus" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ISfinder", "description": "It is a dedicated insertion sequence (IS) database which assigns names to individual ISs to maintain a coherent nomenclature, an IS repositaory including >3000 individual ISs from both bacteria and archaea and provides a basis for IS classification. Each IS is indexed in ISfinder with various associated pieces of information and classified into a group or family to provide some insight into its phylogeny.", "homepage": "http://www-is.biotoul.fr", "biotoolsID": "isfinder", "biotoolsCURIE": "biotools:isfinder", "version": [], "otherID": [ { "value": "RRID:SCR_003020", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3211", "term": "Genome indexing" }, { "uri": "http://edamontology.org/operation_3349", "term": "Bibliography generation" }, { "uri": "http://edamontology.org/operation_2436", "term": "Gene-set enrichment analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3068", "term": "Literature and language" }, { "uri": "http://edamontology.org/topic_0084", "term": "Phylogeny" }, { "uri": "http://edamontology.org/topic_0798", "term": "Mobile genetic elements" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" }, { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "SQL" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [ "Tools" ], "elixirNode": [ "France" ], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://www-is.biotoul.fr/general_information.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkp947", "pmid": "19906702", "pmcid": "PMC2808865", "type": [], "version": null, "note": null, "metadata": { "title": "ISbrowser: An extension of ISfinder for visualizing insertion sequences in prokaryotic genomes", "abstract": "Insertion sequences (ISs) are among the smallest and simplest autonomous transposable elements. ISfinder (http://www-is.biotoul.fr/) is a dedicated IS database which assigns names to individual ISs to maintain a coherent nomenclature, an IS repository including >3000 individual ISs from both bacteria and archaea and provides a basis for IS classification. Each IS is indexed in ISfinder with various associated pieces of information (the complete nucleotide sequence, the sequence of the ends and target sites, potential open reading frames, strain of origin, distribution in other strains and available bibliography) and classified into a group or family to provide some insight into its phylogeny. ISfinder also includes extensive background information on ISs and transposons in general. Online tools are gradually being added. At present, it is difficult to visualize the global distribution of ISs in a given bacterial genome. Such information would facilitate understanding of the impact of these small transposable elements on shaping their host genome. Here we describe ISbrowser (http://www-genome.biotoul.fr/ISbrowser.php), an extension to the ISfinder platform and a tool which permits visualization of the position, orientation and distribution of complete and partial ISs in individual prokaryotic genomes. © The Author(s) 2009. Published by Oxford University Press.", "date": "2009-11-11T00:00:00Z", "citationCount": 43, "authors": [ { "name": "Kichenaradja P." }, { "name": "Siguier P." }, { "name": "Perochon J." }, { "name": "Chandler M." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Patricia Siguier", "email": "Patricia.Siguier@ibcg.biotoul.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "Patricia_SIguier", "additionDate": "2017-03-27T07:19:58Z", "lastUpdate": "2025-01-24T09:59:36.949842Z", "editPermission": { "type": "group", "authors": [ "Patricia_SIguier" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "SILVA rRNA database", "description": "SILVA provides comprehensive, quality checked and regularly updated datasets of aligned small (16S/18S, SSU) and large subunit (23S/28S, LSU) ribosomal RNA (rRNA) sequences for all three domains of life (Bacteria, Archaea and Eukaryota).", "homepage": "http://www.arb-silva.de", "biotoolsID": "silva", "biotoolsCURIE": "biotools:silva", "version": [], "otherID": [ { "value": "RRID:SCR_006423", "type": "rrid", "version": null } ], "relation": [ { "biotoolsID": "silvangs", "type": "usedBy" }, { "biotoolsID": "d3hub", "type": "includedIn" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1097", "term": "Sequence accession (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_1868", "term": "Taxon" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_1046", "term": "Strain name" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_1088", "term": "Article ID" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] }, { "data": { "uri": "http://edamontology.org/data_1383", "term": "Sequence alignment (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] } ], "note": "The search and retrieval functions of the SILVA website can be used to build custom subsets of sequences. In addition to simple searches e.g. for accession numbers, organism names, taxonomic entities, or publication DOI/PubMed IDs, complex queries over several database fields using constraints such as sequence length or quality values are possible. The results can be sorted according to accession numbers, organism names, sequence length, sequence and alignment quality and Pintail values. The search results show accession number, organism name, sequence length, sequence quality values, taxonomic classifications, and links to view the full sequence record on SILVA and on ENA. Sequences found via search and added to download cart can be downloaded as FASTA and ARB files.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Sequence alignment (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] } ], "note": "SILVA Incremental Aligner (SINA) is used to align the rRNA gene databases provided by SILVA, as well as user submitted sequences. SINA uses a combination of k-mer searching and partial order alignment (POA) to maintain very high alignment accuracy while satisfying high throughput performance demands. Aligned sequences can be dowloaded as FASTA or ARB files", "cmd": null }, { "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": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Sequence alignment (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_2333", "term": "Binary format" }, { "uri": "http://edamontology.org/format_1984", "term": "FASTA-aln" } ] }, { "data": { "uri": "http://edamontology.org/data_1872", "term": "Taxonomic classification" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "SINA can also operate as a taxonomic classification tool. It uses the search result to derive a classification with the LCA (lowest common ancestor) method. Each query sequence is assigned the shared part of the classifications of the search results. Aligned sequences can be dowloaded as FASTA or ARB files Taxonomic classification results can be downloaded as csv files.", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2419", "term": "Primer and probe design" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2977", "term": "Nucleic acid sequence" }, "format": [ { "uri": "http://edamontology.org/format_1207", "term": "nucleotide" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2048", "term": "Report" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "note": "The SILVA Probe Match and Evaluation Tool detects and displays all occurrences of a given probe or primer sequence in the SILVA datasets. TestPrime allows you to evaluate the performance of primer pairs by running an in silico PCR on the SILVA databases. From the results of the PCR, TestPrime computes coverages for each taxonomic group in all of the taxonomies offered by SILVA.", "cmd": null } ], "toolType": [ "Web application", "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0659", "term": "Functional, regulatory and non-coding RNA" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_3293", "term": "Phylogenetics" }, { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" }, { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" }, { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" }, { "uri": "http://edamontology.org/topic_0632", "term": "Probes and primers" } ], "operatingSystem": [], "language": [], "license": "CC-BY-4.0", "collectionID": [ "de.NBI", "de.NBI-biodata", "DSMZ Digital Diversity" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Data" ], "elixirNode": [ "Germany" ], "elixirCommunity": [], "link": [ { "url": "https://www.arb-silva.de/browser/", "type": [ "Service" ], "note": "SILVA Taxonomy Browser" }, { "url": "https://www.arb-silva.de/search/", "type": [ "Service" ], "note": "SILVA metadata search" }, { "url": "https://www.arb-silva.de/aligner/", "type": [ "Service" ], "note": "ACT: Alignment, Classification and Tree Service" }, { "url": "https://www.arb-silva.de/search/testprobe/", "type": [ "Service" ], "note": "SILVA Probe Match and Evaluation Tool" }, { "url": "https://www.arb-silva.de/search/testprime/", "type": [ "Service" ], "note": "SILVA Primer Evaluation Tool" }, { "url": "https://treeviewer.arb-silva.de/", "type": [ "Service" ], "note": "Web-based viewer for the SILVA guide trees" } ], "download": [ { "url": "https://www.arb-silva.de/download/archive/", "type": "Downloads page", "note": "SILVA dataset archive", "version": null } ], "documentation": [ { "url": "https://www.arb-silva.de/silva-license-information/", "type": [ "Terms of use" ], "note": null }, { "url": "https://www.arb-silva.de/contact/", "type": [ "Citation instructions" ], "note": null }, { "url": "http://www.arb-silva.de/documentation/", "type": [ "General" ], "note": null }, { "url": "https://www.arb-silva.de/documentation/faqs/", "type": [ "FAQ" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gks1219", "pmid": "23193283", "pmcid": "PMC3531112", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The SILVA ribosomal RNA gene database project: Improved data processing and web-based tools", "abstract": "SILVA (from Latin silva, forest, http://www.arb-silva.de) is a comprehensive web resource for up to date, quality-controlled databases of aligned ribosomal RNA (rRNA) gene sequences from the Bacteria, Archaea and Eukaryota domains and supplementary online services. The referred database release 111 (July 2012) contains 3194 778 small subunit and 288717 large subunit rRNA gene sequences. Since the initial description of the project, substantial new features have been introduced, including advanced quality control procedures, an improved rRNA gene aligner, online tools for probe and primer evaluation and optimized browsing, searching and downloading on the website. Furthermore, the extensively curated SILVA taxonomy and the new non-redundant SILVA datasets provide an ideal reference for high-throughput classification of data from next-generation sequencing approaches. © The Author(s) 2012.", "date": "2013-01-01T00:00:00Z", "citationCount": 20831, "authors": [ { "name": "Quast C." }, { "name": "Pruesse E." }, { "name": "Yilmaz P." }, { "name": "Gerken J." }, { "name": "Schweer T." }, { "name": "Yarza P." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkt1209", "pmid": "24293649", "pmcid": "PMC3965112", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "The SILVA and \"all-species Living Tree Project (LTP)\" taxonomic frameworks", "abstract": "SILVA (from Latin silva, forest, http://www.arb-silva.de) is a comprehensive resource for up-to-date quality-controlled databases of aligned ribosomal RNA (rRNA) gene sequences from the Bacteria, Archaea and Eukaryota domains and supplementary online services. SILVA provides a manually curated taxonomy for all three domains of life, based on representative phylogenetic trees for the small- and large-subunit rRNA genes. This article describes the improvements the SILVA taxonomy has undergone in the last 3 years. Specifically we are focusing on the curation process, the various resources used for curation and the comparison of the SILVA taxonomy with Greengenes and RDP-II taxonomies. Our comparisons not only revealed a reasonable overlap between the taxa names, but also points to significant differences in both names and numbers of taxa between the three resources. © 2013 The Author(s). Published by Oxford University Press.", "date": "2014-01-01T00:00:00Z", "citationCount": 2372, "authors": [ { "name": "Yilmaz P." }, { "name": "Parfrey L.W." }, { "name": "Yarza P." }, { "name": "Gerken J." }, { "name": "Pruesse E." }, { "name": "Quast C." }, { "name": "Schweer T." }, { "name": "Peplies J." }, { "name": "Ludwig W." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkm864", "pmid": "17947321", "pmcid": "PMC2175337", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "SILVA: A comprehensive online resource for quality checked and aligned ribosomal RNA sequence data compatible with ARB", "abstract": "Sequencing ribosomal RNA (rRNA) genes is currently the method of choice for phylogenetic reconstruction, nucleic acid based detection and quantification of microbial diversity. The ARB software suite with its corresponding rRNA datasets has been accepted by researchers worldwide as a standard tool for large scale rRNA analysis. However, the rapid increase of publicly available rRNA sequence data has recently hampered the maintenance of comprehensive and curated rRNA knowledge databases. A new system, SILVA (from Latin silva, forest), was implemented to provide a central comprehensive web resource for up to date, quality controlled databases of aligned rRNA sequences from the Bacteria, Archaea and Eukarya domains. All sequences are checked for anomalies, carry a rich set of sequence associated contextual information, have multiple taxonomic classifications, and the latest validly described nomenclature. Furthermore, two precompiled sequence datasets compatible with ARB are offered for download on the SILVA website: (i) the reference (Ref) datasets, comprising only high quality, nearly full length sequences suitable for in-depth phylogenetic analysis and probe design and (ii) the comprehensive Parc datasets with all publicly available rRNA sequences longer than 300 nucleotides suitable for biodiversity analyses. The latest publicly available database release 91 (August 2007) hosts 547 521 sequences split into 461 823 small subunit and 85 689 large subunit rRNAs. © 2007 The Author(s).", "date": "2007-12-01T00:00:00Z", "citationCount": 5145, "authors": [ { "name": "Pruesse E." }, { "name": "Quast C." }, { "name": "Knittel K." }, { "name": "Fuchs B.M." }, { "name": "Ludwig W." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/bioinformatics/bts252", "pmid": "22556368", "pmcid": "PMC3389763", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "SINA: Accurate high-throughput multiple sequence alignment of ribosomal RNA genes", "abstract": "Motivation: In the analysis of homologous sequences, computation of multiple sequence alignments (MSAs) has become a bottleneck. This is especially troublesome for marker genes like the ribosomal RNA (rRNA) where already millions of sequences are publicly available and individual studies can easily produce hundreds of thousands of new sequences. Methods have been developed to cope with such numbers, but further improvements are needed to meet accuracy requirements.Results: In this study, we present the SILVA Incremental Aligner (SINA) used to align the rRNA gene databases provided by the SILVA ribosomal RNA project. SINA uses a combination of k-mer searching and partial order alignment (POA) to maintain very high alignment accuracy while satisfying high throughput performance demands. SINA was evaluated in comparison with the commonly used high throughput MSA programs PyNAST and mothur. The three BRAliBase III benchmark MSAs could be reproduced with 99.3, 97.6 and 96.1 accuracy. A larger benchmark MSA comprising 38 772 sequences could be reproduced with 98.9 and 99.3% accuracy using reference MSAs comprising 1000 and 5000 sequences. SINA was able to achieve higher accuracy than PyNAST and mothur in all performed benchmarks. © The Author(s) 2012. Published by Oxford University Press.", "date": "2012-07-01T00:00:00Z", "citationCount": 2352, "authors": [ { "name": "Pruesse E." }, { "name": "Peplies J." }, { "name": "Glockner F.O." } ], "journal": "Bioinformatics" } }, { "doi": "10.1016/j.jbiotec.2017.06.1198", "pmid": "28648396", "pmcid": null, "type": [ "Review" ], "version": null, "note": null, "metadata": { "title": "25 years of serving the community with ribosomal RNA gene reference databases and tools", "abstract": "SILVA (lat. forest) is a comprehensive web resource, providing services around up to date, high-quality datasets of aligned ribosomal RNA gene (rDNA) sequences from the Bacteria, Archaea, and Eukaryota domains. SILVA dates back to the year 1991 when Dr. Wolfgang Ludwig from the Technical University Munich started the integrated software workbench ARB (lat. tree) to support high-quality phylogenetic inference and taxonomy based on the SSU and LSU rDNA marker genes. At that time, the ARB project maintained both, the sequence reference datasets and the software package for data analysis. In 2005, with the massive increase of DNA sequence data, the maintenance of the software system ARB and the corresponding rRNA databases SILVA was split between Munich and the Microbial Genomics and Bioinformatics Research Group in Bremen. ARB has been continuously developed to include new features and improve the usability of the workbench. Thousands of users worldwide appreciate the seamless integration of common analysis tools under a central graphical user interface, in combination with its versatility. The first SILVA release was deployed in February 2007 based on the EMBL-EBI/ENA release 89. Since then, full SILVA releases offering the database content in various flavours are published at least annually, complemented by intermediate web-releases where only the SILVA web dataset is updated. SILVA is the only rDNA database project worldwide where special emphasis is given to the consistent naming of clades of uncultivated (environmental) sequences, where no validly described cultivated representatives are available. Also exclusive for SILVA is the maintenance of both comprehensive aligned 16S/18S rDNA and 23S/28S rDNA sequence datasets. Furthermore, the SILVA alignments and trees were designed to include Eukaryota, another unique feature among rDNA databases. With the termination of the European Ribosomal RNA Database Project in 2007, the SILVA database has become the authoritative rDNA database project for Europe. The application spectrum of ARB and SILVA ranges from biodiversity analysis, medical diagnostics, to biotechnology and quality control for academia and industry.", "date": "2017-11-10T00:00:00Z", "citationCount": 578, "authors": [ { "name": "Glockner F.O." }, { "name": "Yilmaz P." }, { "name": "Quast C." }, { "name": "Gerken J." }, { "name": "Beccati A." }, { "name": "Ciuprina A." }, { "name": "Bruns G." }, { "name": "Yarza P." }, { "name": "Peplies J." }, { "name": "Westram R." }, { "name": "Ludwig W." } ], "journal": "Journal of Biotechnology" } }, { "doi": "10.1186/s12859-017-1841-3", "pmid": null, "pmcid": null, "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "SILVA tree viewer: Interactive web browsing of the SILVA phylogenetic guide trees", "abstract": "Background: Phylogenetic trees are an important tool to study the evolutionary relationships among organisms. The huge amount of available taxa poses difficulties in their interactive visualization. This hampers the interaction with the users to provide feedback for the further improvement of the taxonomic framework. Results: The SILVA Tree Viewer is a web application designed for visualizing large phylogenetic trees without requiring the download of any software tool or data files. The SILVA Tree Viewer is based on Web Geographic Information Systems (Web-GIS) technology with a PostgreSQL backend. It enables zoom and pan functionalities similar to Google Maps. The SILVA Tree Viewer enables access to two phylogenetic (guide) trees provided by the SILVA database: the SSU Ref NR99 inferred from high-quality, full-length small subunit sequences, clustered at 99% sequence identity and the LSU Ref inferred from high-quality, full-length large subunit sequences. Conclusions: The Tree Viewer provides tree navigation, search and browse tools as well as an interactive feedback system to collect any kinds of requests ranging from taxonomy to data curation and improving the tool itself.", "date": "2017-09-30T00:00:00Z", "citationCount": 28, "authors": [ { "name": "Beccati A." }, { "name": "Gerken J." }, { "name": "Quast C." }, { "name": "Yilmaz P." }, { "name": "Glockner F.O." } ], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": "Leibniz Institute DSMZ-German Collection of Microorganisms and Cell Cultures", "email": "hub@dsmz.de", "url": "https://www.dsmz.de", "orcidid": null, "gridid": "grid.420081.f", "rorid": "02tyer376", "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": "contact@arb-silva.de", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Project", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "silva", "additionDate": "2016-09-30T15:59:05Z", "lastUpdate": "2025-01-22T09:59:03.064970Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "MassBank", "description": "MassBank is a public repository of mass spectra of small chemical compounds for life sciences (<3000 Da). The database contains spectra from EI‐MS, fast atom bombardment MS, electrospray ionization (ESI)‐MSn data of thousands of authentic standards, EI‐MS and other‐MS data of thousands of volatile natural and synthetic compounds, and ESI‐MS2 data of synthetic drugs contributed by research groups worldwide. ESI‐MS2 data were analyzed under nonstandardized, independent experimental conditions. MassBank users can access either all of the MassBank data or a subset of the data by specifying one or more experimental conditions. In a spectral search to retrieve mass spectra similar to a query mass spectrum, the similarity score is calculated by a weighted cosine correlation in which weighting exponents on peak intensity and the mass‐to‐charge ratio are optimized to the ESI‐MS2 data. MassBank is useful for the identification of chemical compounds and the publication of experimental data.", "homepage": "https://massbank.eu/", "biotoolsID": "massbank", "biotoolsCURIE": "biotools:massbank", "version": [], "otherID": [ { "value": "doi:10.25504/FAIRsharing.dk451a", "type": "doi", "version": null }, { "value": "rrid:SCR_015535", "type": "rrid", "version": null } ], "relation": [], "function": [], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3172", "term": "Metabolomics" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [ "Germany" ], "elixirCommunity": [ "Metabolomics" ], "link": [ { "url": "https://massbank.eu/", "type": [ "Service" ], "note": "European MassBank site" }, { "url": "https://github.com/MassBank/", "type": [ "Other" ], "note": null } ], "download": [ { "url": "https://github.com/MassBank/MassBank-web/", "type": "Source code", "note": null, "version": null } ], "documentation": [], "publication": [ { "doi": "10.1002/jms.1777", "pmid": "20623627", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "MassBank: A public repository for sharing mass spectral data for life sciences", "abstract": "MassBank is the first public repository of mass spectra of small chemical compounds for life sciences (<3000 Da). The database contains 605 electron-ionizationmass spectrometry(EI-MS), 137 fast atom bombardment MS and 9276 electrospray ionization (ESI)-MSn data of 2337 authentic compounds of metabolites, 11 545 EI-MS and 834 other-MS data of 10 286 volatile natural and synthetic compounds, and 3045 ESI-MS2 data of 679 synthetic drugs contributed by 16 research groups (January 2010). ESI-MS 2 data were analyzed under nonstandardized, independent experimental conditions. MassBank is a distributed database. Each research group provides data from its own MassBank data servers distributed on the Internet. MassBank users can access either all of the MassBank data or a subset of the data by specifying one or more experimental conditions. In a spectral search to retrieve mass spectra similar to a query mass spectrum, the similarity score is calculated by a weighted cosine correlation in which weighting exponents on peak intensity and the mass-to-charge ratio are optimized to the ESI-MS2 data. MassBank also provides a merged spectrum for each compound prepared bymerging the analyzed ESI-MS2 data on an identical compound under different collision-induced dissociation conditions. Data merging has significantly improved the precision of the identification of a chemical compound by 21-23% at a similarity score of 0.6. Thus, MassBank is useful for the identification of chemical compounds and the publication of experimental data. Copyright © 2010 John Wiley & Sons, Ltd.", "date": "2010-01-01T00:00:00Z", "citationCount": 1747, "authors": [ { "name": "Horai H." }, { "name": "Arita M." }, { "name": "Kanaya S." }, { "name": "Nihei Y." }, { "name": "Ikeda T." }, { "name": "Suwa K." }, { "name": "Ojima Y." }, { "name": "Tanaka K." }, { "name": "Tanaka S." }, { "name": "Aoshima K." }, { "name": "Oda Y." }, { "name": "Kakazu Y." }, { "name": "Kusano M." }, { "name": "Tohge T." }, { "name": "Matsuda F." }, { "name": "Sawada Y." }, { "name": "Hirai M.Y." }, { "name": "Nakanishi H." }, { "name": "Ikeda K." }, { "name": "Akimoto N." }, { "name": "Maoka T." }, { "name": "Takahashi H." }, { "name": "Ara T." }, { "name": "Sakurai N." }, { "name": "Suzuki H." }, { "name": "Shibata D." }, { "name": "Neumann S." }, { "name": "Iida T." }, { "name": "Tanaka K." }, { "name": "Funatsu K." }, { "name": "Matsuura F." }, { "name": "Soga T." }, { "name": "Taguchi R." }, { "name": "Saito K." }, { "name": "Nishioka T." } ], "journal": "Journal of Mass Spectrometry" } } ], "credit": [ { "name": "The MassBank Project", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Project", "typeRole": [ "Developer" ], "note": "Funded by JST-BIRD 2006-2010" }, { "name": "de.NBI MASH", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": "10.13039/501100002347", "typeEntity": "Project", "typeRole": [], "note": "Funding under FKZ 031L0107" }, { "name": "NORMAN Association", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [], "note": null } ], "owner": "sneumann", "additionDate": "2020-09-23T13:04:28Z", "lastUpdate": "2024-11-24T20:57:46.018856Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Pharos", "description": "Pharos is the web interface for data collected by the Illuminating the Druggable Genome initiative. Target, disease and ligand information are collected and displayed.\n\nYou are using an outdated browser. Please upgrade your browser to improve your experience.", "homepage": "https://pharos.nih.gov/", "biotoolsID": "pharos", "biotoolsCURIE": "biotools:pharos", "version": [], "otherID": [ { "value": "RRID: SCR_016924", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3436", "term": "Aggregation" }, { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_0121", "term": "Proteomics" }, { "uri": "http://edamontology.org/topic_0625", "term": "Genotype and phenotype" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0634", "term": "Pathology" }, { "uri": "http://edamontology.org/topic_3474", "term": "Machine learning" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://pharos.nih.gov/api", "type": [ "API documentation" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkaa993", "pmid": "33156327", "pmcid": "PMC7778974", "type": [], "version": null, "note": null, "metadata": { "title": "TCRD and Pharos 2021: Mining the human proteome for disease biology", "abstract": "In 2014, the National Institutes of Health (NIH) initiated the Illuminating the Druggable Genome (IDG) program to identify and improve our understanding of poorly characterized proteins that can potentially be modulated using small molecules or biologics. Two resources produced from these efforts are: The Target Central Resource Database (TCRD) (http://juniper.health.unm.edu/tcrd/) and Pharos (https://pharos.nih.gov/), a web interface to browse the TCRD. The ultimate goal of these resources is to highlight and facilitate research into currently understudied proteins, by aggregating a multitude of data sources, and ranking targets based on the amount of data available, and presenting data in machine learning ready format. Since the 2017 release, both TCRD and Pharos have produced two major releases, which have incorporated or expanded an additional 25 data sources. Recently incorporated data types include human and viral-human protein-protein interactions, protein-disease and protein-phenotype associations, and drug-induced gene signatures, among others. These aggregated data have enabled us to generate new visualizations and content sections in Pharos, in order to empower users to find new areas of study in the druggable genome.", "date": "2021-01-08T00:00:00Z", "citationCount": 93, "authors": [ { "name": "Sheils T.K." }, { "name": "Mathias S.L." }, { "name": "Kelleher K.J." }, { "name": "Siramshetty V.B." }, { "name": "Nguyen D.-T." }, { "name": "Bologa C.G." }, { "name": "Jensen L.J." }, { "name": "Vidovic D." }, { "name": "Koleti A." }, { "name": "Schurer S.C." }, { "name": "Waller A." }, { "name": "Yang J.J." }, { "name": "Holmes J." }, { "name": "Bocci G." }, { "name": "Southall N." }, { "name": "Dharkar P." }, { "name": "Mathe E." }, { "name": "Simeonov A." }, { "name": "Oprea T.I." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Tudor I Oprea", "email": "toprea@salud.unm.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "zsmag19", "additionDate": "2021-01-18T11:52:53Z", "lastUpdate": "2024-11-24T20:36:55.533021Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "PhenoMan", "description": "Freeware that provides approaches for efficient exploration and management of phenotype data.", "homepage": "https://code.google.com/p/phenoman/", "biotoolsID": "phenoman", "biotoolsCURIE": "biotools:phenoman", "version": [], "otherID": [ { "value": "RRID: SCR_005249", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2428", "term": "Validation" }, { "uri": "http://edamontology.org/operation_2238", "term": "Statistical calculation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" }, { "uri": "http://edamontology.org/topic_0625", "term": "Genotype and phenotype" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "R", "Python" ], "license": "GPL-3.0", "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/phenoman-1-0rc-exploration-and-management-of-phenotype-data.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "https://storage.googleapis.com/google-code-archive-downloads/v2/code.google.com/phenoman/doc_phenoman.pdf", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btt682", "pmid": "24336645", "pmcid": "PMC3904519", "type": [], "version": null, "note": null, "metadata": { "title": "PhenoMan: Phenotypic data exploration, selection, management and quality control for association studies of rare and common variants", "abstract": "Motivation:Next-generation sequencing and other high-throughput technology advances have promoted great interest in detecting associations between complex traits and genetic variants. Phenotype selection, quality control (QC) and control of confounders are crucial and can have a great impact on the ability to detect associations. Although there are programs to perform association analyses, e.g. PLINK and GenABEL, they cannot be used for comprehensive management and QC of phenotype data. To address this need PhenoMan was developed: to select individuals based on multiple phenotype criteria or population membership; control for missing covariate data; remove related individuals, duplicate samples and individuals with incorrect sex specification; recode primary traits and covariates; transform data; remove or winsorize outliers; select covariates for analysis; and create residuals. To ensure consistency and harmonization between analyses, a report is generated for every dataset. Summary statistics are also provided in graphical or text format. PhenoMan can be used for selection and manipulation of quantitative, disease and control data.Summary:Phenoman is freeware that provides approaches for efficient exploration and management of phenotype data. Proper QC of phenotypes before proceeding to the association analysis is critical to ensure control of type I and II errors, reliable effect estimates and consistent results between studies. PhenoMan is highly beneficial for the preparation of qualitative and quantitative trait data for association studies using new datasets as well as those obtained from public repositories. © 2013 The Author 2013.", "date": "2014-02-01T00:00:00Z", "citationCount": 2, "authors": [ { "name": "Li B." }, { "name": "Wang G." }, { "name": "Leal S.M." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": null, "email": "sleal@bcm.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T18:55:38Z", "lastUpdate": "2024-11-24T20:36:54.133767Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Philius", "description": "Philius predicts protein transmembrane topology and signal peptides.", "homepage": "http://noble.gs.washington.edu/proj/philius/", "biotoolsID": "philius", "biotoolsCURIE": "biotools:philius", "version": [], "otherID": [ { "value": "RRID: SCR_004625", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2479", "term": "Protein sequence analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0154", "term": "Peptides" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/philius-predict-protein-transmembrane-topology-signal-peptides.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "https://noble.gs.washington.edu/proj/philius/README", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pcbi.1000213", "pmid": "18989393", "pmcid": "PMC2570248", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Transmembrane topology and signal peptide prediction using dynamic Bayesian networks", "abstract": "Hidden Markov models (HMMs) have been successfully applied to the tasks of transmembrane protein topology prediction and signal peptide prediction. In this paper we expand upon this work by making use of the more powerful class of dynamic Bayesian networks (DBNs). Our model, Philius, is inspired by a previously published HMM, Phobius, and combines a signal peptide submodel with a transmembrane submodel. We introduce a two-stage DBN decoder that combines the power of posterior decoding with the grammar constraints of Viterbi-style decoding. Philius also provides protein type, segment, and topology confidence metrics to aid in the interpretation of the predictions. We report a relative improvement of 13% over Phobius in full-topology prediction accuracy on transmembrane proteins, and a sensitivity and specificity of 0.96 in detecting signal peptides. We also show that our confidence metrics correlate well with the observed precision. In addition, we have made predictions on all 6.3 million proteins in the Yeast Resource Center (YRC) database. This large-scale study provides an overall picture of the relative numbers of proteins that include a signal-peptide and/or one or more transmembrane segments as well as a valuable resource for the scientific community. All DBNs are implemented using the Graphical Models Toolkit. Source code for the models described here is available at http://noble.gs.washington.edu/proj/philius. A Philius Web server is available at http://www.yeastrc.org/philius, and the predictions on the YRC database are available at http://www.yeastrc.org/pdr. © 2008 Reynolds et al.", "date": "2008-01-01T00:00:00Z", "citationCount": 206, "authors": [ { "name": "Reynolds S.M." }, { "name": "Kall L." }, { "name": "Riffle M.E." }, { "name": "Bilmes J.A." }, { "name": "Noble W.S." } ], "journal": "PLoS Computational Biology" } } ], "credit": [ { "name": null, "email": null, "url": "http://noble.gs.washington.edu/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:10:55Z", "lastUpdate": "2024-11-24T20:36:52.933224Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ABNER", "description": "ABNER (A Biomedical Named Entity Recognizer) is a software tool for molecular biology text analysis.", "homepage": "http://pages.cs.wisc.edu/~bsettles/abner/", "biotoolsID": "abner", "biotoolsCURIE": "biotools:abner", "version": [ "1.5" ], "otherID": [ { "value": "RRID:SCR_011868", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0306", "term": "Text mining" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_3070", "term": "Biology" }, { "uri": "http://edamontology.org/topic_3047", "term": "Molecular biology" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Java" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/abner-1-5-molecular-biology-text-analysis.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://pages.cs.wisc.edu/~bsettles/abner/javadoc/", "type": [ "API documentation" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/bti475", "pmid": "15860559", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "ABNER: An open source tool for automatically tagging genes, proteins and other entity names in text", "abstract": "Summary: ABNER (A Biomedical Named Entity Recognizer) is an open source software tool for molecular biology text mining. At its core is a machine learning system using conditional random fields with a variety of orthographic and contextual features. The latest version is 1.5, which has an intuitive graphical interface and includes two modules for tagging entities (e.g. protein and cell line) trained on standard corpora, for which performance is roughly state of the art. It also includes a Java application programming interface allowing users to incorporate ABNER into their own systems and train models on new corpora. © The Author 2005. Published by Oxford University Press. All rights reserved.", "date": "2005-07-15T00:00:00Z", "citationCount": 361, "authors": [ { "name": "Settles B." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": null, "email": null, "url": "http://www.cs.cmu.edu/~bsettles/index.html", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:03:07Z", "lastUpdate": "2024-11-24T20:36:50.416529Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ACLAME", "description": "This database is dedicated to the collection, analysis and classification of sequenced mobile genetic elements (MGEs, in particular phages and plasmids). In addition to providing information on the MGEs content, classifications are available at various levels of organization.", "homepage": "http://aclame.ulb.ac.be/", "biotoolsID": "aclame", "biotoolsCURIE": "biotools:aclame", "version": [], "otherID": [ { "value": "RRID:SCR_001694", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2995", "term": "Sequence classification" }, { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" }, { "uri": "http://edamontology.org/operation_3197", "term": "Genetic variation analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0798", "term": "Mobile genetic elements" }, { "uri": "http://edamontology.org/topic_0623", "term": "Gene and protein families" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" }, { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" }, { "uri": "http://edamontology.org/topic_3957", "term": "Protein interaction experiment" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "SQL" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://aclame.ulb.ac.be/Classification/description.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkp938", "pmid": "19933762", "pmcid": "PMC2808911", "type": [], "version": null, "note": null, "metadata": { "title": "ACLAME: A CLAssification of mobile genetic elements, update 2010", "abstract": "The ACLAME database is dedicated to the collection, analysis and classification of sequenced mobile genetic elements (MGEs, in particular phages and plasmids). In addition to providing information on the MGEs content, classifications are available at various levels of organization. At the gene/protein level, families group similar sequences that are expected to share the same function. Families of four or more proteins are manually assigned with a functional annotation using the GeneOntology and the locally developed ontology MeGO dedicated to MGEs. At the genome level, evolutionary cohesive modules group sets of protein families shared among MGEs. At the population level, networks display the reticulate evolutionary relationships among MGEs. To increase the coverage of the phage sequence space, ACLAME version 0.4 incorporates 760 high-quality predicted prophages selected from the Prophinder database. Most of the data can be downloaded from the freely accessible ACLAME web site (http://aclame.ulb.ac.be). The BLAST interface for querying the database has been extended and numerous tools for in-depth analysis of the results have been added. © The Author(s) 2009. Published by Oxford University Press.", "date": "2009-11-23T00:00:00Z", "citationCount": 242, "authors": [ { "name": "Leplae R." }, { "name": "Lima-Mendez G." }, { "name": "Toussaint A." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "The ACLAME team", "email": "aclame@bigre.ulb.ac.be", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-03-27T07:20:14Z", "lastUpdate": "2024-11-24T20:36:49.231353Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "AdmixTools", "description": "Implements five methods to analyze admixture: the three-population test, D-statistics, F4-ratio estimation, admixture graph fitting, and rolloff. In addition, it computes lower and upper bounds on admixture proportions based on f3-statistics. Contains 6 programs: convertf, qp3Pop, qpBound, qpDstat, qpF4Ratio, and rolloff.", "homepage": "https://github.com/DReichLab/AdmixTools", "biotoolsID": "admixtools", "biotoolsCURIE": "biotools:admixtools", "version": [], "otherID": [ { "value": "RRID:SCR_018495", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3197", "term": "Genetic variation analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3056", "term": "Population genetics" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "R", "C++", "Perl", "C" ], "license": "Unlicense", "collectionID": [ "Animal and Crop Genomics" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://github.com/DReichLab/AdmixTools", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1534/genetics.112.145037", "pmid": "22960212", "pmcid": "PMC3522152", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Ancient admixture in human history", "abstract": "Population mixture is an important process in biology. We present a suite of methods for learning about population mixtures, implemented in a software package called ADMIXTOOLS, that support formal tests for whether mixture occurred and make it possible to infer proportions and dates of mixture. We also describe the development of a new single nucleotide polymorphism (SNP) array consisting of 629,433 sites with clearly documented ascertainment that was specifically designed for population genetic analyses and that we genotyped in 934 individuals from 53 diverse populations. To illustrate the methods, we give a number of examples that provide new insights about the history of human admixture. The most striking finding is a clear signal of admixture into northern Europe, with one ancestral population related to present-day Basques and Sardinians and the other related to present-day populations of northeast Asia and the Americas. This likely reflects a history of admixture between Neolithic migrants and the indigenous Mesolithic population of Europe, consistent with recent analyses of ancient bones from Sweden and the sequencing of the genome of the Tyrolean \"Iceman.\" © 2012 by the Genetics Society of America.", "date": "2012-11-01T00:00:00Z", "citationCount": 1605, "authors": [ { "name": "Patterson N." }, { "name": "Moorjani P." }, { "name": "Luo Y." }, { "name": "Mallick S." }, { "name": "Rohland N." }, { "name": "Zhan Y." }, { "name": "Genschoreck T." }, { "name": "Webster T." }, { "name": "Reich D." } ], "journal": "Genetics" } } ], "credit": [ { "name": null, "email": "nickp@broadinstitute.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "admin", "additionDate": "2017-08-20T14:56:58Z", "lastUpdate": "2024-11-24T20:36:47.815847Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ALCHEMY", "description": "ALCHEMY is a method for automated calling of diploid genotypes from raw intensity data produced by various high-throughput multiplexed SNP genotyping methods.", "homepage": "http://alchemy.sourceforge.net/", "biotoolsID": "alchemy", "biotoolsCURIE": "biotools:alchemy", "version": [ "1.07" ], "otherID": [ { "value": "RRID:SCR_005761", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3196", "term": "Genotyping" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0625", "term": "Genotype and phenotype" }, { "uri": "http://edamontology.org/topic_2885", "term": "DNA polymorphism" }, { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "C" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/alchemy-1-07-an-automated-population-genetic-model-driven-snp-genotype-calling-method.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://alchemy.sourceforge.net/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btq533", "pmid": "20926420", "pmcid": "PMC2982150", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "ALCHEMY: A reliable method for automated SNP genotype calling for small batch sizes and highly homozygous populations", "abstract": "Motivation: The development of new high-throughput genotyping products requires a significant investment in testing and training samples to evaluate and optimize the product before it can be used reliably on new samples. One reason for this is current methods for automated calling of genotypes are based on clustering approaches which require a large number of samples to be analyzed simultaneously, or an extensive training dataset to seed clusters. In systems where inbred samples are of primary interest, current clustering approaches perform poorly due to the inability to clearly identify a heterozygote cluster. Results: As part of the development of two custom single nucleotide polymorphism genotyping products for Oryza sativa (domestic rice), we have developed a new genotype calling algorithm called 'ALCHEMY' based on statistical modeling of the raw intensity data rather than modelless clustering. A novel feature of the model is the ability to estimate and incorporate inbreeding information on a per sample basis allowing accurate genotyping of both inbred and heterozygous samples even when analyzed simultaneously. Since clustering is not used explicitly, ALCHEMY performs well on small sample sizes with accuracy exceeding 99% with as few as 18 samples. © The Author(s) 2010. Published by Oxford University Press.", "date": "2010-12-01T00:00:00Z", "citationCount": 40, "authors": [ { "name": "Wright M.H." }, { "name": "Tung C.