Resource List
List all resources, or create a new resource.
GET /api/t?format=api
{ "count": 30491, "next": "?page=2", "previous": null, "list": [ { "name": "Abiotic", "description": "Pipeline for chemical exposome integration and analysis with biotic data", "homepage": "https://github.com/PimenoffV/Abiotic", "biotoolsID": "abiotic", "biotoolsCURIE": "biotools:abiotic", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-27T08:37:28.981121Z", "lastUpdate": "2025-06-27T08:37:28.983316Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "VIBE-UPAS", "description": "Visualisation of Integrated Biological Exposures from UPAS wearable devices", "homepage": "https://github.com/PimenoffV/VIBE", "biotoolsID": "vibe-upas", "biotoolsCURIE": "biotools:vibe-upas", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-27T08:34:59.189067Z", "lastUpdate": "2025-06-27T08:35:24.792249Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Metagenome Assenbly", "description": "Pipeline for parallel computing of improved metagenomic assembly using Spark-based computing and Hopsworks platform", "homepage": "https://github.com/HEAP-EXPOSOME/megahit-assembly", "biotoolsID": "metagenome_assenbly", "biotoolsCURIE": "biotools:metagenome_assenbly", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-27T08:30:35.923745Z", "lastUpdate": "2025-06-27T08:30:35.925952Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Biotic", "description": "Pipeline for taxonomic classification outperforming standard Kraken2 application, including control of false-positive detection of microbial taxa", "homepage": "https://github.com/PimenoffV/biotic", "biotoolsID": "biotic", "biotoolsCURIE": "biotools:biotic", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-27T08:23:47.715898Z", "lastUpdate": "2025-06-27T08:29:24.193702Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Biopipe", "description": "Pipeline for taxonomic classification of microbiome profiles and subsequent diversity analysis, suitable for both WGS and RNA-Seq. Bash and R scripts.", "homepage": "https://github.com/HEAP-EXPOSOME/biopipe", "biotoolsID": "biopipe", "biotoolsCURIE": "biotools:biopipe", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-27T08:21:56.744004Z", "lastUpdate": "2025-06-27T08:21:56.746222Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "KITE", "description": "A Java application aiming to detect any combination of microbe genomes selected to be detected from metagenome data", "homepage": "https://github.com/HEAP-EXPOSOME/KITE", "biotoolsID": "kite", "biotoolsCURIE": "biotools:kite", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-27T08:20:38.689434Z", "lastUpdate": "2025-06-27T08:20:46.074120Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "DALIA", "description": "DALIA promotes the learning and teaching of Data Literacy through the curated supply of open teaching and learning content, empowering everyone to collect, analyze, critically evaluate, and use data in a FAIR way.", "homepage": "https://search.dalia.education", "biotoolsID": "dalia", "biotoolsCURIE": "biotools:dalia", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [ "Web application", "Database portal", "SPARQL endpoint", "Web API" ], "topic": [ { "uri": "http://edamontology.org/topic_4012", "term": "FAIR data" }, { "uri": "http://edamontology.org/topic_3366", "term": "Data integration and warehousing" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": null, "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://git.rwth-aachen.de/dalia", "type": [ "Repository" ], "note": null }, { "url": "https://nfdi.social/@dalia", "type": [ "Social media" ], "note": null }, { "url": "https://bsky.app/profile/daliaeducation.bsky.social", "type": [ "Social media" ], "note": null }, { "url": "https://dalia.education/en/newsletter", "type": [ "Other" ], "note": "Newsletter" } ], "download": [], "documentation": [], "publication": [], "credit": [ { "name": "Sonja Herres-Pawlis", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0002-4354-4353", "gridid": null, "rorid": "04xfq0f34", "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "cthoyt", "additionDate": "2025-06-26T12:43:43.738614Z", "lastUpdate": "2025-06-26T13:20:18.702036Z", "editPermission": { "type": "group", "authors": [ "jortmeyer" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "The MINERVA Platform", "description": "The MINERVA (Molecular Interaction NEtwoRk VisuAlization) platform is a standalone webserver for visualization, exploration and management of molecular networks encoded in SBGN-compliant format, including files produced using CellDesigner or SBGN editors. Visualization of uploaded networks generated by the platform is accessible via a web browser to all viewers with the weblink to the resource.\n\nThe MINERVA Platform is a webservice using the Java Server Faces 2 technology. The server side, including data parsing, integration, annotation and verification, is implemented in Java. The platform uses the Postgres SQL database for data storage and the Hibernate framework as a middle layer between web server and database. The user web-interface is generated using React.js. The displayed content is visualized by OpenLayers API, dedicated JavaScript and CSS.", "homepage": "https://minerva.uni.lu", "biotoolsID": "MINERVA_Platform", "biotoolsCURIE": "biotools:MINERVA_Platform", "version": [ "13.1.3", "13.2.0", "14.0.13", "15.0.3", "16.4.0", "17.1.3", "18.1.1" ], "otherID": [], "relation": [ { "biotoolsID": "pathvisio", "type": "uses" }, { "biotoolsID": "sbgn", "type": "uses" }, { "biotoolsID": "libsbml", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3926", "term": "Pathway visualisation" } ], "input": [], "output": [], "note": "Visualise systems biology diagrams online, on a standalone web server", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0571", "term": "Expression data visualisation" } ], "input": [], "output": [], "note": "Visualise omics data from multiple datasets on top of the diagrams", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3434", "term": "Conversion" } ], "input": [], "output": [], "note": "Convert between main systems biology layout formats: CellDeslgners SBML, SBML layout+render, SBGN-ML, GPML", "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2426", "term": "Modelling and simulation" } ], "input": [], "output": [], "note": "Use MINERVA API to access systems biology formats for modelling", "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_0602", "term": "Molecular interactions, pathways and networks" }, { "uri": "http://edamontology.org/topic_3391", "term": "Omics" }, { "uri": "http://edamontology.org/topic_3342", "term": "Translational medicine" }, { "uri": "http://edamontology.org/topic_2259", "term": "Systems biology" } ], "operatingSystem": [], "language": [], "license": "AGPL-3.0", "collectionID": [ "ELIXIR-LU", "LCSB" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Tools" ], "elixirNode": [ "Luxembourg" ], "elixirCommunity": [], "link": [ { "url": "https://gitlab.lcsb.uni.lu/minerva/core/", "type": [ "Repository" ], "note": "GiLab repository for core functionalities (data and format handling, service stability, API access)" }, { "url": "https://gitlab.lcsb.uni.lu/minerva/core/-/issues", "type": [ "Issue tracker" ], "note": "Issue tracker for core functionalities (data and format handling, service stability, API access)" }, { "url": "https://gitlab.lcsb.uni.lu/minerva/frontend", "type": [ "Repository" ], "note": "GiLab repository for frontend functionalities" }, { "url": "https://gitlab.lcsb.uni.lu/minerva/frontend/-/issues", "type": [ "Issue tracker" ], "note": "Issue tracker for frontend functionalities" } ], "download": [ { "url": "https://minerva.pages.uni.lu/doc/install/", "type": "Other", "note": "Installation instructions, including debian package, virtual machine images and docker containers.", "version": "13.1.3 - 18.1.1" } ], "documentation": [ { "url": "https://minerva.uni.lu", "type": [ "Quick start guide", "Release notes", "User manual", "API documentation", "Citation instructions", "Terms of use" ], "note": null } ], "publication": [ { "doi": "10.1038/npjsba.2016.20", "pmid": "28725475", "pmcid": "PMC5516855", "type": [ "Primary" ], "version": "10.0", "note": null, "metadata": { "title": "MINERVA—A platform for visualization and curation of molecular interaction networks", "abstract": "Our growing knowledge about various molecular mechanisms is becoming increasingly more structured and accessible. Different repositories of molecular interactions and available literature enable construction of focused and high-quality molecular interaction networks. Novel tools for curation and exploration of such networks are needed, in order to foster the development of a systems biology environment. In particular, solutions for visualization, annotation and data cross-linking will facilitate usage of network-encoded knowledge in biomedical research. To this end we developed the MINERVA (Molecular Interaction NEtwoRks VisuAlization) platform, a standalone webservice supporting curation, annotation and visualization of molecular interaction networks in Systems Biology Graphical Notation (SBGN)-compliant format. MINERVA provides automated content annotation and verification for improved quality control. The end users can explore and interact with hosted networks, and provide direct feedback to content curators. MINERVA enables mapping drug targets or overlaying experimental data on the visualized networks. Extensive export functions enable downloading areas of the visualized networks as SBGN-compliant models for efficient reuse of hosted networks. The software is available under Affero GPL 3.0 as a Virtual Machine snapshot, Debian package and Docker instance at http://r3lab.uni.lu/web/minerva-website/. We believe that MINERVA is an important contribution to systems biology community, as its architecture enables set-up of locally or globally accessible SBGN-oriented repositories of molecular interaction networks. Its functionalities allow overlay of multiple information layers, facilitating exploration of content and interpretation of data. Moreover, annotation and verification workflows of MINERVA improve the efficiency of curation of networks, allowing life-science researchers to better engage in development and use of biomedical knowledge repositories.", "date": "2016-01-01T00:00:00Z", "citationCount": 65, "authors": [ { "name": "Gawron P." }, { "name": "Ostaszewski M." }, { "name": "Satagopam V." }, { "name": "Gebel S." }, { "name": "Mazein A." }, { "name": "Kuzma M." }, { "name": "Zorzan S." }, { "name": "McGee F." }, { "name": "Otjacques B." }, { "name": "Balling R." }, { "name": "Schneider R." } ], "journal": "npj Systems Biology and Applications" } }, { "doi": "10.1093/bioinformatics/btz286", "pmid": "31074494", "pmcid": "PMC6821317", "type": [ "Primary" ], "version": "12.2.3", "note": null, "metadata": { "title": "MINERVA API and plugins: Opening molecular network analysis and visualization to the community", "abstract": "Summary: The complexity of molecular networks makes them difficult to navigate and interpret, creating a need for specialized software. MINERVA is a web platform for visualization, exploration and management of molecular networks. Here, we introduce an extension to MINERVA architecture that greatly facilitates the access and use of the stored molecular network data. It allows to incorporate such data in analytical pipelines via a programmatic access interface, and to extend the platform's visual exploration and analytics functionality via plugin architecture. This is possible for any molecular network hosted by the MINERVA platform encoded in well-recognized systems biology formats. To showcase the possibilities of the plugin architecture, we have developed several plugins extending the MINERVA core functionalities. In the article, we demonstrate the plugins for interactive tree traversal of molecular networks, for enrichment analysis and for mapping and visualization of known disease variants or known adverse drug reactions to molecules in the network. Availability and implementation: Plugins developed and maintained by the MINERVA team are available under the AGPL v3 license at https://git-r3lab.uni.lu/minerva/plugins/. The MINERVA API and plugin documentation is available at https://minerva-web.lcsb.uni.lu.", "date": "2019-11-01T00:00:00Z", "citationCount": 25, "authors": [ { "name": "Hoksza D." }, { "name": "Gawron P." }, { "name": "Ostaszewski M." }, { "name": "Smula E." }, { "name": "Schneider R." } ], "journal": "Bioinformatics" } }, { "doi": "10.1093/bib/bbz067", "pmid": "31273380", "pmcid": "PMC7373180", "type": [ "Primary" ], "version": "13.1.1", "note": null, "metadata": { "title": "Closing the gap between formats for storing layout information in systems biology", "abstract": "The understanding of complex biological networks often relies on both a dedicated layout and a topology. Currently, there are three major competing layout-aware systems biology formats, but there are no software tools or software libraries supporting all of them. This complicates the management of molecular network layouts and hinders their reuse and extension. In this paper, we present a high-level overview of the layout formats in systems biology, focusing on their commonalities and differences, review their support in existing software tools, libraries and repositories and finally introduce a new conversion module within the MINERVA platform. The module is available via a REST API and offers, besides the ability to convert between layout-aware systems biology formats, the possibility to export layouts into several graphical formats. The module enables conversion of very large networks with thousands of elements, such as disease maps or metabolic reconstructions, rendering it widely applicable in systems biology.", "date": "2019-07-10T00:00:00Z", "citationCount": 17, "authors": [ { "name": "Hoksza D." }, { "name": "Gawron P." }, { "name": "Ostaszewski M." }, { "name": "Hasenauer J." }, { "name": "Schneider R." } ], "journal": "Briefings in Bioinformatics" } }, { "doi": "10.1089/big.2015.0057", "pmid": "27441714", "pmcid": "PMC4932659", "type": [ "Usage" ], "version": "10.0", "note": null, "metadata": { "title": "Integration and Visualization of Translational Medicine Data for Better Understanding of Human Diseases", "abstract": "Translational medicine is a domain turning results of basic life science research into new tools and methods in a clinical environment, for example, as new diagnostics or therapies. Nowadays, the process of translation is supported by large amounts of heterogeneous data ranging from medical data to a whole range of -omics data. It is not only a great opportunity but also a great challenge, as translational medicine big data is difficult to integrate and analyze, and requires the involvement of biomedical experts for the data processing. We show here that visualization and interoperable workflows, combining multiple complex steps, can address at least parts of the challenge. In this article, we present an integrated workflow for exploring, analysis, and interpretation of translational medicine data in the context of human health. Three Web services - tranSMART, a Galaxy Server, and a MINERVA platform - are combined into one big data pipeline. Native visualization capabilities enable the biomedical experts to get a comprehensive overview and control over separate steps of the workflow. The capabilities of tranSMART enable a flexible filtering of multidimensional integrated data sets to create subsets suitable for downstream processing. A Galaxy Server offers visually aided construction of analytical pipelines, with the use of existing or custom components. A MINERVA platform supports the exploration of health and disease-related mechanisms in a contextualized analytical visualization system. We demonstrate the utility of our workflow by illustrating its subsequent steps using an existing data set, for which we propose a filtering scheme, an analytical pipeline, and a corresponding visualization of analytical results. The workflow is available as a sandbox environment, where readers can work with the described setup themselves. Overall, our work shows how visualization and interfacing of big data processing services facilitate exploration, analysis, and interpretation of translational medicine data.", "date": "2016-06-01T00:00:00Z", "citationCount": 39, "authors": [ { "name": "Satagopam V." }, { "name": "Gu W." }, { "name": "Eifes S." }, { "name": "Gawron P." }, { "name": "Ostaszewski M." }, { "name": "Gebel S." }, { "name": "Barbosa-Silva A." }, { "name": "Balling R." }, { "name": "Schneider R." } ], "journal": "Big Data" } }, { "doi": "10.1016/j.envpol.2019.04.005", "pmid": "30991279", "pmcid": null, "type": [], "version": "13.1.1", "note": null, "metadata": { "title": "Genes associated with Parkinson's disease respond to increasing polychlorinated biphenyl levels in the blood of healthy females", "abstract": "Polychlorinated biphenyls (PCBs) are a class of widespread environmental pollutants, commonly found in human blood, that have been suggested to be linked to the occurrence of sporadic Parkinson's disease (PD). It has been reported that some non-coplanar PCBs accumulate in the brains of female PD patients. To improve our understanding of the association between PCB exposure and PD risk we have applied whole transcriptome gene expression analysis in blood cells from 594 PCB-exposed subjects (369 female, 225 male). Interestingly, we observe that in females, blood levels of non-coplanar PCBs appear to be associated with expression levels of PD-specific genes. However, no such association was detected in males. Among the 131 PD-specific genes affected, 39 have been shown to display similar changes in expression levels in the substantia nigra of deceased PD patients. Especially among the down-regulated genes, transcripts of genes involved in neurotransmitter vesicle-related functions were predominant. Capsule: Plasma PCB levels are associated with gene expression changes in females only, resulting in brain-related genes changing in blood cells of healthy individuals exposed to PCBs.", "date": "2019-07-01T00:00:00Z", "citationCount": 5, "authors": [ { "name": "Bohler S." }, { "name": "Krauskopf J." }, { "name": "Espin-Perez A." }, { "name": "Gebel S." }, { "name": "Palli D." }, { "name": "Rantakokko P." }, { "name": "Kiviranta H." }, { "name": "Kyrtopoulos S.A." }, { "name": "Balling R." }, { "name": "Kleinjans J." } ], "journal": "Environmental Pollution" } } ], "credit": [], "owner": "mjostaszewski", "additionDate": "2019-08-26T14:34:55Z", "lastUpdate": "2025-06-26T13:15:59.673112Z", "editPermission": { "type": "group", "authors": [ "sascha.herzinger" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "FANTASIAV2", "description": "FANTASIA (Functional ANnoTAtion based on embedding space SImilArity) is a pipeline for protein annotating via GO term transference using the embedding space. FANTASIA’s latest developments include additional protein language models and provide enhanced functionalities.", "homepage": "https://github.com/CBBIO/FANTASIA", "biotoolsID": "fantasiav2", "biotoolsCURIE": "biotools:fantasiav2", "version": [ "2.8.