{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:14:47Z","timestamp":1772172887166,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1009014","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T00:00:00Z","timestamp":1623974400000}}],"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","award":["HG006620"],"award-info":[{"award-number":["HG006620"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["CA233280"],"award-info":[{"award-number":["CA233280"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["CA231877"],"award-info":[{"award-number":["CA231877"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000076","name":"Directorate for Biological Sciences","doi-asserted-by":"publisher","award":["1661497"],"award-info":[{"award-number":["1661497"]}],"id":[{"id":"10.13039\/100000076","id-type":"DOI","asserted-by":"publisher"}]},{"name":"German Federal Ministry of Education and Research","award":["031L0101C"],"award-info":[{"award-number":["031L0101C"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    Supervised machine learning is an essential but difficult to use approach in biomedical data analysis. The Galaxy-ML toolkit (\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/galaxyproject.org\/community\/machine-learning\/\" xlink:type=\"simple\">https:\/\/galaxyproject.org\/community\/machine-learning\/<\/jats:ext-link>\n                    ) makes supervised machine learning more accessible to biomedical scientists by enabling them to perform end-to-end reproducible machine learning analyses at large scale using only a web browser. Galaxy-ML extends Galaxy (\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/galaxyproject.org\/\" xlink:type=\"simple\">https:\/\/galaxyproject.org<\/jats:ext-link>\n                    ), a biomedical computational workbench used by tens of thousands of scientists across the world, with a suite of tools for all aspects of supervised machine learning.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1009014","type":"journal-article","created":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T16:46:50Z","timestamp":1622566010000},"page":"e1009014","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":18,"title":["Galaxy-ML: An accessible, reproducible, and scalable machine learning toolkit for biomedicine"],"prefix":"10.1371","volume":"17","author":[{"given":"Qiang","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2068-4695","authenticated-orcid":true,"given":"Anup","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0621-6705","authenticated-orcid":true,"given":"Simon","family":"Bray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5724-1276","authenticated-orcid":true,"given":"Allison","family":"Creason","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6811-9196","authenticated-orcid":true,"given":"Alireza","family":"Khanteymoori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4986-2157","authenticated-orcid":true,"given":"Vahid","family":"Jalili","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3079-6586","authenticated-orcid":true,"given":"Bj\u00f6rn","family":"Gr\u00fcning","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4583-5226","authenticated-orcid":true,"given":"Jeremy","family":"Goecks","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2021,6,1]]},"reference":[{"key":"pcbi.1009014.ref001","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.cell.2020.03.022","article-title":"How Machine Learning Will Transform Biomedicine","volume":"181","author":"J Goecks","year":"2020","journal-title":"Cell"},{"key":"pcbi.1009014.ref002","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1016\/j.cell.2018.05.015","article-title":"Next-Generation Machine Learning for Biological Networks","volume":"173","author":"DM Camacho","year":"2018","journal-title":"Cell"},{"key":"pcbi.1009014.ref003","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.inffus.2018.09.012","article-title":"Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities","volume":"50","author":"M Zitnik","year":"2019","journal-title":"Inf Fusion"},{"key":"pcbi.1009014.ref004","doi-asserted-by":"crossref","first-page":"6083072","DOI":"10.1155\/2017\/6083072","article-title":"An Update on Statistical Boosting in Biomedicine","volume":"2017","author":"A Mayr","year":"2017","journal-title":"Comput Math Methods Med"},{"key":"pcbi.1009014.ref005","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.pscychresns.2016.11.005","article-title":"Predicting CYP2D6 phenotype from resting brain perfusion images by gradient boosting","volume":"259","author":"G Napolitano","year":"2017","journal-title":"Psychiatry Res Neuroimaging"},{"key":"pcbi.1009014.ref006","first-page":"63","article-title":"Systematic assessment of analytical methods for drug sensitivity prediction from cancer cell line data","author":"IS Jang","year":"2014","journal-title":"Pac Symp Biocomput"},{"key":"pcbi.1009014.ref007","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1038\/nbt.2877","article-title":"A community effort to assess and improve drug sensitivity prediction algorithms","volume":"32","author":"JC Costello","year":"2014","journal-title":"Nat Biotechnol"},{"key":"pcbi.1009014.ref008","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.cell.2018.12.015","article-title":"Predicting Splicing from Primary Sequence with Deep Learning","volume":"176","author":"K Jaganathan","year":"2019","journal-title":"Cell"},{"key":"pcbi.1009014.ref009","doi-asserted-by":"crossref","first-page":"4862","DOI":"10.1093\/bioinformatics\/btz422","article-title":"AlphaFold