{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T17:48:37Z","timestamp":1769881717211,"version":"3.49.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013133","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T00:00:00Z","timestamp":1749686400000}}],"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014261","name":"National Institute for Health Care Management Foundation","doi-asserted-by":"publisher","award":["R01CA197903"],"award-info":[{"award-number":["R01CA197903"]}],"id":[{"id":"10.13039\/100014261","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014261","name":"National Institute for Health Care Management Foundation","doi-asserted-by":"publisher","award":["R01CA251848"],"award-info":[{"award-number":["R01CA251848"]}],"id":[{"id":"10.13039\/100014261","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Accurate estimation of malignant cell fractions in tissues plays a critical role in cancer diagnosis, prognosis, and subsequent treatment decisions. However, most currently available methods provide only point estimates, neglecting the quantification of uncertainties, which is essential for both clinical and research applications. This study introduces DeepDeconUQ, a deep neural network model developed to estimate prediction intervals for malignant cell fractions based on bulk RNA-seq data. This approach addresses limitations in current malignant cell fraction estimation methods by integrating uncertainty quantification into predictions of cancer cell fractions. DeepDeconUQ leverages single-cell RNA sequencing (scRNA-seq) data in conjunction with conformalized quantile regression to produce reliable prediction intervals. The model trains a quantile regression neural network to establish upper and lower bounds for cancer cell proportions, followed by a calibration step that refines these intervals to ensure both statistical validity (coverage probability) and discrimination (narrow intervals). Benchmark analyses indicate that DeepDeconUQ consistently surpasses existing methods, achieving high coverage accuracy with tight prediction intervals across simulated and real cancer datasets. The robustness of DeepDeconUQ is further demonstrated by its resilience to various gene expression perturbations. The DeepDeconUQ method is publicly accessible at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/jiaweih14\/DeepDeconUQ\" xlink:type=\"simple\">https:\/\/github.com\/jiaweih14\/DeepDeconUQ<\/jats:ext-link>.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013133","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T18:09:36Z","timestamp":1749060576000},"page":"e1013133","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["DeepDeconUQ estimates malignant cell fraction prediction intervals in bulk RNA-seq tissue"],"prefix":"10.1371","volume":"21","author":[{"given":"Jiawei","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin R.","family":"Kelly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchi","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingying","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang F.","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8552-043X","authenticated-orcid":true,"given":"Fengzhu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"issue":"6","key":"pcbi.1013133.ref001","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1038\/nmeth.1613","article-title":"Computational methods for transcriptome annotation and quantification using RNA-seq","volume":"8","author":"M Garber","year":"2011","journal-title":"Nat Methods"},{"issue":"2","key":"pcbi.1013133.ref002","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1093\/bfgp\/elu035","article-title":"Measuring differential gene expression with RNA-seq: challenges and strategies for data analysis","volume":"14","author":"F Finotello","year":"2015","journal-title":"Brief Funct Genomics"},{"issue":"11","key":"pcbi.1013133.ref003","article-title":"Deconvolution of heterogeneous tumor samples using partial reference signals","volume":"16","author":"Y Qin","year":"2020","journal-title":"PLoS Comput Biol"},{"issue":"6","key":"pcbi.1013133.ref004","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1038\/nm.4336","article-title":"Single-cell transcriptomics uncovers distinct molecular signatures of stem cells in chronic myeloid leukemia","volume":"23","author":"A Giustacchini","year":"2017","journal-title":"Nat Med"},{"issue":"7","key":"pcbi.1013133.ref005","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1038\/s41587-019-0114-2","article-title":"Determining cell type abundance and expression from bulk tissues with digital cytometry","volume":"37","author":"AM Newman","year":"2019","journal-title":"Nat Biotechnol"},{"issue":"1","key":"pcbi.1013133.ref006","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1038\/s41467-018-08023-x","article-title":"Bulk tissue cell type deconvolution with multi-subject single-cell expression reference","volume":"10","author":"X Wang","year":"2019","journal-title":"Nat Commun"},{"key":"pcbi.1013133.ref007","unstructured":"Xie D, Wang J. Robust statistical inference for cell type deconvolution. 