{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:05Z","timestamp":1772138045103,"version":"3.50.1"},"reference-count":17,"publisher":"Oxford University Press (OUP)","issue":"18","license":[{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Wendy Schmidt Foundation"},{"name":"National Institutes of Health Common Funds","award":["U54HG006093"],"award-info":[{"award-number":["U54HG006093"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5U01HG008699"],"award-info":[{"award-number":["5U01HG008699"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Do machine learning methods improve standard deconvolution techniques for gene expression data? This article uses a unique new dataset combined with an open innovation competition to evaluate a wide range of approaches developed by 294 competitors from 20 countries. The competition\u2019s objective was to address a deconvolution problem critical to analyzing genetic perturbations from the Connectivity Map. The issue consists of separating gene expression of individual genes from raw measurements obtained from gene pairs. We evaluated the outcomes using ground-truth data (direct measurements for single genes) obtained from the same samples.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We find that the top-ranked algorithm, based on random forest regression, beat the other methods in accuracy and reproducibility; more traditional gaussian-mixture methods performed well and tended to be faster, and the best deep learning approach yielded outcomes slightly inferior to the above methods. We anticipate researchers in the field will find the dataset and algorithms developed in this study to be a powerful research tool for benchmarking their deconvolution methods and a resource useful for multiple applications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The data is freely available at clue.io\/data (section Contests) and the software is on GitHub at https:\/\/github.com\/cmap\/gene_deconvolution_challenge<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab192","type":"journal-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T16:24:02Z","timestamp":1616171042000},"page":"2889-2895","source":"Crossref","is-referenced-by-count":1,"title":["Improving deconvolution methods in biology through open innovation competitions: an application to the connectivity map"],"prefix":"10.1093","volume":"37","author":[{"given":"Andrea","family":"Blasco","sequence":"first","affiliation":[{"name":"Harvard Business School, Harvard University , Boston, MA 02163, USA"},{"name":"Broad Institute of Harvard and MIT , Cambridge, MA 02142, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ted","family":"Natoli","sequence":"additional","affiliation":[{"name":"Broad Institute of Harvard and MIT , Cambridge, MA 02142, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael G","family":"Endres","sequence":"additional","affiliation":[{"name":"Harvard Business School, Harvard University , Boston, MA 02163, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rinat A","family":"Sergeev","sequence":"additional","affiliation":[{"name":"Harvard Business School, Harvard University , Boston, MA 02163, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Randazzo","sequence":"additional","affiliation":[{"name":"Harvard Business School, Harvard University , Boston, MA 02163, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin H","family":"Paik","sequence":"additional","affiliation":[{"name":"Harvard Business School, Harvard University , Boston, MA 02163, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N J Maximilian","family":"Macaluso","sequence":"additional","affiliation":[{"name":"Broad Institute of Harvard and MIT , Cambridge, MA 02142, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajiv","family":"Narayan","sequence":"additional","affiliation":[{"name":"Broad Institute of Harvard and MIT , Cambridge, MA 02142, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Lu","sequence":"additional","affiliation":[{"name":"Broad Institute of Harvard and MIT , Cambridge, MA 02142, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Peck","sequence":"additional","affiliation":[{"name":"Broad Institute of Harvard and MIT , Cambridge, MA 02142, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karim R","family":"Lakhani","sequence":"additional","affiliation":[{"name":"Harvard Business School, Harvard University , Boston, MA 02163, USA"},{"name":"National Bureau of Economic Research (NBER) , Cambridge, MA 02138, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aravind","family":"Subramanian","sequence":"additional","affiliation":[{"name":"Broad Institute of Harvard and MIT , Cambridge, MA 02142, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,3,22]]},"reference":[{"key":"2023061310560288000_btab192-B1","doi-asserted-by":"crossref","first-page":"e0222165","DOI":"10.1371\/journal.pone.0222165","article-title":"Advancing computational biology and bioinformatics research through open innovation competitions","volume":"14","author":"Blasco","year":"2019","journal-title":"PLoS