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3672", "term": "Gene functional annotation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3945", "term": "Molecular evolution" }, { "uri": "http://edamontology.org/topic_0218", "term": "Natural language processing" }, { "uri": "http://edamontology.org/topic_0085", "term": "Functional genomics" }, { "uri": "http://edamontology.org/topic_4010", "term": "Open science" } ], "operatingSystem": [ "Linux" ], "language": [ "Python", "SQL" ], "license": "MIT", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [ "Tools" ], "elixirNode": [ "Spain" ], "elixirCommunity": [ "3D-BioInfo", "Proteomics" ], "link": [ { "url": "https://github.com/CBBIO/FANTASIA", "type": [ "Repository" ], "note": "Main repository contains documentation from latest version" }, { "url": "https://github.com/MetazoaPhylogenomicsLab/FANTASIA", "type": [ "Repository" ], "note": "Main repository contains documentation from linitial version based on Bioembeddings implementation." }, { "url": "https://www.earthbiogenome.org/report-on-annotation-recommended-tools", "type": [ "Software catalogue" ], "note": "Recommended tool for the Earth Biogenome Project" } ], "download": [], "documentation": [ { "url": "https://fantasia.readthedocs.io/en/latest/", "type": [ "General" ], "note": "Full documetnation with user cases, benchmarking, and cluster implementations" } ], "publication": [ { "doi": "10.1093/nargab/lqae078", "pmid": null, "pmcid": null, "type": [ "Usage" ], "version": null, "note": null, "metadata": { "title": "Decoding functional proteome information in model organisms using protein language models", "abstract": "Protein language models have been tested and proved to be reliable when used on curated datasets but have not yet been applied to full proteomes. Accordingly, we tested how two different machine learning-based methods performed when decoding functional information from the proteomes of selected model organisms. We found that protein language models are more precise and informative than deep learning methods for all the species tested and across the three gene ontologies studied, and that they better recover functional information from transcriptomic experiments. The results obtained indicate that these language models are likely to be suitable for large-scale annotation and downstream analyses, and we recommend a guide for their use.", "date": "2024-09-01T00:00:00Z", "citationCount": 1, "authors": [ { "name": "Barrios-Nunez I." }, { "name": "Martinez-Redondo G.I." }, { "name": "Medina-Burgos P." }, { "name": "Cases I." }, { "name": "Fernandez R." }, { "name": "Rojas A.M." } ], "journal": "NAR Genomics and Bioinformatics" } }, { "doi": "10.1101/2024.02.28.582465", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Francisco Miguel Pérez Canales", "email": "fmpercan@upo.es", "url": "http://www.bioinfocb.es/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Developer", "Documentor", "Maintainer", "Support", "Provider" ], "note": "Programmer" }, { "name": "Ana M Rojas Mendoza", "email": "a.rojas.m@csic.es", "url": "http://www.bioinfocb.es/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact", "Contributor", "Documentor", "Support" ], "note": "Scientific concept and functionalities" }, { "name": "Rosa Fernandez", "email": "rosa.fernandez@ibe.upf-csic.es", "url": "https://www.metazomics.com/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Contributor", "Documentor" ], "note": "Scientific concept and functionalities" }, { "name": "Francisco J. Ruiz Mota", "email": "fraruimot@alum.us.es", "url": "http://www.bioinfocb.es/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": "Junior developer" }, { "name": "Gemma Martinez Redondo", "email": "gemma.martinez@ibe.upf-csic.es", "url": "https://www.metazomics.com/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Contributor", "Developer" ], "note": "Contributed as developer of the first version of FANTASIA V1" } ], "owner": "arojas", "additionDate": "2025-06-25T13:31:29.384393Z", "lastUpdate": "2025-06-25T14:34:50.629045Z", "editPermission": { "type": "group", "authors": [ "frapercan" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "CoreProfiler", "description": "CoreProfiler is a cgMLST (core genome multilocus sequence typing) software that identifies alleles in bacterial genome assemblies by comparing them to a reference allele scheme. It detects both exact matches to known alleles and potential novel alleles using a two-step BLAST-based approach, enabling robust and reproducible strain genotyping.", "homepage": "https://gitlab.com/ifb-elixirfr/abromics/coreprofiler", "biotoolsID": "coreprofiler", "biotoolsCURIE": "biotools:coreprofiler", "version": [ "1.1.1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3840", "term": "Multilocus sequence typing" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" }, { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" }, { "uri": "http://edamontology.org/topic_3293", "term": "Phylogenetics" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://gitlab.com/ifb-elixirfr/abromics/coreprofiler/-/blob/main/README.md?ref_type=heads", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.5281/ZENODO.8282656", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null }, { "doi": "10.1016/S0022-2836(05)80360-2", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Basic local alignment search tool", "abstract": "A new approach to rapid sequence comparison, basic local alignment search tool (BLAST), directly approximates alignments that optimize a measure of local similarity, the maximal segment pair (MSP) score. Recent mathematical results on the stochastic properties of MSP scores allow an analysis of the performance of this method as well as the statistical significance of alignments it generates. The basic algorithm is simple and robust; it can be implemented in a number of ways and applied in a variety of contexts including straight-forward DNA and protein sequence database searches, motif searches, gene identification searches, and in the analysis of multiple regions of similarity in long DNA sequences. In addition to its flexibility and tractability to mathematical analysis, BLAST is an order of magnitude faster than existing sequence comparison tools of comparable sensitivity. © 1990, Academic Press Limited. All rights reserved.", "date": "1990-01-01T00:00:00Z", "citationCount": 80157, "authors": [ { "name": "Altschul S.F." }, { "name": "Gish W." }, { "name": "Miller W." }, { "name": "Myers E.W." }, { "name": "Lipman D.J." } ], "journal": "Journal of Molecular Biology" } } ], "credit": [], "owner": "clsiguret", "additionDate": "2025-04-08T08:17:22.895529Z", "lastUpdate": "2025-06-25T07:31:27.919999Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Hopsworks", "description": "Data-Intensive AI platform with a Feature Store. Open-source PaaS for distributed data management, data analysis, and machine learning based on Hopsworks: \nhttps://www.hopsworks.ai/\nhttps://docs.hopsworks.ai/latest/\nDeployed at CSC– IT Center for Science: https://heap-hopsworks.csc.fi/login", "homepage": "https://github.com/HEAP-EXPOSOME/hopsworks", "biotoolsID": "heap-hopsworks", "biotoolsCURIE": "biotools:heap-hopsworks", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-12T12:27:05.542308Z", "lastUpdate": "2025-06-21T19:17:05.018729Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Cytoscape Web", "description": "An online implementation of Cytoscape Desktop that captures its interface and key visualization functionality while providing integration with web tools and databases.", "homepage": "https://web.cytoscape.org/", "biotoolsID": "cytoscape_web", "biotoolsCURIE": "biotools:cytoscape_web", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_1812", "term": "Loading" }, { "uri": "http://edamontology.org/operation_0276", "term": "Protein interaction network analysis" }, { "uri": "http://edamontology.org/operation_0277", "term": "Pathway or network comparison" }, { "uri": "http://edamontology.org/operation_3083", "term": "Pathway or network visualisation" }, { "uri": "http://edamontology.org/operation_3439", "term": "Pathway or network prediction" } ], "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_0128", "term": "Protein interactions" }, { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" }, { "uri": "http://edamontology.org/topic_3382", "term": "Imaging" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "JavaScript" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://cytoscape-web.readthedocs.io/en/latest/", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/nar/gkaf365", "pmid": "40308211", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Gary D. Bader", "email": "gary.bader@utoronto.ca", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "garybader", "additionDate": "2017-04-21T12:12:09Z", "lastUpdate": "2025-06-19T13:28:13.117454Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "DeepSig", "description": "Prediction of secretory signal peptides in protein sequences", "homepage": "https://busca.biocomp.unibo.it/deepsig/", "biotoolsID": "deepsig", "biotoolsCURIE": "biotools:deepsig", "version": [ "1.2.5" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0418", "term": "Protein signal peptide detection" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2974", "term": "Protein sequence (raw)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] }, { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_2330", "term": "Textual format" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0896", "term": "Protein report" }, "format": [ { "uri": "http://edamontology.org/format_2331", "term": "HTML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Web application", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3307", "term": "Computational biology" }, { "uri": "http://edamontology.org/topic_3510", "term": "Protein sites, features and motifs" }, { "uri": "http://edamontology.org/topic_0123", "term": "Protein properties" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Python", "C++" ], "license": "GPL-3.0", "collectionID": [ "Bologna Biocomputing Group" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "Italy" ], "elixirCommunity": [], "link": [], "download": [ { "url": "https://github.com/BolognaBiocomp/deepsig", "type": "Source code", "note": null, "version": "1.2.5" }, { "url": "https://hub.docker.com/r/bolognabiocomp/deepsig", "type": "Container file", "note": null, "version": "1.2.5" } ], "documentation": [ { "url": "https://github.com/BolognaBiocomp/deepsig", "type": [ "Command-line options" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btx818", "pmid": "29280997", "pmcid": "PMC5946842", "type": [ "Primary" ], "version": "1.0", "note": null, "metadata": { "title": "DeepSig: Deep learning improves signal peptide detection in proteins", "abstract": "Motivation The identification of signal peptides in protein sequences is an important step toward protein localization and function characterization. Results Here, we present DeepSig, an improved approach for signal peptide detection and cleavage-site prediction based on deep learning methods. Comparative benchmarks performed on an updated independent dataset of proteins show that DeepSig is the current best performing method, scoring better than other available state-of-the-art approaches on both signal peptide detection and precise cleavage-site identification. Availability and implementation DeepSig is available as both standalone program and web server at https://deepsig.biocomp.unibo.it. All datasets used in this study can be obtained from the same website.", "date": "2018-05-15T00:00:00Z", "citationCount": 96, "authors": [ { "name": "Savojardo C." }, { "name": "Martelli P.L." }, { "name": "Fariselli P." }, { "name": "Casadio R." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "ELIXIR-ITA-BOLOGNA", "email": null, "url": "http://biocomp.unibo.it", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Castrense Savojardo", "email": "castrense.savojardo2@unibo.it", "url": null, "orcidid": "https://orcid.org/0000-0002-7359-0633", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Primary contact" ], "note": null }, { "name": "Pier Luigi Martelli", "email": "pierluigi.martelli@unibo.it", "url": "http://biocomp.unibo.it", "orcidid": "https://orcid.org/0000-0002-0274-5669", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "ELIXIR-ITA-BOLOGNA", "additionDate": "2018-05-28T14:50:09Z", "lastUpdate": "2025-06-19T11:55:09.017105Z", "editPermission": { "type": "group", "authors": [ "savo", "ELIXIR-ITA-BOLOGNA" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "Breast Dense Tissue Segmentation", "description": "The tool takes a digital mammogram and performs an automatic segmentation of the breast area and the dense tissue. After the mammogram segmentation, the tool returns a DICOM-SEG image with both the dense tissue and the breast tissue mask combined.", "homepage": "https://pubmed.ncbi.nlm.nih.gov/36010173/", "biotoolsID": "breast_dense_tissue_segmentation", "biotoolsCURIE": "biotools:breast_dense_tissue_segmentation", "version": [ "v1.0.6" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3553", "term": "Image annotation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3382", "term": "Imaging" }, { "uri": "http://edamontology.org/topic_3384", "term": "Medical imaging" } ], "operatingSystem": [], "language": [], "license": "Proprietary", "collectionID": [ "EUCAIM" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.3390/diagnostics12081822", "pmid": "36010173", "pmcid": "PMC9406546", "type": [], "version": null, "note": null, "metadata": { "title": "Breast Dense Tissue Segmentation with Noisy Labels: A Hybrid Threshold-Based and Mask-Based Approach", "abstract": "Breast density assessed from digital mammograms is a known biomarker related to a higher risk of developing breast cancer. Supervised learning algorithms have been implemented to determine this. However, the performance of these algorithms depends on the quality of the ground-truth information, which expert readers usually provide. These expert labels are noisy approximations to the ground truth, as there is both intra- and inter-observer variability among them. Thus, it is crucial to provide a reliable method to measure breast density from mammograms. This paper presents a fully automated method based on deep learning to estimate breast density, including breast detection, pectoral muscle exclusion, and dense tissue segmentation. We propose a novel confusion matrix (CM)—YNet model for the segmentation step. This architecture includes networks to model each radiologist’s noisy label and gives the estimated ground-truth segmentation as well as two parameters that allow interaction with a threshold-based labeling tool. A multi-center study involving 1785 women whose “for presentation” mammograms were obtained from 11 different medical facilities was performed. A total of 2496 mammograms were used as the training corpus, and 844 formed the testing corpus. Additionally, we included a totally independent dataset from a different center, composed of 381 women with one image per patient. Each mammogram was labeled independently by two expert radiologists using a threshold-based tool. The implemented CM-Ynet model achieved the highest DICE score averaged over both test datasets (0.82 ± 0.14) when compared to the closest dense-tissue segmentation assessment from both radiologists. The level of concordance between the two radiologists showed a DICE score of (0.76 ± 0.17). An automatic breast density estimator based on deep learning exhibited higher performance when compared with two experienced radiologists. This suggests that modeling each radiologist’s label allows for better estimation of the unknown ground-truth segmentation. The advantage of the proposed model is that it also provides the threshold parameters that enable user interaction with a threshold-based tool.", "date": "2022-08-01T00:00:00Z", "citationCount": 5, "authors": [ { "name": "Larroza A." }, { "name": "Perez-Benito F.J." }, { "name": "Perez-Cortes J.