{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:30:22Z","timestamp":1771957822847,"version":"3.50.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Swedish Cancer Society, Karolinska Institutet"},{"name":"Cancer Research KI"},{"DOI":"10.13039\/100017156","name":"Swedish e-science Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017156","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,27]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Molecular phenotyping by gene expression profiling is central in contemporary cancer research and in molecular diagnostics but remains resource intense to implement. Changes in gene expression occurring in tumours cause morphological changes in tissue, which can be observed on the microscopic level. The relationship between morphological patterns and some of the molecular phenotypes can be exploited to predict molecular phenotypes from routine haematoxylin and eosin-stained whole slide images (WSIs) using convolutional neural networks (CNNs). In this study, we propose a new, computationally efficient approach to model relationships between morphology and gene expression.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We conducted the first transcriptome-wide analysis in prostate cancer, using CNNs to predict bulk RNA-sequencing estimates from WSIs for 370 patients from the TCGA PRAD study. Out of 15\u00a0586 protein coding transcripts, 6618 had predicted expression significantly associated with RNA-seq estimates (FDR-adjusted P-value &amp;lt;1\u00d710\u22124) in a cross-validation and 5419 (81.9%) of these associations were subsequently validated in a held-out test set. We furthermore predicted the prognostic cell-cycle progression score directly from WSIs. These findings suggest that contemporary computer vision models offer an inexpensive and scalable solution for prediction of gene expression phenotypes directly from WSIs, providing opportunity for cost-effective large-scale research studies and molecular diagnostics.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>A self-contained example is available from http:\/\/github.com\/phiwei\/prostate_coexpression. Model predictions and metrics are available from doi.org\/10.5281\/zenodo.4739097.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac343","type":"journal-article","created":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T23:36:17Z","timestamp":1653089777000},"page":"3462-3469","source":"Crossref","is-referenced-by-count":25,"title":["Transcriptome-wide prediction of prostate cancer gene expression from histopathology images using co-expression-based convolutional neural networks"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1788-0716","authenticated-orcid":false,"given":"Philippe","family":"Weitz","sequence":"first","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet , 17177 Stockholm, Sweden"}]},{"given":"Yinxi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet , 17177 Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9470-4783","authenticated-orcid":false,"given":"Kimmo","family":"Kartasalo","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet , 17177 Stockholm, Sweden"},{"name":"Faculty of Medicine and Health Technology, Tampere University , 33100 Tampere, Finland"}]},{"given":"Lars","family":"Egevad","sequence":"additional","affiliation":[{"name":"Department of Oncology and Pathology, Karolinska Institutet , 17177 Stockholm, Sweden"}]},{"given":"Johan","family":"Lindberg","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet , 17177 Stockholm, Sweden"},{"name":"Science for Life Laboratory , 17177 Stockholm, Sweden"}]},{"given":"Henrik","family":"Gr\u00f6nberg","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet , 17177 Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5032-5266","authenticated-orcid":false,"given":"Martin","family":"Eklund","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet , 17177 Stockholm, Sweden"}]},{"given":"Mattias","family":"Rantalainen","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet , 17177 Stockholm, Sweden"},{"name":"MedTechLabs, BioClinicum, Karolinska University Hospital , 17176 Stockholm, Sweden"}]}],"member":"286","published-online":{"date-parts":[[2022,5,20]]},"reference":[{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"11428","DOI":"10.1073\/pnas.1902651116","article-title":"Genomic correlates of clinical outcome in advanced prostate cancer","volume":"116","author":"Abida","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1093\/bioinformatics\/btu638","article-title":"HTSeq\u2013a Python framework to work with high-throughput sequencing data","volume":"31","author":"Anders","year":"2015","journal-title":"Bioinformatics"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1038\/ng.2279","article-title":"Exome sequencing identifies recurrent SPOP, FOXA1 and MED12 mutations in prostate cancer","volume":"44","author":"Barbieri","year":"2012","journal-title":"Nat. Genet"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc. Series B Methodol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/j.juro.2014.02.003","article-title":"Prognostic utility of the cell cycle progression score generated from biopsy in men treated with prostatectomy","volume":"192","author":"Bishoff","year":"2014","journal-title":"J. Urol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA Cancer J. Clin"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1038\/nature11412","article-title":"Comprehensive molecular portraits of human breast tumours","volume":"490","year":"2012","journal-title":"Nature"},{"key":"2023041408093555300_","first-page":"704","article-title":"SPOP and cancer: a systematic review","volume":"10","author":"Clark","year":"2020","journal-title":"Am. J. Cancer