2022. https:\/\/arxiv.org\/abs\/2202.06420"},{"issue":"30","key":"pcbi.1013133.ref008","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.aba2619","article-title":"Deep learning-based cell composition analysis from tissue expression profiles","volume":"6","author":"K Menden","year":"2020","journal-title":"Sci Adv"},{"issue":"10","key":"pcbi.1013133.ref009","doi-asserted-by":"crossref","first-page":"1794","DOI":"10.1101\/gr.272344.120","article-title":"Likelihood-based deconvolution of bulk gene expression data using single-cell references","volume":"31","author":"DD Erdmann-Pham","year":"2021","journal-title":"Genome Res"},{"issue":"2","key":"pcbi.1013133.ref010","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1109\/JPROC.2016.2607121","article-title":"A critical survey of deconvolution methods for separating cell types in complex tissues","volume":"105","author":"S Mohammadi","year":"2017","journal-title":"Proc IEEE"},{"issue":"1","key":"pcbi.1013133.ref011","doi-asserted-by":"crossref","first-page":"5650","DOI":"10.1038\/s41467-020-19015-1","article-title":"Benchmarking of cell type deconvolution pipelines for transcriptomics data","volume":"11","author":"F Avila Cobos","year":"2020","journal-title":"Nat Commun"},{"key":"pcbi.1013133.ref012","first-page":"8378","article-title":"Locally valid and discriminative prediction intervals for deep learning models","volume":"34","author":"Z Lin","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"issue":"548","key":"pcbi.1013133.ref013","doi-asserted-by":"crossref","first-page":"2521","DOI":"10.1080\/01621459.2024.2382435","article-title":"Statistical inference of cell-type proportions estimated from bulk expression data","volume":"119","author":"B Cai","year":"2024","journal-title":"J Am Stat Assoc"},{"key":"pcbi.1013133.ref014","unstructured":"Romano Y, Patterson E, Candes E. Conformalized quantile regression. Adv Neural Inf Process Syst. 2019. doi: 10.48550\/arXiv.1905.03222"},{"issue":"1","key":"pcbi.1013133.ref015","doi-asserted-by":"crossref","first-page":"4846","DOI":"10.1038\/s41467-023-40503-7","article-title":"Cell-type-specific co-expression inference from single cell RNA-sequencing data","volume":"14","author":"C Su","year":"2023","journal-title":"Nat Commun"},{"issue":"2","key":"pcbi.1013133.ref016","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"Q McNEMAR","year":"1947","journal-title":"Psychometrika"},{"issue":"1","key":"pcbi.1013133.ref017","doi-asserted-by":"crossref","first-page":"6735","DOI":"10.1038\/s41467-022-34550-9","article-title":"Deep autoencoder for interpretable tissue-adaptive deconvolution and cell-type-specific gene analysis","volume":"13","author":"Y Chen","year":"2022","journal-title":"Nat Commun"},{"issue":"3","key":"pcbi.1013133.ref018","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s12551-024-01201-w","article-title":"Structure-based prediction of protein-nucleic acid binding using graph neural networks","volume":"16","author":"JM Sagendorf","year":"2024","journal-title":"Biophys Rev"},{"key":"pcbi.1013133.ref019","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks.","volume-title":"International conference on machine learning","author":"M Long","year":"2017"},{"issue":"10","key":"pcbi.1013133.ref020","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1038\/s42256-022-00532-1","article-title":"Transformer-based protein generation with regularized latent space optimization","volume":"4","author":"E Castro","year":"2022","journal-title":"Nat Mach Intell"},{"key":"pcbi.1013133.ref021","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1186\/s13059-015-0844-5","article-title":"MAST: a flexible statistical framework for assessing transcriptional changes and characterizing heterogeneity in single-cell RNA sequencing data","volume":"16","author":"G Finak","year":"2015","journal-title":"Genome Biol"},{"issue":"5","key":"pcbi.1013133.ref022","doi-asserted-by":"crossref","first-page":"100969","DOI":"10.1016\/j.patter.2024.100969","article-title":"DeepDecon accurately estimates cancer cell fractions in bulk RNA-seq data","volume":"5","author":"J Huang","year":"2024","journal-title":"Patterns (N Y)"},{"issue":"6","key":"pcbi.1013133.ref023","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2019.01.031","article-title":"Single-cell RNA-Seq reveals AML hierarchies relevant to disease progression and immunity","volume":"176","author":"P van Galen","year":"2019","journal-title":"Cell"},{"issue":"1","key":"pcbi.1013133.ref024","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13059-017-1382-0","article-title":"SCANPY: large-scale single-cell gene expression data analysis","volume":"19","author":"FA Wolf","year":"2018","journal-title":"Genome