{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:02:25Z","timestamp":1789671745338,"version":"4.0.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Medical Research Council DTP","award":["MR\/W007428\/1"],"award-info":[{"award-number":["MR\/W007428\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"Abstract<\/jats:title>\n \n Motivation<\/jats:title>\n Spatial transcriptomics (ST) technologies provide spatially resolved gene expression along with image data, allowing the integrative analysis of complex tissue microenvironment. Despite their potential, the widespread adoption of ST remains limited due to high costs, and methodological challenges in data acquisition. Thus, there have been recent efforts to develop deep learning methods for inferring spatial gene expression from much cheaper and easily available haematoxylin and eosin (H&E) images. These methods demonstrate promising results in reconstructing transcriptomic landscapes within tissue sections. While existing approaches focus on gene-level predictions, biological processes are often regulated at the pathway level through coordinated activity among functionally related genes.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n We present DeepPathway, a contrastive learning-based approach trained on ST data to predict pathway expression from H&Es. We compute input pathway expression by summarizing the expression of constituent genes using established pathway definitions. We evaluate the performance of DeepPathway on multiple cancer datasets and validate it on the H&E images from The Cancer Genome Atlas (TCGA) clearly differentiating certain pathway activities in normal and tumour tissue regions. Finally, we apply our method to predict hypoxia signatures using H&Es of brain tumour samples where hypoxia staining with pimonidazole was available as ground truth.<\/jats:p>\n <\/jats:sec>\n \n Code availability<\/jats:title>\n Implementation code for DeepPathway is available at https:\/\/doi.org\/10.5281\/zenodo.21100191 and at GitHub repository: https:\/\/github.com\/aahsan045\/DeepPathway.<\/jats:p>\n <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag643","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:34:31Z","timestamp":1787657671000},"source":"Crossref","is-referenced-by-count":0,"title":["DeepPathway: predicting pathway expression from histopathology images"],"prefix":"10.1093","volume":"42","author":[{"given":"Muhammad Ahtazaz","family":"Ahsan","sequence":"first","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Piper Hanley","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Fergie","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claire","family":"O\u2019leary","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerben","family":"Borst","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3650-5572","authenticated-orcid":false,"given":"Federico","family":"Roncaroli","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9129-1189","authenticated-orcid":false,"given":"Fayyaz","family":"Minhas","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Warwick , Coventry, CV4 7AL,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8196-5565","authenticated-orcid":false,"given":"Magnus","family":"Rattray","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5006-4331","authenticated-orcid":false,"given":"Mudassar","family":"Iqbal","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6633-333X","authenticated-orcid":false,"given":"Syed Murtuza","family":"Baker","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Medicine and Health, The University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]},{"name":"Advanced Bioinformatics and Computational, University of Manchester , Manchester, M13 9PT,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"2026091714071239900_btag643-B1","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1038\/nmeth.4463","article-title":"Scenic: single-cell regulatory network inference and clustering","volume":"14","author":"Aibar","year":"2017","journal-title":"Nat Methods"},{"key":"2026091714071239900_btag643-B2","doi-asserted-by":"crossref","first-page":"3796","DOI":"10.1016\/j.csbj.2021.06.043","article-title":"UCell: robust and scalable single-cell gene signature scoring","volume":"19","author":"Andreatta","year":"2021","journal-title":"Comput Struct Biotechnol J"},{"key":"2026091714071239900_btag643-B3","doi-asserted-by":"crossref","first-page":"e55","DOI":"10.1093\/nar\/gkab095","article-title":"Discovery of molecular features underlying the morphological landscape by integrating spatial transcriptomic data with deep features of tissue images","volume":"49","author":"Bae","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2026091714071239900_btag643-B4","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat Med"},{"key":"2026091714071239900_btag643-B5","first-page":"1597","author":"Chen","year":"2020"},{"key":"2026091714071239900_btag643-B6","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1038\/s41392-023-01332-8","article-title":"Hypoxic microenvironment in cancer: molecular mechanisms and therapeutic interventions","volume":"8","author":"Chen","year":"2023","journal-title":"Signal Transduct Target Ther"},{"key":"2026091714071239900_btag643-B7","first-page":"898","article-title":"Contrastive learning for image captioning","volume":"30","author":"Dai","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091714071239900_btag643-B8","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1038\/s41586-022-05023-2","article-title":"Spatially resolved clonal copy number alterations in benign and malignant tissue","volume":"608","author":"Erickson","year":"2022","journal-title":"Nature"},{"key":"2026091714071239900_btag643-B9","doi-asserted-by":"crossref","first-page":"1384249","DOI":"10.3389\/fimmu.2024.1384249","article-title":"Hypoxia within the