One"},{"key":"2023061310560288000_btab192-B2","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1016\/j.cell.2017.10.023","article-title":"Efficient generation of transcriptomic profiles by random composite measurements","volume":"171","author":"Cleary","year":"2017","journal-title":"Cell"},{"key":"2023061310560288000_btab192-B3","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1038\/s41592-019-0353-7","article-title":"Scalable analysis of cell-type composition from single-cell transcriptomics using deep recurrent learning","volume":"16","author":"Deng","year":"2019","journal-title":"Nat. Methods"},{"key":"2023061310560288000_btab192-B4","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1093\/bioinformatics\/btt333","article-title":"Crowdsourcing for bioinformatics","volume":"29","author":"Good","year":"2013","journal-title":"Bioinformatics"},{"key":"2023061310560288000_btab192-B5","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1038\/nbt.2495","article-title":"Prize-based contests can provide solutions to computational biology problems","volume":"31","author":"Lakhani","year":"2013","journal-title":"Nat. Biotechnol"},{"key":"2023061310560288000_btab192-B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-016-1414-x","article-title":"l1kdeconv: an r package for peak calling analysis with LINCS L1000 data","volume":"18","author":"Li","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2023061310560288000_btab192-B7","doi-asserted-by":"crossref","first-page":"10370","DOI":"10.1073\/pnas.1832361100","article-title":"Expression deconvolution: a reinterpretation of DNA microarray data reveals dynamic changes in cell populations","volume":"100","author":"Lu","year":"2003","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023061310560288000_btab192-B8","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1038\/nmeth.3337","article-title":"Robust enumeration of cell subsets from tissue expression profiles","volume":"12","author":"Newman","year":"2015","journal-title":"Nat. Methods"},{"key":"2023061310560288000_btab192-B9","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1038\/nmeth.2929","article-title":"Efficient Bayesian-based multiview deconvolution","volume":"11","author":"Preibisch","year":"2014","journal-title":"Nat. Methods"},{"key":"2023061310560288000_btab192-B10","doi-asserted-by":"crossref","first-page":"2787","DOI":"10.1093\/bioinformatics\/btaa064","article-title":"A Bayesian approach to accurate and robust signature detection on LINCS L1000 data","volume":"36","author":"Qiu","year":"2020","journal-title":"Bioinformatics"},{"key":"2023061310560288000_btab192-B11","first-page":"234","author":"Ronneberger","year":"2015"},{"key":"2023061310560288000_btab192-B12","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1016\/j.coi.2013.09.015","article-title":"Computational deconvolution: extracting cell type-specific information from heterogeneous samples","volume":"25","author":"Shen-Orr","year":"2013","journal-title":"Curr. Opin. Immunol"},{"key":"2023061310560288000_btab192-B13","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1038\/nmeth.1439","article-title":"Cell type-specific gene expression differences in complex tissues","volume":"7","author":"Shen-Orr","year":"2010","journal-title":"Nat. Methods"},{"key":"2023061310560288000_btab192-B14","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1016\/j.cell.2017.10.049","article-title":"A next generation connectivity map: L1000 platform and the first 1,000,000 profiles","volume":"171","author":"Subramanian","year":"2017","journal-title":"Cell"},{"key":"2023061310560288000_btab192-B15","first-page":"1998","article-title":"Model-based clustering with data correction for removing artifacts in gene expression data","volume":"11","author":"Young","year":"2016","journal-title":"Ann. Appl. Stat"},{"key":"2023061310560288000_btab192-B16","doi-asserted-by":"crossref","first-page":"2209","DOI":"10.1038\/s41467-019-09990-5","article-title":"Complete deconvolution of cellular mixtures based on linearity of transcriptional signatures","volume":"10","author":"Zaitsev","year":"2019","journal-title":"Nat. Commun"},{"key":"2023061310560288000_btab192-B17","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1038\/nmeth.1830","article-title":"Gene expression deconvolution in linear space","volume":"9","author":"Zhong","year":"2011","journal-title":"Nat. Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab192\/36940231\/btab192.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/18\/2889\/50579161\/btab192.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/18\/2889\/50579161\/btab192.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T06:58:02Z","timestamp":1686639482000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/18\/2889\/6180069"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,3,22]]},"references-count":17,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2021,9,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab192","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.01.10.897363","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,9,15]]},"published":{"date-parts":[[2021,3,22]]}}}