Biol"},{"issue":"7728","key":"pcbi.1013133.ref025","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1038\/s41586-018-0623-z","article-title":"Functional genomic landscape of acute myeloid leukaemia","volume":"562","author":"JW Tyner","year":"2018","journal-title":"Nature"},{"issue":"5","key":"pcbi.1013133.ref026","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1158\/2159-8290.CD-12-0095","article-title":"The cBio cancer genomics portal: an open platform for exploring multidimensional cancer genomics data","volume":"2","author":"E Cerami","year":"2012","journal-title":"Cancer Discov"},{"issue":"5","key":"pcbi.1013133.ref027","doi-asserted-by":"crossref","DOI":"10.1016\/j.ccell.2020.08.014","article-title":"Single-cell characterization of malignant phenotypes and developmental trajectories of adrenal neuroblastoma","volume":"38","author":"R Dong","year":"2020","journal-title":"Cancer Cell"},{"key":"pcbi.1013133.ref028","article-title":"TISCH: a comprehensive web resource enabling interactive single-cell transcriptome visualization of tumor microenvironment","volume":"49","author":"D Sun","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1013133.ref029","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkx1090","article-title":"LinkedOmics: analyzing multi-omics data within and across 32 cancer types","volume":"46","author":"SV Vasaikar","year":"2018","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1013133.ref030","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1158\/1078-0432.CCR-22-2041","article-title":"Colorectal cancer metastases in the liver establish immunosuppressive spatial networking between tumor-associated SPP1+ macrophages and fibroblasts","volume":"29","author":"A Sathe","year":"2023","journal-title":"Clin Cancer Res"},{"issue":"4","key":"pcbi.1013133.ref031","first-page":"638","article-title":"Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition","volume":"26","author":"V Teller","year":"2000","journal-title":"Comput Linguist"},{"key":"pcbi.1013133.ref032","volume-title":"Introduction to modern information retrieval","author":"GG Chowdhury","year":"2010"},{"key":"pcbi.1013133.ref033","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1186\/s12864-018-4922-4","article-title":"Single cell RNA-seq data clustering using TF-IDF based methods","volume":"19","author":"M Moussa","year":"2018","journal-title":"BMC Genomics"},{"issue":"1","key":"pcbi.1013133.ref034","doi-asserted-by":"crossref","first-page":"211","DOI":"10.3150\/10-BEJ267","article-title":"Estimating conditional quantiles with the help of the pinball loss","volume":"17","author":"I Steinwart","year":"2011","journal-title":"Bernoulli"},{"issue":"4","key":"pcbi.1013133.ref035","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1002\/1099-131X(200007)19:4<299::AID-FOR775>3.0.CO;2-V","article-title":"A quantile regression neural network approach to estimating the conditional density of multiperiod returns","volume":"19","author":"JW Taylor","year":"2000","journal-title":"J Forecast"},{"issue":"45","key":"pcbi.1013133.ref036","first-page":"1231","article-title":"Nonparametric quantile estimation","volume":"7","author":"I Takeuchi","year":"2006","journal-title":"J Mach Learn Res"},{"key":"pcbi.1013133.ref037","first-page":"444","article-title":"Machine-learning applications of algorithmic randomness.","volume-title":"Proceedings of the Sixteenth International Conference on Machine Learning. ICML \u201999","author":"V Vovk","year":"1999"},{"key":"pcbi.1013133.ref038","first-page":"345","volume-title":"Machine learning: ECML 2002: 13th European conference on machine learning Helsinki, Finland, August 19\u201323, 2002 proceedings","author":"H Papadopoulos","year":"2002"},{"key":"pcbi.1013133.ref039","volume-title":"Algorithmic learning in a random world","author":"V Vovk","year":"2005"},{"issue":"24","key":"pcbi.1013133.ref040","first-page":"1","article-title":"Calibrated multiple-output quantile regression with representation learning","volume":"24","author":"S Feldman","year":"2023","journal-title":"J Mach Learn Res"},{"issue":"523","key":"pcbi.1013133.ref041","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1080\/01621459.2017.1307116","volume":"113","author":"J Lei","year":"2018","journal-title":"J Am Statist Assoc"},{"key":"pcbi.1013133.ref042","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. 2017."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013133","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T00:00:00Z","timestamp":1749686400000}},{"DOI":"10.1371\/journal.pcbi.1013876","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T18:56:57Z","timestamp":1749754617000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013133"}},"subtitle":[],"editor":[{"given":"Lin","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":42,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013133","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]}}}