-C." }, { "name": "Roman M." }, { "name": "Pollan M." }, { "name": "Perez-Gomez B." }, { "name": "Salas-Trejo D." }, { "name": "Casals M." }, { "name": "Llobet R." } ], "journal": "Diagnostics" } } ], "credit": [], "owner": "dsilveira", "additionDate": "2025-05-22T12:06:46.866961Z", "lastUpdate": "2025-06-19T06:23:14.022250Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "EAPP - Extended a Priori Probability tool", "description": "The tool provides a semi-supervised metric (EAPP) for binary classification tasks that considers not only the a priori probability but also some possible bias present in the dataset, as well as other features that could provide a relatively trivial separability of the target classes. Therefore, it allows for evaluating the ease or complexity of the task or bias of the data beyond the well-established baseline for any binary classification.", "homepage": "https://ieeexplore.ieee.org/document/9950248", "biotoolsID": "extended_a_priori_probability_tool", "biotoolsCURIE": "biotools:extended_a_priori_probability_tool", "version": [ "v1.0.1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2945", "term": "Data analysis" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3443", "term": "Image analysis" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3474", "term": "Machine learning" }, { "uri": "http://edamontology.org/topic_2269", "term": "Statistics and probability" } ], "operatingSystem": [], "language": [], "license": "Proprietary", "collectionID": [ "EUCAIM" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1109/ACCESS.2022.3221936", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Extended a Priori Probability (EAPP): A Data-Driven Approach for Machine Learning Binary Classification Tasks", "abstract": "The a priori probability of a dataset is usually used as a baseline for comparing a particular algorithm's accuracy in a given binary classification task. ZeroR is the simplest algorithm for this, predicting the majority class for all examples. However, this is an extremely simple approach that has no predictive power and does not describe other dataset features that could lead to a more demanding baseline. In this paper, we present the Extended A Priori Probability (EAPP), a novel semi-supervised baseline metric for binary classification tasks that considers not only the a priori probability but also some possible bias present in the dataset as well as other features that could provide a relatively trivial separability of the target classes. The approach is based on the area under the ROC curve (AUC ROC), known to be quite insensitive to class imbalance. The procedure involves multiobjective feature extraction and a clustering stage in the input space with autoencoders and a subsequent combinatory weighted assignation from clusters to classes depending on the distance to nearest clusters for each class. Class labels are then assigned to establish the combination that maximizes AUC ROC for each number of clusters considered. To avoid overfit in the combined feature extraction and clustering method, a cross-validation scheme is performed in each case. EAPP is defined for different numbers of clusters, starting from the inverse of the minority class proportion, which is useful for a fair comparison among diversely imbalanced datasets. A high EAPP usually relates to an easy binary classification task, but it also may be due to a significant coarse-grained bias in the dataset, when the task is previously known to be difficult. This metric represents a baseline beyond the a priori probability to assess the actual capabilities of binary classification models.", "date": "2022-01-01T00:00:00Z", "citationCount": 0, "authors": [ { "name": "Castello V.O." }, { "name": "Perez-Benito F.J." }, { "name": "Catala O.D.T." }, { "name": "Igual I.S." }, { "name": "Llobet R." }, { "name": "Perez-Cortes J.-C." } ], "journal": "IEEE Access" } } ], "credit": [], "owner": "dsilveira", "additionDate": "2025-05-22T14:58:20.772120Z", "lastUpdate": "2025-06-19T06:22:40.072300Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "QIIME 2", "description": "QIIME 2 is an AI-ready microbiome multi-omics data science platform that is trusted, free, open source, extensible, and community developed and supported bioinformatics.", "homepage": "https://qiime2.org", "biotoolsID": "qiime2", "biotoolsCURIE": "biotools:qiime2", "version": [ "2.0" ], "otherID": [], "relation": [ { "biotoolsID": "qiime", "type": "isNewVersionOf" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3933", "term": "Demultiplexing" }, { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Suite", "Command-line tool", "Library" ], "topic": [ { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" }, { "uri": "http://edamontology.org/topic_3941", "term": "Metatranscriptomics" }, { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "Python" ], "license": "BSD-3-Clause", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [ "Galaxy" ], "link": [ { "url": "https://github.com/qiime2", "type": [ "Repository" ], "note": null }, { "url": "https://library.qiime2.org", "type": [ "Software catalogue" ], "note": null }, { "url": "https://forum.qiime2.org", "type": [ "Discussion forum" ], "note": null }, { "url": "https://view.qiime2.org", "type": [ "Other" ], "note": "Site for viewing and interacting with QIIME 2 results." } ], "download": [], "documentation": [ { "url": "https://amplicon-docs.qiime2.org", "type": [ "General" ], "note": "User documentation for amplicon analysis, oriented to new users." }, { "url": "https://moshpit.qiime2.org", "type": [ "Installation instructions" ], "note": "User documentation for metagenome analysis, oriented to new users." }, { "url": "https://use.qiime2.org", "type": [ "User manual" ], "note": "User documentation, oriented toward power users." }, { "url": "https://develop.qiime2.org", "type": [ "API documentation" ], "note": "Developer documentation, including a plugin development tutorial." }, { "url": "https://library.qiime2.org/books", "type": [ "Other" ], "note": "The QIIME 2 Library Stacks: a resource for discovering relevant documentation." } ], "publication": [ { "doi": "10.1038/s41587-019-0209-9", "pmid": "31341288", "pmcid": "PMC7015180", "type": [ "Primary" ], "version": "2.0", "note": null, "metadata": { "title": "Reproducible, interactive, scalable and extensible microbiome data science using QIIME 2", "abstract": "", "date": "2019-08-01T00:00:00Z", "citationCount": 14289, "authors": [ { "name": "Bolyen E." }, { "name": "Rideout J.R." }, { "name": "Dillon M.R." }, { "name": "Bokulich N.A." }, { "name": "Abnet C.C." }, { "name": "Al-Ghalith G.A." }, { "name": "Alexander H." }, { "name": "Alm E.J." }, { "name": "Arumugam M." }, { "name": "Asnicar F." }, { "name": "Bai Y." }, { "name": "Bisanz J.E." }, { "name": "Bittinger K." }, { "name": "Brejnrod A." }, { "name": "Brislawn C.J." }, { "name": "Brown C.T." }, { "name": "Callahan B.J." }, { "name": "Caraballo-Rodriguez A.M." }, { "name": "Chase J." }, { "name": "Cope E.K." }, { "name": "Da Silva R." }, { "name": "Diener C." }, { "name": "Dorrestein P.C." }, { "name": "Douglas G.M." }, { "name": "Durall D.M." }, { "name": "Duvallet C." }, { "name": "Edwardson C.F." }, { "name": "Ernst M." }, { "name": "Estaki M." }, { "name": "Fouquier J." }, { "name": "Gauglitz J.M." }, { "name": "Gibbons S.M." }, { "name": "Gibson D.L." }, { "name": "Gonzalez A." }, { "name": "Gorlick K." }, { "name": "Guo J." }, { "name": "Hillmann B." }, { "name": "Holmes S." }, { "name": "Holste H." }, { "name": "Huttenhower C." }, { "name": "Huttley G.A." }, { "name": "Janssen S." }, { "name": "Jarmusch A.K." }, { "name": "Jiang L." }, { "name": "Kaehler B.D." }, { "name": "Kang K.B." }, { "name": "Keefe C.R." }, { "name": "Keim P." }, { "name": "Kelley S.T." }, { "name": "Knights D." }, { "name": "Koester I." }, { "name": "Kosciolek T." }, { "name": "Kreps J." }, { "name": "Langille M.G.I." }, { "name": "Lee J." }, { "name": "Ley R." }, { "name": "Liu Y.-X." }, { "name": "Loftfield E." }, { "name": "Lozupone C." }, { "name": "Maher M." }, { "name": "Marotz C." }, { "name": "Martin B.D." }, { "name": "McDonald D." }, { "name": "McIver L.J." }, { "name": "Melnik A.V." }, { "name": "Metcalf J.L." }, { "name": "Morgan S.C." }, { "name": "Morton J.T." }, { "name": "Naimey A.T." }, { "name": "Navas-Molina J.A." }, { "name": "Nothias L.F." }, { "name": "Orchanian S.B." }, { "name": "Pearson T." }, { "name": "Peoples S.L." }, { "name": "Petras D." }, { "name": "Preuss M.L." }, { "name": "Pruesse E." }, { "name": "Rasmussen L.B." }, { "name": "Rivers A." }, { "name": "Robeson M.S." }, { "name": "Rosenthal P." }, { "name": "Segata N." }, { "name": "Shaffer M." }, { "name": "Shiffer A." }, { "name": "Sinha R." }, { "name": "Song S.J." }, { "name": "Spear J.R." }, { "name": "Swafford A.D." }, { "name": "Thompson L.R." }, { "name": "Torres P.J." }, { "name": "Trinh P." }, { "name": "Tripathi A." }, { "name": "Turnbaugh P.J." }, { "name": "Ul-Hasan S." }, { "name": "van der Hooft J.J.J." }, { "name": "Vargas F." }, { "name": "Vazquez-Baeza Y." }, { "name": "Vogtmann E." }, { "name": "von Hippel M." }, { "name": "Walters W." }, { "name": "Wan Y." }, { "name": "Wang M." }, { "name": "Warren J." }, { "name": "Weber K.C." }, { "name": "Williamson C.H.D." }, { "name": "Willis A.D." }, { "name": "Xu Z.Z." }, { "name": "Zaneveld J.R." }, { "name": "Zhang Y." }, { "name": "Zhu Q." }, { "name": "Knight R." }, { "name": "Caporaso J.G." } ], "journal": "Nature Biotechnology" } } ], "credit": [ { "name": "Greg Caporaso", "email": "greg.caporaso@nau.edu", "url": "https://cap-lab.bio", "orcidid": "https://orcid.org/0000-0002-8865-1670", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Primary contact" ], "note": null } ], "owner": "gregcaporaso", "additionDate": "2021-05-27T09:02:10Z", "lastUpdate": "2025-06-18T21:00:46.185472Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "MetaSBT", "description": "MetaSBT is a scalable framework designed to automatically index microbial genomes and accurately characterize metagenome-assembled genomes using Sequence Bloom Trees.", "homepage": "https://github.com/cumbof/MetaSBT", "biotoolsID": "metasbt", "biotoolsCURIE": "biotools:metasbt", "version": [ "0.1.4.post1" ], "otherID": [], "relation": [], "function": [], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": "MIT", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/cumbof/MetaSBT", "type": [ "Repository" ], "note": "Framework Repository" }, { "url": "https://github.com/cumbof/MetaSBT-DBs", "type": [ "Repository" ], "note": "Repository with Public MetaSBT Databases" } ], "download": [ { "url": "https://pypi.io/packages/source/m/metasbt/metasbt-0.1.4.post1.tar.gz", "type": "Software package", "note": null, "version": "0.1.4" } ], "documentation": [ { "url": "https://github.com/cumbof/MetaSBT/wiki", "type": [ "General" ], "note": "Official MetaSBT Wiki" } ], "publication": [], "credit": [ { "name": "Fabio Cumbo", "email": "fabio.cumbo@gmail.com", "url": "https://cumbof.github.io", "orcidid": "https://orcid.org/0000-0003-2920-5838", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Primary contact", "Developer", "Maintainer", "Support" ], "note": null } ], "owner": "fabiocumbo", "additionDate": "2025-06-17T20:53:54.551980Z", "lastUpdate": "2025-06-18T17:12:50.842659Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NanoPlot", "description": "NanoPlot is a tool with various visualizations of sequencing data in bam, cram, fastq, fasta or platform-specific TSV summaries, mainly intended for long-read sequencing from Oxford Nanopore Technologies and Pacific Biosciences", "homepage": "https://github.com/wdecoster/NanoPlot", "biotoolsID": "nanoplot", "biotoolsCURIE": "biotools:nanoplot", "version": [ "v.1.42.0" ], "otherID": [], "relation": [ { "biotoolsID": "nanopack", "type": "includedIn" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2940", "term": "Scatter plot plotting" }, { "uri": "http://edamontology.org/operation_2943", "term": "Box-Whisker plot plotting" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" }, { "uri": "http://edamontology.org/format_1207", "term": "nucleotide" } ] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Mac", "Linux", "Windows" ], "language": [ "Python" ], "license": "GPL-3.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge (with restrictions)", "accessibility": "Open access (with restrictions)", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/wdecoster/NanoPlot", "type": [ "Repository" ], "note": "Issue tracker and most up to date software version" }, { "url": "http://nanoplot.bioinf.be/", "type": [ "Service" ], "note": "Web service with more limited options compared to the command line tool" } ], "download": [ { "url": "https://anaconda.org/bioconda/nanoplot", "type": "Command-line specification", "note": null, "version": null }, { "url": "https://pypi.org/project/NanoPlot/", "type": "Command-line specification", "note": null, "version": null } ], "documentation": [ { "url": "https://github.com/wdecoster/NanoPlot", "type": [ "Command-line options" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/bty149", "pmid": "29547981", "pmcid": "PMC6061794", "type": [ "Method" ], "version": null, "note": null, "metadata": { "title": "NanoPack: Visualizing and processing long-read sequencing data", "abstract": "Summary: Here we describe NanoPack, a set of tools developed for visualization and processing of long-read sequencing data from Oxford Nanopore Technologies and Pacific Biosciences. Availability and implementation: The NanoPack tools are written in Python3 and released under the GNU GPL3.0 License. The source code can be found at https://github.com/wdecoster/nanopack, together with links to separate scripts and their documentation. The scripts are compatible with Linux, Mac OS and the MS Windows 10 subsystem for Linux and are available as a graphical user interface, a web service at http://nanoplot.bioinf.be and command line tools.", "date": "2018-08-01T00:00:00Z", "citationCount": 1840, "authors": [ { "name": "De Coster W." }, { "name": "D'Hert S." }, { "name": "Schultz D.T." }, { "name": "Cruts M." }, { "name": "Van Broeckhoven C." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Wouter De Coster", "email": null, "url": "https://gigabaseorgigabyte.wordpress.com/", "orcidid": "https://orcid.org/0000-0002-5248-8197", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "wdecoster", "additionDate": "2021-07-06T20:27:27Z", "lastUpdate": "2025-06-18T12:31:48.762608Z", "editPermission": { "type": "public", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "kraken2", "description": "Kraken 2 is the newest version of Kraken, a taxonomic classification system using exact k-mer matches to achieve high accuracy and fast classification speeds. This classifier matches each k-mer within a query sequence to the lowest common ancestor (LCA) of all genomes containing the given k-mer. The k-mer assignments inform the classification algorithm.