at CASP13","volume":"35","author":"M AlQuraishi","year":"2019","journal-title":"Bioinformatics"},{"key":"pcbi.1009014.ref010","article-title":"Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging","author":"Y Xu","year":"2019","journal-title":"Clin Cancer Res"},{"key":"pcbi.1009014.ref011","article-title":"The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2020 update","author":"V Jalili","year":"2020","journal-title":"Nucleic Acids Research"},{"key":"pcbi.1009014.ref012","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1186\/gb4161","article-title":"Dissemination of scientific software with Galaxy ToolShed","volume":"15","author":"D Blankenberg","year":"2014","journal-title":"Genome Biol"},{"key":"pcbi.1009014.ref013","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1126\/science.359.6377.725","article-title":"Artificial intelligence faces reproducibility crisis","volume":"359","author":"M Hutson","year":"2018","journal-title":"Science"},{"key":"pcbi.1009014.ref014","doi-asserted-by":"crossref","first-page":"E14","DOI":"10.1038\/s41586-020-2766-y","article-title":"Transparency and reproducibility in artificial intelligence","volume":"586","author":"Massive Analysis Quality Control (MAQC) Society Board of Directors","year":"2020","journal-title":"Nature"},{"key":"pcbi.1009014.ref015","unstructured":"Polkh E, Kumar A. Hands-on for \u201cAge prediction using machine learning\u201d tutorial. [cited 14 May 2020]. Available: https:\/\/galaxyproject.github.io\/training-material\/topics\/statistics\/tutorials\/age-prediction-with-ml\/tutorial.html"},{"key":"pcbi.1009014.ref016","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1186\/s13059-018-1599-6","article-title":"Predicting age from the transcriptome of human dermal fibroblasts","volume":"19","author":"JG Fleischer","year":"2018","journal-title":"Genome Biol"},{"key":"pcbi.1009014.ref017","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.fsigen.2017.07.015","article-title":"Chronological age prediction based on DNA methylation: Massive parallel sequencing and random forest regression","volume":"31","author":"J Naue","year":"2017","journal-title":"Forensic Sci Int Genet"},{"key":"pcbi.1009014.ref018","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pcbi.1009014.ref019","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.jbi.2018.07.014","article-title":"Relief-based feature selection: Introduction and review","volume":"85","author":"RJ Urbanowicz","year":"2018","journal-title":"J Biomed Inform"},{"key":"pcbi.1009014.ref020","first-page":"559","article-title":"Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"G Lema\u00eetre","year":"2017","journal-title":"J Mach Learn Res"},{"key":"pcbi.1009014.ref021","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","volume-title":"Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"T Chen","year":"2016"},{"key":"pcbi.1009014.ref022","unstructured":"Keras Team. Keras: the Python deep learning API. [cited 15 May 2020]. Available: https:\/\/keras.io"},{"key":"pcbi.1009014.ref023","first-page":"3","article-title":"MLxtend: Providing machine learning and data science utilities and extensions to Python\u2019s scientific computing stack","author":"S Raschka","year":"2018","journal-title":"The Journal of Open Source Software"},{"key":"pcbi.1009014.ref024","first-page":"192","article-title":"Data-driven advice for applying machine learning to bioinformatics problems","volume":"23","author":"RS Olson","year":"2018","journal-title":"Pac Symp Biocomput"},{"key":"pcbi.1009014.ref025","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s13040-017-0154-4","article-title":"PMLB: a large benchmark suite for machine learning evaluation and comparison","volume":"10","author":"RS Olson","year":"2017","journal-title":"BioData Min"},{"key":"pcbi.1009014.ref026","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1093\/jnci\/djt007","article-title":"The Clinical Relevance of Cancer Cell Lines","volume":"105","author":"J-P Gillet","year":"2013","journal-title":"J Natl Cancer Inst"},{"key":"pcbi.1009014.ref027","article-title":"Next-generation characterization of the Cancer Cell Line Encyclopedia","author":"M Ghandi","year":"2019","journal-title":"Nature"},{"key":"pcbi.1009014.ref028","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1038\/s41592-019-0360-8","article-title":"Selene: a PyTorch-based deep learning library for sequence data","volume":"16","author":"KM Chen","year":"2019","journal-title":"Nat Methods"},{"key":"pcbi.1009014.ref029","author":"P Amstutz","year":"2016","journal-title":"Common Workflow Language"},{"key":"pcbi.1009014.ref030","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning-based sequence model","volume":"12","author":"J Zhou","year":"2015","journal-title":"Nat Methods"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1009014","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T00:00:00Z","timestamp":1623974400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T13:41:17Z","timestamp":1624023677000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009014"}},"subtitle":[],"editor":[{"given":"Mihaela","family":"Pertea","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,6,1]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,6,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009014","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.06.25.172445","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,1]]}}}