-W." }, { "name": "Zhao K." }, { "name": "Reynolds A." }, { "name": "McCouch S.R." }, { "name": "Bustamante C.D." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": null, "email": null, "url": "http://alchemy.sourceforge.net/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:03:10Z", "lastUpdate": "2024-11-24T20:36:46.685521Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Allele frequency net", "description": "The allele frequency net database is an online repository that contains information on the frequencies of immune genes and their corresponding alleles in different populations. At present, the system contains data on the frequency of genes from different polymorphic regions such as human leukocyte antigens, killer-cell immunoglobulin-like receptors, major histocompatibility complex Class I chain-related genes and a number of cytokine gene polymorphisms.", "homepage": "http://www.allelefrequencies.net", "biotoolsID": "allele_frequency_net", "biotoolsCURIE": "biotools:allele_frequency_net", "version": [], "otherID": [ { "value": "RRID:SCR_007259", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3221", "term": "Species frequency estimation" }, { "uri": "http://edamontology.org/operation_0487", "term": "Haplotype mapping" }, { "uri": "http://edamontology.org/operation_3196", "term": "Genotyping" }, { "uri": "http://edamontology.org/operation_0542", "term": "Phylogenetic tree generation (from gene frequencies)" }, { "uri": "http://edamontology.org/operation_3227", "term": "Variant calling" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_2830", "term": "Immunoproteins and antigens" }, { "uri": "http://edamontology.org/topic_0199", "term": "Genetic variation" }, { "uri": "http://edamontology.org/topic_3056", "term": "Population genetics" }, { "uri": "http://edamontology.org/topic_3305", "term": "Public health and epidemiology" }, { "uri": "http://edamontology.org/topic_0208", "term": "Pharmacogenomics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "JavaScript" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1093/nar/gkq1128", "pmid": "21062830", "pmcid": "PMC3013710", "type": [], "version": null, "note": null, "metadata": { "title": "Allele frequency net: A database and online repository for immune gene frequencies in worldwide populations", "abstract": "The allele frequency net database (http://www.allelefrequencies.net) is an online repository that contains information on the frequencies of immune genes and their corresponding alleles in different populations. The extensive variability observed in genes and alleles related to the immune system response and its significance in transplantation, disease association studies and diversity in populations led to the development of this electronic resource. At present, the system contains data from 1133 populations in 608 813 individuals on the frequency of genes from different polymorphic regions such as human leukocyte antigens, killer-cell immunoglobulin-like receptors, major histocompatibility complex Class I chainrelated genes and a number of cytokine gene polymorphisms. The project was designed to create a central source for the storage of frequency data and provide individuals with a set of bioinformatics tools to analyze the occurrence of these variants in worldwide populations. The resource has been used in a wide variety of contexts, including clinical applications (histocompatibility, immunology, epidemiology and pharmacogenetics) and population genetics. Demographic information, frequency data and searching tools can be freely accessed through the website. © The Author(s) 2010.", "date": "2011-01-01T00:00:00Z", "citationCount": 618, "authors": [ { "name": "Gonzalez-Galarza F.F." }, { "name": "Christmas S." }, { "name": "Middleton D." }, { "name": "Jones A.R." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Support", "email": "support@allelefrequencies.net", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-03-30T21:27:33Z", "lastUpdate": "2024-11-24T20:36:45.470688Z", "editPermission": { "type": "group", "authors": [ "Kigaard" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Alohomora", "description": "Alohomora was designed to facilitate genome-wide linkage studies performed with high-density single nucleotide polymorphism (SNP) marker panels such as the Affymetrix GeneChip(R) Human Mapping 10K Array", "homepage": "http://gmc.mdc-berlin.de/alohomora/", "biotoolsID": "alohomora", "biotoolsCURIE": "biotools:alohomora", "version": [ "0.33" ], "otherID": [ { "value": "RRID:SCR_009117", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2429", "term": "Mapping" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0283", "term": "Linkage analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_2885", "term": "Single nucleotide polymorphism" }, { "uri": "http://edamontology.org/topic_0102", "term": "Mapping" }, { "uri": "http://edamontology.org/topic_3678", "term": "Studies" }, { "uri": "http://edamontology.org/topic_2885", "term": "SNP" }, { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" }, { "uri": "http://edamontology.org/topic_0102", "term": "Linkage" }, { "uri": "http://edamontology.org/topic_0199", "term": "Polymorphism" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Perl" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/alohomora-0-33-linkage-analysis-tools-affymetrix-mapping.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "https://gmc.mdc-berlin.de/alohomora/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/bti264", "pmid": "15647291", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "ALOHOMORA: A tool for linkage analyisi using 10K SNP array data", "abstract": "Summary: ALOHOMORA is a software tool designed to facilitate genome-wide linkage studies performed with high-density single nucleotide polymorphism (SNP) marker panels such as the Affymetrix GeneChip® Human Mapping 10K Array. Genotype data are converted into appropriate formats for a number of common linkage programs and subjected to standard quality control routines before linkage runs are started. ALOHOMORA is written in Perl and may be used to perform state-of-the-art linkage scans in small and large families with any genetic model. Options for using different genetic maps or ethnicity-specific allele frequencies are implemented. Graphic outputs of whole-genome multipoint LOD score values are provided for the entire dataset as well as for individual families. © The Author 2005. Published by Oxford University Press. All rights reserved.", "date": "2005-05-01T00:00:00Z", "citationCount": 155, "authors": [ { "name": "Ruschendorf F." }, { "name": "Nurnberg P." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": null, "email": null, "url": "http://gmc.mdc-berlin.de/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:03:31Z", "lastUpdate": "2024-11-24T20:36:43.983149Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Alta-Cyclic", "description": "Alta-Cyclic is a Illumina Genome-Analyzer (Solexa) base caller.", "homepage": "http://hannonlab.cshl.edu/Alta-Cyclic/main.html", "biotoolsID": "alta-cyclic", "biotoolsCURIE": "biotools:alta-cyclic", "version": [], "otherID": [ { "value": "RRID:SCR_013373", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3185", "term": "Base-calling" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Script" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux" ], "language": [ "Perl" ], "license": null, "collectionID": [], "maturity": "Legacy", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://hannonlab.cshl.edu/Alta-Cyclic/usage.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1038/nmeth.1230", "pmid": "18604217", "pmcid": "PMC2978646", "type": [], "version": null, "note": null, "metadata": { "title": "Alta-Cyclic: A self-optimizing base caller for next-generation sequencing", "abstract": "Next-generation sequencing is limited to short read lengths and by high error rates. We systematically analyzed sources of noise in the Illumina Genome Analyzer that contribute to these high error rates and developed a base caller, Alta-Cyclic, that uses machine learning to compensate for noise factors. Alta-Cyclic substantially improved the number of accurate reads for sequencing runs up to 78 bases and reduced systematic biases, facilitating confident identification of sequence variants.", "date": "2008-08-01T00:00:00Z", "citationCount": 156, "authors": [ { "name": "Erlich Y." }, { "name": "Mitra P.P." }, { "name": "delaBastide M." }, { "name": "McCombie W.R." }, { "name": "Hannon G.J." } ], "journal": "Nature Methods" } } ], "credit": [ { "name": "Yaniv Erlich", "email": "erlich@cshl.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:13:31Z", "lastUpdate": "2024-11-24T20:36:42.725560Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Alternative Splicing Gallery", "description": "The Alternative Splicing Gallery (ASG) takes an identifier such as an EnsEMBL gene ID or a RefSeq ID as input, and provides a graph mapping splice events to transcript information. The user can also view GO information for the record, and select one or more exons and download the resulting sequence. ASG also links out to other alternative splicing databases like ProSplicer.", "homepage": "http://statgen.ncsu.edu/asg/", "biotoolsID": "alternative_splicing_gallery", "biotoolsCURIE": "biotools:alternative_splicing_gallery", "version": [], "otherID": [ { "value": "RRID:SCR_008129", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0264", "term": "Splice transcript prediction" }, { "uri": "http://edamontology.org/operation_0433", "term": "Splice site prediction" }, { "uri": "http://edamontology.org/operation_2499", "term": "Splicing model analysis" }, { "uri": "http://edamontology.org/operation_0232", "term": "Sequence merging" }, { "uri": "http://edamontology.org/operation_0526", "term": "EST assembly" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3320", "term": "RNA splicing" }, { "uri": "http://edamontology.org/topic_3512", "term": "Gene transcripts" }, { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" }, { "uri": "http://edamontology.org/topic_0102", "term": "Mapping" }, { "uri": "http://edamontology.org/topic_3120", "term": "Protein variants" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1093/nar/gkh731", "pmid": "15292448", "pmcid": "PMC506815", "type": [], "version": null, "note": null, "metadata": { "title": "The Alternative Splicing Gallery (ASG): Bridging the gap between genome and transcriptome", "abstract": "Alternative splicing essentially increases the diversity of the transcriptome and has important implications for physiology, development and the genesis of diseases. Conventionally, alternative splicing is investigated in a case-by-case fashion, but this becomes cumbersome and error prone if genes show a huge abundance of different splice variants. We use a different approach and integrate all transcripts derived from a gene into a single splicing graph. Each transcript corresponds to a path in the graph, and alternative splicing is displayed by bifurcations. This representation preserves the relationships between different splicing variants and allows us to investigate systematically all possible putative transcripts. We built a database of splicing graphs for human genes, using transcript information from various major sources (Ensembl, RefSeq, STACK, TIGR and UniGene). A Web interface allows users to display the splicing graphs, to interactively assemble transcripts and to access their sequences as well as neighboring genomic regions. We also provide for each gene an exhaustive pre-computed catalog of putative transcripts - in total more than 1.2 million sequences. We found that ∼65% of the investigated genes show evidence for alternative splicing, and in 5% of the cases, a single gene might produce over 100 transcripts. © Oxford University Press 2004; all rights reserved.", "date": "2004-09-21T00:00:00Z", "citationCount": 72, "authors": [ { "name": "Leipzig J." }, { "name": "Pevzner P." }, { "name": "Heber S." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Steffen Heber", "email": "sheber@ncsu.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Jeremy Leipzig", "email": "leipzig@med.upenn.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-03-30T21:27:46Z", "lastUpdate": "2024-11-24T20:36:41.576074Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ANDES", "description": "The fundamental data structure underlying, is the position profile, which contains the nucleotide distributions for each genomic position resultant from a multiple sequence alignment. They include the root mean square deviation plot and the computation of base conversion frequencies, variation, inter-sample clustering and visualization, threshold-driven consensus sequence generation and polymorphism detection, and the estimation of empirically determined sequencing quality values.", "homepage": "http://andestools.sourceforge.net/", "biotoolsID": "andes", "biotoolsCURIE": "biotools:andes", "version": [ "20120225" ], "otherID": [ { "value": "RRID:SCR_002791", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3202", "term": "Polymorphism detection" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0492", "term": "Multiple sequence alignment" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2424", "term": "Comparison" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0230", "term": "Sequence generation" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3429", "term": "Generation" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2423", "term": "Prediction and recognition" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3432", "term": "Clustering" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_0199", "term": "Genetic variation" }, { "uri": "http://edamontology.org/topic_0654", "term": "DNA" }, { "uri": "http://edamontology.org/topic_3277", "term": "Sample collections" } ], "operatingSystem": [ "Linux" ], "language": [ "R", "Perl" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/andes-20100709-analysis-deep-sequencing.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://andestools.sourceforge.net/OnlineManual.htm", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1186/1756-0500-3-199", "pmid": "20633290", "pmcid": "PMC2921379", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "ANDES: Statistical tools for the analyses of deep sequencing", "abstract": "Background: The advancements in DNA sequencing technologies have allowed researchers to progress from the analyses of a single organism towards the deep sequencing of a sample of organisms. With sufficient sequencing depth, it is now possible to detect subtle variations between members of the same species, or between mixed species with shared biomarkers, such as the 16S rRNA gene. However, traditional sequencing analyses of samples from largely homogeneous populations are often still based on multiple sequence alignments (MSA), where each sequence is placed along a separate row and similarities between aligned bases can be followed down each column. While this visual format is intuitive for a small set of aligned sequences, the representation quickly becomes cumbersome as sequencing depths cover loci hundreds or thousands of reads deep. Findings: We have developed ANDES, a software library and a suite of applications, written in Perl and R, for the statistical ANalyses of DEep Sequencing. The fundamental data structure underlying ANDES is the position profile, which contains the nucleotide distributions for each genomic position resultant from a multiple sequence alignment (MSA). Tools include the root mean square deviation (RMSD) plot, which allows for the visual comparison of multiple samples on a position-by-position basis, and the computation of base conversion frequencies (transition/transversion rates), variation (Shannon entropy), inter-sample clustering and visualization (dendrogram and multidimensional scaling (MDS) plot), threshold-driven consensus sequence generation and polymorphism detection, and the estimation of empirically determined sequencing quality values. Conclusions: As new sequencing technologies evolve, deep sequencing will become increasingly cost-efficient and the inter and intra-sample comparisons of largely homogeneous sequences will become more common. We have provided a software package and demonstrated its application on various empirically-derived datasets. Investigators may download the software from Sourceforge at https://sourceforge.net/projects/andestools. © 2010 Li et al; licensee BioMed Central Ltd.", "date": "2010-08-27T00:00:00Z", "citationCount": 20, "authors": [ { "name": "Li K." }, { "name": "Venter E." }, { "name": "Yooseph S." }, { "name": "Stockwell T.B." }, { "name": "Eckerle L.D." }, { "name": "Denison M.R." }, { "name": "Spiro D.J." }, { "name": "Methe B.A." } ], "journal": "BMC Research Notes" } } ], "credit": [ { "name": null, "email": null, "url": "http://www.jcvi.org/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:03:15Z", "lastUpdate": "2024-11-24T20:36:40.094706Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "aroma.affymetrix", "description": "R package for analyzing large Affymetrix data sets which allows to analyze 100-1,000s of arrays of various chip types, e.g. expression arrays, SNP chips, exon arrays and so on.", "homepage": "http://aroma-project.org/", "biotoolsID": "aroma.affymetrix", "biotoolsCURIE": "biotools:aroma.affymetrix", "version": [], "otherID": [ { "value": "RRID:SCR_010919", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0571", "term": "Expression data rendering" }, { "uri": "http://edamontology.org/operation_2495", "term": "Gene expression analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Script" ], "topic": [ { "uri": "http://edamontology.org/topic_3169", "term": "ChIP-seq" }, { "uri": "http://edamontology.org/topic_2885", "term": "DNA polymorphism" }, { "uri": "http://edamontology.org/topic_3056", "term": "Population genetics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "R" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/aroma-affymetrix-v2-10-0-open-source-framework-microarray-analysis.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://aroma-project.org/docs/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btq300", "pmid": "20529889", "pmcid": "PMC2913655", "type": [], "version": null, "note": null, "metadata": { "title": "ACNE: A summarization method to estimate allele-specific copy numbers for Affymetrix SNP arrays", "abstract": "Motivation: Current algorithms for estimating DNA copy numbers (CNs) borrow concepts from gene expression analysis methods. However, single nucleotide polymorphism (SNP) arrays have special characteristics that, if taken into account, can improve the overall performance. For example, cross hybridization between alleles occurs in SNP probe pairs. In addition, most of the current CN methods are focused on total CNs, while it has been shown that allele-specific CNs are of paramount importance for some studies. Therefore, we have developed a summarization method that estimates high-quality allele-specific CNs. Results: The proposed method estimates the allele-specific DNA CNs for all Affymetrix SNP arrays dealing directly with the cross hybridization between probes within SNP probesets. This algorithm outperforms (or at least it performs as well as) other state-of-the-art algorithms for computing DNA CNs. It better discerns an aberration from a normal state and it also gives more precise allele-specific CNs. © The Author 2010. Published by Oxford University Press. All rights reserved.", "date": "2010-06-06T00:00:00Z", "citationCount": 17, "authors": [ { "name": "Ortiz-Estevez M." }, { "name": "Bengtsson H." }, { "name": "Rubio A." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": null, "email": null, "url": "http://aroma-project.org/about", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T19:04:59Z", "lastUpdate": "2024-11-24T20:36:38.680706Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ArrayPipe", "description": "ArrayPipe allows users to customize a processing pipeline for the analysis of microarray data. Includes methods for quality assessment of slides, data visualization, normalization, and detection of differentially expressed genes. Output consists of reports formatted as standard web pages and tab-delimited lists of calculated values.", "homepage": "http://koch.pathogenomics.ca/cgi-bin/pub/arraypipe.pl", "biotoolsID": "arraypipe", "biotoolsCURIE": "biotools:arraypipe", "version": [], "otherID": [ { "value": "RRID:SCR_010934", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2409", "term": "Data handling" }, { "uri": "http://edamontology.org/operation_3223", "term": "Differential gene expression analysis" }, { "uri": "http://edamontology.org/operation_0314", "term": "Gene expression profiling" }, { "uri": "http://edamontology.org/operation_2495", "term": "Gene expression analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3518", "term": "Microarray experiment" }, { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" }, { "uri": "http://edamontology.org/topic_0769", "term": "Workflows" }, { "uri": "http://edamontology.org/topic_3365", "term": "Data architecture, analysis and design" }, { "uri": "http://edamontology.org/topic_3179", "term": "ChIP-on-chip" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://www.pathogenomics.ca/arraypipe/info/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkh446", "pmid": "15215429", "pmcid": "PMC441584", "type": [], "version": null, "note": null, "metadata": { "title": "ArrayPipe: A flexible processing pipeline for microarray data", "abstract": "A number of microarray analysis software packages exist already; however, none combines the user-friendly features of a web-based interface with potential ability to analyse multiple arrays at once using flexible analysis steps. The ArrayPipe web server (freely available at www.pathogenomics.ca/arraypipe) allows the automated application of complex analyses to microarray data which can range from single slides to large data sets including replicates and dye-swaps. It handles output from most commonly used quantification software packages for dual-labelled arrays. Application features range from quality assessment of slides through various data visualizations to multi-step analyses including normalization, detection of differentially expressed genes, and comparison and highlighting of gene lists. A highly customizable action set-up facilitates unrestricted arrangement of functions, which can be stored as action profiles. A unique combination of web-based and command-line functionality enables comfortable configuration of processes that can be repeatedly applied to large data sets in high throughput. The output consists of reports formatted as standard web pages and tab-delimited lists of calculated values that can be inserted into other analysis programs. Additional features, such as web-based spreadsheet functionality, auto-parallelization and password protection make this a powerful tool in microarray research for individuals and large groups alike. © Oxford University Press 2004; all rights reserved.", "date": "2004-07-01T00:00:00Z", "citationCount": 66, "authors": [ { "name": "Hokamp K." }, { "name": "Roche F.M." }, { "name": "Acab M." }, { "name": "Rousseau M.