\nAny assumption that Kraken’s raw read assignments can be directly translated into species or strain-level abundance estimates is flawed. Bracken (Bayesian Reestimation of Abundance after Classification with KrakEN), estimates species abundances in metagenomics samples by probabilistically re-distributing reads in the taxonomic tree. (Lu, Jennifer et al. “Bracken: estimating species abundance in metagenomics data.”)", "homepage": "https://ccb.jhu.edu/software/kraken2/", "biotoolsID": "kraken2", "biotoolsCURIE": "biotools:kraken2", "version": [ "2.0.8-beta" ], "otherID": [], "relation": [ { "biotoolsID": "kraken", "type": "isNewVersionOf" }, { "biotoolsID": "bracken", "type": "usedBy" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "note": null, "cmd": "`kraken2 --db <kraken2_database> <input.fastq>`" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0637", "term": "Taxonomy" }, { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_3697", "term": "Microbial ecology" }, { "uri": "http://edamontology.org/topic_3301", "term": "Microbiology" } ], "operatingSystem": [], "language": [ "C++", "Perl" ], "license": "MIT", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/DerrickWood/kraken2", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/DerrickWood/kraken2/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "https://github.com/DerrickWood/kraken2/archive/v2.0.8-beta.tar.gz", "type": "Source code", "note": null, "version": "2.0.8-beta" } ], "documentation": [ { "url": "https://github.com/DerrickWood/kraken2/wiki/Manual", "type": [ "User manual" ], "note": null }, { "url": "https://benlangmead.github.io/aws-indexes/k2", "type": [ "User manual" ], "note": "Links to multiple Kraken 2 and bracken databases and indexes" } ], "publication": [ { "doi": "10.1101/762302", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Derrick E. Wood", "email": null, "url": null, "orcidid": "http://orcid.org/0000-0002-7429-1854", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Jennifer Lu", "email": null, "url": null, "orcidid": "http://orcid.org/0000-0001-9167-2002", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Ben Langmead", "email": "langmea@cs.jhu.edu", "url": null, "orcidid": "http://orcid.org/0000-0003-2437-1976", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "anand-anshu", "additionDate": "2019-09-13T12:51:16Z", "lastUpdate": "2025-06-18T12:24:26.657325Z", "editPermission": { "type": "group", "authors": [ "vashokan", "Keiler_Collier" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NanoPack", "description": "Visualizing and processing long-read sequencing data.", "homepage": "https://github.com/wdecoster/nanopack", "biotoolsID": "nanopack", "biotoolsCURIE": "biotools:nanopack", "version": [ "1.1.0" ], "otherID": [], "relation": [ { "biotoolsID": "nanoplot", "type": "includes" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2403", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" }, { "uri": "http://edamontology.org/topic_0092", "term": "Data visualisation" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Python" ], "license": null, "collectionID": [ "VIB" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://github.com/wdecoster/nanopack", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/bty149", "pmid": "29547981", "pmcid": "PMC6061794", "type": [], "version": null, "note": null, "metadata": { "title": "NanoPack: Visualizing and processing long-read sequencing data", "abstract": "Summary: Here we describe NanoPack, a set of tools developed for visualization and processing of long-read sequencing data from Oxford Nanopore Technologies and Pacific Biosciences. Availability and implementation: The NanoPack tools are written in Python3 and released under the GNU GPL3.0 License. The source code can be found at https://github.com/wdecoster/nanopack, together with links to separate scripts and their documentation. The scripts are compatible with Linux, Mac OS and the MS Windows 10 subsystem for Linux and are available as a graphical user interface, a web service at http://nanoplot.bioinf.be and command line tools.", "date": "2018-08-01T00:00:00Z", "citationCount": 1840, "authors": [ { "name": "De Coster W." }, { "name": "D'Hert S." }, { "name": "Schultz D.T." }, { "name": "Cruts M." }, { "name": "Van Broeckhoven C." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Wouter De Coster", "email": "wouter.decoster@molgen.vib-ua.be", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "d.gabrielaitis", "additionDate": "2018-07-01T13:17:42Z", "lastUpdate": "2025-06-18T12:21:28.393467Z", "editPermission": { "type": "group", "authors": [ "bits@vib.be" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "NextDenovo", "description": "NextDenovo is a string graph-based de novo assembler for long reads (CLR, HiFi and ONT). It uses a \"correct-then-assemble\" strategy similar to canu (no correction step for PacBio Hifi reads), but requires significantly less computing resources and storages.", "homepage": "https://github.com/Nextomics/NextDenovo", "biotoolsID": "nextdenovo", "biotoolsCURIE": "biotools:nextdenovo", "version": [ "v.2.5.2" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0524", "term": "De-novo assembly" }, { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0924", "term": "Sequence trace" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" }, { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_0925", "term": "Sequence assembly" }, "format": [ { "uri": "http://edamontology.org/format_2561", "term": "Sequence assembly format (text)" }, { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [], "language": [ "Python", "C" ], "license": "GPL-3.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/Nextomics/NextDenovo/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [ { "url": "https://github.com/Nextomics/NextDenovo/releases/tag/2.5.2", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "https://nextdenovo.readthedocs.io/en/latest/", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1101/2023.03.09.531669.", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": "Nextomics", "email": "support@nextomics.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "Kigaard", "additionDate": "2021-05-26T21:13:32Z", "lastUpdate": "2025-06-18T12:20:23.607241Z", "editPermission": { "type": "group", "authors": [ "jw", "ELIXIR-CZ", "Keiler_Collier" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "quickmerge", "description": "Quickmerge is a program that uses complementary information from genomes assembled with long reads in order to improve contiguity, and works with assemblies derived from both Pacific Biosciences or Oxford Nanopore. Quickmerge will even work with hybrid assemblies made by combining long reads and Illumina short reads.", "homepage": "https://github.com/mahulchak/quickmerge", "biotoolsID": "quickmerge", "biotoolsCURIE": "biotools:quickmerge", "version": [ "v.0.3" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_3216", "term": "Scaffolding" }, { "uri": "http://edamontology.org/operation_0524", "term": "De-novo assembly" }, { "uri": "http://edamontology.org/operation_3196", "term": "Genotyping" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": "Runs whole merge process on an input assembly.\nAssembly 2 will be used to fill gaps in assembly 1.", "cmd": "merge_wrapper.py -pre output_prefix assembly_1.fa assembly_2.fa" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3175", "term": "Structural variation" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_2885", "term": "DNA polymorphism" }, { "uri": "http://edamontology.org/topic_3673", "term": "Whole genome sequencing" }, { "uri": "http://edamontology.org/topic_0625", "term": "Genotype and phenotype" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "C++", "C" ], "license": "GPL-3.0", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/mahulchak/quickmerge/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/mahulchak/quickmerge", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1534/g3.118.200162", "pmid": "30018084", "pmcid": "PMC6169397", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Rapid low-cost assembly of the drosophila melanogaster reference genome using low-coverage, long-read sequencing", "abstract": "Accurate and comprehensive characterization of genetic variation is essential for deciphering the genetic basis of diseases and other phenotypes. A vast amount of genetic variation stems from largescale sequence changes arising from the duplication, deletion, inversion, and translocation of sequences. In the past 10 years, high-throughput short reads have greatly expanded our ability to assay sequence variation due to single nucleotide polymorphisms. However, a recent de novo assembly of a second Drosophila melanogaster reference genome has revealed that short read genotyping methods miss hundreds of structural variants, including those affecting phenotypes. While genomes assembled using highcoverage long reads can achieve high levels of contiguity and completeness, concerns about cost, errors, and low yield have limited widespread adoption of such sequencing approaches. Here we resequenced the reference strain of D. melanogaster (ISO1) on a single Oxford Nanopore MinION flow cell run for 24 hr. Using only reads longer than 1 kb or with at least 30x coverage, we assembled a highly contiguous de novo genome. The addition of inexpensive paired reads and subsequent scaffolding using an optical map technology achieved an assembly with completeness and contiguity comparable to the D. melanogaster reference assembly. Comparison of our assembly to the reference assembly of ISO1 uncovered a number of structural variants (SVs), including novel LTR transposable element insertions and duplications affecting genes with developmental, behavioral, and metabolic functions. Collectively, these SVs provide a snapshot of the dynamics of genome evolution. Furthermore, our assembly and comparison to the D. melanogaster reference genome demonstrates that high-quality de novo assembly of reference genomes and comprehensive variant discovery using such assemblies are now possible by a single lab for under $1,000 (USD).", "date": "2018-10-01T00:00:00Z", "citationCount": 70, "authors": [ { "name": "Solares E.A." }, { "name": "Chakraborty M." }, { "name": "Miller D.E." }, { "name": "Kalsow S." }, { "name": "Hall K." }, { "name": "Perera A.G." }, { "name": "Emerson J.J." }, { "name": "Scott Hawley R." } ], "journal": "G3: Genes, Genomes, Genetics" } } ], "credit": [ { "name": "Mahul Chakraborty", "email": null, "url": "https://mahulchakraborty.wordpress.com/", "orcidid": "https://orcid.org/0000-0003-2414-9187", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "Kigaard", "additionDate": "2021-05-27T09:04:45Z", "lastUpdate": "2025-06-18T12:17:20.983962Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-CZ", "Keiler_Collier" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "SKM", "description": "Stress Knowledge Map: A compilation of knowledge on mechanisms underlying responses of plants to stress, the so called stress signalling network.", "homepage": "https://skm.nib.si/", "biotoolsID": "skm", "biotoolsCURIE": "biotools:skm", "version": [], "otherID": [], "relation": [ { "biotoolsID": "gomapman", "type": "uses" }, { "biotoolsID": "newt-ve", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2421", "term": "Database search" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2299", "term": "Gene name" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2080", "term": "Database search results" }, "format": [ { "uri": "http://edamontology.org/format_3464", "term": "JSON" }, { "uri": "http://edamontology.org/format_3619", "term": "sif" } ] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [], "output": [ { "data": { "uri": "http://edamontology.org/data_0950", "term": "Mathematical model" }, "format": [ { "uri": "http://edamontology.org/format_2585", "term": "SBML" }, { "uri": "http://edamontology.org/format_3692", "term": "SBGN-ML" }, { "uri": "http://edamontology.org/format_3619", "term": "sif" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Web application", "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_2259", "term": "Systems biology" }, { "uri": "http://edamontology.org/topic_0602", "term": "Molecular interactions, pathways and networks" }, { "uri": "http://edamontology.org/topic_0780", "term": "Plant biology" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [ "ELIXIR-SI", "Plant Systems Biology" ], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "Slovenia" ], "elixirCommunity": [ "Plant Sciences" ], "link": [ { "url": "https://skm.nib.si/contact", "type": [ "Other" ], "note": null } ], "download": [], "documentation": [ { "url": "https://skm.nib.si/documentation", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1016/j.xplc.2024.100920", "pmid": "38616489", "pmcid": null, "type": [ "Primary" ], "version": null, "note": "Stress Knowledge Map: A knowledge graph resource for systems biology analysis of plant stress responses", "metadata": { "title": "Stress Knowledge Map: A knowledge graph resource for systems biology analysis of plant stress responses", "abstract": "Stress Knowledge Map (SKM; https://skm.nib.si) is a publicly available resource containing two complementary knowledge graphs that describe the current knowledge of biochemical, signaling, and regulatory molecular interactions in plants: a highly curated model of plant stress signaling (PSS; 543 reactions) and a large comprehensive knowledge network (488 390 interactions). Both were constructed by domain experts through systematic curation of diverse literature and database resources. SKM provides a single entry point for investigations of plant stress response and related growth trade-offs, as well as interactive explorations of current knowledge. PSS is also formulated as a qualitative and quantitative model for systems biology and thus represents a starting point for a plant digital twin. Here, we describe the features of SKM and show, through two case studies, how it can be used for complex analyses, including systematic hypothesis generation and design of validation experiments, or to gain new insights into experimental observations in plant biology.", "date": "2024-06-10T00:00:00Z", "citationCount": 8, "authors": [ { "name": "Bleker C." }, { "name": "Ramsak" }, { "name": "Bittner A." }, { "name": "Podpecan V." }, { "name": "Zagorscak M." }, { "name": "Wurzinger B." }, { "name": "Baebler" }, { "name": "Petek M." }, { "name": "Kriznik M." }, { "name": "van Dieren A." }, { "name": "Gruber J." }, { "name": "Afjehi-Sadat L." }, { "name": "Weckwerth W." }, { "name": "Zupanic A." }, { "name": "Teige M." }, { "name": "Vothknecht U.C." }, { "name": "Gruden K." } ], "journal": "Plant Communications" } } ], "credit": [ { "name": "National Institute of Biology, Department of Biotechnology and Systems Biology", "email": null, "url": "http://www.nib.si/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": "Carissa Bleker", "email": "carissarobyn.bleker@nib.si", "url": null, "orcidid": "https://orcid.org/0000-0003-1617-7145", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Maintainer" ], "note": null }, { "name": "Kristina Gruden", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Contributor" ], "note": null }, { "name": "Živa Ramšak", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Contributor" ], "note": null }, { "name": "Vid Podpečan", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": null, "typeRole": [ "Developer" ], "note": null } ], "owner": "carissa", "additionDate": "2022-05-16T13:26:15.720803Z", "lastUpdate": "2025-06-18T12:10:26.465410Z", "editPermission": { "type": "group", "authors": [ "zagor" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Compleasm", "description": "Compleasm: a faster and more accurate reimplementation of BUSCO.\nIt provides measures for quantitative assessment of genome assembly, gene set, and transcriptome completeness based on evolutionarily informed expectations of gene content from near-universal single-copy orthologs.", "homepage": "https://github.com/huangnengCSU/compleasm", "biotoolsID": "compleasm", "biotoolsCURIE": "biotools:compleasm", "version": [ "v.0.2.5" ], "otherID": [], "relation": [ { "biotoolsID": "busco", "type": "isNewVersionOf" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3180", "term": "Sequence assembly validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_2546", "term": "FASTA-like" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [] } ], "note": "Runs compleasm using the BUSCO set corresponding to the lineage given.", "cmd": "compleasm run -l \"$lineage\" -a assembly.fa -o output_prefix" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_3308", "term": "Transcriptomics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [], "language": [ "Python" ], "license": "Apache-2.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/huangnengCSU/compleasm", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/huangnengCSU/compleasm/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://busco.ezlab.org/list_of_lineages.html", "type": [ "Other" ], "note": "List of accepted lineages (taxonomic groups with curated BUSCO sets)" } ], "download": [], "documentation": [ { "url": "https://github.com/huangnengCSU/compleasm/blob/0.2.6/README.md", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btad595", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "compleasm: a faster and more accurate reimplementation of BUSCO", "abstract": "Motivation: Evaluating the gene completeness is critical to measuring the quality of a genome assembly. An incomplete assembly can lead to errors in gene predictions, annotation, and other downstream analyses. Benchmarking Universal Single-Copy Orthologs (BUSCO) is a widely used tool for assessing the completeness of genome assembly by testing the presence of a set of single-copy orthologs conserved across a wide range of taxa. However, BUSCO is slow particularly for large genome assemblies. It is cumbersome to apply BUSCO to a large number of assemblies. Results: Here, we present compleasm, an efficient tool for assessing the completeness of genome assemblies. Compleasm utilizes the miniprot protein-to-genome aligner and the conserved orthologous genes from BUSCO. It is 14 times faster than BUSCO for human assemblies and reports a more accurate completeness of 99.6% than BUSCO's 95.7%, which is in close agreement with the annotation completeness of 99.5% for T2T-CHM13.", "date": "2023-10-01T00:00:00Z", "citationCount": 92, "authors": [ { "name": "Huang N." }, { "name": "Li H." } ], "journal": "Bioinformatics" } } ], "credit": [], "owner": "rlibouban", "additionDate": "2024-03-18T14:51:49.667412Z", "lastUpdate": "2025-06-18T12:00:20.662241Z", "editPermission": { "type": "public", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "QUAST", "description": "QUAST stands for QUality ASsessment Tool. \nIt evaluates a quality of genome assemblies by computing various metrics and providing nice reports.", "homepage": "http://quast.sourceforge.net/quast", "biotoolsID": "quast", "biotoolsCURIE": "biotools:quast", "version": [ "v.5.3.