Res"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1056\/NEJMp1500523","article-title":"A new initiative on precision medicine","volume":"372","author":"Collins","year":"2015","journal-title":"N. Engl. J. Med"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"1428","DOI":"10.1200\/JCO.2012.46.4396","article-title":"Validation of a cell-cycle progression gene panel to improve risk stratification in a contemporary prostatectomy cohort","volume":"31","author":"Cooperberg","year":"2013","journal-title":"JCO"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.eururo.2014.11.030","article-title":"A biopsy-based 17-gene genomic prostate score predicts recurrence after radical prostatectomy and adverse surgical pathology in a racially diverse population of men with clinically low- and intermediate-risk prostate cancer","volume":"68","author":"Cullen","year":"2015","journal-title":"Eur. Urol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1038\/bjc.2012.39","article-title":"Prognostic value of a cell cycle progression signature for prostate cancer death in a conservatively managed needle biopsy cohort","volume":"106","author":"Cuzick","year":"2012","journal-title":"Br. J. Cancer"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"3439","DOI":"10.1093\/bioinformatics\/bti525","article-title":"BioMart and Bioconductor: a powerful link between biological databases and microarray data analysis","volume":"21","author":"Durinck","year":"2005","journal-title":"Bioinformatics"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1097\/PAS.0000000000000530","article-title":"The 2014 international society of urological pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma: definition of grading patterns and proposal for a new grading system","volume":"40","author":"Epstein","year":"2016","journal-title":"Am. J. Surg. Pathol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"e66855","DOI":"10.1371\/journal.pone.0066855","article-title":"Discovery and validation of a prostate cancer genomic classifier that predicts early metastasis following radical prostatectomy","volume":"8","author":"Erho","year":"2013","journal-title":"PLoS One"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.urology.2017.02.052","article-title":"Use of a 17-gene prognostic assay in contemporary urologic practice: results of an interim analysis in an observational cohort","volume":"107","author":"Eure","year":"2017","journal-title":"Urology"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1038\/s43018-020-0085-8","article-title":"Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis","volume":"1","author":"Fu","year":"2020","journal-title":"Nat. Cancer"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1016\/j.ccell.2018.10.016","article-title":"Molecular evolution of early-onset prostate cancer identifies molecular risk markers and clinical trajectories","volume":"34","author":"Gerhauser","year":"2018","journal-title":"Cancer Cell"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1038\/nature11125","article-title":"The mutational landscape of lethal castration-resistant prostate cancer","volume":"487","author":"Grasso","year":"2012","journal-title":"Nature"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1016\/S1470-2045(15)00361-7","article-title":"Prostate cancer screening in men aged 50-69 years (STHLM3): a prospective population-based diagnostic study","volume":"16","author":"Gr\u00f6nberg","year":"2015","journal-title":"Lancet Oncol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1038\/nm.3967","article-title":"The consensus molecular subtypes of colorectal cancer","volume":"21","author":"Guinney","year":"2015","journal-title":"Nat. Med"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"219","DOI":"10.3390\/diagnostics9040219","article-title":"A hierarchical machine learning model to discover Gleason Grade-Specific biomarkers in prostate cancer","volume":"9","author":"Hamzeh","year":"2019","journal-title":"Diagnostics"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1038\/s41551-020-0578-x","article-title":"Integrating spatial gene expression and breast tumour morphology via deep learning","volume":"4","author":"He","year":"2020","journal-title":"Nat. Biomed. Eng"},{"key":"2023041408093555300_","first-page":"770","author":"He","year":"2016"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1038\/s41389-019-0138-y","article-title":"ZFHX3 is indispensable for ER\u03b2 to inhibit cell proliferation via MYC downregulation in prostate cancer cells","volume":"8","author":"Hu","year":"2019","journal-title":"Oncogenesis"},{"key":"2023041408093555300_","first-page":"D498","article-title":"The reactome pathway knowledgebase","volume":"48","author":"Jassal","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1002\/pro.123","article-title":"The Brichos domain of prosurfactant protein C can hold and fold a transmembrane segment","volume":"18","author":"Johansson","year":"2009","journal-title":"Protein Sci"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1038\/s43018-020-0087-6","article-title":"Pan-cancer image-based detection of clinically actionable genetic alterations","volume":"1","author":"Kather","year":"2020","journal-title":"Nat. Cancer"},{"key":"2023041408093555300_","first-page":"3146","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1016\/j.eururo.2014.05.004","article-title":"A 17-gene assay to predict prostate cancer aggressiveness in the context of Gleason grade heterogeneity, tumor multifocality, and biopsy undersampling","volume":"66","author":"Klein","year":"2014","journal-title":"Eur. Urol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1186\/1471-2164-14-690","article-title":"Analytical validation of the