glioblastoma tumor microenvironment: a master saboteur of novel treatments","volume":"15","author":"Feldman","year":"2024","journal-title":"Front Immunol"},{"key":"2026091714071239900_btag643-B10","doi-asserted-by":"publisher","first-page":"288","DOI":"10.5534\/wjmh.180040","article-title":"Role of Androgen Receptor in Prostate Cancer: A review","volume":"37","author":"Fujita","year":"2019","journal-title":"World J Mens Health"},{"key":"2026091714071239900_btag643-B11","doi-asserted-by":"crossref","first-page":"27","DOI":"10.4103\/2153-3539.119005","article-title":"Openslide: a vendor-neutral software foundation for digital pathology","volume":"4","author":"Goode","year":"2013","journal-title":"J Pathol Inform"},{"key":"2026091714071239900_btag643-B12","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":"2026091714071239900_btag643-B13","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1038\/s43018-024-00793-2","article-title":"A deep-learning framework to predict cancer treatment response from histopathology images through imputed transcriptomics","volume":"5","author":"Hoang","year":"2024","journal-title":"Nat Cancer"},{"key":"2026091714071239900_btag643-B14","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1016\/j.csbj.2021.01.022","article-title":"QuPath: the global impact of an open source digital pathology system","volume":"19","author":"Humphries","year":"2021","journal-title":"Comput Struct Biotechnol J"},{"key":"2026091714071239900_btag643-B15","first-page":"53798","article-title":"HEST-1k: a dataset for spatial transcriptomics and histology image analysis","volume":"37","author":"Jaume","year":"2025","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091714071239900_btag643-B16","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.cell.2020.05.039","article-title":"Multimodal analysis of composition and spatial architecture in human squamous cell carcinoma","volume":"182","author":"Ji","year":"2020","journal-title":"Cell"},{"key":"2026091714071239900_btag643-B17","doi-asserted-by":"crossref","first-page":"bbad464","DOI":"10.1093\/bib\/bbad464","article-title":"THItoGene: a deep learning method for predicting spatial transcriptomics from histological images","volume":"25","author":"Jia","year":"2024","journal-title":"Briefings Bioinformatics"},{"key":"2026091714071239900_btag643-B18","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/s41698-024-00499-9","article-title":"Open and reusable deep learning for pathology with wsinfer and qupath","volume":"8","author":"Kaczmarzyk","year":"2024","journal-title":"NPJ Precis Oncol"},{"key":"2026091714071239900_btag643-B19","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091714071239900_btag643-B20","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1111\/j.1349-7006.2009.01195.x","article-title":"Significance of nitroimidazole compounds and hypoxia-inducible factor-1 for imaging tumor hypoxia","volume":"100","author":"Kizaka-Kondoh","year":"2009","journal-title":"Cancer Sci"},{"key":"2026091714071239900_btag643-B21","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","article-title":"Fast, sensitive and accurate integration of single-cell data with harmony","volume":"16","author":"Korsunsky","year":"2019","journal-title":"Nat Methods"},{"key":"2026091714071239900_btag643-B22","doi-asserted-by":"crossref","first-page":"bbae500","DOI":"10.1093\/bib\/bbae500","article-title":"Gene expression prediction from histology images via hypergraph neural networks","volume":"25","author":"Li","year":"2024","journal-title":"Briefings Bioinformatics"},{"key":"2026091714071239900_btag643-B23","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The molecular signatures database hallmark gene set collection","volume":"1","author":"Liberzon","year":"2015","journal-title":"Cell Syst"},{"key":"2026091714071239900_btag643-B24","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"Lopez","year":"2018","journal-title":"Nat Methods"},{"key":"2026091714071239900_btag643-B25","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1038\/s41592-024-02212-x","article-title":"SpatialData: an open and universal data framework for spatial omics","volume":"22","author":"Marconato","year":"2025","journal-title":"Nat Methods"},{"key":"2026091714071239900_btag643-B26","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/s41592-020-01033-y","article-title":"Method of the year: spatially resolved transcriptomics","volume":"18","author":"Marx","year":"2021","journal-title":"Nat Methods"},{"key":"2026091714071239900_btag643-B27","doi-asserted-by":"crossref","first-page":"bbae551","DOI":"10.1093\/bib\/bbae551","article-title":"Multimodal contrastive learning for spatial gene expression prediction using histology images","volume":"25","author":"Min","year":"2024","journal-title":"Briefings Bioinformatics"},{"key":"2026091714071239900_btag643-B28","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1038\/s41467-023-36071-5","article-title":"Spatially resolved transcriptomic profiling of degraded and challenging fresh frozen samples","volume":"14","author":"Mirzazadeh","year":"2023","journal-title":"Nat Commun"},{"key":"2026091714071239900_btag643-B29","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1146\/annurev-pathol-020117-043854","article-title":"Epithelial mesenchymal transition in tumor metastasis","volume":"13","author":"Mittal","year":"2018","journal-title":"Annu Rev Pathol"},{"key":"2026091714071239900_btag643-B30","doi-asserted-by":"crossref","first-page":"4133","DOI":"10.1038\/s41598-022-07685-4","article-title":"Efficient prediction of a spatial transcriptomics profile better characterizes breast cancer tissue sections without costly experimentation","volume":"12","author":"Monjo","year":"2022","journal-title":"Sci Rep"},{"key":"2026091714071239900_btag643-B31","doi-asserted-by":"crossref","first-page":"83","DOI":"10.2147\/HP.S93413","article-title":"The