-E." }, { "name": "Kuo B." }, { "name": "Goode D." }, { "name": "Aeschliman D." }, { "name": "Bryan J." }, { "name": "Babiuk L.A." }, { "name": "Hancock R.E.W." }, { "name": "Brinkman F.S.L." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Karsten Hokamp", "email": "karsten.hokamp@tcd.ie", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-03-24T09:34:10Z", "lastUpdate": "2024-11-24T20:36:37.459362Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ASPEX", "description": "ASPEX is a set of programs for performing multipoint exclusion mapping of affected sibling pair data for discrete traits.There are five main analysis programs: sib_ibd, sib_phase, sib_map, sib_tdt, and sib_kin.", "homepage": "http://aspex.sourceforge.net/", "biotoolsID": "aspex", "biotoolsCURIE": "biotools:aspex", "version": [], "otherID": [ { "value": "RRID:SCR_008414", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2429", "term": "Mapping" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0102", "term": "Mapping" }, { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" } ], "operatingSystem": [ "Linux" ], "language": [ "Perl" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/aspex-2-5-affected-sib-pair-exclusion-mapping.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://aspex.sourceforge.net/usage.pdf", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1002/gepi.1370170732", "pmid": "10597434", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Sib-pair analysis of the Collaborative Study on the Genetics of Alcoholism data set", "abstract": "Nonparametric sib-pair analysis was performed on the Collaborative Study on the Genetics of Alcoholism data set. Concordant and discordant pair groups were examined using the ASPEX package of programs. Allele sharing and multipoint lod scores for six comparison groups were obtained. Sharing and lod score patterns were not consistent with a simple genetic interpretation.", "date": "1999-01-01T00:00:00Z", "citationCount": 2, "authors": [ { "name": "Jorgenson E." }, { "name": "Hinds D." }, { "name": "Risch N." } ], "journal": "Genetic Epidemiology" } } ], "credit": [ { "name": "David Hinds", "email": "dahinds@users.sourceforge.net", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T18:35:58Z", "lastUpdate": "2024-11-24T20:36:36.096556Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Association Viewer", "description": "AssociationViewer is a Java application used to display SNPs in a genetic context. Supplementary data (such as genes or LD plots) is downloaded from various public data sources on the fly and saved locally in a cache. Custom data can be added as supplementary tracks.", "homepage": "http://associationviewer.vital-it.ch/", "biotoolsID": "association_viewer", "biotoolsCURIE": "biotools:association_viewer", "version": [], "otherID": [ { "value": "RRID:SCR_009063", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0226", "term": "Annotation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Java" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://associationviewer.vital-it.ch/usage.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btp017", "pmid": "19168913", "pmcid": "PMC2647839", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "AssociationViewer: A scalable and integrated software tool for visualization of large-scale variation data in genomic context", "abstract": "We present a tool designed for visualization of large-scale genetic and genomic data exemplified by results from genome-wide association studies. This software provides an integrated framework to facilitate the interpretation of SNP association studies in genomic context. Gene annotations can be retrieved from Ensembl, linkage disequilibrium data downloaded from HapMap and custom data imported in BED or WIG format. AssociationViewer integrates functionalities that enable the aggregation or intersection of data tracks. It implements an efficient cache system and allows the display of several, very large-scale genomic datasets. Availability: The Java code for AssociationViewer is distributed under the GNU General Public Licence and has been tested on Microsoft Windows XP, MacOSX and GNU/Linux operating systems. It is available from the SourceForge repository. This also includes Java webstart, documentation and example datafiles. © 2009 The Author(s).", "date": "2009-03-01T00:00:00Z", "citationCount": 1, "authors": [ { "name": "Martin O." }, { "name": "Valsesia A." }, { "name": "Telenti A." }, { "name": "Xenarios I." }, { "name": "Stevenson B.J." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Olivier Martin", "email": null, "url": "https://sourceforge.net/u/voltigeur/profile/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "admin", "additionDate": "2017-12-06T18:14:07Z", "lastUpdate": "2024-11-24T20:36:34.942698Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ASTD", "description": "AltSplice and AltExtron provide information on alternative intron/exons, alternative splice events, and isoform splice patterns. AEdb contains: AEdb-Sequence (sequence and properties of alternatively splice exons), AEdb-Function (data on functional aspects of alternative splicing), AEdb-motif (data and sequence of known splice regulatory motifs), and AEdb-minigene (a collection of known minigene constructs for alternative splice events).", "homepage": "http://www.ebi.ac.uk/astd/", "biotoolsID": "astd", "biotoolsCURIE": "biotools:astd", "version": [], "otherID": [ { "value": "RRID:SCR_001883", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1033", "term": "Ensembl gene ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1033", "term": "Ensembl gene ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_1927", "term": "EMBL format" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1033", "term": "Ensembl gene ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1033", "term": "Ensembl gene ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_2305", "term": "GFF" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1033", "term": "Ensembl gene ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_2306", "term": "GTF" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2367", "term": "ASTD ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3134", "term": "Gene transcript report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2367", "term": "ASTD ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3134", "term": "Gene transcript report" }, "format": [ { "uri": "http://edamontology.org/format_1927", "term": "EMBL format" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2367", "term": "ASTD ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3134", "term": "Gene transcript report" }, "format": [ { "uri": "http://edamontology.org/format_2305", "term": "GFF" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2367", "term": "ASTD ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3134", "term": "Gene transcript report" }, "format": [ { "uri": "http://edamontology.org/format_2306", "term": "GTF" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2398", "term": "Ensembl protein ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2398", "term": "Ensembl protein ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2368", "term": "ASTD ID (exon)" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2367", "term": "ASTD ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1276", "term": "Nucleic acid features" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2369", "term": "ASTD ID (intron)" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2367", "term": "ASTD ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1276", "term": "Nucleic acid features" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2371", "term": "ASTD ID (tss)" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2367", "term": "ASTD ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1276", "term": "Nucleic acid features" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2370", "term": "ASTD ID (polya)" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1276", "term": "Nucleic acid features" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0114", "term": "Gene structure" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [ "DRCAT" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://www.ebi.ac.uk/asd", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkv1352", "pmid": "26673705", "pmcid": "PMC4702932", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "The European Bioinformatics Institute in 2016: Data growth and integration", "abstract": "New technologies are revolutionising biological research and its applications by making it easier and cheaper to generate ever-greater volumes and types of data. In response, the services and infrastructure of the European Bioinformatics Institute (EMBL-EBI, www.ebi.ac.UK) are continually expanding: total disk capacity increases significantly every year to keep pace with demand (75 petabytes as of December 2015), and interoperability between resources remains a strategic priority. Since 2014 we have launched two new resources: the European Variation Archive for genetic variation data and EMPIAR for two-dimensional electron microscopy data, as well as a Resource Description Framework platform. We also launched the Embassy Cloud service, which allows users to run large analyses in a virtual environment next to EMBL-EBI's vast public data resources.", "date": "2016-01-01T00:00:00Z", "citationCount": 98, "authors": [ { "name": "Cook C.E." }, { "name": "Bergman M.T." }, { "name": "Finn R.D." }, { "name": "Cochrane G." }, { "name": "Birney E." }, { "name": "Apweiler R." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "DRCAT", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Project", "typeRole": [ "Documentor" ], "note": null }, { "name": "Contact List", "email": null, "url": "http://www.ensembl.org/info/about/contact/index.html", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "DRCAT", "additionDate": "2015-01-21T13:56:26Z", "lastUpdate": "2024-11-24T20:36:33.591864Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "AthaMap", "description": "AthaMap is a genome-wide map of putative transcription factor binding sites in Arabidopsis thaliana", "homepage": "http://www.athamap.de/", "biotoolsID": "athamap", "biotoolsCURIE": "biotools:athamap", "version": [], "otherID": [ { "value": "RRID:SCR_006717", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0445", "term": "Transcription factor binding site prediction" }, { "uri": "http://edamontology.org/operation_2436", "term": "Gene-set enrichment analysis" }, { "uri": "http://edamontology.org/operation_0438", "term": "Transcriptional regulatory element prediction" } ], "input": [], "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_0203", "term": "Gene expression" }, { "uri": "http://edamontology.org/topic_0102", "term": "Mapping" }, { "uri": "http://edamontology.org/topic_3512", "term": "Gene transcripts" }, { "uri": "http://edamontology.org/topic_3125", "term": "DNA binding sites" } ], "operatingSystem": [ "Linux" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://www.athamap.de/documentation.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkh017", "pmid": "14681436", "pmcid": "PMC308752", "type": [], "version": null, "note": null, "metadata": null }, { "doi": "10.1093/nar/gki395", "pmid": "15980498", "pmcid": "PMC1160156", "type": [], "version": null, "note": null, "metadata": { "title": "AthaMap web tools for database-assisted identification of combinatorial cis-regulatory elements and the display of highly conserved transcription factor binding sites in Arabidopsis thaliana", "abstract": "The AthaMap database generates a map of cis-regulatory elements for the Arabidopsis thaliana genome. AthaMap contains more than 7.4 × 106 putative binding sites for 36 transcription factors (TFs) from 16 different TF families. A newly implemented functionality allows the display of subsets of higher conserved transcription factor binding sites (TFBSs). Furthermore, a web tool was developed that permits a user-defined search for co-localizing cis-regulatory elements. The user can specify individually the level of conservation for each TFBS and a spacer range between them. This web tool was employed for the identification of co-localizing sites of known interacting TFs and TFs containing two DNA-binding domains. More than 1.8 × 105 combinatorial elements were annotated in the AthaMap database. These elements can also be used to identify more complex co-localizing elements consisting of up to four TFBSs. The AthaMap database and the connected web tools are a valuable resource for the analysis and the prediction of gene expression regulation at http://www.athamap.de. © 2005 Oxford University Press.", "date": "2005-07-01T00:00:00Z", "citationCount": 37, "authors": [ { "name": "Steffens N.O." }, { "name": "Galuschka C." }, { "name": "Schindler M." }, { "name": "Bulow L." }, { "name": "Hehl R." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkl1006", "pmid": "17148485", "pmcid": "PMC1761422", "type": [], "version": null, "note": null, "metadata": { "title": "AthaMap web tools for the analysis and identification of co-regulated genes", "abstract": "The AthaMap database generates a map of cis-regulatory elements for the whole Arabidopsis thaliana genome. This database has been extended by new tools to identify common cis-regulatory elements in specific regions of user-provided gene sets. A resulting table displays all cis-regulatory elements annotated in AthaMap including positional information relative to the respective gene. Further tables show overviews with the number of individual transcription factor binding sites (TFBS) present and TFBS common to the whole set of genes. Over represented cis-elements are easily identified. These features were used to detect specific enrichment of drought-responsive elements in cold-induced genes. For identification of co-regulated genes, the output table of the colocalization function was extended to show the closest genes and their relative distances to the colocalizing TFBS. Gene sets determined by this function can be used for a co-regulation analysis in microarray gene expression databases such as Genevestigator or PathoPlant. Additional improvements of AthaMap include display of the gene structure in the sequence window and a significant data increase. AthaMap is freely available at http://www.athamap.de/. © 2007 Oxford University Press.", "date": "2007-01-01T00:00:00Z", "citationCount": 41, "authors": [ { "name": "Galuschka C." }, { "name": "Schindler M." }, { "name": "Bulow L." }, { "name": "Hehl R." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkn709", "pmid": "18842622", "pmcid": "PMC2686474", "type": [], "version": null, "note": null, "metadata": { "title": "AthaMap, integrating transcriptional and post-transcriptional data", "abstract": "The AthaMap database generates a map of predicted transcription factor binding sites (TFBS) for the whole Arabidopsis thaliana genome. AthaMap has now been extended to include data on post-transcriptional regulation. A total of 403 173 genomic positions of small RNAs have been mapped in the A. thaliana genome. These identify 5772 putative post-transcriptionally regulated target genes. AthaMap tools have been modified to improve the identification of common TFBS in co-regulated genes by subtracting post-transcriptionally regulated genes from such analyses. Furthermore, AthaMap was updated to the TAIR7 genome annotation, a graphic display of gene analysis results was implemented, and the TFBS data content was increased. AthaMap is freely available at http://www.athamap.de/. © 2008 The Author(s).", "date": "2009-01-09T00:00:00Z", "citationCount": 44, "authors": [ { "name": "Bulow L." }, { "name": "Engelmann S." }, { "name": "Schindler M." }, { "name": "Hehl R." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/database/baq034", "pmid": "21177332", "pmcid": "PMC3011983", "type": [], "version": null, "note": null, "metadata": { "title": "AthaMap-assisted transcription factor target gene identification in Arabidopsis thaliana.", "abstract": "The AthaMap database generates a map of potential transcription factor binding sites (TFBS) and small RNA target sites in the Arabidopsis thaliana genome. The database contains sites for 115 different transcription factors (TFs). TFBS were identified with positional weight matrices (PWMs) or with single binding sites. With the new web tool 'Gene Identification', it is possible to identify potential target genes for selected TFs. For these analyses, the user can define a region of interest of up to 6000bp in all annotated genes. For TFBS determined with PWMs, the search can be restricted to high-quality TFBS. The results are displayed in tables that identify the gene, position of the TFBS and, if applicable, individual score of the TFBS. In addition, data files can be downloaded that harbour positional information of TFBS of all TFs in a region between -2000 and +2000bp relative to the transcription or translation start site. Also, data content of AthaMap was increased and the database was updated to the TAIR8 genome release. Database URL: http://www.athamap.de/gene_ident.php.", "date": "2010-01-01T00:00:00Z", "citationCount": 26, "authors": [ { "name": "Bulow L." }, { "name": "Brill Y." }, { "name": "Hehl R." } ], "journal": "Database : the journal of biological databases and curation" } } ], "credit": [ { "name": "Artyom Romanov (Webmaster)", "email": "k.romanov@tu-braunschweig.de", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-03-24T11:31:28Z", "lastUpdate": "2024-11-24T20:36:26.103448Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "AutoAssemblyD", "description": "A software which performed the local and remote genome assembly by several assemblers based on an XML Template which can replace the large command lines required by most assemblers.", "homepage": "http://sourceforge.net/projects/autoassemblyd/", "biotoolsID": "autoassemblyd", "biotoolsCURIE": "biotools:autoassemblyd", "version": [], "otherID": [ { "value": "RRID:SCR_001087", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/autoassemblyd-0-1-graphical-user-interface-system-for-several-genome-assembler.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "https://sourceforge.net/projects/autoassemblyd/files/release/version_0.1/AutoAssemblyD_USER%20GUIDE.pdf/download", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.6026/97320630009840", "pmid": "24143057", "pmcid": "PMC3796888", "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": null, "email": null, "url": "http://sourceforge.net/projects/autoassemblyd/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T18:36:33Z", "lastUpdate": "2024-11-24T20:36:24.948267Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "AutoDock Vina", "description": "AutoDock Vina is a new open-source program for drug discovery, molecular docking and virtual screening, offering multi-core capability, high performance and enhanced accuracy and ease of use.", "homepage": "http://vina.scripps.edu/", "biotoolsID": "autodock_vina", "biotoolsCURIE": "biotools:autodock_vina", "version": [ "1.1.2" ], "otherID": [ { "value": "RRID:SCR_011958", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0478", "term": "Molecular docking" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_3336", "term": "Drug discovery" }, { "uri": "http://edamontology.org/topic_2275", "term": "Molecular modelling" }, { "uri": "http://edamontology.org/topic_2275", "term": "Molecular docking" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "C++" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/autodock-vina-1-1-2-molecular-docking-virtual-screening-program.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://vina.scripps.edu/manual.html", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1002/jcc.21334", "pmid": "19499576", "pmcid": "PMC3041641", "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": null, "email": null, "url": "http://olegtrott.com/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:03:45Z", "lastUpdate": "2024-11-24T20:36:23.904477Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Avogadro", "description": "Avogadro is an advanced molecule editor and visualizer designed for cross-platform use in computational chemistry, molecular modeling, bioinformatics, materials science, and related areas. It offers flexible high quality rendering and a powerful plugin architecture.", "homepage": "http://avogadro.cc/", "biotoolsID": "avogadro", "biotoolsCURIE": "biotools:avogadro", "version": [ "2.0.8.0" ], "otherID": [ { "value": "RRID:SCR_015983", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_2275", "term": "Molecular modelling" }, { "uri": "http://edamontology.org/topic_3332", "term": "Computational chemistry" }, { "uri": "http://edamontology.org/topic_3314", "term": "Chemistry" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Python" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/avogadro-1-0-3-molecule-editor-visualizer.