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_3180", "term": "Sequence assembly validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [], "note": "# Running quast on a eukaryotic genome", "cmd": "quast -ek assembly.fa --out output_prefix" } ], "toolType": [ "Workflow" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Linux", "Mac" ], "language": [ "Perl", "Python", "C" ], "license": "GPL-2.0", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/ablab/quast", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/ablab/quast/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [ { "url": "http://quast.bioinf.spbau.ru/", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btt086", "pmid": "23422339", "pmcid": "PMC3624806", "type": [], "version": null, "note": null, "metadata": { "title": "QUAST: Quality assessment tool for genome assemblies", "abstract": "Limitations of genome sequencing techniques have led to dozens of assembly algorithms, none of which is perfect. A number of methods for comparing assemblers have been developed, but none is yet a recognized benchmark. Further, most existing methods for comparing assemblies are only applicable to new assemblies of finished genomes; the problem of evaluating assemblies of previously unsequenced species has not been adequately considered. Here, we present QUAST - a quality assessment tool for evaluating and comparing genome assemblies. This tool improves on leading assembly comparison software with new ideas and quality metrics. QUAST can evaluate assemblies both with a reference genome, as well as without a reference. QUAST produces many reports, summary tables and plots to help scientists in their research and in their publications. In this study, we used QUAST to compare several genome assemblers on three datasets. QUAST tables and plots for all of them are available in the Supplementary Material, and interactive versions of these reports are on the QUAST website. © 2013 The Author.", "date": "2013-04-15T00:00:00Z", "citationCount": 6872, "authors": [ { "name": "Gurevich A." }, { "name": "Saveliev V." }, { "name": "Vyahhi N." }, { "name": "Tesler G." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "QUAST Support", "email": "quast.support@cab.spbu.ru", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "seqwiki_import", "additionDate": "2017-01-13T13:16:01Z", "lastUpdate": "2025-06-18T11:53:52.861712Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-CZ", "Keiler_Collier" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "purge_dups", "description": "Identifying and removing haplotypic duplication in primary genome assemblies | haplotypic duplication identification tool | scripts/pd_config.py: script to generate a configuration file used by run_purge_dups.py | purge haplotigs and overlaps in an assembly based on read depth | Given a primary assembly pri_asm and an alternative assembly hap_asm (optional, if you have one), follow the steps shown below to build your own purge_dups pipeline, steps with same number can be run simultaneously. Among all the steps, although step 4 is optional, we highly recommend our users to do so, because assemblers may produce overrepresented seqeuences. In such a case, The final step 4 can be applied to remove those seqeuences", "homepage": "https://github.com/dfguan/purge_dups", "biotoolsID": "purge_dups", "biotoolsCURIE": "biotools:purge_dups", "version": [ "v.1.2.6" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_3798", "term": "Read binning" }, { "uri": "http://edamontology.org/operation_3216", "term": "Scaffolding" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "Python", "C" ], "license": "MIT", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/dfguan/purge_dups", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/dfguan/purge_dups/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1101/729962", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [], "owner": "Pub2Tools", "additionDate": "2019-11-14T18:08:10Z", "lastUpdate": "2025-06-18T11:49:23.596041Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "Racon", "description": "Consensus module for raw de novo DNA assembly of long uncorrected reads\n\nRacon is intended as a standalone consensus module to correct raw contigs generated by rapid assembly methods which do not include a consensus step. The goal of Racon is to generate genomic consensus which is of similar or better quality compared to the output generated by assembly methods which employ both error correction and consensus steps, while providing a speedup of several times compared to those methods. It supports data produced by both Pacific Biosciences and Oxford Nanopore Technologies.", "homepage": "https://github.com/isovic/racon", "biotoolsID": "Racon", "biotoolsCURIE": "biotools:Racon", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_0523", "term": "Mapping assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [ { "uri": "http://edamontology.org/format_2572", "term": "BAM" }, { "uri": "http://edamontology.org/format_2573", "term": "SAM" } ] }, { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] }, { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": "# The mapping file can be generated with any mapping program - eg, bwa-mem or minimap2.\n# The following is an example using minimap2 with ONT data\nminimap2 assembly.fa-ax map-ont reads.fa > mapped_reads.sam", "cmd": "racon -u reads.fa mapped_reads.sam assembly.fa > assembly_racon.fa" } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_3673", "term": "Whole genome sequencing" }, { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "C++", "Python" ], "license": "MIT", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/isovic/racon", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/isovic/racon/issues", "type": [ "Issue tracker" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.3390/plants8080270", "pmid": "31390788", "pmcid": "PMC6724115", "type": [], "version": null, "note": null, "metadata": { "title": "Constructing a reference genome in a single lab: The possibility to use oxford nanopore technology", "abstract": "The whole genome sequencing (WGS) has become a crucial tool in understanding genome structure and genetic variation. The MinION sequencing of Oxford Nanopore Technologies (ONT) is an excellent approach for performing WGS and it has advantages in comparison with other Next-Generation Sequencing (NGS): It is relatively inexpensive, portable, has simple library preparation, can be monitored in real-time, and has no theoretical limits on reading length. Sorghum bicolor (L.) Moench is diploid (2n = 2x = 20) with a genome size of about 730 Mb, and its genome sequence information is released in the Phytozome database. Therefore, sorghum can be used as a good reference. However, plant species have complex and large genomes when compared to animals or microorganisms. As a result, complete genome sequencing is difficult for plant species. MinION sequencing that produces long-reads can be an excellent tool for overcoming the weak assembly of short-reads generated from NGS by minimizing the generation of gaps or covering the repetitive sequence that appears on the plant genome. Here, we conducted the genome sequencing for S. bicolor cv. BTx623 while using the MinION platform and obtained 895,678 reads and 17.9 gigabytes (Gb) (ca. 25× coverage of reference) from long-read sequence data. A total of 6124 contigs (covering 45.9%) were generated from Canu, and a total of 2661 contigs (covering 50%) were generated from Minimap and Miniasm with a Racon through a de novo assembly using two different tools and mapped assembled contigs against the sorghum reference genome. Our results provide an optimal series of long-read sequencing analysis for plant species while using the MinION platform and a clue to determine the total sequencing scale for optimal coverage that is based on various genome sizes.", "date": "2019-08-01T00:00:00Z", "citationCount": 13, "authors": [ { "name": "Lee Y.G." }, { "name": "Choi S.C." }, { "name": "Kang Y." }, { "name": "Kim K.M." }, { "name": "Kang C.-S." }, { "name": "Kim C." } ], "journal": "Plants" } } ], "credit": [ { "name": "Chon-Sik Kang", "email": "cskang@korea.kr", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null }, { "name": "Changsoo Kim", "email": "changsookim@cnu.ac.kr", "url": null, "orcidid": "https://orcid.org/0000-0002-3596-2934", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "Pub2Tools", "additionDate": "2019-11-14T18:44:38Z", "lastUpdate": "2025-06-18T11:42:42.378216Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "Chopper", "description": "Rust implementation of NanoFilt+NanoLyse, both originally written in Python. This tool, intended for long read sequencing such as PacBio or ONT, filters and trims a fastq file.", "homepage": "https://github.com/wdecoster/chopper", "biotoolsID": "chopper", "biotoolsCURIE": "biotools:chopper", "version": [ "v0.10.0b" ], "otherID": [], "relation": [ { "biotoolsID": "nanopack", "type": "isNewVersionOf" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3695", "term": "Data filtering" }, { "uri": "http://edamontology.org/operation_3192", "term": "Sequence trimming" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "note": null, "cmd": "gunzip -c reads.fastq.gz | chopper -q 10 -l 500 | gzip > filtered_reads.fastq.gz\nchopper -q 10 -l 500 -i reads.fastq > filtered_reads.fastq\nchopper -q 10 -l 500 -i reads.fastq.gz | gzip > filtered_reads.fastq.gz" } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3168", "term": "Sequencing" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [], "license": "MIT", "collectionID": [ "ONTeater" ], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/wdecoster/chopper", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1093/bioinformatics/btad311", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "NanoPack2: population-scale evaluation of long-read sequencing data", "abstract": "Increases in the cohort size in long-read sequencing projects necessitate more efficient software for quality assessment and processing of sequencing data from Oxford Nanopore Technologies and Pacific Biosciences. Here, we describe novel tools for summarizing experiments, filtering datasets, visualizing phased alignments results, and updates to the NanoPack software suite. Availability and implementation: The cramino, chopper, kyber, and phasius tools are written in Rust and available as executable binaries without requiring installation or managing dependencies. Binaries build on musl are available for broad compatibility. NanoPlot and NanoComp are written in Python3. Links to the separate tools and their documentation can be found at https://github.com/wdecoster/nanopack. All tools are compatible with Linux, Mac OS, and the MS Windows Subsystem for Linux and are released under the MIT license. The repositories include test data, and the tools are continuously tested using GitHub Actions and can be installed with the conda dependency manager.", "date": "2023-05-01T00:00:00Z", "citationCount": 203, "authors": [ { "name": "De Coster W." }, { "name": "Rademakers R." } ], "journal": "Bioinformatics" } } ], "credit": [], "owner": "Keiler_Collier", "additionDate": "2025-06-18T09:20:19.874306Z", "lastUpdate": "2025-06-18T10:20:49.646869Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Flye", "description": "Flye is a de novo assembler for single molecule sequencing reads, such as those produced by PacBio and Oxford Nanopore Technologies. It is designed for a wide range of datasets, from small bacterial projects to large mammalian-scale assemblies. The package represents a complete pipeline: it takes raw PB / ONT reads as input and outputs polished contigs.", "homepage": "https://github.com/fenderglass/Flye", "biotoolsID": "Flye", "biotoolsCURIE": "biotools:Flye", "version": [ "2.9.6" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0525", "term": "Genome assembly" }, { "uri": "http://edamontology.org/operation_0524", "term": "De-novo assembly" }, { "uri": "http://edamontology.org/operation_0523", "term": "Mapping assembly" }, { "uri": "http://edamontology.org/operation_3730", "term": "Cross-assembly" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1930", "term": "FASTQ" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Workflow" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_3673", "term": "Whole genome sequencing" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" } ], "operatingSystem": [ "Mac", "Linux" ], "language": [ "C++", "Python", "C" ], "license": "BSD-3-Clause", "collectionID": [ "ONTeater" ], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/fenderglass/Flye/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/mikolmogorov/Flye", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": "10.1099/mgen.0.000294", "pmid": "31483244", "pmcid": "PMC6807382", "type": [ "Usage" ], "version": null, "note": null, "metadata": { "title": "Comparison of long-read sequencing technologies in the hybrid assembly of complex bacterial genomes", "abstract": "Illumina sequencing allows rapid, cheap and accurate whole genome bacterial analyses, but short reads (<300 bp) do not usually enable complete genome assembly. Long-read sequencing greatly assists with resolving complex bacterial genomes, particularly when combined with short-read Illumina data (hybrid assembly). However, it is not clear how different long-read sequencing methods affect hybrid assembly accuracy. Relative automation of the assembly process is also crucial to facilitating high-throughput complete bacterial genome reconstruction, avoiding multiple bespoke filtering and data manipulation steps. In this study, we compared hybrid assemblies for 20 bacterial isolates, including two reference strains, using Illumina sequencing and long reads from either Oxford Nanopore Technologies (ONT) or SMRT Pacific Biosciences (PacBio) sequencing platforms. We chose isolates from the family Enterobacteriaceae, as these frequently have highly plastic, repetitive genetic structures, and complete genome reconstruction for these species is relevant for a precise understanding of the epidemiology of antimicrobial resistance. We de novo assembled genomes using the hybrid assembler Unicycler and compared different read processing strategies, as well as comparing to long-read-only assembly with Flye followed by short-read polishing with Pilon. Hybrid assembly with either PacBio or ONT reads facilitated high-quality genome reconstruction, and was superior to the longread assembly and polishing approach evaluated with respect to accuracy and completeness. Combining ONT and Illumina reads fully resolved most genomes without additional manual steps, and at a lower consumables cost per isolate in our setting. Automated hybrid assembly is a powerful tool for complete and accurate bacterial genome assembly.", "date": "2019-01-01T00:00:00Z", "citationCount": 166, "authors": [ { "name": "De Maio N." }, { "name": "Shaw L.P." }, { "name": "Hubbard A." }, { "name": "George S." }, { "name": "Sanderson N.D." }, { "name": "Swann J." }, { "name": "Wick R." }, { "name": "Oun M.A." }, { "name": "Stubberfield E." }, { "name": "Hoosdally S.J." }, { "name": "Crook D.W." }, { "name": "Peto T.E.A." }, { "name": "Sheppard A.E." }, { "name": "Bailey M.J." }, { "name": "Read D.S." }, { "name": "Anjum M.F." }, { "name": "Sarah Walker A." }, { "name": "Stoesser N." } ], "journal": "Microbial Genomics" } }, { "doi": "10.1038/s41587-019-0072-8", "pmid": "30936562", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Assembly of long, error-prone reads using repeat graphs", "abstract": "Accurate genome assembly is hampered by repetitive regions. Although long single molecule sequencing reads are better able to resolve genomic repeats than short-read data, most long-read assembly algorithms do not provide the repeat characterization necessary for producing optimal assemblies. Here, we present Flye, a long-read assembly algorithm that generates arbitrary paths in an unknown repeat graph, called disjointigs, and constructs an accurate repeat graph from these error-riddled disjointigs. We benchmark Flye against five state-of-the-art assemblers and show that it generates better or comparable assemblies, while being an order of magnitude faster. Flye nearly doubled the contiguity of the human genome assembly (as measured by the NGA50 assembly quality metric) compared with existing assemblers.", "date": "2019-05-01T00:00:00Z", "citationCount": 3077, "authors": [ { "name": "Kolmogorov M." }, { "name": "Yuan J." }, { "name": "Lin Y." }, { "name": "Pevzner P.A." } ], "journal": "Nature Biotechnology" } }, { "doi": "10.1038/s41592-020-00971-x", "pmid": "33020656", "pmcid": "PMC10699202", "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "metaFlye: scalable long-read metagenome assembly using repeat graphs", "abstract": "Long-read sequencing technologies have substantially improved the assemblies of many isolate bacterial genomes as compared to fragmented short-read assemblies. However, assembling complex metagenomic datasets remains difficult even for state-of-the-art long-read assemblers. Here we present metaFlye, which addresses important long-read metagenomic assembly challenges, such as uneven bacterial composition and intra-species heterogeneity. First, we benchmarked metaFlye using simulated and mock bacterial communities and show that it consistently produces assemblies with better completeness and contiguity than state-of-the-art long-read assemblers. Second, we performed long-read sequencing of the sheep microbiome and applied metaFlye to reconstruct 63 complete or nearly complete bacterial genomes within single contigs. Finally, we show that long-read assembly of human microbiomes enables the discovery of full-length biosynthetic gene clusters that encode biomedically important natural products.", "date": "2020-11-01T00:00:00Z", "citationCount": 511, "authors": [ { "name": "Kolmogorov M." }, { "name": "Bickhart D.M." }, { "name": "Behsaz B." }, { "name": "Gurevich A." }, { "name": "Rayko M." }, { "name": "Shin S.B." }, { "name": "Kuhn K." }, { "name": "Yuan J." }, { "name": "Polevikov E." }, { "name": "Smith T.P.L." }, { "name": "Pevzner P.A." } ], "journal": "Nature Methods" } } ], "credit": [ { "name": "Mikhail Kolmogorov", "email": "fenderglass@gmail.com", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer", "Support" ], "note": null }, { "name": "Yu Lin", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Jeffrey Yuan", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "Pub2Tools", "additionDate": "2019-11-14T20:08:20Z", "lastUpdate": "2025-06-18T10:20:03.775603Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "iNaturalist", "description": "Methods for broad-scale plant phenology assessments using citizen scientists’ photographs | iNaturalist.org is a joint initiative of the California Academy of Sciences and the National Geographic Society | Explore and share your observations from the natural world", "homepage": "http://www.inaturalist.org/", "biotoolsID": "iNaturalist", "biotoolsCURIE": "biotools:iNaturalist", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0780", "term": "Plant biology" }, { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" }, { "uri": "http://edamontology.org/topic_0089", "term": "Ontology and terminology" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1101/754275", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": null } ], "credit": [], "owner": "Pub2Tools", "additionDate": "2019-11-14T19:55:10Z", "lastUpdate": "2025-06-17T16:48:56.129888Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": "tool" }, { "name": "BOLD (Barcode of Life Database)", "description": "An interactive gateway designed for the tracking and dissemination of DNA barcode reference data. The most commonly used marker is a region of the cytochrome c oxidase I (COI) gene found in mitochondria but multiple other are used for plants and fungi.