role of hypoxia in cancer progression, angiogenesis, metastasis, and resistance to therapy","volume":"3","author":"Muz","year":"2015","journal-title":"Hypoxia (Auckl)"},{"key":"2026091714071239900_btag643-B32","doi-asserted-by":"crossref","first-page":"9886","DOI":"10.1038\/s41467-024-54182-5","article-title":"Digital profiling of gene expression from histology images with linearized attention","volume":"15","author":"Pizurica","year":"2024","journal-title":"Nat Commun"},{"key":"2026091714071239900_btag643-B33","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1038\/s43856-022-00186-5","article-title":"Tiatoolbox as an end-to-end library for advanced tissue image analytics","volume":"2","author":"Pocock","year":"2022","journal-title":"Commun Med (Lond)"},{"key":"2026091714071239900_btag643-B34","doi-asserted-by":"crossref","first-page":"2559","DOI":"10.1038\/s41467-022-30257-z","article-title":"Myc drives aggressive prostate cancer by disrupting transcriptional pause release at androgen receptor targets","volume":"13","author":"Qiu","year":"2022","journal-title":"Nat Commun"},{"key":"2026091714071239900_btag643-B35","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1016\/j.ccell.2022.05.009","article-title":"Spatially resolved multi-omics deciphers bidirectional tumor-host interdependence in glioblastoma","volume":"40","author":"Ravi","year":"2022","journal-title":"Cancer Cell"},{"key":"2026091714071239900_btag643-B36","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1126\/science.aaw1219","article-title":"Slide-seq: a scalable technology for measuring genome-wide expression at high spatial resolution","volume":"363","author":"Rodriques","year":"2019","journal-title":"Science"},{"key":"2026091714071239900_btag643-B37","author":"Saillard","year":"2024"},{"key":"2026091714071239900_btag643-B38","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.ymeth.2024.11.016","article-title":"Inferring multi-slice spatially resolved gene expression from H&E-stained histology images with STMCL","volume":"234","author":"Shi","year":"2025","journal-title":"Methods"},{"key":"2026091714071239900_btag643-B39","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091714071239900_btag643-B40","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","article-title":"A foundation model for clinical-grade computational pathology and rare cancers detection","volume":"30","author":"Vorontsov","year":"2024","journal-title":"Nat Med"},{"key":"2026091714071239900_btag643-B41","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1038\/s41467-025-56618-y","article-title":"Benchmarking the translational potential of spatial gene expression prediction from histology","volume":"16","author":"Wang","year":"2025","journal-title":"Nat Commun"},{"key":"2026091714071239900_btag643-B42","doi-asserted-by":"crossref","first-page":"btaf363","DOI":"10.1093\/bioinformatics\/btaf363","article-title":"HECLIP: histology-enhanced contrastive learning for imputation of transcriptomics profiles","volume":"41","author":"Wang","year":"2025","journal-title":"Bioinformatics"},{"key":"2026091714071239900_btag643-B43","first-page":"100585","article-title":"Study protocol: PreOperative Brain Irradiation in Glioblastoma (POBIG)\u2014a phase I trial","volume":"39","author":"Waqar","year":"2023","journal-title":"Clin Transl Radiat Oncol"},{"key":"2026091714071239900_btag643-B44","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":"Wolf","year":"018","journal-title":"Genome Biol"},{"key":"2026091714071239900_btag643-B45","doi-asserted-by":"crossref","first-page":"103040","DOI":"10.1016\/j.media.2023.103040","article-title":"Transformer with convolution and graph-node co-embedding: an accurate and interpretable vision backbone for predicting gene expressions from local histopathological image","volume":"91","author":"Xiao","year":"2024","journal-title":"Med Image Anal"},{"key":"2026091714071239900_btag643-B46","doi-asserted-by":"crossref","first-page":"70626","DOI":"10.52202\/075280-3095","article-title":"Spatially resolved gene expression prediction from histology images via bi-modal contrastive learning","volume":"36","author":"Xie","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091714071239900_btag643-B47","doi-asserted-by":"crossref","first-page":"bbac297","DOI":"10.1093\/bib\/bbac297","article-title":"Spatial transcriptomics prediction from histology jointly through transformer and graph neural networks","volume":"23","author":"Zeng","year":"2022","journal-title":"Briefings in Bioinformatics"},{"key":"2026091714071239900_btag643-B48","first-page":"833","author":"Zhang","year":"2021"},{"key":"2026091714071239900_btag643-B49","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1186\/s13046-022-02385-3","article-title":"Spatially resolved transcriptomics provide a new method for cancer research","volume":"41","author":"Zheng","year":"2022","journal-title":"J Exp Clin Cancer Res"},{"key":"2026091714071239900_btag643-B50","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41592-020-01037-8","article-title":"Spatially resolved single-cell genomics and transcriptomics by imaging","volume":"18","author":"Zhuang","year":"2021","journal-title":"Nat Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag643\/70806531\/btag643.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag643\/70806531\/btag643.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag643\/70806531\/btag643.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:07:33Z","timestamp":1789668453000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag643\/8771241"}},"subtitle":[],"editor":[{"given":"Peter","family":"Robinson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":50,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag643","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":[[2026,8,26]]},"article-number":"btag643"}}