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "https://avogadro.cc/docs/", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1186/1758-2946-4-17", "pmid": "22889332", "pmcid": "PMC3542060", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Avogadro: An advanced semantic chemical editor, visualization, and analysis platform", "abstract": "Background: The Avogadro project has developed an advanced molecule editor and visualizer designed for cross-platform use in computational chemistry, molecular modeling, bioinformatics, materials science, and related areas. It offers flexible, high quality rendering, and a powerful plugin architecture. Typical uses include building molecular structures, formatting input files, and analyzing output of a wide variety of computational chemistry packages. By using the CML file format as its native document type, Avogadro seeks to enhance the semantic accessibility of chemical data types. Results: The work presented here details the Avogadro library, which is a framework providing a code library and application programming interface (API) with three-dimensional visualization capabilities; and has direct applications to research and education in the fields of chemistry, physics, materials science, and biology. The Avogadro application provides a rich graphical interface using dynamically loaded plugins through the library itself. The application and library can each be extended by implementing a plugin module in C++ or Python to explore different visualization techniques, build/manipulate molecular structures, and interact with other programs. We describe some example extensions, one which uses a genetic algorithm to find stable crystal structures, and one which interfaces with the PackMol program to create packed, solvated structures for molecular dynamics simulations. The 1.0 release series of Avogadro is the main focus of the results discussed here. Conclusions: Avogadro offers a semantic chemical builder and platform for visualization and analysis. For users, it offers an easy-to-use builder, integrated support for downloading from common databases such as PubChem and the Protein Data Bank, extracting chemical data from a wide variety of formats, including computational chemistry output, and native, semantic support for the CML file format. For developers, it can be easily extended via a powerful plugin mechanism to support new features in organic chemistry, inorganic complexes, drug design, materials, biomolecules, and simulations. Avogadro is freely available under an open-source license from http://avogadro.openmolecules.net.", "date": "2012-08-01T00:00:00Z", "citationCount": 6783, "authors": [ { "name": "Hanwell M.D." }, { "name": "Curtis D.E." }, { "name": "Lonie D.C." }, { "name": "Vandermeerschd T." }, { "name": "Zurek E." }, { "name": "Hutchison G.R." } ], "journal": "Journal of Cheminformatics" } } ], "credit": [ { "name": null, "email": null, "url": "http://blog.cryos.net/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:03:47Z", "lastUpdate": "2024-11-24T20:36:22.622810Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BamView", "description": "Interactive Java application for visualising the large amounts of data stored for sequence reads which are aligned against a reference genome sequence", "homepage": "http://bamview.sourceforge.net/", "biotoolsID": "bamview", "biotoolsCURIE": "biotools:bamview", "version": [], "otherID": [ { "value": "RRID:SCR_004207", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Java" ], "license": "GPL-3.0", "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://bamview.sourceforge.net", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bib/bbr073", "pmid": "22253280", "pmcid": "PMC3603209", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "BamView: Visualizing and interpretation of next-generation sequencing read alignments", "abstract": "So-called next-generation sequencing (NGS) has provided the ability to sequence on a massive scale at low cost, enabling biologists to perform powerful experiments and gain insight into biological processes. BamView has been developed to visualize and analyse sequence reads from NGS platforms, which have been aligned to a reference sequence. It is a desktop application for browsing the aligned or mapped reads [Ruffalo, M, LaFramboise, T, Koyutürk, M. Comparative analysis of algorithms for next-generation sequencing read alignment. Bioinformatics 2011;27:2790-6] at different levels of magnification, from nucleotide level, where the base qualities can be seen, to genome or chromosome level where overall coverage is shown. To enable in-depth investigation of NGS data, various views are provided that can be configured to highlight interesting aspects of the data. Multiple read alignment files can be overlaid to compare results from different experiments, and filters can be applied to facilitate the interpretation of the aligned reads. As well as being a standalone application it can be used as an integrated part of the Artemis genome browser, BamView allows the user to study NGS data in the context of the sequence and annotation of the reference genome. Single nucleotide polymorphism (SNP) density and candidate SNP sites can be highlighted and investigated, and read-pair information can be used to discover large structural insertions and deletions. The application will also calculate simple analyses of the read mapping, including reporting the read counts and reads per kilobase per million mapped reads (RPKM) for genes selected by the user. Availability: BamView and Artemis are freely available software. These can be downloaded from their home pages: http://bamview.sourceforge.net/; http://www.sanger.ac.uk/resources/software/artemis/. Requirements: Java 1.6 or higher. © The Author 2011. Published by Oxford University Press.", "date": "2013-03-01T00:00:00Z", "citationCount": 54, "authors": [ { "name": "Carver T." }, { "name": "Harris S.R." }, { "name": "Otto T.D." }, { "name": "Berriman M." }, { "name": "Parkhill J." }, { "name": "McQuillan J.A." } ], "journal": "Briefings in Bioinformatics" } } ], "credit": [ { "name": "BamView development team", "email": "artemis@sanger.ac.uk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:13:37Z", "lastUpdate": "2024-11-24T20:36:21.221611Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BarraCUDA", "description": "Barracuda is a high-speed sequence aligner based on BWA and uses the latest Nvidia CUDA architecture for accelerating alignments of sequence reads generated by the next-generation sequencers.", "homepage": "http://seqbarracuda.sourceforge.net/", "biotoolsID": "barracuda", "biotoolsCURIE": "biotools:barracuda", "version": [], "otherID": [ { "value": "RRID:SCR_006881", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3198", "term": "Read mapping" }, { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux" ], "language": [ "C++", "C" ], "license": "MIT", "collectionID": [], "maturity": "Mature", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1186/1756-0500-5-27", "pmid": "22244497", "pmcid": "PMC3278344", "type": [], "version": null, "note": null, "metadata": { "title": "BarraCUDA - A fast short read sequence aligner using graphics processing units", "abstract": "Background: With the maturation of next-generation DNA sequencing (NGS) technologies, the throughput of DNA sequencing reads has soared to over 600 gigabases from a single instrument run. General purpose computing on graphics processing units (GPGPU), extracts the computing power from hundreds of parallel stream processors within graphics processing cores and provides a cost-effective and energy efficient alternative to traditional high-performance computing (HPC) clusters. In this article, we describe the implementation of BarraCUDA, a GPGPU sequence alignment software that is based on BWA, to accelerate the alignment of sequencing reads generated by these instruments to a reference DNA sequence. Findings. Using the NVIDIA Compute Unified Device Architecture (CUDA) software development environment, we ported the most computational-intensive alignment component of BWA to GPU to take advantage of the massive parallelism. As a result, BarraCUDA offers a magnitude of performance boost in alignment throughput when compared to a CPU core while delivering the same level of alignment fidelity. The software is also capable of supporting multiple CUDA devices in parallel to further accelerate the alignment throughput. Conclusions: BarraCUDA is designed to take advantage of the parallelism of GPU to accelerate the alignment of millions of sequencing reads generated by NGS instruments. By doing this, we could, at least in part streamline the current bioinformatics pipeline such that the wider scientific community could benefit from the sequencing technology. BarraCUDA is currently available from. © 2012 Klus et al; licensee BioMed Central Ltd.", "date": "2012-01-16T00:00:00Z", "citationCount": 109, "authors": [ { "name": "Klus P." }, { "name": "Lam S." }, { "name": "Lyberg D." }, { "name": "Cheung M." }, { "name": "Pullan G." }, { "name": "McFarlane I." }, { "name": "Yeo G.S.H." }, { "name": "Lam B.Y.H." } ], "journal": "BMC Research Notes" } } ], "credit": [ { "name": "Klus P.", "email": "yhbl2@cam.ac.uk", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:13:38Z", "lastUpdate": "2024-11-24T20:36:20.031054Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BARS", "description": "BARS is a statistical method that bridges the gap between single-locus and haplotype-based tests of association. It is based on the non-parametric regression techniques embodied by Bayesian Adaptive Regression Splines.", "homepage": "http://wpicr.wpic.pitt.edu/WPICCompGen/bars.htm", "biotoolsID": "bars", "biotoolsCURIE": "biotools:bars", "version": [], "otherID": [ { "value": "RRID:SCR_009123", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3659", "term": "Regression" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" } ], "operatingSystem": [ "Linux" ], "language": [ "R" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/bars-bayesian-adaptive-regression-splines.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://wpicr.wpic.pitt.edu/WPICCompGen/BARS/BARS_R_INSTRUCTIONS.htm", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1479-7364-1-1-20", "pmid": "15601530", "pmcid": "PMC3525002", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Integration of association statistics over genomic regions using Bayesian adaptive regression splines.", "abstract": "In the search for genetic determinants of complex disease, two approaches to association analysis are most often employed, testing single loci or testing a small group of loci jointly via haplotypes for their relationship to disease status. It is still debatable which of these approaches is more favourable, and under what conditions. The former has the advantage of simplicity but suffers severely when alleles at the tested loci are not in linkage disequilibrium (LD) with liability alleles; the latter should capture more of the signal encoded in LD, but is far from simple. The complexity of haplotype analysis could be especially troublesome for association scans over large genomic regions, which, in fact, is becoming the standard design. For these reasons, the authors have been evaluating statistical methods that bridge the gap between single-locus and haplotype-based tests. In this article, they present one such method, which uses non-parametric regression techniques embodied by Bayesian adaptive regression splines (BARS). For a set of markers falling within a common genomic region and a corresponding set of single-locus association statistics, the BARS procedure integrates these results into a single test by examining the class of smooth curves consistent with the data. The non-parametric BARS procedure generally finds no signal when no liability allele exists in the tested region (ie it achieves the specified size of the test) and it is sensitive enough to pick up signals when a liability allele is present. The BARS procedure provides a robust and potentially powerful alternative to classical tests of association, diminishes the multiple testing problem inherent in those tests and can be applied to a wide range of data types, including genotype frequencies estimated from pooled samples.", "date": "2003-01-01T00:00:00Z", "citationCount": 20, "authors": [ { "name": "Zhang X." }, { "name": "Roeder K." }, { "name": "Wallstrom G." }, { "name": "Devlin B." } ], "journal": "Human genomics" } } ], "credit": [ { "name": null, "email": null, "url": "http://wpicr.wpic.pitt.edu/WPICCompGen/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:03:50Z", "lastUpdate": "2024-11-24T20:36:18.873362Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BayesCall", "description": "Bayesian basecaller", "homepage": "http://bayescall.sourceforge.net/", "biotoolsID": "bayescall", "biotoolsCURIE": "biotools:bayescall", "version": [], "otherID": [ { "value": "RRID:SCR_011866", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3185", "term": "Base-calling" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "C++", "Python" ], "license": "GPL-3.0", "collectionID": [], "maturity": "Legacy", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://bayescall.sourceforge.net/README.txt", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1101/gr.095299.109", "pmid": "19661376", "pmcid": "PMC2765266", "type": [], "version": null, "note": null, "metadata": { "title": "BayesCall: A model-based base-calling algorithm for high-throughput short-read sequencing", "abstract": "Extracting sequence information from raw images of fluorescence is the foundation underlying several high-throughput sequencing platforms. Some of the main challenges associated with this technology include reducing the error rate, assigning accurate base-specific quality scores, and reducing the cost of sequencing by increasing the throughput per run. To demonstrate how computational advancement can help to meet these challenges, a novel model-based base-calling algorithm, BayesCall, is introduced for the Illumina sequencing platform. Being founded on the tools of statistical learning, BayesCall is flexible enough to incorporate various features of the sequencing process. In particular, it can easily incorporate time-dependent parameters and model residual effects. This new approach significantly improves the accuracy over Illumina's base-caller Bustard, particularly in the later cycles of a sequencing run. For 76-cycle data on a standard viral sample, phiX174, BayesCall improves Bustard's average per-base error rate by ∼51%. The probability of observing each base can be readily computed in BayesCall, and this probability can be transformed into a useful basespecific quality score with a high discrimination ability. A detailed study of BayesCall's performance is presented here. © 2009 by Cold Spring Harbor Laboratory Press.", "date": "2009-10-01T00:00:00Z", "citationCount": 69, "authors": [ { "name": "Kao W.-C." }, { "name": "Stevens K." }, { "name": "Song Y.S." } ], "journal": "Genome Research" } } ], "credit": [ { "name": "Wei-Chun Kao", "email": "wckao@eecs.berkeley.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Yun S. Song", "email": "yss@eecs.berkeley.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:13:39Z", "lastUpdate": "2024-11-24T20:36:17.804936Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BAYESFST", "description": "Bayesian estimation of the coancestry coefficient FST", "homepage": "http://www.reading.ac.uk/Statistics/genetics/software.html", "biotoolsID": "bayesfst", "biotoolsCURIE": "biotools:bayesfst", "version": [], "otherID": [ { "value": "RRID:SCR_013479", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3658", "term": "Statistical inference" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" }, { "uri": "http://edamontology.org/topic_3056", "term": "Population genetics" }, { "uri": "http://edamontology.org/topic_2269", "term": "Statistics and probability" } ], "operatingSystem": [ "Linux", "Windows" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/bayesfst-bayesian-estimation-coancestry-coefficient-fst.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://www.reading.ac.uk/Statistics/genetics/software.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1111/j.1365-294x.2004.02125.x", "pmid": "15012769", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Identifying adaptive genetic divergence among populations from genome scans", "abstract": "The identification of signatures of natural selection in genomic surveys has become an area of intense research, stimulated by the increasing ease with which genetic markers can be typed. Loci identified as subject to selection may be functionally important, and hence (weak) candidates for involvement in disease causation. They can also be useful in determining the adaptive differentiation of populations, and exploring hypotheses about speciation. Adaptive differentiation has traditionally been identified from differences in allele frequencies among different populations, summarised by an estimate of F ST. Low outliers relative to an appropriate neutral population-genetics model indicate loci subject to balancing selection, whereas high outliers suggest adaptive (directional) selection. However, the problem of identifying statistically significant departures from neutrality is complicated by confounding effects on the distribution of F ST estimates, and current methods have not yet been tested in large-scale simulation experiments. Here, we simulate data from a structured population at many unlinked, diallelic loci that are predominantly neutral but with some loci subject to adaptive or balancing selection. We develop a hierarchical-Bayesian method, implemented via Markov chain Monte Carlo (MCMC), and assess its performance in distinguishing the loci simulated under selection from the neutral loci. We also compare this performance with that of a frequentist method, based on moment-based estimates of F ST. We find that both methods can identify loci subject to adaptive selection when the selection coefficient is at least five times the migration rate. Neither method could reliably distinguish loci under balancing selection in our simulations, even when the selection coefficient is twenty times the migration rate.", "date": "2004-04-01T00:00:00Z", "citationCount": 811, "authors": [ { "name": "Beaumont M.A." }, { "name": "Balding D.J." } ], "journal": "Molecular Ecology" } } ], "credit": [ { "name": "D.J. Balding", "email": "d.balding@ic.ac.uk", "url": "http://www.reading.ac.uk/maths-and-stats/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T18:36:46Z", "lastUpdate": "2024-11-24T20:36:16.676331Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BBSeq", "description": "An R package for analyzing RNA-Seq transcriptional count data.", "homepage": "http://www.bios.unc.edu/research/genomic_software/BBSeq/", "biotoolsID": "bbseq", "biotoolsCURIE": "biotools:bbseq", "version": [], "otherID": [ { "value": "RRID:SCR_011877", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3800", "term": "RNA-Seq quantification" }, { "uri": "http://edamontology.org/operation_3563", "term": "RNA-seq read count analysis" }, { "uri": "http://edamontology.org/operation_2495", "term": "Gene expression analysis" }, { "uri": "http://edamontology.org/operation_2238", "term": "Statistical calculation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3495", "term": "RNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1213", "term": "rna" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0950", "term": "Mathematical model" }, "format": [ { "uri": "http://edamontology.org/format_2032", "term": "Workflow format" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Library" ], "topic": [ { "uri": "http://edamontology.org/topic_3170", "term": "RNA-Seq" }, { "uri": "http://edamontology.org/topic_2269", "term": "Statistics and probability" }, { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "R" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://www.bios.unc.edu/research/genomic_software/BBSeq/index_files/manual.pdf", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btr449", "pmid": "21810900", "pmcid": "PMC3179656", "type": [], "version": null, "note": null, "metadata": { "title": "A powerful and flexible approach to the analysis of RNA sequence count data", "abstract": "Motivation: A number of penalization and shrinkage approaches have been proposed for the analysis of microarray gene expression data. Similar techniques are now routinely applied to RNA sequence transcriptional count data, although the value of such shrinkage has not been conclusively established. If penalization is desired, the explicit modeling of mean-variance relationships provides a flexible testing regimen that 'borrows' information across genes, while easily incorporating design effects and additional covariates.Results: We describe BBSeq, which incorporates two approaches: (i) a simple beta-binomial generalized linear model, which has not been extensively tested for RNA-Seq data and (ii) an extension of an expression mean-variance modeling approach to RNA-Seq data, involving modeling of the overdispersion as a function of the mean. Our approaches are flexible, allowing for general handling of discrete experimental factors and continuous covariates. We report comparisons with other alternate methods to handle RNA-Seq data. Although penalized methods have advantages for very small sample sizes, the beta-binomial generalized linear model, combined with simple outlier detection and testing approaches, appears to have favorable characteristics in power and flexibility. © The Author 2011. Published by Oxford University Press. All rights reserved.", "date": "2011-10-01T00:00:00Z", "citationCount": 91, "authors": [ { "name": "Zhou Y.-H." }, { "name": "Xia K." }, { "name": "Wright F.A." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Yi-Hui Zhou", "email": "yzhou@bios.unc.edu", "url": "http://www.bios.unc.edu/~yihuiz", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:13:41Z", "lastUpdate": "2024-11-24T20:36:15.513581Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-EE" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BCBtoolkit", "description": "Aims to provide the scientific community with the several tools to indirectly assess brain disconnections.", "homepage": "http://toolkit.bcblab.com/", "biotoolsID": "bcbtoolkit", "biotoolsCURIE": "biotools:bcbtoolkit", "version": [], "otherID": [ { "value": "RRID:SCR_015519", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2497", "term": "Pathway or network analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3334", "term": "Neurology" }, { "uri": "http://edamontology.org/topic_3304", "term": "Neurobiology" }, { "uri": "http://edamontology.org/topic_0602", "term": "Molecular interactions, pathways and networks" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "R", "Java" ], "license": "BSD-3-Clause", "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://toolkit.bcblab.com/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/gigascience/giy004", "pmid": "29432527", "pmcid": "PMC5863218", "type": [], "version": null, "note": null, "metadata": { "title": "Advanced lesion symptom mapping analyses and implementation as BCBtoolkit", "abstract": "Background: Patients with brain lesions provide a unique opportunity to understand the functioning of the human mind. However, even when focal, brain lesions have local and remote effects that impact functionally and structurally connected circuits. Similarly, function emerges from the interaction between brain areas rather than their sole activity. For instance, category fluency requires the associations between executive, semantic, and language production functions. Findings: Here, we provide, for the first time, a set of complementary solutions for measuring the impact of a given lesion on the neuronal circuits. Our methods, which were applied to 37 patients with a focal frontal brain lesions, revealed a large set of directly and indirectly disconnected brain regions that had significantly impacted category fluency performance. The directly disconnected regions corresponded to areas that are classically considered as functionally engaged in verbal fluency and categorization tasks. These regions were also organized into larger directly and indirectly disconnected functional networks, including the left ventral fronto-parietal network, whose cortical thickness correlated with performance on category fluency. Conclusions: The combination of structural and functional connectivity together with cortical thickness estimates reveal the remote effects of brain lesions, provide for the identification of the affected networks, and strengthen our understanding of their relationship with cognitive and behavioral measures. The methods presented are available and freely accessible in the BCBtoolkit as supplementary software [1].", "date": "2018-03-01T00:00:00Z", "citationCount": 223, "authors": [ { "name": "Foulon C." }, { "name": "Cerliani L." }, { "name": "Kinkingnehun S." }, { "name": "Levy R." }, { "name": "Rosso C." }, { "name": "Urbanski M." }, { "name": "Volle E." }, { "name": "de Schotten M.T." } ], "journal": "GigaScience" } } ], "credit": [ { "name": "Michel Thiebaut de Schotten", "email": "michel.thiebaut@gmail.com", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "d.gabrielaitis", "additionDate": "2018-07-13T18:06:51Z", "lastUpdate": "2024-11-24T20:36:14.041890Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BeetleBase", "description": "The database contains genomic sequence scaffolds mapped to 10 linkage groups, genetic linkage maps, the official gene set, Reference Sequences from NCBI (RefSeq), predicted gene models, ESTs and whole-genome tiling array data representing several developmental stages. The database was reconstructed using the upgraded Generic Model Organism Database (GMOD) modules, it has been updated to provide more comprehensive genomic information for the red flour beetle Tribolium castaneum.", "homepage": "http://beetlebase.org/", "biotoolsID": "beetlebase", "biotoolsCURIE": "biotools:beetlebase", "version": [], "otherID": [ { "value": "RRID:SCR_001955", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_2871", "term": "Sequence tagged site (STS) mapping" }, { "uri": "http://edamontology.org/operation_0282", "term": "Genetic mapping" }, { "uri": "http://edamontology.org/operation_3216", "term": "Scaffolding" }, { "uri": "http://edamontology.org/operation_2429", "term": "Mapping" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0102", "term": "Mapping" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" }, { "uri": "http://edamontology.org/topic_3512", "term": "Gene transcripts" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://beetlebase.org/?q=home", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkp807", "pmid": "19820115", "pmcid": "PMC2808946", "type": [], "version": null, "note": null, "metadata": { "title": "BeetleBase in 2010: Revisions to provide comprehensive genomic information for Tribolium castaneum", "abstract": "BeetleBase (http://www.beetlebase.org) has been updated to provide more comprehensive genomic information for the red flour beetle Tribolium castaneum. The database contains genomic sequence scaffolds mapped to 10 linkage groups (genome assembly release Tcas_3.0), genetic linkage maps, the official gene set, Reference Sequences from NCBI (RefSeq), predicted gene models, ESTs and whole-genome tiling array data representing several developmental stages. The database was reconstructed using the upgraded Generic Model Organism Database (GMOD) modules. The genomic data is stored in a PostgreSQL relatational database using the Chado schema and visualized as tracks in GBrowse. The updated genetic map is visualized using the comparative genetic map viewer CMAP. To enhance the database search capabilities, the BLAST and BLAT search tools have been integrated with the GMOD tools. BeetleBase serves as a long-term repository for Tribolium genomic data, and is compatible with other model organism databases. © The Author(s) 2009. Published by Oxford University Press.", "date": "2009-10-09T00:00:00Z", "citationCount": 129, "authors": [ { "name": "Kim H.S." }, { "name": "Murphy T." }, { "name": "Xia J." }, { "name": "Caragea D." }, { "name": "Park Y." }, { "name": "Beeman R.W." }, { "name": "Lorenzen M.D." }, { "name": "Butcher S." }, { "name": "Manak J.R." }, { "name": "Brown S.J." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "Support", "email": "bioinfo@ksu.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-03-27T07:20:05Z", "lastUpdate": "2024-11-24T20:36:12.854574Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BiNGO", "description": "A tool to determine which Gene Ontology (GO) categories are statistically overrepresented in a set of genes or a subgraph of a biological network.", "homepage": "http://www.psb.ugent.be/cbd/papers/BiNGO/Home.html", "biotoolsID": "bingo", "biotoolsCURIE": "biotools:bingo", "version": [ "3.0.2" ], "otherID": [ { "value": "RRID:SCR_005736", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3501", "term": "Enrichment analysis" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1025", "term": "Gene identifier" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2338", "term": "Ontology identifier" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2338", "term": "Ontology identifier" }, "format": [ { "uri": "http://edamontology.org/format_1964", "term": "plain text format (unformatted)" } ] }, { "data": { "uri": "http://edamontology.org/data_1669", "term": "P-value" }, "format": [] } ], "note": "GO enrichment analysis", "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_0085", "term": "Functional genomics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [ "VIB", "Plant Systems Biology", "UGent" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://www.psb.ugent.be/cbd/papers/BiNGO/Tutorial.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/bti551", "pmid": "15972284", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "BiNGO: A Cytoscape plugin to assess overrepresentation of Gene Ontology categories in Biological Networks", "abstract": "Summary: The Biological Networks Gene Ontology tool (BiNGO) is an open-source Java tool to determine which Gene Ontology (GO) terms are significantly overrepresented in a set of genes. BiNGO can be used either on a list of genes, pasted as text, or interactively on subgraphs of biological networks visualized in Cytoscape. BiNGO maps the predominant functional themes of the tested gene set on the GO hierarchy, and takes advantage of Cytoscape's versatile visualization environment to produce an intuitive and customizable visual representation of the results. © The Author 2005. Published by Oxford University Press. All rights reserved.", "date": "2005-08-15T00:00:00Z", "citationCount": 3355, "authors": [ { "name": "Maere S." }, { "name": "Heymans K." }, { "name": "Kuiper M." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "PSB", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Steven Maere", "email": "steven.maere@psb.vib-ugent.be", "url": "http://www.psb.ugent.be/esb/ESB/Home.html", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "PSB", "additionDate": "2015-02-02T11:23:55Z", "lastUpdate": "2024-11-24T20:36:11.478539Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Bio-Analytic Resource (BAR)", "description": "User-friendly web-based tools for working with functional genomics and other data. Most are designed with the plant (mainly Arabidopsis) reseacher in mind, but a couple of them can be useful to the wider research community.", "homepage": "http://bar.utoronto.ca/welcome.htm", "biotoolsID": "bioanalres_bar", "biotoolsCURIE": "biotools:bioanalres_bar", "version": [], "otherID": [ { "value": "RRID:SCR_006748", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3501", "term": "Over-representation analysis" }, { "uri": "http://edamontology.org/operation_0314", "term": "Gene expression profiling" }, { "uri": "http://edamontology.org/operation_3463", "term": "Gene expression correlation analysis" }, { "uri": "http://edamontology.org/operation_2464", "term": "Protein-protein binding site prediction" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3173", "term": "Epigenomics" }, { "uri": "http://edamontology.org/topic_3308", "term": "Transcriptomics" }, { "uri": "http://edamontology.org/topic_0602", "term": "Molecular interactions, pathways and networks" }, { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1007/978-1-4939-6658-5_6", "pmid": "27987167", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "The bio-analytic resource for plant biology", "abstract": "Bioinformatic tools have become part of the way plant researchers undertake investigations. Large data sets encompassing genomes, transcriptomes, proteomes, epigenomes, and other “-omes” that have been generated in the past decade may be easily accessed with such tools, such that hypotheses may be generated at the click of a mouse. In this chapter, we’ll cover the use of bioinformatic tools available at the Bio-Analytic Resource for Plant Biology at http://bar.utoronto.ca for exploring gene expression and coexpression patterns, undertaking promoter analyses, performing functional classification enrichment analyses for sets of genes, and examining protein-protein interactions. We also touch on some newer bioinformatic tools that allow integration of data from several sources for improved hypothesis generation, both for Arabidopsis and translationally. Most of the data sets come from Arabidopsis, but useful BAR tools for other species will be mentioned where appropriate.", "date": "2017-01-01T00:00:00Z", "citationCount": 37, "authors": [ { "name": "Waese J." }, { "name": "Provart N.J." } ], "journal": "Methods in Molecular Biology" } }, { "doi": "10.1111/tpj.13261", "pmid": "27401965", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "New BAR tools for mining expression data and exploring Cis-elements in Arabidopsis thaliana", "abstract": "Identifying sets of genes that are specifically expressed in certain tissues or in response to an environmental stimulus is useful for designing reporter constructs, generating gene expression markers, or for understanding gene regulatory networks. We have developed an easy-to-use online tool for defining a desired expression profile (a modification of our Expression Angler program), which can then be used to identify genes exhibiting patterns of expression that match this profile as closely as possible. Further, we have developed another online tool, Cistome, for predicting or exploring cis-elements in the promoters of sets of co-expressed genes identified by such a method, or by other methods. We present two use cases for these tools, which are freely available on the Bio-Analytic Resource at http://BAR.utoronto.ca.", "date": "2016-11-01T00:00:00Z", "citationCount": 41, "authors": [ { "name": "Austin R.S." }, { "name": "Hiu S." }, { "name": "Waese J." }, { "name": "Ierullo M." }, { "name": "Pasha A." }, { "name": "Wang T.T." }, { "name": "Fan J." }, { "name": "Foong C." }, { "name": "Breit R." }, { "name": "Desveaux D." }, { "name": "Moses A." }, { "name": "Provart N.J." } ], "journal": "Plant Journal" } } ], "credit": [ { "name": "Nicholas J. Provart", "email": "nicholas.provart@utoronto.ca", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-05-16T12:57:23Z", "lastUpdate": "2024-11-24T20:36:09.173434Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GenMAPP", "description": "Microarray expression data visualization tool, allowing data to be viewed on maps representing gene groupings and biological pathways.", "homepage": "http://www.genmapp.org/", "biotoolsID": "genmapp", "biotoolsCURIE": "biotools:genmapp", "version": [], "otherID": [ { "value": "RRID:SCR_005094", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0313", "term": "Gene expression clustering" }, { "uri": "http://edamontology.org/operation_0315", "term": "Gene expression comparison" }, { "uri": "http://edamontology.org/operation_0314", "term": "Gene expression profiling" }, { "uri": "http://edamontology.org/operation_2495", "term": "Gene expression analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0602", "term": "Molecular interactions, pathways and networks" }, { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" }, { "uri": "http://edamontology.org/topic_3518", "term": "Microarray experiment" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" }, { "uri": "http://edamontology.org/topic_0102", "term": "Mapping" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1038/ng0502-19", "pmid": "11984561", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "GenMAPP, a new tool for viewing and analyzing microarray data on biological pathways", "abstract": "", "date": "2002-01-01T00:00:00Z", "citationCount": 818, "authors": [ { "name": "Dahlquist K.D." }, { "name": "Salomonis N." }, { "name": "Vranizan K." }, { "name": "Lawlor S.C." }, { "name": "Conklin B.R." } ], "journal": "Nature Genetics" } } ], "credit": [ { "name": "Bruce R. Conklin", "email": "bconklin@gladstone.ucsf.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-05-02T07:18:39Z", "lastUpdate": "2024-11-24T20:36:07.676279Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Genome Projector", "description": "Searchable database browser with zoomable user interface using Google Map API. Genome Projector currently contains 4 views: Genome map, Plasmid map, Pathway map, and DNA walk.", "homepage": "http://www.g-language.org/GenomeProjector/", "biotoolsID": "genome_projector", "biotoolsCURIE": "biotools:genome_projector", "version": [], "otherID": [ { "value": "RRID:SCR_011790", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3208", "term": "Genome visualisation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3070", "term": "Biology" }, { "uri": "http://edamontology.org/topic_3047", "term": "Molecular biology" }, { "uri": "http://edamontology.org/topic_0654", "term": "DNA" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0092", "term": "Data visualisation" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "JavaScript", "Perl" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/genome-projector-zoomable-user-interface-molecular-biology.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://www.g-language.org/GenomeProjector/wiki/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-10-31", "pmid": "19166610", "pmcid": "PMC2636772", "type": [], "version": null, "note": null, "metadata": { "title": "Genome Projector: zoomable genome map with multiple views.", "abstract": "BACKGROUND: Molecular biology data exist on diverse scales, from the level of molecules to -omics. At the same time, the data at each scale can be categorised into multiple layers, such as the genome, transcriptome, proteome, metabolome, and biochemical pathways. Due to the highly multi-layer and multi-dimensional nature of biological information, software interfaces for database browsing should provide an intuitive interface that allows for rapid migration across different views and scales. The Zoomable User Interface (ZUI) and tabbed browsing have proven successful for this purpose in other areas, especially to navigate the vast information in the World Wide Web. RESULTS: This paper presents Genome Projector, a Web-based gateway for genomics information with a zoomable user interface using Google Maps API, equipped with four seamlessly accessible and searchable views: a circular genome map, a traditional genome map, a biochemical pathways map, and a DNA walk map. The Web application for 320 bacterial genomes is available at http://www.g-language.org/GenomeProjector/. All data and software including the source code, documentations, and development API are freely available under the GNU General Public License. Zoomable maps can be easily created from any image file using the development API, and an online data mapping service for Genome Projector is also available at our Web site. CONCLUSION: Genome Projector is an intuitive Web application for browsing genomics information, implemented with a zoomable user interface and tabbed browsing utilising Google Maps API and Asynchronous JavaScript and XML (AJAX) technology.", "date": "2009-01-01T00:00:00Z", "citationCount": 34, "authors": [ { "name": "Arakawa K." }, { "name": "Tamaki S." }, { "name": "Kono N." }, { "name": "Kido N." }, { "name": "Ikegami K." }, { "name": "Ogawa R." }, { "name": "Tomita M." } ], "journal": "BMC bioinformatics" } } ], "credit": [ { "name": null, "email": null, "url": "http://www.g-language.org/GenomeProjector/members.html", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T18:45:26Z", "lastUpdate": "2024-11-24T20:36:06.278615Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Genomedata", "description": "Genomedata is a format for efficient storage of multiple tracks of numeric data anchored to a genome. The format allows fast random access to hundreds of gigabytes of data, while retaining a small disk space footprint.", "homepage": "http://noble.gs.washington.edu/proj/genomedata/", "biotoolsID": "genomedata", "biotoolsCURIE": "biotools:genomedata", "version": [], "otherID": [ { "value": "RRID:SCR_004544", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2478", "term": "Nucleic acid sequence analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Library" ], "topic": [ { "uri": "http://edamontology.org/topic_3071", "term": "Data management" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Python", "C" ], "license": "GPL-3.0", "collectionID": [], "maturity": "Mature", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://hoffmanlab.org/proj/genomedata/doc/1.4.0/genomedata.pdf", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btq164", "pmid": "20435580", "pmcid": "PMC2872006", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "The genomedata format for storing large-scale functional genomics data", "abstract": "Summary: We present a format for efficient storage of multiple tracks of numeric data anchored to a genome. The format allows fast random access to hundreds of gigabytes of data, while retaining a small disk space footprint. We have also developed utilities to load data into this format. We show that retrieving data from this format is more than 2900 times faster than a naive approach using wiggle fileson.edu/ proj/genomedata/ under the GNU General Public License. © The Author(s) 2010. Published by Oxford University Press.", "date": "2010-04-29T00:00:00Z", "citationCount": 14, "authors": [ { "name": "Hoffman M.M." }, { "name": "Buske O.J." }, { "name": "Noble W.S." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Jay Hesselberth", "email": "jay.hesselberth@ucdenver.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:14:49Z", "lastUpdate": "2024-11-24T20:36:05.072939Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Genometa", "description": "Java based local bioinformatics program which allows rapid analysis of metagenomic short read datasets. Millions of short reads can be accurately analysed within minutes and visualised in the browser component. A large database of diverse bacteria and archaea has been constructed as a reference sequence.", "homepage": "http://genomics1.mh-hannover.de/genometa/index.php?Site=Home", "biotoolsID": "genometa", "biotoolsCURIE": "biotools:genometa", "version": [], "otherID": [ { "value": "RRID:SCR_001181", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_3198", "term": "Read mapping" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Java" ], "license": null, "collectionID": [], "maturity": "Mature", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://genomics1.mh-hannover.de/genometa/index.php?Site=Tutorial%201", "type": [ "User manual" ], "note": null }, { "url": "http://genomics1.mh-hannover.de/genometa/index.php?Site=Tutorial%202", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pone.0041224", "pmid": "22927906", "pmcid": "PMC3424124", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Genometa - A fast and accurate classifier for short metagenomic shotgun reads", "abstract": "Summary: Metagenomic studies use high-throughput sequence data to investigate microbial communities in situ. However, considerable challenges remain in the analysis of these data, particularly with regard to speed and reliable analysis of microbial species as opposed to higher level taxa such as phyla. We here present Genometa, a computationally undemanding graphical user interface program that enables identification of bacterial species and gene content from datasets generated by inexpensive high-throughput short read sequencing technologies. Our approach was first verified on two simulated metagenomic short read datasets, detecting 100% and 94% of the bacterial species included with few false positives or false negatives. Subsequent comparative benchmarking analysis against three popular metagenomic algorithms on an Illumina human gut dataset revealed Genometa to attribute the most reads to bacteria at species level (i.e. including all strains of that species) and demonstrate similar or better accuracy than the other programs. Lastly, speed was demonstrated to be many times that of BLAST due to the use of modern short read aligners. Our method is highly accurate if bacteria in the sample are represented by genomes in the reference sequence but cannot find species absent from the reference. This method is one of the most user-friendly and resource efficient approaches and is thus feasible for rapidly analysing millions of short reads on a personal computer. Availability: The Genometa program, a step by step tutorial and Java source code are freely available from http://genomics1.mh-hannover.de/genometa/ and on http://code.google.com/p/genometa/. This program has been tested on Ubuntu Linux and Windows XP/7. © 2012 Davenport et al.", "date": "2012-08-21T00:00:00Z", "citationCount": 29, "authors": [ { "name": "Davenport C.F." }, { "name": "Neugebauer J." }, { "name": "Beckmann N." }, { "name": "Friedrich B." }, { "name": "Kameri B." }, { "name": "Kokott S." }, { "name": "Paetow M." }, { "name": "Siekmann B." }, { "name": "Wieding-Drewes M." }, { "name": "Wienhofer M." }, { "name": "Wolf S." }, { "name": "Tummler B." }, { "name": "Ahlers V." }, { "name": "Sprengel F." } ], "journal": "PLoS ONE" } } ], "credit": [ { "name": "Dr. Colin Davenport", "email": "davenport.colin@mh-hannover.de", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:14:51Z", "lastUpdate": "2024-11-24T20:36:03.841934Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GenomeTools", "description": "Free collection of bioinformatics tools for genome informatics.", "homepage": "http://genometools.org/", "biotoolsID": "genometools", "biotoolsCURIE": "biotools:genometools", "version": [], "otherID": [ { "value": "RRID:SCR_018970", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2403", "term": "Sequence analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Suite" ], "topic": [ { "uri": "http://edamontology.org/topic_3511", "term": "Nucleic acid sites, features and motifs" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "C" ], "license": "BSD-3-Clause", "collectionID": [ "Animal and Crop Genomics" ], "maturity": "Mature", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://genometools.org/documentation.