oncotype DX prostate cancer assay - a clinical RT-PCR assay optimized for prostate needle biopsies","volume":"14","author":"Knezevic","year":"2013","journal-title":"BMC Genomics"},{"key":"2023041408093555300_","article-title":"A 22 gene-expression assay, Decipher\u00ae (GenomeDx Biosciences) to predict five-year risk of metastatic prostate cancer in men treated with radical prostatectomy","volume":"7","author":"Marrone","year":"2015","journal-title":"PLoS Curr"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"237","DOI":"10.2174\/156800909787580999","article-title":"Targeted therapy for advanced prostate cancer: inhibition of the PI3K\/Akt\/mTOR pathway","volume":"9","author":"Morgan","year":"2009","journal-title":"Curr. Cancer Drug Targets"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1016\/j.eururo.2017.05.009","article-title":"Ability of a genomic classifier to predict metastasis and prostate cancer-specific mortality after radiation or surgery based on needle biopsy specimens","volume":"72","author":"Nguyen","year":"2017","journal-title":"Eur. Urol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"2391","DOI":"10.1200\/JCO.2010.32.6421","article-title":"mRNA expression signature of Gleason grade predicts lethal prostate cancer","volume":"29","author":"Penney","year":"2011","journal-title":"J. Clin. Oncol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"4988","DOI":"10.1038\/ncomms5988","article-title":"Complex MSH2 and MSH6 mutations in hypermutated microsatellite unstable advanced prostate cancer","volume":"5","author":"Pritchard","year":"2014","journal-title":"Nat. Commun"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.eururo.2017.08.027","article-title":"Whole-genome and transcriptome sequencing of prostate cancer identify new genetic alterations driving disease progression","volume":"73","author":"Ren","year":"2018","journal-title":"Eur. Urol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis"},{"key":"2023041408093555300_","article-title":"H&E-stained whole slide image deep learning predicts SPOP mutation state in prostate cancer","volume":"064279","author":"Schaumberg","year":"2018","journal-title":"bioArxiv"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"3877","DOI":"10.1038\/s41467-020-17678-4","article-title":"A deep learning model to predict RNA-Seq expression of tumours from whole slide images","volume":"11","author":"Schmauch","year":"2020","journal-title":"Nat. Commun"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1530\/ERC-14-0171","article-title":"MED12 overexpression is a frequent event in castration-resistant prostate cancer","volume":"21","author":"Shaikhibrahim","year":"2014","journal-title":"Endocr. Relat. Cancer"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"4900","DOI":"10.1038\/s41467-018-07270-2","article-title":"Integrative epigenetic taxonomy of primary prostate cancer","volume":"9","author":"Stelloo","year":"2018","journal-title":"Nat. Commun"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/S1470-2045(19)30738-7","article-title":"Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study","volume":"21","author":"Str\u00f6m","year":"2020","journal-title":"Lancet. Oncol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"15545","DOI":"10.1073\/pnas.0506580102","article-title":"Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles","volume":"102","author":"Subramanian","year":"2005","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.ccr.2010.05.026","article-title":"Integrative genomic profiling of human prostate cancer","volume":"18","author":"Taylor","year":"2010","journal-title":"Cancer Cell"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1016\/j.cell.2015.10.025","article-title":"The Molecular Taxonomy of Primary Prostate Cancer","volume":"163","year":"2015","journal-title":"Cell,"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.molmed.2014.01.008","article-title":"Role of tRNA modifications in human diseases","volume":"20","author":"Torres","year":"2014","journal-title":"Trends Mol. Med"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.eururo.2017.09.013","article-title":"A biopsy-based 17-gene genomic prostate score as a predictor of metastases and prostate cancer death in surgically treated men with clinically localized disease","volume":"73","author":"Van Den Eeden","year":"2018","journal-title":"Eur. Urol"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"5115","DOI":"10.1158\/0008-5472.CAN-21-0482","article-title":"Predicting molecular phenotypes from histopathology images: a transcriptome-wide expression-morphology analysis in breast cancer","volume":"81","author":"Wang","year":"2021","journal-title":"Cancer Res"},{"key":"2023041408093555300_","doi-asserted-by":"crossref","first-page":"R65","DOI":"10.1186\/bcr2124","article-title":"Meta-analysis of gene expression profiles in breast cancer: toward a unified understanding of breast cancer subtyping and prognosis signatures","volume":"10","author":"Wirapati","year":"2008","journal-title":"Breast Cancer Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac343\/43993380\/btac343.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/13\/3462\/49883805\/btac343.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/13\/3462\/49883805\/btac343.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T17:47:09Z","timestamp":1727286429000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/13\/3462\/6589889"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,5,20]]},"references-count":50,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,6,27]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac343","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,7,1]]},"published":{"date-parts":[[2022,5,20]]}}}