{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T07:57:12Z","timestamp":1790495832623,"version":"4.1.0"},"reference-count":16,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["HL180612"],"award-info":[{"award-number":["HL180612"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["CA271891"],"award-info":[{"award-number":["CA271891"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["MH110504"],"award-info":[{"award-number":["MH110504"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["NS123719"],"award-info":[{"award-number":["NS123719"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Reference-free deconvolution methods are widely used to estimate cell-type composition and expression profiles from bulk transcriptomic data when native cell type references are unavailable. However, these methods often suffer from systematic biases caused by the asymmetric differential gene expressions across cell types and biological or experimental conditions, producing inaccurate proportion inference and reduced interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Here we present IECP (Iterative Equilibration of Cell-type Expression Profiles), an R package that improves deconvolution accuracy by iteratively equilibrating the asymmetric differential gene expressions across cell types. IECP identifies consistently expressed genes (CEGs) across estimated cell-type profiles, computes CEG-based sample-wise scaling factors, and equilibrates the bulk data matrix before the next deconvolution iteration. By integrating IECP with five popular reference-free deconvolution methods, CAM3.0, TOAST, PREDE, RefFreeEWAS, and CDseq, we demonstrate consistent improvements in cell-type proportion estimation on multiple benchmark datasets<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability<\/jats:title>\n                    <jats:p>IECP R package is freely available at https:\/\/github.com\/niccolodpdu\/IECP, with sample data and application vignettes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag686","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:00:05Z","timestamp":1789473605000},"source":"Crossref","is-referenced-by-count":0,"title":["IECP: iterative equilibration of cell-type expression profiles improves accuracy of reference-free deconvolution"],"prefix":"10.1093","volume":"42","author":[{"given":"Dongping","family":"Du","sequence":"first","affiliation":[{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University , Arlington, VA 22203,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David M","family":"Herrington","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Wake Forest University School of Medicine , Winston-Salem, NC 27157,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6743-7413","authenticated-orcid":false,"given":"Guoqiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University , Beijing 100084,","place":["P.R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1788-1102","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University , Arlington, VA 22203,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9456-0743","authenticated-orcid":false,"given":"Yizhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University , Arlington, VA 22203,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"2026092703014235000_btag686-B1","doi-asserted-by":"publisher","first-page":"eadh2588","DOI":"10.1126\/sciadv.adh2588","article-title":"Evaluating performance and applications of sample-wise cell deconvolution methods on human brain transcriptomic data","volume":"10","author":"Dai","year":"2024","journal-title":"Sci Adv"},{"key":"2026092703014235000_btag686-B2","article-title":"When does non-negative matrix factorization give a correct decomposition into parts? In:","author":"Donoho","year":"2003","journal-title":"Advances in Neural Information Processing Systems."},{"key":"2026092703014235000_btag686-B3","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1093\/bib\/bbx008","article-title":"Selecting between-sample RNA-Seq normalization methods from the perspective of their assumptions","volume":"19","author":"Evans","year":"2018","journal-title":"Brief Bioinform"},{"key":"2026092703014235000_btag686-B4","author":"Ge"},{"key":"2026092703014235000_btag686-B5","first-page":"1249","article-title":"Robust near-separable nonnegative matrix factorization using linear optimization","volume":"15","author":"Gillis","year":"2014","journal-title":"J Mach Learn Res"},{"key":"2026092703014235000_btag686-B6","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1038\/nmeth.3254","article-title":"Inferring biological tasks using Pareto analysis of high-dimensional data","volume":"12","author":"Hart","year":"2015","journal-title":"Nat Methods"},{"key":"2026092703014235000_btag686-B7","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1186\/s12859-016-1140-4","article-title":"Reference-free deconvolution of DNA methylation data and mediation by cell composition effects","volume":"17","author":"Houseman","year":"2016","journal-title":"BMC Bioinform"},{"key":"2026092703014235000_btag686-B8","doi-asserted-by":"publisher","first-page":"e1007510","DOI":"10.1371\/journal.pcbi.1007510","article-title":"CDSeq: a novel complete deconvolution method for dissecting heterogeneous samples using gene expression data","volume":"15","author":"Kang","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"2026092703014235000_btag686-B9","doi-asserted-by":"publisher","first-page":"vbae136","DOI":"10.1093\/bioadv\/vbae136","article-title":"DECOMICS, a shiny application for unsupervised cell type deconvolution and biological interpretation of bulk omic data","volume":"4","author":"Karkar","year":"2024","journal-title":"Bioinform Adv"},{"key":"2026092703014235000_btag686-B10","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1038\/nmeth.1710","article-title":"Population-specific expression analysis (PSEA) reveals molecular changes in diseased brain","volume":"8","author":"Kuhn","year":"2011","journal-title":"Nat Methods"},{"key":"2026092703014235000_btag686-B11","doi-asserted-by":"publisher","first-page":"764206","DOI":"10.1155\/2008\/764206","article-title":"Theorems on positive data: on the uniqueness of NMF","volume":"2008","author":"Laurberg","year":"2008","journal-title":"Comput Intell Neurosci"},{"key":"2026092703014235000_btag686-B12","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1186\/s13059-019-1778-0","article-title":"TOAST: improving reference-free cell composition estimation by cross-cell type differential analysis","volume":"20","author":"Li","year":"2019","journal-title":"Genome Biol"},{"key":"2026092703014235000_btag686-B13","doi-asserted-by":"publisher","first-page":"e1008452","DOI":"10.1371\/journal.pcbi.1008452","article-title":"Deconvolution of heterogeneous tumor samples using partial reference signals","volume":"16","author":"Qin","year":"2020","journal-title":"PLoS Comput Biol"},{"key":"2026092703014235000_btag686-B14","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1038\/s41467-022-28655-4","article-title":"Comprehensive evaluation of deconvolution methods for human brain gene expression","volume":"13","author":"Sutton","year":"2022","journal-title":"Nat Commun"},{"key":"2026092703014235000_btag686-B15","doi-asserted-by":"publisher","first-page":"18909","DOI":"10.1038\/srep18909","article-title":"Mathematical modelling of transcriptional heterogeneity identifies novel markers and subpopulations in complex tissues","volume":"6","author":"Wang","year":"2016","journal-title":"Sci Rep"},{"key":"2026092703014235000_btag686-B16","doi-asserted-by":"publisher","first-page":"vbac076","DOI":"10.1093\/bioadv\/vbac076","article-title":"Cosbin: cosine score-based iterative normalization of biologically diverse samples","volume":"2","author":"Wu","year":"2022","journal-title":"Bioinform Adv"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag686\/71110177\/btag686.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag686\/71110177\/btag686.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag686\/71110177\/btag686.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T07:01:50Z","timestamp":1790492510000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag686\/8800075"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":16,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag686","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,8,31]]},"article-number":"btag686"}}