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1109/tcbb.2013.68", "pmid": "24091398", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Genome tools: A comprehensive software library for efficient processing of structured genome annotations", "abstract": "Genome annotations are often published as plain text files describing genomic features and their subcomponents by an implicit annotation graph. In this paper, we present the GenomeTools, a convenient and efficient software library and associated software tools for developing bioinformatics software intended to create, process or convert annotation graphs. The GenomeTools strictly follow the annotation graph approach, offering a unified graph-based representation. This gives the developer intuitive and immediate access to genomic features and tools for their manipulation. To process large annotation sets with low memory overhead, we have designed and implemented an efficient pull-based approach for sequential processing of annotations. This allows to handle even the largest annotation sets, such as a complete catalogue of human variations. Our object-oriented C-based software library enables a developer to conveniently implement their own functionality on annotation graphs and to integrate it into larger workflows, simultaneously accessing compressed sequence data if required. The careful C implementation of the GenomeTools does not only ensure a light-weight memory footprint while allowing full sequential as well as random access to the annotation graph, but also facilitates the creation of bindings to a variety of script programming languages (like Python and Ruby) sharing the same interface. © 2004-2012 IEEE.", "date": "2013-11-25T00:00:00Z", "citationCount": 270, "authors": [ { "name": "Gremme G." }, { "name": "Steinbiss S." }, { "name": "Kurtz S." } ], "journal": "IEEE/ACM Transactions on Computational Biology and Bioinformatics" } } ], "credit": [ { "name": "GenomeTools Support", "email": "gordon@gremme.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:14:51Z", "lastUpdate": "2024-11-24T20:36:02.703842Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Genovar", "description": "Freely accessible and provides a user-friendly graphic user interface (GUI) to facilitate the detection of CNV regions. The program also provides comprehensive information to help in the elimination of spurious signals by visual inspection, making Genovar a valuable tool for reducing false positive CNV results.", "homepage": "http://genovar.sourceforge.net/", "biotoolsID": "genovar", "biotoolsCURIE": "biotools:genovar", "version": [], "otherID": [ { "value": "RRID:SCR_010930", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3197", "term": "Genetic variation analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_3053", "term": "Genetics" }, { "uri": "http://edamontology.org/topic_2533", "term": "DNA mutation" }, { "uri": "http://edamontology.org/topic_0092", "term": "Data visualisation" }, { "uri": "http://edamontology.org/topic_0654", "term": "DNA" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/genovar-0-951b-detection-and-visualization-tool-for-genomic-variants.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://genovar.sourceforge.net/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-13-s7-s12", "pmid": "22594998", "pmcid": "PMC3348018", "type": [], "version": null, "note": null, "metadata": { "title": "Genovar: A detection and visualization tool for genomic variants", "abstract": "Background: Along with single nucleotide polymorphisms (SNPs), copy number variation (CNV) is considered an important source of genetic variation associated with disease susceptibility. Despite the importance of CNV, the tools currently available for its analysis often produce false positive results due to limitations such as low resolution of array platforms, platform specificity, and the type of CNV. To resolve this problem, spurious signals must be separated from true signals by visual inspection. None of the previously reported CNV analysis tools support this function and the simultaneous visualization of comparative genomic hybridization arrays (aCGH) and sequence alignment. The purpose of the present study was to develop a useful program for the efficient detection and visualization of CNV regions that enables the manual exclusion of erroneous signals.Results: A JAVA-based stand-alone program called Genovar was developed. To ascertain whether a detected CNV region is a novel variant, Genovar compares the detected CNV regions with previously reported CNV regions using the Database of Genomic Variants (DGV, http://projects.tcag.ca/variation) and the Single Nucleotide Polymorphism Database (dbSNP). The current version of Genovar is capable of visualizing genomic data from sources such as the aCGH data file and sequence alignment format files.Conclusions: Genovar is freely accessible and provides a user-friendly graphic user interface (GUI) to facilitate the detection of CNV regions. The program also provides comprehensive information to help in the elimination of spurious signals by visual inspection, making Genovar a valuable tool for reducing false positive CNV results. Availability: http://genovar.sourceforge.net/. © 2012 Jung et al.; licensee BioMed Central Ltd.", "date": "2012-05-08T00:00:00Z", "citationCount": 3, "authors": [ { "name": "Jung K.S." }, { "name": "Moon S." }, { "name": "Kim Y.J." }, { "name": "Kim B.-J." }, { "name": "Park K." } ], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": "Kwang Su Jung", "email": "ksjung76@gmail.com", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T18:45:29Z", "lastUpdate": "2024-11-24T20:36:01.462818Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GensearchNGS", "description": "A user friendly framework for re-sequencing in a diagnostics context: searching for mutations/variants, especially on well known genes.", "homepage": "http://www.phenosystems.com/www/index.php/products/gensearchngs", "biotoolsID": "gensearchngs", "biotoolsCURIE": "biotools:gensearchngs", "version": [], "otherID": [ { "value": "RRID:SCR_010802", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3202", "term": "Polymorphism detection" }, { "uri": "http://edamontology.org/operation_3226", "term": "Variant prioritisation" }, { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" }, { "uri": "http://edamontology.org/operation_3198", "term": "Read mapping" }, { "uri": "http://edamontology.org/operation_0292", "term": "Sequence alignment" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_3676", "term": "Exome sequencing" } ], "operatingSystem": [ "Linux", "Windows" ], "language": [ "Java" ], "license": "Unlicense", "collectionID": [], "maturity": "Mature", "cost": "Commercial", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://www.phenosystems.com/www/index.php/products/gensearchngs", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1155/2015/403497", "pmid": "26137478", "pmcid": "PMC4475531", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "DNAseq workflow in a diagnostic context and an example of a user friendly implementation", "abstract": "Over recent years next generation sequencing (NGS) technologies evolved from costly tools used by very few, to a much more accessible and economically viable technology. Through this recently gained popularity, its use-cases expanded from research environments into clinical settings. But the technical know-how and infrastructure required to analyze the data remain an obstacle for a wider adoption of this technology, especially in smaller laboratories. We present GensearchNGS, a commercial DNAseq software suite distributed by Phenosystems SA. The focus of GensearchNGS is the optimal usage of already existing infrastructure, while keeping its use simple. This is achieved through the integration of existing tools in a comprehensive software environment, as well as custom algorithms developed with the restrictions of limited infrastructures in mind. This includes the possibility to connect multiple computers to speed up computing intensive parts of the analysis such as sequence alignments. We present a typical DNAseq workflow for NGS data analysis and the approach GensearchNGS takes to implement it. The presented workflow goes from raw data quality control to the final variant report. This includes features such as gene panels and the integration of online databases, like Ensembl for annotations or Cafe Variome for variant sharing.", "date": "2015-01-01T00:00:00Z", "citationCount": 9, "authors": [ { "name": "Wolf B." }, { "name": "Kuonen P." }, { "name": "Dandekar T." }, { "name": "Atlan D." } ], "journal": "BioMed Research International" } } ], "credit": [ { "name": null, "email": "contact@phenosystems.com", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:14:53Z", "lastUpdate": "2024-11-24T20:35:59.891365Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GEPAT", "description": "GEPAT (Genome Expression Pathway Analysis Tool) is a modular, scalable and professional-grade software integrating analysis and interpretation of microarray gene expression data.", "homepage": "http://gepat.sourceforge.net/", "biotoolsID": "gepat", "biotoolsCURIE": "biotools:gepat", "version": [], "otherID": [ { "value": "RRID:SCR_003597", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3928", "term": "Pathway analysis" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2495", "term": "Microarray data analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Java" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/gepat-genome-expression-pathway-analysis-tool.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://gepat.sourceforge.net/documentation.htm", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-8-179", "pmid": "17543125", "pmcid": "PMC1896182", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Genome Expression Pathway Analysis Tool - Analysis and visualization of microarray gene expression data under genomic, proteomic and metabolic context", "abstract": "Background: Regulation of gene expression is relevant to many areas of biology and medicine, in the study of treatments, diseases, and developmental stages. Microarrays can be used to measure the expression level of thousands of mRNAs at the same time, allowing insight into or comparison of different cellular conditions. The data derived out of microarray experiments is highly dimensional and often noisy, and interpretation of the results can get intricate. Although programs for the statistical analysis of microarray data exist, most of them lack an integration of analysis results and biological interpretation. Results: We have developed GEPAT, Genome Expression Pathway Analysis Tool, offering an analysis of gene expression data under genomic, proteomic and metabolic context. We provide an integration of statistical methods for data import and data analysis together with a biological interpretation for subsets of probes or single probes on the chip. GEPAT imports various types of oligonucleotide and cDNA array data formats. Different normalization methods can be applied to the data, afterwards data annotation is performed. After import, GEPAT offers various statistical data analysis methods, as hierarchical, k-means and PCA clustering, a linear model based t-test or chromosomal profile comparison. The results of the analysis can be interpreted by enrichment of biological terms, pathway analysis or interaction networks. Different biological databases are included, to give various information for each probe on the chip. GEPAT offers no linear work flow, but allows the usage of any subset of probes and samples as a start for a new data analysis. GEPAT relies on established data analysis packages, offers a modular approach for an easy extension, and can be run on a computer grid to allow a large number of users. It is freely available under the LGPL open source license for academic and commercial users at http://gepat.sourceforge.net. Conclusion: GEPAT is a modular, scalable and professional-grade software integrating analysis and interpretation of microarray gene expression data. An installation available for academic users can be found at http://gepat.bioapps.biozentrum.uni-wuerzburg.de. © 2007 Weniger et al; licensee BioMed Central Ltd.", "date": "2007-06-02T00:00:00Z", "citationCount": 22, "authors": [ { "name": "Weniger M." }, { "name": "Engelmann J.C." }, { "name": "Schultz J." } ], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": null, "email": null, "url": "http://biozentrum.uni-wuerzburg.de/bioinformatik", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:06:45Z", "lastUpdate": "2024-11-24T20:35:58.528535Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "germ-line V genes", "description": "An integrative database of germ-line variable genes from the immunoglobulin loci of human and mouse. All variable gene sequences are extracted from the EMBL-Bank.", "homepage": "http://www.vbase2.org/", "biotoolsID": "germ-line_v_genes", "biotoolsCURIE": "biotools:germ-line_v_genes", "version": [], "otherID": [ { "value": "RRID:SCR_007082", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2835", "term": "Gene ID (VBASE2)" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" }, { "uri": "http://edamontology.org/topic_2815", "term": "Human biology" }, { "uri": "http://edamontology.org/topic_2830", "term": "Immunoproteins and antigens" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [ "DRCAT" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://www.vbase2.org/vbhelp.php", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gki088", "pmid": "15608286", "pmcid": "PMC540042", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "VBASE2, an integrative V gene database", "abstract": "The database VBASE2 provides germ-line sequences of human and mouse immunoglobulin variable (V) genes. It acts as an interconnecting platform between several existing self-contained data systems: VBASE2 integrates genome sequence data and links to the V genes in the Ensembl Genome Browser. For a single V gene sequence, all references to the EMBL nucleotide sequence database are provided, including references for V(D)J rearrangements. Furthermore, cross-references to the VBASE database, the IMGT database and the Kabat database are available. A DAS server allows the display of VBASE2 V genes within the Ensembl Genome Browser. VBASE2 can be accessed either by a web-based text query or by a sequence similarity search with the DNAPLOT software. VBASE2 is available at http://www.vbase2.org, and the DAS server is located at http://www.dnaplot.com/das. © Oxford University Press 2005; all rights reserved.", "date": "2005-01-01T00:00:00Z", "citationCount": 157, "authors": [ { "name": "Retter I." }, { "name": "Althaus H.H." }, { "name": "Munch R." }, { "name": "Muller W." } ], "journal": "Nucleic Acids Research" } } ], "credit": [ { "name": "DRCAT", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Project", "typeRole": [ "Documentor" ], "note": null }, { "name": null, "email": "info@vbase2.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "DRCAT", "additionDate": "2015-09-18T21:34:09Z", "lastUpdate": "2024-11-24T20:35:57.332952Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Gametogenesis and reproductive tissue expression", "description": "High-throughput expression data relevant for germline development and fertility across species.", "homepage": "http://www.germonline.org/", "biotoolsID": "germonline", "biotoolsCURIE": "biotools:germonline", "version": [], "otherID": [ { "value": "RRID:SCR_002807", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1026", "term": "Gene symbol" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0224", "term": "Query and retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1033", "term": "Ensembl gene ID" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0916", "term": "Gene report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0623", "term": "Gene and protein families" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [ "DRCAT" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.germonline.org/gol_4_userguide.pdf", "type": [ "Repository" ], "note": null } ], "download": [ { "url": "http://www.germonline.org/gol_4_userguide.pdf", "type": "Source code", "note": null, "version": null }, { "url": "http://www.germonline.org/gol_4_userguide.pdf", "type": "Binaries", "note": null, "version": null } ], "documentation": [ { "url": "http://www.germonline.org/gol_4_userguide.pdf", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/database/baq030", "pmid": "21149299", "pmcid": "PMC3004465", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "GermOnline 4.0 is a genomics gateway for germline development, meiosis and the mitotic cell cycle.", "abstract": "GermOnline 4.0 is a cross-species database portal focusing on high-throughput expression data relevant for germline development, the meiotic cell cycle and mitosis in healthy versus malignant cells. It is thus a source of information for life scientists as well as clinicians who are interested in gene expression and regulatory networks. The GermOnline gateway provides unlimited access to information produced with high-density oligonucleotide microarrays (3'-UTR GeneChips), genome-wide protein-DNA binding assays and protein-protein interaction studies in the context of Ensembl genome annotation. Samples used to produce high-throughput expression data and to carry out genome-wide in vivo DNA binding assays are annotated via the MIAME-compliant Multiomics Information Management and Annotation System (MIMAS 3.0). Furthermore, the Saccharomyces Genomics Viewer (SGV) was developed and integrated into the gateway. SGV is a visualization tool that outputs genome annotation and DNA-strand specific expression data produced with high-density oligonucleotide tiling microarrays (Sc_tlg GeneChips) which cover the complete budding yeast genome on both DNA strands. It facilitates the interpretation of expression levels and transcript structures determined for various cell types cultured under different growth and differentiation conditions. Database URL: www.germonline.org/", "date": "2010-01-01T00:00:00Z", "citationCount": 42, "authors": [ { "name": "Lardenois A." }, { "name": "Gattiker A." }, { "name": "Collin O." }, { "name": "Chalmel F." }, { "name": "Primig M." } ], "journal": "Database : the journal of biological databases and curation" } } ], "credit": [ { "name": "DRCAT", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Project", "typeRole": [ "Documentor" ], "note": null }, { "name": null, "email": "michael.primig@inserm.fr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "DRCAT", "additionDate": "2015-09-12T10:59:01Z", "lastUpdate": "2024-11-24T20:35:55.972418Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GFINDer", "description": "Characterize the different gene classes in the list using annotations of various types from several different sources.", "homepage": "http://www.medinfopoli.polimi.it/GFINDer/", "biotoolsID": "gfinder", "biotoolsCURIE": "biotools:gfinder", "version": [], "otherID": [ { "value": "RRID:SCR_008868", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3672", "term": "Gene functional annotation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1093/nar/gki454", "pmid": "15980570", "pmcid": "PMC1160215", "type": [], "version": null, "note": null, "metadata": { "title": "GFINDer: Genetic disease and phenotype location statistical analysis and mining of dynamically annotated gene lists", "abstract": "Phenotype analysis is commonly recognized to be of great importance for gaining insight into genetic interaction underlying inherited diseases. However, few computational contributions have been proposed for this purpose, mainly owing to lack of controlled clinical information easily accessible and structured for computational genome-wise analyses. We developed and made available through GFINDer web server an original approach for the analysis of genetic disorder related genes by exploiting the information on genetic diseases and their clinical phenotypes present in textual form within the Online Mendelian Inheritance in Man (OMIM) database. Because several synonyms for the same name and different names for overlapping concepts are often used in OMIM, we first normalized phenotype location descriptions reducing them to a list of unique controlled terms representing phenotype location categories. Then, we hierarchically structured them and the correspondent genetic diseases according to their topology and granularity of description, respectively. Thus, in GFINDer we could implement specific Genetic Disorders modules for the analysis of these structured data. Such modules allow to automatically annotate user-classified gene lists with updated disease and clinical information, classify them according to the genetic syndrome and the phenotypic location categories, and statistically identify the most relevant categories in each gene class. GFINDer is available for non-profit use at http://www.bioinformatics.polimi.it/GFINDer/. © 2005 Oxford University Press.", "date": "2005-07-01T00:00:00Z", "citationCount": 50, "authors": [ { "name": "Masseroli M." }, { "name": "Galati O." }, { "name": "Pinciroli F." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/gkh432", "pmid": "15215397", "pmcid": "PMC441570", "type": [], "version": null, "note": null, "metadata": { "title": "GFINDer: Genome Function INtegrated Discoverer through dynamic annotation, statistical analysis, and mining", "abstract": "Statistical and clustering analyses of gene expression results from high-density microarray experiments produce lists of hundreds of genes regulated differentially, or with particular expression profiles, in the conditions under study. Independent of the microarray platforms and analysis methods used, these lists must be biologically interpreted to gain a better knowledge of the patho-physiological phenomena involved. To this end, numerous biological annotations are available within heterogeneous and widely distributed databases. Although several tools have been developed for annotating lists of genes, most of them do not give methods for evaluating the relevance of the annotations provided, or for estimating the functional bias introduced by the gene set on the array used to identify the gene list considered. We developed Genome Functional INtegrated Discoverer (GFINDer), a web server able to automatically provide large-scale lists of user-classified genes with functional profiles biologically characterizing the different gene classes in the list. GFINDer automatically retrieves annotations of several functional categories from different sources, identifies the categories enriched in each class of a user-classified gene list and calculates statistical significance values for each category. Moreover, GFINDer enables the functional classification of genes according to mined functional categories and the statistical analysis is of the classifications obtained, aiding better interpretation of microarray experiment results. GFINDer is available online at http://www.medinfopoli.polimi.it/GFINDer/. © Oxford University Press 2004; all rights reserved.", "date": "2004-07-01T00:00:00Z", "citationCount": 61, "authors": [ { "name": "Masseroli M." }, { "name": "Martucci D." }, { "name": "Pinciroli F." } ], "journal": "Nucleic Acids Research" } } ], "credit": [], "owner": "ELIXIR-EE", "additionDate": "2017-02-10T11:35:50Z", "lastUpdate": "2024-11-24T20:35:53.663649Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GGB", "description": "The GGB (Gaggle Genome Browser) is an open source software tool for visualizing high-density data plotted against coordinates on the genome. Tiling arrays, ChIP-chip, and high-throughput sequencing are a few potential use-cases. The genome browser is designed to gracefully handle large datasets, allow easy import of user data, and interoperate with other bioinformatics tools through the Gaggle framework.", "homepage": "http://gaggle.systemsbiology.net/docs/geese/genomebrowser/", "biotoolsID": "ggb", "biotoolsCURIE": "biotools:ggb", "version": [ "1.0" ], "otherID": [ { "value": "RRID:SCR_011780", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3208", "term": "Genome browser" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Desktop application" ], "topic": [ { "uri": "http://edamontology.org/topic_3179", "term": "ChiP" }, { "uri": "http://edamontology.org/topic_3179", "term": "ChIP-chip" }, { "uri": "http://edamontology.org/topic_3070", "term": "Biology" }, { "uri": "http://edamontology.org/topic_2259", "term": "Systems biology" }, { "uri": "http://edamontology.org/topic_3179", "term": "ChIP-chip" }, { "uri": "http://edamontology.org/topic_3168", "term": "High-throughput sequencing" }, { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Java" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/ggb-1-0-visualization-systems-biology-data-context-genome.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://gaggle.systemsbiology.net/docs/geese/genomebrowser/help/start/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1186/1471-2105-11-382", "pmid": "20642854", "pmcid": "PMC2912892", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Integration and visualization of systems biology data in context of the genome", "abstract": "Background: High-density tiling arrays and new sequencing technologies are generating rapidly increasing volumes of transcriptome and protein-DNA interaction data. Visualization and exploration of this data is critical to understanding the regulatory logic encoded in the genome by which the cell dynamically affects its physiology and interacts with its environment.Results: The Gaggle Genome Browser is a cross-platform desktop program for interactively visualizing high-throughput data in the context of the genome. Important features include dynamic panning and zooming, keyword search and open interoperability through the Gaggle framework. Users may bookmark locations on the genome with descriptive annotations and share these bookmarks with other users. The program handles large sets of user-generated data using an in-process database and leverages the facilities of SQL and the R environment for importing and manipulating data.A key aspect of the Gaggle Genome Browser is interoperability. By connecting to the Gaggle framework, the genome browser joins a suite of interconnected bioinformatics tools for analysis and visualization with connectivity to major public repositories of sequences, interactions and pathways. To this flexible environment for exploring and combining data, the Gaggle Genome Browser adds the ability to visualize diverse types of data in relation to its coordinates on the genome.Conclusions: Genomic coordinates function as a common key by which disparate biological data types can be related to one another. In the Gaggle Genome Browser, heterogeneous data are joined by their location on the genome to create information-rich visualizations yielding insight into genome organization, transcription and its regulation and, ultimately, a better understanding of the mechanisms that enable the cell to dynamically respond to its environment. © 2010 Bare et al; licensee BioMed Central Ltd.", "date": "2010-07-19T00:00:00Z", "citationCount": 24, "authors": [ { "name": "Bare J.C." }, { "name": "Koide T." }, { "name": "Reiss D.J." }, { "name": "Tenenbaum D." }, { "name": "Baliga N.S." } ], "journal": "BMC Bioinformatics" } } ], "credit": [ { "name": null, "email": "nbaliga@systemsbiology.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-12-18T00:06:46Z", "lastUpdate": "2024-11-24T20:35:52.506984Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Gibbs Motif Sampler", "description": "Gibbs Motif Sampler allows you to identify motifs, conserved regions, in DNA or protein sequences. This tool can be applied for the detection of transcription factor binding sites (TFBS).", "homepage": "http://ccmbweb.ccv.brown.edu/gibbs/gibbs.html", "biotoolsID": "gibbs_motif_sampler", "biotoolsCURIE": "biotools:gibbs_motif_sampler", "version": [], "otherID": [ { "value": "RRID:SCR_002550", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0239", "term": "Sequence motif recognition" }, { "uri": "http://edamontology.org/operation_0445", "term": "Transcription factor binding site prediction" }, { "uri": "http://edamontology.org/operation_0438", "term": "Transcriptional regulatory element prediction" }, { "uri": "http://edamontology.org/operation_2238", "term": "Statistical calculation" } ], "input": [], "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_0160", "term": "Sequence sites, features and motifs" }, { "uri": "http://edamontology.org/topic_0203", "term": "Gene expression" }, { "uri": "http://edamontology.org/topic_0166", "term": "Protein structural motifs and surfaces" }, { "uri": "http://edamontology.org/topic_3511", "term": "Nucleic acid sites, features and motifs" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://ccmbweb.ccv.brown.edu/gibbs/bernoulli.html", "type": [ "User manual" ], "note": null }, { "url": "http://ccmbweb.ccv.brown.edu/gibbs/web_help_text.Gibbs_versions.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkg608", "pmid": "12824370", "pmcid": "PMC169014", "type": [], "version": null, "note": null, "metadata": { "title": "Gibbs Recursive Sampler: Finding transcription factor binding sites", "abstract": "The Gibbs Motif Sampler is a software package for locating common elements in collections of biopolymer sequences. In this paper we describe a new variation of the Gibbs Motif Sampler, the Gibbs Recursive Sampler, which has been developed specifically for locating multiple transcription factor binding sites for multiple transcription factors simultaneously in unaligned DNA sequences that may be heterogeneous in DNA composition. Here we describe the basic operation of the web-based version of this sampler. The sampler may be accessed at http://bayesweb.wadsworth.org/gibbs/gibbs.html and at http://www.bioinfo.rpi.edu/applications/bayesian/gibbs/gibbs.html. An online user guide is available at http://bayesweb.wadsworth.org/gibbs/bernoulli.html and at Solaris, Solaris.x86 and Linux versions of the sampler are available as stand-alone programs for academic and not-for-profit users. Commercial licenses are also available. The Gibbs Recursive Sampler is distributed in accordance with the ISCB level 0 guidelines and a requirement for citation of use in scientific publications.", "date": "2003-07-01T00:00:00Z", "citationCount": 248, "authors": [ { "name": "Thompson W." }, { "name": "Rouchka E.C." }, { "name": "Lawrence C.E." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1002/pro.5560040820", "pmid": "8520488", "pmcid": "PMC2143180", "type": [], "version": null, "note": null, "metadata": { "title": "Gibbs motif sampling: Detection of bacterial outer membrane protein repeats", "abstract": "The detection and alignment of locally conserved regions (motifs) in multiple sequences can provide insight into protein structure, function, and evolution. A new Gibbs sampling algorithm is described that detects motif‐encoding regions in sequences and optimally partitions them into distinct motif models; this is illustrated using a set of immunoglobulin fold proteins. When applied to sequences sharing a single motif, the sampler can be used to classify motif regions into related submodels, as is illustrated using helix‐turn‐helix DNA‐binding proteins. Other statistically based procedures are described for searching a database for sequences matching motifs found by the sampler. When applied to a set of 32 very distantly related bacterial integral outer membrane proteins, the sampler revealed that they share a subtle, repetitive motif. Although BLAST (Altschul SF et al., 1990, J Mol Biol 215:403–410) fails to detect significant pairwise similarity between any of the sequences, the repeats present in these outer membrane proteins, taken as a whole, are highly significant (based on a generally applicable statistical test for motifs described here). Analysis of bacterial porins with known trimeric β‐barrel structure and related proteins reveals a similar repetitive motif corresponding to alternating membrane‐spanning β‐strands. These β‐strands occur on the membrane interface (as opposed to the trimeric interface) of the β‐barrel. The broad conservation and structural location of these repeats suggests that they play important functional roles. Copyright © 1995 The Protein Society", "date": "1995-01-01T00:00:00Z", "citationCount": 332, "authors": [ { "name": "Neuwald A.F." }, { "name": "Liu J.S." }, { "name": "Lawrence C.E." } ], "journal": "Protein Science" } }, { "doi": "10.1093/nar/gkm265", "pmid": "17483517", "pmcid": "PMC1933196", "type": [], "version": null, "note": null, "metadata": { "title": "The gibbs centroid sampler", "abstract": "The Gibbs Centroid Sampler is a software package designed for locating conserved elements in biopolymer sequences. The Gibbs Centroid Sampler reports a centroid alignment, i.e. an alignment that has the minimum total distance to the set of samples chosen from the a posteriori probability distribution of transcription factor binding-site alignments. In so doing, it garners information from the full ensemble of solutions, rather than only the single most probable point that is the target of many motif-finding algorithms, including its predecessor, the Gibbs Recursive Sampler. Centroid estimators have been shown to yield substantial improvements, in both sensitivity and positive predictive values, to the prediction of RNA secondary structure and motif finding. The Gibbs Centroid Sampler, along with interactive tutorials, an online user manual, and information on downloading the software, is available at: http://bayesweb.wadsworth.org/gibbs/gibbs.html. © 2007 The Author(s).", "date": "2007-07-01T00:00:00Z", "citationCount": 53, "authors": [ { "name": "Thompson W.A." }, { "name": "Newberg L.A." }, { "name": "Conlan S." }, { "name": "McCue L.A." }, { "name": "Lawrence C.E." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1093/nar/29.3.774", "pmid": "11160901", "pmcid": "PMC30389", "type": [], "version": null, "note": null, "metadata": { "title": "Phylogenetic footprinting of transcription factor binding sites in proteobacterial genomes", "abstract": "Toward the goal of identifying complete sets of transcription factor (TF)-binding sites in the genomes of several gamma proteobacteria, and hence describing their transcription regulatory networks, we present a phylogenetic footprinting method for identifying these sites. Probable transcription regulatory sites upstream of Escherichia coli genes were identified by cross-species comparison using an extended Gibbs sampling algorithm. Close examination of a study set of 184 genes with documented transcription regulatory sites revelead that when orthologous data were available from at least two other gamma proteobacterial species, 81% of our predictions corresponded with the documented sites, and 67% corresponded when data from only one other species were available. That the remaining predictions included bona fide TF-binding sites was proven by affinity purification of a putative transcription factor (YijC) bound to such a site upstream of the fabA gene. Predicted regulatory sites for 2097 E.coli genes are available at http://www.wadsworth.org/ resnres/bioinfo/.", "date": "2001-02-01T00:00:00Z", "citationCount": 214, "authors": [ { "name": "McCue L.A." }, { "name": "Thompson W." }, { "name": "Carmack C.S." }, { "name": "Ryan M.P." }, { "name": "Liu J.S." }, { "name": "Derbyshire V." }, { "name": "Lawrence C.E." } ], "journal": "Nucleic Acids Research" } }, { "doi": "10.1126/science.8211139", "pmid": "8211139", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Detecting subtle sequence signals: A gibbs sampling strategy for multiple alignment", "abstract": "A wealth of protein and DNA sequence data is being generated by genome projects and other sequencing efforts. A crucial barrier to deciphering these sequences and understanding the relations among them is the difficulty of detecting subtle local residue patterns common to multiple sequences. Such patterns frequently reflect similar molecular structures and biological properties. A mathematical definition of this \"local multiple alignment\" problem suitable for full computer automation has been used to develop a new and sensitive algorithm, based on the statistical method of iterative sampling. This algorithm finds an optimized local alignment model for N sequences in N-linear time, requiring only seconds on current workstations, and allows the simultaneous detection and optimization of multiple patterns and pattern repeats. The method is illustrated as applied to helixturn-helix proteins, lipocalins, and prenyltransferases.", "date": "1993-01-01T00:00:00Z", "citationCount": 1471, "authors": [ { "name": "Lawrence C.E." }, { "name": "Altschul S.F." }, { "name": "Boguski M.S." }, { "name": "Liu J.S." }, { "name": "Neuwald A.F." }, { "name": "Wootton J.C." } ], "journal": "Science" } }, { "doi": "10.1038/79965", "pmid": "11017083", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Human-mouse genome comparisons to locate regulatory sites", "abstract": "Elucidating the human transcriptional regulatory network is a challenge of the post-genomic era. Technical progress so far is impressive, including detailed understanding of regulatory mechanisms for at least a few genes in multicellular organisms, rapid and precise localization of regulatory regions within extensive regions of DNA by means of cross-species comparison, and de novo determination of transcription-factor binding specificities from large-scale yeast expression data. Here we address two problems involved in extending these results to the human genome: first, it has been unclear how many model organism genomes will be needed to delineate most regulatory regions; and second, the discovery of transcription-factor binding sites (response elements) from expression data has not yet been generalized from single-celled organisms to multicellular organisms. We found that 98% (74/75) of experimentally defined sequence-specific binding sites of skeletal-muscle-specific transcription factors are confined to the 19% of human sequences that are most conserved in the orthologous rodent sequences. Also we found that in using this restriction, the binding specificities of all three major muscle-specific transcription factors (MYF, SRF and MEF2) can be computationally identified.", "date": "2000-10-01T00:00:00Z", "citationCount": 390, "authors": [ { "name": "Wasserman W.W." }, { "name": "Palumbo M." }, { "name": "Thompson W." }, { "name": "Fickett J.W." }, { "name": "Lawrence C.E." } ], "journal": "Nature Genetics" } }, { "doi": "10.1101/gr.2589004", "pmid": "15466295", "pmcid": "PMC524421", "type": [], "version": null, "note": null, "metadata": { "title": "Decoding human regulatory circuits", "abstract": "Clusters of transcription factor binding sites (TFBSs) which direct gene expression constitute cis-regulatory modules (CRMs). We present a novel algorithm, based on Gibbs sampling, which locates, de novo, the cis features of these CRMs, their component TFBSs, and the properties of their spatial distribution. The algorithm finds 69% of experimentally reported TFBSs and 85% of the CRMs in a reference data set of regions upstream of genes differentially expressed in skeletal muscle cells. A discriminant procedure based on the output of the model specifically discriminated regulatory sequences in muscle-specific genes in an independent test set. Application of the method to the analysis of 2710 10-kb fragments upstream of annotated human genes identified 17 novel candidate modules with a false discovery rate ≤0.05, demonstrating the applicability of the method to genome-scale data. © 2004 by Cold Spring Harbor Laboratory Press.", "date": "2004-10-01T00:00:00Z", "citationCount": 74, "authors": [ { "name": "Thompson W." }, { "name": "Palumbo M.J." }, { "name": "Wasserman W.W." }, { "name": "Liu J.S." }, { "name": "Lawrence C.E." } ], "journal": "Genome Research" } } ], "credit": [ { "name": "Gibbs Motif Sampler Team", "email": "gibbs@brown.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-EE", "additionDate": "2017-03-24T09:34:17Z", "lastUpdate": "2024-11-24T20:35:45.502825Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GLOBETROTTER", "description": "Identify, date and describe admixture events occurring in the ancestral history of a given target population within the last ~4,500 years.", "homepage": "http://paintmychromosomes.com/", "biotoolsID": "globetrotter", "biotoolsCURIE": "biotools:globetrotter", "version": [], "otherID": [ { "value": "RRID:SCR_018170", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3197", "term": "Genetic variation analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3056", "term": "Population genetics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "R" ], "license": "Not licensed", "collectionID": [ "Animal and Crop Genomics" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://paintmychromosomes.com/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1126/science.1243518", "pmid": "24531965", "pmcid": "PMC4209567", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "A genetic atlas of human admixture history", "abstract": "Modern genetic data combined with appropriate statistical methods have the potential to contribute substantially to our understanding of human history. We have developed an approach that exploits the genomic structure of admixed populations to date and characterize historical mixture events at fine scales. We used this to produce an atlas of worldwide human admixture history, constructed by using genetic data alone and encompassing over 100 events occurring over the past 4000 years. We identified events whose dates and participants suggest they describe genetic impacts of the Mongol empire, Arab slave trade, Bantu expansion, first millennium CE migrations in Eastern Europe, and European colonialism, as well as unrecorded events, revealing admixture to be an almost universal force shaping human populations.", "date": "2014-01-01T00:00:00Z", "citationCount": 536, "authors": [ { "name": "Hellenthal G." }, { "name": "Busby G.B.J." }, { "name": "Band G." }, { "name": "Wilson J.F." }, { "name": "Capelli C." }, { "name": "Falush D." }, { "name": "Myers S." } ], "journal": "Science" } } ], "credit": [ { "name": null, "email": "ghellenthal@gmail.com", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "admin", "additionDate": "2017-08-20T15:57:25Z", "lastUpdate": "2024-11-24T20:35:44.077875Z", "editPermission": { "type": "group", "authors": [ "animalandcropgenomics" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "GMcloser", "description": "Fill and close the gaps present in scaffold assemblies, especially those generated by the de novo assembly of whole genomes with next-generation sequencing (NGS) reads.", "homepage": "http://sourceforge.net/projects/gmcloser/", "biotoolsID": "gmcloser", "biotoolsCURIE": "biotools:gmcloser", "version": [], "otherID": [ { "value": "RRID:SCR_000646", "type": "rrid", "version": null } ], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3217", "term": "Scaffold gap completion" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0654", "term": "DNA" }, { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/gmcloser-gmvalue-closing-the-gaps-in-scaffolds-with-preassembled-contigs.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "https://sourceforge.net/projects/gmcloser/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btv465", "pmid": "26261222", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "GMcloser: Closing gaps in assemblies accurately with a likelihood-based selection of contig or long-read alignments", "abstract": "Motivation: Genome assemblies generated with next-generation sequencing (NGS) reads usually contain a number of gaps. Several tools have recently been developed to close the gaps in these assemblies with NGS reads. Although these gap-closing tools efficiently close the gaps, they entail a high rate of misassembly at gap-closing sites. Results: We have found that the assembly error rates caused by these tools are 20-500-fold higher than the rate of errors introduced into contigs by de novo assemblers. We here describe GMcloser, a tool that accurately closes these gaps with a preassembled contig set or a long read set (i.e. error-corrected PacBio reads). GMcloser uses likelihood-based classifiers calculated from the alignment statistics between scaffolds, contigs and paired-end reads to correctly assign contigs or long reads to gap regions of scaffolds, thereby achieving accurate and efficient gap closure. We demonstrate with sequencing data from various organisms that the gap-closing accuracy of GMcloser is 3-100-fold higher than those of other available tools, with similar efficiency.", "date": "2015-06-18T00:00:00Z", "citationCount": 66, "authors": [ { "name": "Kosugi S." }, { "name": "Hirakawa H." }, { "name": "Tabata S." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": null, "email": "shunichi.kosugi@riken.jp", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "mbs_import", "additionDate": "2017-08-03T18:44:27Z", "lastUpdate": "2024-11-24T20:35:42.996733Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null } ] }{ "count": 728, "next": "?page=2", "previous": null, "list": [ { "name": "PSIPRED", "description": "The PSIPRED Protein Analysis Workbench unites many available analysis tools into a single web based framework. An excellent tool for prediction of secondary structure, with access to GenTHREADER for protein fold recognition and MEMSAT-2 transmembrane topology prediction.", "homepage": "