\nSupported markers: COI, ITS, rbcL, matK and 18S.", "homepage": "https://boldsystems.org/", "biotoolsID": "barcode_of_life_database", "biotoolsCURIE": "biotools:barcode_of_life_database", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0338", "term": "Sequence database search" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3720", "term": "Geographic location" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1868", "term": "Taxon" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3720", "term": "Geographic location" }, "format": [] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0573", "term": "Map drawing" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal", "Web API" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" }, { "uri": "http://edamontology.org/topic_4038", "term": "Metabarcoding" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-16T09:48:41.534811Z", "lastUpdate": "2025-06-17T16:32:35.017034Z", "editPermission": { "type": "group", "authors": [ "Keiler_Collier" ] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "PyRx", "description": "Virtual Screening software for Computational Drug Discovery that can be used to screen libraries of compounds against potential drug targets.", "homepage": "http://pyrx.sourceforge.net/", "biotoolsID": "pyrx", "biotoolsCURIE": "biotools:pyrx", "version": [ "0.9.2" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3431", "term": "Submission" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2430", "term": "Design" } ], "input": [], "output": [], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2945", "term": "Analysis" } ], "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_0154", "term": "Drug targets" }, { "uri": "http://edamontology.org/topic_0154", "term": "Targets" }, { "uri": "http://edamontology.org/topic_0209", "term": "Drug design" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "Python" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "http://www.mybiosoftware.com/pyrx-0-8-virtual-screening-software-computer-aided-drug-design.html", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [], "publication": [ { "doi": null, "pmid": "29167582", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Pyridoxine dipharmacophore derivatives as potent glucokinase activators for the treatment of type 2 diabetes mellitus", "abstract": "© 2017 The Author(s).Glucokinase is one of the promising targets for glucose-lowering agents, and the development of GK activators are now considered as one of the most promising strategies for the treatment of type 2 diabetes mellitus. In this work, a series of novel symmetric molecular constructs, in which two pyridoxine moieties are connected via sulfur-containing linkers, have been synthesized and tested in vitro for glucokinase activation potential. The enzyme activation rates by two most active compounds at 100 μM (~150% and 130%) were comparable to that of the reference agent PF-04937319 (~154%). Both leading compounds demonstrated low cytotoxicity and excellent safety profile in acute toxicity experiment in rats after oral administration with LD50 exceeding 2000 mg/kg of body weight. Binding mode of the active compounds in comparison with the reference agent was studied using molecular docking. The leading compounds represent viable preclinical candidates for the treatment of type 2 diabetes mellitus, as well as a promising starting point for the design of structural analogs with improved activity.", "date": "2017-12-01T00:00:00Z", "citationCount": 7, "authors": [ { "name": "Dzyurkevich M.S." }, { "name": "Babkov D.A." }, { "name": "Shtyrlin N.V." }, { "name": "Mayka O.Y." }, { "name": "Iksanova A.G." }, { "name": "Vassiliev P.M." }, { "name": "Balakin K.V." }, { "name": "Spasov A.A." }, { "name": "Tarasov V.V." }, { "name": "Barreto G." }, { "name": "Shtyrlin Y.G." }, { "name": "Aliev G." } ], "journal": "Scientific Reports" } } ], "credit": [ { "name": null, "email": null, "url": "http://mgl.scripps.edu/", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null }, { "name": "Alfiya Iksanova", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0003-0474-6638", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [], "note": null } ], "owner": "Bioinfo", "additionDate": "2017-12-18T00:11:28Z", "lastUpdate": "2025-06-17T16:32:33.365776Z", "editPermission": { "type": "private", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "EUCAIM DICOM Anonymizer", "description": "The EUCAIM DICOM Anonymizer anonymizes a set of DICOM files. It supports both anonymization on a case-by-case scenario, meaning one DICOM Study at a time (single-mode) or on multiple cases concurrently (batch mode). Additionally it hashes and links clinical data.", "homepage": "https://harbor.eucaim.cancerimage.eu/harbor/projects/3/repositories/eucaim-anonymizer/", "biotoolsID": "eucaim_dicom_anonymizer", "biotoolsCURIE": "biotools:eucaim_dicom_anonymizer", "version": [ "0.12.0" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3283", "term": "Anonymisation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [], "topic": [ { "uri": "http://edamontology.org/topic_3384", "term": "Medical imaging" } ], "operatingSystem": [ "Mac", "Windows", "Linux" ], "language": [ "C++" ], "license": null, "collectionID": [ "EUCAIM" ], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "vpapageor", "additionDate": "2025-04-14T16:46:40.806977Z", "lastUpdate": "2025-06-17T16:32:31.400731Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BioSimulations", "description": "BioSimulations is a web application for sharing and re-using biomodels, simulations, and visualizations of simulations results. BioSimulations supports a wide range of modeling frameworks (e.g., kinetic, constraint-based, and logical modeling), model formats (e.g., BNGL, CellML, SBML), and simulation tools (e.g., COPASI, libRoadRunner/tellurium, NFSim, VCell). BioSimulations aims to help researchers discover published models that might be useful for their research and quickly try them via a simple web-based interface.", "homepage": "https://www.biosimulations.org/", "biotoolsID": "biosimulations", "biotoolsCURIE": "biotools:biosimulations", "version": [], "otherID": [ { "value": "RRID:SCR_018733", "type": "rrid", "version": null } ], "relation": [ { "biotoolsID": "runbiosimulations", "type": "uses" }, { "biotoolsID": "biosimulators", "type": "uses" }, { "biotoolsID": "biomodels", "type": "uses" }, { "biotoolsID": "sbml", "type": "uses" }, { "biotoolsID": "bionetgen", "type": "uses" }, { "biotoolsID": "cobrapy", "type": "uses" }, { "biotoolsID": "copasi", "type": "uses" }, { "biotoolsID": "libroadrunner", "type": "uses" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0337", "term": "Visualisation" }, { "uri": "http://edamontology.org/operation_2426", "term": "Modelling and simulation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_0950", "term": "Mathematical model" }, "format": [ { "uri": "http://edamontology.org/format_2585", "term": "SBML" }, { "uri": "http://edamontology.org/format_3240", "term": "CellML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3870", "term": "Trajectory data" }, "format": [ { "uri": "http://edamontology.org/format_3752", "term": "CSV" }, { "uri": "http://edamontology.org/format_3604", "term": "SVG" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Web API", "Web application", "Web service" ], "topic": [ { "uri": "http://edamontology.org/topic_2259", "term": "Systems biology" }, { "uri": "http://edamontology.org/topic_0602", "term": "Molecular interactions, pathways and networks" } ], "operatingSystem": [], "language": [ "JavaScript", "Python" ], "license": "MIT", "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/reproducible-biomedical-modeling/Biosimulations/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/reproducible-biomedical-modeling/Biosimulations", "type": [ "Repository" ], "note": null }, { "url": "https://api.biosimulations.org/", "type": [ "Service" ], "note": null } ], "download": [], "documentation": [ { "url": "https://docs.biosimulations.org", "type": [ "General" ], "note": null }, { "url": "https://api.biosimulations.org/", "type": [ "API documentation" ], "note": null }, { "url": "https://docs.biosimulations.org/developers/conduct/", "type": [ "Code of conduct" ], "note": null }, { "url": "https://docs.biosimulations.org/about/terms/", "type": [ "Terms of use" ], "note": null } ], "publication": [], "credit": [ { "name": "Jonathan Karr", "email": "karr@mssm.edu", "url": "https://www.karrlab.org", "orcidid": "https://orcid.org/0000-0002-2605-5080", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null }, { "name": "Bilal Shaikh", "email": null, "url": null, "orcidid": "https://orcid.org/0000-0001-5801-5510", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Developer" ], "note": null } ], "owner": "Bioinfo", "additionDate": "2020-06-18T05:28:02Z", "lastUpdate": "2025-06-17T16:32:28.548746Z", "editPermission": { "type": "group", "authors": [ "bilalshaikh42", "Bioinfo" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Bird 10,000 Genomes (B10K)", "description": "The Bird 10,000 Genomes (B10K) Project is an initiative to generate representative draft genome sequences from all extant bird species. The project aims to reconstruct the tree of life with full genome data, reveal the genomic basis of global bird diversity, and assess the impact of environmental change on diversity.", "homepage": "https://b10k.com/", "biotoolsID": "b10k", "biotoolsCURIE": "biotools:b10k", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0338", "term": "Sequence database search" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1868", "term": "Taxon" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Emerging", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-17T15:24:06.806811Z", "lastUpdate": "2025-06-17T15:25:02.609832Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Pavian", "description": "Web application for exploring metagenomics classification results, with a special focus on infectious disease diagnosis. Pinpointing pathogens in metagenomics classification results is often complicated by host and laboratory contaminants as well as many non-pathogenic microbiota. Researchers can analyze, display and transform results from the Kraken and Centrifuge classifiers using interactive tables, heatmaps and flow diagrams.", "homepage": "https://ccb.jhu.edu/software/pavian/", "biotoolsID": "pavian", "biotoolsCURIE": "biotools:pavian", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0226", "term": "Annotation" }, { "uri": "http://edamontology.org/operation_3460", "term": "Taxonomic classification" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3028", "term": "Taxonomy" }, "format": [ { "uri": "http://edamontology.org/format_3475", "term": "TSV" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2884", "term": "Plot" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Web application", "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3174", "term": "Metagenomics" }, { "uri": "http://edamontology.org/topic_0621", "term": "Model organisms" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "R" ], "license": "GPL-3.0", "collectionID": [ "Animal and Crop Genomics", "Biodiversity", "microbiome" ], "maturity": null, "cost": null, "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/fbreitwieser/pavian/tree/master", "type": [ "Repository" ], "note": null } ], "download": [], "documentation": [ { "url": "https://ccb.jhu.edu/software/pavian/index.shtml?t=manual", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1101/084715", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": null } ], "credit": [ { "name": null, "email": "fbreitw1@jhmi.edu", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "admin", "additionDate": "2017-08-20T16:34:27Z", "lastUpdate": "2025-06-17T15:12:54.095225Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BUSCO", "description": "Provides measures for quantitative assessment of genome assembly, gene set, and transcriptome completeness based on evolutionarily informed expectations of gene content from near-universal single-copy orthologs.", "homepage": "https://busco.ezlab.org/", "biotoolsID": "busco", "biotoolsCURIE": "biotools:busco", "version": [ "1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3180", "term": "Sequence assembly validation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1234", "term": "Sequence set (nucleic acid)" }, "format": [ { "uri": "http://edamontology.org/format_1929", "term": "FASTA" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2955", "term": "Sequence report" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0196", "term": "Sequence assembly" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_3308", "term": "Transcriptomics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux" ], "language": [ "Python" ], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [ "Tools" ], "elixirNode": [ "Switzerland" ], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "https://busco.ezlab.org/busco_userguide.html", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btv351", "pmid": "26059717", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO: Assessing genome assembly and annotation completeness with single-copy orthologs", "abstract": "Motivation: Genomics has revolutionized biological research, but quality assessment of the resulting assembled sequences is complicated and remains mostly limited to technical measures like N50. Results: We propose a measure for quantitative assessment of genome assembly and annotation completeness based on evolutionarily informed expectations of gene content. We implemented the assessment procedure in open-source software, with sets of Benchmarking Universal Single-Copy Orthologs, named BUSCO.", "date": "2015-10-01T00:00:00Z", "citationCount": 8766, "authors": [ { "name": "Simao F.A." }, { "name": "Waterhouse R.M." }, { "name": "Ioannidis P." }, { "name": "Kriventseva E.V." }, { "name": "Zdobnov E.M." } ], "journal": "Bioinformatics" } }, { "doi": "10.1002/cpz1.323", "pmid": "34936221", "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO: Assessing Genomic Data Quality and Beyond", "abstract": "Evaluation of the quality of genomic “data products” such as genome assemblies or gene sets is of critical importance in order to recognize possible issues and correct them during the generation of new data. It is equally essential to guide subsequent or comparative analyses with existing data, as the correct interpretation of the results necessarily requires knowledge about the quality level and reliability of the inputs. Using datasets of near universal single-copy orthologs derived from OrthoDB, BUSCO can estimate the completeness and redundancy of genomic data by providing biologically meaningful metrics based on expected gene content. These can complement technical metrics such as contiguity measures (e.g., number of contigs/scaffolds, and N50 values). Here, we describe the use of the BUSCO tool suite to assess different data types that can range from genome assemblies of single isolates and assembled transcriptomes and annotated gene sets to metagenome-assembled genomes where the taxonomic origin of the species is unknown. BUSCO is the only tool capable of assessing all these types of sequences from both eukaryotic and prokaryotic species. The protocols detail the various BUSCO running modes and the novel workflows introduced in versions 4 and 5, including the batch analysis on multiple inputs, the auto-lineage workflow to run assessments without specifying a dataset, and a workflow for the evaluation of (large) eukaryotic genomes. The protocols further cover the BUSCO setup, guidelines to interpret the results, and BUSCO “plugin” workflows for performing common operations in genomics using BUSCO results, such as building phylogenomic trees and visualizing syntenies. © 2021 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Assessing an input sequence with a BUSCO dataset specified manually. Basic Protocol 2: Assessing an input sequence with a dataset automatically selected by BUSCO. Basic Protocol 3: Assessing multiple inputs. Alternate Protocol: Decreasing analysis runtime when assessing a large number of small genomes with BUSCO auto-lineage workflow and Snakemake. Support Protocol 1: BUSCO setup. Support Protocol 2: Visualizing BUSCO results. Support Protocol 3: Building phylogenomic trees.", "date": "2021-12-01T00:00:00Z", "citationCount": 566, "authors": [ { "name": "Manni M." }, { "name": "Berkeley M.R." }, { "name": "Seppey M." }, { "name": "Zdobnov E.M." } ], "journal": "Current Protocols" } }, { "doi": "10.1093/molbev/msx319", "pmid": "29220515", "pmcid": "PMC5850278", "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO applications from quality assessments to gene prediction and phylogenomics", "abstract": "Genomics promises comprehensive surveying of genomes and metagenomes, but rapidly changing technologies and expanding data volumes make evaluation of completeness a challenging task. Technical sequencing quality metrics can be complemented by quantifying completeness of genomic data sets in terms of the expected gene content of Benchmarking Universal Single-Copy Orthologs (BUSCO, http://busco.ezlab.org). The latest software release implements a complete refactoring of the code tomake itmore flexible and extendable to facilitate high-Throughput assessments. The original six lineage assessment data sets have been updated with improved species sampling, 34 new subsets have been built for vertebrates, arthropods, fungi, and prokaryotes that greatly enhance resolution, and data sets are now also available for nematodes, protists, and plants. Here, we present BUSCO v3 with example analyses that highlight the wideranging utility of BUSCO assessments, which extend beyond quality control of genomics data sets to applications in comparative genomics analyses, gene predictor training, metagenomics, and phylogenomics.", "date": "2018-03-01T00:00:00Z", "citationCount": 1508, "authors": [ { "name": "Waterhouse R.M." }, { "name": "Seppey M." }, { "name": "Simao F.A." }, { "name": "Manni M." }, { "name": "Ioannidis P." }, { "name": "Klioutchnikov G." }, { "name": "Kriventseva E.V." }, { "name": "Zdobnov E.M." } ], "journal": "Molecular Biology and Evolution" } }, { "doi": "10.1093/molbev/msab199", "pmid": "34320186", "pmcid": "PMC8476166", "type": [], "version": null, "note": null, "metadata": { "title": "BUSCO Update: Novel and Streamlined Workflows along with Broader and Deeper Phylogenetic Coverage for Scoring of Eukaryotic, Prokaryotic, and Viral Genomes", "abstract": "Methods for evaluating the quality of genomic and metagenomic data are essential to aid genome assembly procedures and to correctly interpret the results of subsequent analyses. BUSCO estimates the completeness and redundancy of processed genomic data based on universal single-copy orthologs. Here, we present new functionalities and major improvements of the BUSCO software, as well as the renewal and expansion of the underlying data sets in sync with the OrthoDB v10 release. Among the major novelties, BUSCO now enables phylogenetic placement of the input sequence to automatically select the most appropriate BUSCO data set for the assessment, allowing the analysis of metagenome-Assembled genomes of unknown origin. A newly introduced genome workflow increases the efficiency and runtimes especially on large eukaryotic genomes. BUSCO is the only tool capable of assessing both eukaryotic and prokaryotic species, and can be applied to various data types, from genome assemblies and metagenomic bins, to transcriptomes and gene sets.", "date": "2021-10-01T00:00:00Z", "citationCount": 2710, "authors": [ { "name": "Manni M." }, { "name": "Berkeley M.R." }, { "name": "Seppey M." }, { "name": "Simao F.A." }, { "name": "Zdobnov E.M." } ], "journal": "Molecular Biology and Evolution" } } ], "credit": [ { "name": "SIB Swiss Institute of Bioinformatics", "email": null, "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Institute", "typeRole": [ "Provider" ], "note": null }, { "name": null, "email": "evgeny.zdobnov@unige.ch", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "SIB", "additionDate": "2016-10-10T07:21:30Z", "lastUpdate": "2025-06-17T15:10:57.224896Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "World Register of Marine Species (WORMS)", "description": "Search the WoRMS taxonomy.", "homepage": "http://www.marinespecies.org/aphia.php?p=webservice", "biotoolsID": "worms", "biotoolsCURIE": "biotools:worms", "version": [ "1" ], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3737", "term": "Alpha diversity data" }, "format": [] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_2421", "term": "Database search" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_3737", "term": "Alpha diversity data" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Web service" ], "topic": [ { "uri": "http://edamontology.org/topic_3071", "term": "Data management" }, { "uri": "http://edamontology.org/topic_3473", "term": "Data mining" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://www.biocatalogue.org/services/3332", "type": [ "Software catalogue" ], "note": null } ], "download": [], "documentation": [ { "url": "http://www.marinespecies.org/aphia.php?p=webservice", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1371/journal.pone.0051629", "pmid": "23505408", "pmcid": "PMC3541386", "type": [ "Other" ], "version": null, "note": null, "metadata": { "title": "Global Coordination and Standardisation in Marine Biodiversity through the World Register of Marine Species (WoRMS) and Related Databases", "abstract": "The World Register of Marine Species is an over 90% complete open-access inventory of all marine species names. Here we illustrate the scale of the problems with species names, synonyms, and their classification, and describe how WoRMS publishes online quality assured information on marine species. Within WoRMS, over 100 global, 12 regional and 4 thematic species databases are integrated with a common taxonomy. Over 240 editors from 133 institutions and 31 countries manage the content. To avoid duplication of effort, content is exchanged with 10 external databases. At present WoRMS contains 460,000 taxonomic names (from Kingdom to subspecies), 368,000 species level combinations of which 215,000 are currently accepted marine species names, and 26,000 related but non-marine species. Associated information includes 150,000 literature sources, 20,000 images, and locations of 44,000 specimens. Usage has grown linearly since its launch in 2007, with about 600,000 unique visitors to the website in 2011, and at least 90 organisations from 12 countries using WoRMS for their data management. By providing easy access to expert-validated content, WoRMS improves quality control in the use of species names, with consequent benefits to taxonomy, ecology, conservation and marine biodiversity research and management. The service manages information on species names that would otherwise be overly costly for individuals, and thus minimises errors in the application of nomenclature standards. WoRMS' content is expanding to include host-parasite relationships, additional literature sources, locations of specimens, images, distribution range, ecological, and biological data. Species are being categorised as introduced (alien, invasive), of conservation importance, and on other attributes. These developments have a multiplier effect on its potential as a resource for biodiversity research and management. As a consequence of WoRMS, we are witnessing improved communication within the scientific community, and anticipate increased taxonomic efficiency and quality control in marine biodiversity research and management. © 2013 Costello et al.", "date": "2013-01-16T00:00:00Z", "citationCount": 168, "authors": [ { "name": "Costello M.J." }, { "name": "Bouchet P." }, { "name": "Boxshall G." }, { "name": "Fauchald K." }, { "name": "Gordon D." }, { "name": "Hoeksema B.W." }, { "name": "Poore G.C.B." }, { "name": "van Soest R.W.M." }, { "name": "Stohr S." }, { "name": "Walter T.C." }, { "name": "Vanhoorne B." }, { "name": "Decock W." }, { "name": "Appeltans W." } ], "journal": "PLoS ONE" } } ], "credit": [ { "name": "BioCatalogue", "email": null, "url": "https://www.biocatalogue.org", "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Project", "typeRole": [ "Documentor" ], "note": null }, { "name": null, "email": "info@marinespecies.org", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "BioCatalogue", "additionDate": "2015-08-03T09:36:04Z", "lastUpdate": "2025-06-17T15:01:01.595342Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MitoFish", "description": "Mitochondrial genome database of fish with an accurate and automatic annotation pipeline.", "homepage": "http://mitofish.aori.u-tokyo.ac.jp/", "biotoolsID": "mitofish", "biotoolsCURIE": "biotools:mitofish", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2421", "term": "Database search" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3500", "term": "Zoology" }, { "uri": "http://edamontology.org/topic_2229", "term": "Cell biology" }, { "uri": "http://edamontology.org/topic_0622", "term": "Genomics" }, { "uri": "http://edamontology.org/topic_0654", "term": "DNA" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [ { "url": "http://mitofish.aori.u-tokyo.ac.jp/about/overview.html", "type": [ "General" ], "note": null } ], "publication": [ { "doi": "10.1093/MOLBEV/MST141", "pmid": "23955518", "pmcid": "PMC3808866", "type": [], "version": null, "note": null, "metadata": { "title": "Mitofish and mitoannotator: A mitochondrial genome database of fish with an accurate and automatic annotation pipeline", "abstract": "Mitofish is a database of fish mitochondrial genomes (mitogenomes) that includes powerful and precise de novo annotations for mitogenome sequences. Fish occupy an important position in the evolution of vertebrates and the ecology of the hydrosphere, and mitogenomic sequence data have served as a rich source of information for resolving fish phylogenies and identifying new fish species. The importance of a mitogenomic database continues to grow at a rapid pace as massive amounts of mitogenomic data are generated with the advent of new sequencing technologies. A severe bottleneck seems likely to occur with regard to mitogenome annotation because of the overwhelming pace of data accumulation and the intrinsic difficulties in annotating sequences with degenerating transfer RNA structures, divergent start/stop codons of the coding elements, and the overlapping of adjacent elements. To ease this data backlog, we developed an annotation pipeline named MitoAnnotator. MitoAnnotator automatically annotates a fish mitogenome with a high degree of accuracy in approximately 5 min; thus, it is readily applicable to data sets of dozens of sequences. MitoFish also contains re-annotations of previously sequenced fish mitogenomes, enabling researchers to refer to them when they find annotations that are likely to be erroneous or while conducting comparative mitogenomic analyses. For users who need more information on the taxonomy, habitats, phenotypes, or life cycles of fish, MitoFish provides links to related databases. MitoFish and MitoAnnotator are freely available at http://mitofish.aori.u-tokyo.ac.jp/ (last accessed August 28, 2013); all of the data can be batch downloaded, and the annotation pipeline can be used via a web interface. © The Author 2013.", "date": "2013-11-01T00:00:00Z", "citationCount": 675, "authors": [ { "name": "Iwasaki W." }, { "name": "Fukunaga T." }, { "name": "Isagozawa R." }, { "name": "Yamada K." }, { "name": "Maeda Y." }, { "name": "Satoh T.P." }, { "name": "Sado T." }, { "name": "Mabuchi K." }, { "name": "Takeshima H." }, { "name": "Miya M." }, { "name": "Nishida M." } ], "journal": "Molecular Biology and Evolution" } } ], "credit": [ { "name": "Wataru Iwasaki", "email": "mitofish@aori.u-tokyo.ac.jp", "url": null, "orcidid": null, "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "d.gabrielaitis", "additionDate": "2018-05-06T11:28:11Z", "lastUpdate": "2025-06-17T14:49:20.489786Z", "editPermission": { "type": "public", "authors": [] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "xcms", "description": "Framework for processing and visualization of chromatographically separated and single-spectra mass spectral data. The packages enables imports from AIA/ANDI NetCDF, mzXML, mzData and mzML files and preprocesses data for high-throughput, untargeted analyte profiling.", "homepage": "http://bioconductor.org/packages/release/bioc/html/xcms.html", "biotoolsID": "xcms", "biotoolsCURIE": "biotools:xcms", "version": [ "3.0.2" ], "otherID": [], "relation": [ { "biotoolsID": "ramclustr", "type": "usedBy" }, { "biotoolsID": "camera", "type": "usedBy" }, { "biotoolsID": "workflow4metabolomics", "type": "usedBy" } ], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_3694", "term": "Mass spectrum visualisation" }, { "uri": "http://edamontology.org/operation_3634", "term": "Label-free quantification" }, { "uri": "http://edamontology.org/operation_2428", "term": "Validation" }, { "uri": "http://edamontology.org/operation_3628", "term": "Chromatographic alignment" }, { "uri": "http://edamontology.org/operation_3215", "term": "Peak detection" }, { "uri": "http://edamontology.org/operation_3203", "term": "Chromatogram visualisation" }, { "uri": "http://edamontology.org/operation_3695", "term": "Data filtering" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2536", "term": "Mass spectrometry data" }, "format": [ { "uri": "http://edamontology.org/format_3650", "term": "NetCDF" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" }, { "uri": "http://edamontology.org/format_3654", "term": "mzXML" } ] }, { "data": { "uri": "http://edamontology.org/data_0943", "term": "Mass spectrometry spectra" }, "format": [ { "uri": "http://edamontology.org/format_3650", "term": "NetCDF" }, { "uri": "http://edamontology.org/format_3244", "term": "mzML" }, { "uri": "http://edamontology.org/format_3654", "term": "mzXML" } ] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2536", "term": "Mass spectrometry data" }, "format": [ { "uri": "http://edamontology.org/format_3650", "term": "NetCDF" }, { "uri": "http://edamontology.org/format_3248", "term": "mzQuantML" } ] } ], "note": null, "cmd": null } ], "toolType": [ "Command-line tool", "Library", "Web application" ], "topic": [ { "uri": "http://edamontology.org/topic_3383", "term": "Biological imaging" }, { "uri": "http://edamontology.org/topic_0092", "term": "Data visualisation" }, { "uri": "http://edamontology.org/topic_3172", "term": "Metabolomics" } ], "operatingSystem": [ "Linux", "Windows", "Mac" ], "language": [ "R" ], "license": "GPL-2.0", "collectionID": [ "BioConductor", "Bioconda", "Galaxy Tools" ], "maturity": "Mature", "cost": null, "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [ "Germany", "France", "Czech Republic" ], "elixirCommunity": [ "Metabolomics" ], "link": [ { "url": "http://metlin.scripps.edu/download/", "type": [ "Mirror" ], "note": null }, { "url": "https://github.com/sneumann/xcms", "type": [ "Repository" ], "note": "Link to the repository hosting the R code." }, { "url": "https://usegalaxy.eu/root?tool_id=toolshed.g2.bx.psu.edu/repos/lecorguille/xcms_xcmsset/abims_xcms_xcmsSet/3.12.0+galaxy1", "type": [ "Galaxy service" ], "note": null } ], "download": [ { "url": "http://bioconductor/packages/release/bioc/src/contrib/xcms_1.50.1.tar.gz", "type": "Source code", "note": null, "version": null }, { "url": "https://github.com/sneumann/xcms", "type": "Source code", "note": null, "version": null } ], "documentation": [ { "url": "http://bioconductor.org/packages/release/bioc/html/xcms.html", "type": [ "User manual" ], "note": null }, { "url": "https://training.galaxyproject.org/training-material/topics/metabolomics/tutorials/lcms-preprocessing/tutorial.html", "type": [ "Training material" ], "note": "Galaxy training material for LC-MS data preprocessing with XCMS" }, { "url": "https://training.galaxyproject.org/training-material/topics/metabolomics/tutorials/gc_ms_with_xcms/tutorial.html", "type": [ "Training material" ], "note": "Galaxy training for GC-MS data preprocessing with XCMS" }, { "url": "https://jorainer.github.io/xcmsTutorials/", "type": [ "Training material" ], "note": "Tutorial on using the XCMS R library" } ], "publication": [ { "doi": "10.1093/bioinformatics/btq441", "pmid": "20671148", "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "Correction of mass calibration gaps in liquid chromatography-mass spectrometry metabolomics data", "abstract": "Motivation: High mass accuracy is an important goal in liquid chromatography-mass spectrometry experiments. Some manufacturers employ a mass calibration system that regularly switches between the analyte and a standard reference compound, and leads to gaps in the analyte data. We present a method for correction of such gaps in global molecular profiling applications such as metabolomics. We demonstrate that it improves peak detection and quantification, successfully recovering the expected number of peaks and intensity distribution in an example metabolomics dataset. © The Author 2010. Published by Oxford University Press. All rights reserved.", "date": "2010-07-29T00:00:00Z", "citationCount": 159, "authors": [ { "name": "Benton H.P." }, { "name": "Want E.J." }, { "name": "Ebbels T.M.D." } ], "journal": "Bioinformatics" } } ], "credit": [ { "name": "Steffen Neumann", "email": "sneumann@ipb-halle.de", "url": null, "orcidid": "https://orcid.org/0000-0002-7899-7192", "gridid": null, "rorid": null, "fundrefid": null, "typeEntity": "Person", "typeRole": [ "Primary contact" ], "note": null } ], "owner": "bioconductor_import", "additionDate": "2017-01-17T15:04:54Z", "lastUpdate": "2025-06-17T13:07:05.749022Z", "editPermission": { "type": "group", "authors": [ "ELIXIR-EE", "n.m.palmblad@lumc.nl", "recetox-specdatri", "sneumann" ] }, "validated": 1, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "hictk", "description": "Blazing fast toolkit to work with .hic and .cool files", "homepage": "https://github.com/paulsengroup/hictk", "biotoolsID": "hictk", "biotoolsCURIE": "biotools:hictk", "version": [ "0.0.1", "0.0.2", "0.0.3", "0.0.4", "0.0.5", "0.0.6", "0.0.7", "0.0.8", "0.0.9", "0.0.10", "0.0.11", "0.0.12", "1.0.0", "2.0.0", "2.0.1", "2.0.2", "2.1.0", "2.1.1", "2.1.2", "2.1.3" ], "otherID": [], "relation": [ { "biotoolsID": "hictkpy", "type": "usedBy" }, { "biotoolsID": "hictkr", "type": "usedBy" } ], "function": [], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_0091", "term": "Bioinformatics" }, { "uri": "http://edamontology.org/topic_0080", "term": "Sequence analysis" } ], "operatingSystem": [ "Linux", "Mac", "Windows" ], "language": [], "license": "MIT", "collectionID": [], "maturity": "Mature", "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://github.com/paulsengroup/hictk", "type": [ "Repository" ], "note": null }, { "url": "https://github.com/paulsengroup/hictk/issues", "type": [ "Issue tracker" ], "note": null }, { "url": "https://github.com/paulsengroup/hictk/discussions", "type": [ "Helpdesk" ], "note": null } ], "download": [ { "url": "https://github.com/paulsengroup/hictk/releases", "type": "Downloads page", "note": null, "version": null }, { "url": "https://anaconda.org/bioconda/hictk", "type": "Binaries", "note": null, "version": null }, { "url": "https://github.com/paulsengroup/hictk/pkgs/container/hictk", "type": "Container file", "note": null, "version": null } ], "documentation": [ { "url": "https://hictk.readthedocs.io/en/stable/index.html", "type": [ "User manual" ], "note": null } ], "publication": [ { "doi": "10.1093/bioinformatics/btae408", "pmid": null, "pmcid": null, "type": [ "Primary" ], "version": null, "note": null, "metadata": { "title": "hictk: blazing fast toolkit to work with. hic and. cool files", "abstract": "Motivation: Hi-C is gaining prominence as a method for mapping genome organization. With declining sequencing costs and a growing demand for higher-resolution data, efficient tools for processing Hi-C datasets at different resolutions are crucial. Over the past decade, the. hic and Cooler file formats have become the de-facto standard to store interaction matrices produced by Hi-C experiments in binary format. Interoperability issues make it unnecessarily difficult to convert between the two formats and to develop applications that can process each format natively. Results: We developed hictk, a toolkit that can transparently operate on. hic and. cool files with excellent performance. The toolkit is written in C++ and consists of a C++ library with Python and R bindings as well as CLI tools to perform common operations directly from the shell, including converting between. hic and. mcool formats. We benchmark the performance of hictk and compare it with other popular tools and libraries. We conclude that hictk significantly outperforms existing tools while providing the flexibility of natively working with both file formats without code duplication.", "date": "2024-07-01T00:00:00Z", "citationCount": 0, "authors": [ { "name": "Rossini R." }, { "name": "Paulsen J." } ], "journal": "Bioinformatics" } } ], "credit": [], "owner": "robomics", "additionDate": "2024-02-02T14:42:46.030561Z", "lastUpdate": "2025-06-16T21:27:36.087171Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "MitoAnnotator", "description": "MitoAnnotator is a pipeline for annotating fish mitogenomic sequence fully automatically and accurately just in 30 seconds.", "homepage": "https://mitofish.aori.u-tokyo.ac.jp/annotation/input/", "biotoolsID": "mitoannotator", "biotoolsCURIE": "biotools:mitoannotator", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0362", "term": "Genome annotation" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_1193", "term": "Tool name (FASTA)" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1015", "term": "Sequence feature ID" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1279", "term": "Sequence map" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Bioinformatics portal" ], "topic": [ { "uri": "http://edamontology.org/topic_0085", "term": "Functional genomics" } ], "operatingSystem": [], "language": [], "license": "CC-BY-NC-3.0", "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [ { "url": "https://mitofish.aori.u-tokyo.ac.jp/about/refs/", "type": [ "Other" ], "note": "References used in developing MitoFish" }, { "url": "https://mitofish.aori.u-tokyo.ac.jp/species/detail/?genus=Anguilla&species=japonica", "type": [ "Other" ], "note": "Sample input and output" }, { "url": "https://github.com/tao-bioinfo/MiFish", "type": [ "Repository" ], "note": "GitHub Repo of the MiFish and MitoAnnotator pipelines" } ], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "Keiler_Collier", "additionDate": "2025-06-16T15:26:37.851391Z", "lastUpdate": "2025-06-16T15:37:19.175954Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "eBird", "description": "eBird gathers knowledge from birdwatchers in the form of checklists of birds, maps, audio recordings .", "homepage": "https://ebird.org/home", "biotoolsID": "ebird", "biotoolsCURIE": "biotools:ebird", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3720", "term": "Geographic location" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2019", "term": "Map data" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3720", "term": "Geographic location" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3905", "term": "Histogram" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3424", "term": "Raw image" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_0957", "term": "Database metadata" }, "format": [] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_3431", "term": "Data deposition" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3424", "term": "Raw image" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3546", "term": "Image metadata" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3720", "term": "Geographic location" }, "format": [] } ], "output": [], "note": null, "cmd": null } ], "toolType": [ "Database portal", "Web API" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-16T15:04:50.524484Z", "lastUpdate": "2025-06-16T15:15:22.271977Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Zoonomia", "description": "The Zoonomia Project provides access to genomic data including assemblies, annotations and alignments for 240 mammalian species.", "homepage": "https://zoonomiaproject.org/", "biotoolsID": "zoonomiaproject", "biotoolsCURIE": "biotools:zoonomiaproject", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1383", "term": "Nucleic acid sequence alignment" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_0925", "term": "Sequence assembly" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-16T13:44:36.983992Z", "lastUpdate": "2025-06-16T13:51:19.876113Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "DNA Zoo", "description": "DNA Zoo data includes genome assemblies, genome annotations, DNA-Seq data, and Hi-C maps.", "homepage": "https://www.dnazoo.org/", "biotoolsID": "dnazoo", "biotoolsCURIE": "biotools:dnazoo", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3273", "term": "Sample ID" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2193", "term": "Database entry metadata" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_0925", "term": "Sequence assembly" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_2711", "term": "Genome report" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3495", "term": "RNA sequence" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3002", "term": "Annotation track" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-16T13:31:23.224167Z", "lastUpdate": "2025-06-16T13:40:44.050187Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "ARCTOS", "description": "Arctos is both a community and an online museum collection management information system; as such Arctos is also a provider of research-grade data. It provides fundamental research infrastructure and is intended for curators, collection managers, investigators, educators, and anyone interested in natural and cultural history.", "homepage": "https://arctosdb.org", "biotoolsID": "arctosdb", "biotoolsCURIE": "biotools:arctosdb", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1868", "term": "Taxon" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2193", "term": "Database entry metadata" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-16T12:47:37.282204Z", "lastUpdate": "2025-06-16T13:26:43.492654Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "birdsoftheworld", "description": "Comprehensive life histories for all bird species and families.", "homepage": "https://birdsoftheworld.org/bow/home", "biotoolsID": "birdsoftheworld", "biotoolsCURIE": "biotools:birdsoftheworld", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2422", "term": "Data retrieval" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_2909", "term": "Organism name" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3273", "term": "Sample ID" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_1045", "term": "Species name" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_2193", "term": "Database entry metadata" }, "format": [] } ], "note": null, "cmd": null } ], "toolType": [ "Database portal" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Commercial", "accessibility": "Restricted access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-16T13:18:03.857639Z", "lastUpdate": "2025-06-16T13:18:57.717962Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "BOLD CLI", "description": "A command line interface for data retrieval from the barcode of life data system.", "homepage": "https://github.com/CNuge/BOLD-CLI", "biotoolsID": "barcode_of_life_cli", "biotoolsCURIE": "biotools:barcode_of_life_cli", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_0338", "term": "Sequence database search" } ], "input": [ { "data": { "uri": "http://edamontology.org/data_3494", "term": "DNA sequence" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3720", "term": "Geographic location" }, "format": [] } ], "output": [ { "data": { "uri": "http://edamontology.org/data_1868", "term": "Taxon" }, "format": [] }, { "data": { "uri": "http://edamontology.org/data_3720", "term": "Geographic location" }, "format": [] } ], "note": null, "cmd": null }, { "operation": [ { "uri": "http://edamontology.org/operation_0573", "term": "Map drawing" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Command-line tool" ], "topic": [ { "uri": "http://edamontology.org/topic_3050", "term": "Biodiversity" }, { "uri": "http://edamontology.org/topic_4038", "term": "Metabarcoding" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": "Mature", "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "adriaan", "additionDate": "2025-06-16T12:07:16.055880Z", "lastUpdate": "2025-06-16T12:09:59.575046Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "Genomics 2 Proteins portal", "description": "Genomics 2 Proteins (G2P) is a browser-based portal that lets you paste or upload variants and instantly map them onto PDB or AlphaFold structures. The viewer overlays UniProt domains, PTMs, disorder, conservation, and public variant tracks such as ClinVar, gnomAD, and HGMD, highlights 3-D hotspots, and can export a combined TSV or PyMOL session. Everything runs in the browser with no installation required, and a REST API is available for batch use.", "homepage": "https://g2p.broadinstitute.org", "biotoolsID": "genomics_2_proteins_portal", "biotoolsCURIE": "biotools:genomics_2_proteins_portal", "version": [], "otherID": [], "relation": [], "function": [ { "operation": [ { "uri": "http://edamontology.org/operation_2429", "term": "Mapping" }, { "uri": "http://edamontology.org/operation_0570", "term": "Structure visualisation" }, { "uri": "http://edamontology.org/operation_0564", "term": "Sequence visualisation" }, { "uri": "http://edamontology.org/operation_0361", "term": "Sequence annotation" } ], "input": [], "output": [], "note": null, "cmd": null } ], "toolType": [ "Bioinformatics portal" ], "topic": [ { "uri": "http://edamontology.org/topic_2814", "term": "Protein structure analysis" }, { "uri": "http://edamontology.org/topic_0199", "term": "Genetic variation" } ], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": "Free of charge", "accessibility": "Open access", "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [ { "doi": "10.1038/s41592-024-02409-0", "pmid": null, "pmcid": null, "type": [], "version": null, "note": null, "metadata": { "title": "Genomics 2 Proteins portal: a resource and discovery tool for linking genetic screening outputs to protein sequences and structures", "abstract": "Recent advances in AI-based methods have revolutionized the field of structural biology. Concomitantly, high-throughput sequencing and functional genomics have generated genetic variants at an unprecedented scale. However, efficient tools and resources are needed to link disparate data types—to ‘map’ variants onto protein structures, to better understand how the variation causes disease, and thereby design therapeutics. Here we present the Genomics 2 Proteins portal (https://g2p.broadinstitute.org/): a human proteome-wide resource that maps 20,076,998 genetic variants onto 42,413 protein sequences and 77,923 structures, with a comprehensive set of structural and functional features. Additionally, the Genomics 2 Proteins portal allows users to interactively upload protein residue-wise annotations (for example, variants and scores) as well as the protein structure beyond databases to establish the connection between genomics to proteins. The portal serves as an easy-to-use discovery tool for researchers and scientists to hypothesize the structure–function relationship between natural or synthetic variations and their molecular phenotypes.", "date": "2024-10-01T00:00:00Z", "citationCount": 1, "authors": [ { "name": "Kwon S." }, { "name": "Safer J." }, { "name": "Nguyen D.T." }, { "name": "Hoksza D." }, { "name": "May P." }, { "name": "Arbesfeld J.A." }, { "name": "Rubin A.F." }, { "name": "Campbell A.J." }, { "name": "Burgin A." }, { "name": "Iqbal S." } ], "journal": "Nature Methods" } } ], "credit": [], "owner": "unethical", "additionDate": "2025-06-15T04:45:08.927267Z", "lastUpdate": "2025-06-15T04:51:27.735002Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null }, { "name": "HPV-Meta", "description": "A pipeline to detect human papillomavirus (HPV) transcripts in RNA sequencing (RNA-seq) data. Designed to enhance the accuracy of HPV detection and minimise false positives due to contamination, HPV-meta is particularly valuable in cancer genomics research.\nUre A, Mukhedkar D, Arroyo Mühr LS. Using HPV-meta for human papillomavirus RNA quality detection. Scientific Reports. 2022 Jul 29;12(1):13058. doi:10.1038/s41598-022-17318-5.", "homepage": "https://github.com/HEAP-EXPOSOME/HPV-meta", "biotoolsID": "hpv-meta", "biotoolsCURIE": "biotools:hpv-meta", "version": [], "otherID": [], "relation": [], "function": [], "toolType": [], "topic": [], "operatingSystem": [], "language": [], "license": null, "collectionID": [], "maturity": null, "cost": null, "accessibility": null, "elixirPlatform": [], "elixirNode": [], "elixirCommunity": [], "link": [], "download": [], "documentation": [], "publication": [], "credit": [], "owner": "roxana.martinez", "additionDate": "2025-06-12T17:40:44.726868Z", "lastUpdate": "2025-06-12T17:44:55.562738Z", "editPermission": { "type": "private", "authors": [] }, "validated": 0, "homepage_status": 0, "elixir_badge": 0, "confidence_flag": null } ] }