{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T18:14:16Z","timestamp":1789150456294,"version":"build-2803163510"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014762","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000}}],"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","award":["CRC-2021-00482"],"award-info":[{"award-number":["CRC-2021-00482"]}],"id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2021-04072"],"award-info":[{"award-number":["RGPIN-2021-04072"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Canadian Foundation for Innovation","award":["#43481"],"award-info":[{"award-number":["#43481"]}]},{"DOI":"10.13039\/100012172","name":"Breast Cancer Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012172","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","award":["PLL 185683, PJT 204042"],"award-info":[{"award-number":["PLL 185683, PJT 204042"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Spatial transcriptomics (ST) enhances single-cell RNA sequencing by revealing transcript distribution, offering critical insights into heterogeneous diseases such as breast cancer. However, the high cost and lengthy processes of generating high-quality ST data limit clinical application. Recent deep learning methods predict ST from histology images, but often fail to capture both morphological features and spatial context. We introduce FOCST, a foundation model-driven framework for ST imputation that leverages spatial guided contrastive learning. FOCST begins with UNI, a large histopathology foundation model, to extract visual features from tissue images. These are integrated with expression data in a unified embedding space via contrastive learning, enabling cross-modal prediction and imputation. To further enhance spatial awareness, a graph neural network incorporates positional information, improving regional detection and interpretability.Benchmarking demonstrates FOCST\u2019s superior performance over state-of-the-art methods and alternative vision encoders (paired Wilcoxon signed-rank tests, FDR-adjusted p\u2009&lt;\u20090.05, N\u2009=\u20096 images). Predicted profiles enable clinically relevant downstream analyses, including patient stratification by treatment response (ROC AUC (Receiver Operating Characteristic \u2013 Area Under the Curve) = 0.79). Our results highlight the promise of combining foundation models and spatially guided learning to efficiently generate ST insights, advancing cancer research and precision medicine.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014762","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:53:16Z","timestamp":1788889996000},"page":"e1014762","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatially guided translation from histology images to transcriptomic profiles using foundation model-driven contrastive learning"],"prefix":"10.1371","volume":"22","author":[{"given":"Zi Huai","family":"Huang","sequence":"first","affiliation":[{"name":"Western University","place":["London, Canada"],"department":["Department of Biochemistry"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Xu","sequence":"additional","affiliation":[{"name":"Western University","place":["London, Canada"],"department":["Department of Biochemistry"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9546-2245","authenticated-orcid":true,"given":"Pingzhao","family":"Hu","sequence":"additional","affiliation":[{"name":"Western University","place":["London, Canada"],"department":["Department of Biochemistry"]},{"name":"Western University","place":["London, Canada"],"department":["Department of Computer Sciences"]},{"name":"University of Toronto","place":["Toronto, Canada"],"department":["Division of Biostatistics"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"issue":"1","key":"pcbi.1014762.ref001","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1186\/s12967-023-04150-2","article-title":"Advances in spatial transcriptomics and related data analysis strategies","volume":"21","author":"J Du","year":"2023","journal-title":"J Transl Med"},{"issue":"8","key":"pcbi.1014762.ref002","doi-asserted-by":"crossref","first-page":"1999","DOI":"10.3390\/cancers14081999","article-title":"Dissecting Tumor-Immune Microenvironment in Breast Cancer at a Spatial and Multiplex Resolution","volume":"14","author":"E Tzoras","year":"2022","journal-title":"Cancers (Basel)"},{"key":"pcbi.1014762.ref003","doi-asserted-by":"crossref","first-page":"1483595","DOI":"10.3389\/fimmu.2024.1483595","article-title":"Spatial transcriptomics: a new frontier in accurate localization of breast cancer diagnosis and treatment","volume":"15","author":"Y Zhang","year":"2024","journal-title":"Front Immunol"},{"issue":"1","key":"pcbi.1014762.ref004","doi-asserted-by":"crossref","first-page":"6012","DOI":"10.1038\/s41467-021-26271-2","article-title":"Spatial deconvolution of HER2-positive breast cancer delineates tumor-associated cell type interactions","volume":"12","author":"A Andersson","year":"2021","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014762.ref005","doi-asserted-by":"crossref","first-page":"6278","DOI":"10.1038\/s41467-021-26614-z","article-title":"Spatially resolved transcriptomics reveals the architecture of the tumor-microenvironment interface","volume":"12","author":"MV Hunter","year":"2021","journal-title":"Nat Commun"},{"key":"pcbi.1014762.ref006","article-title":"seqFISH Accurately Detects Transcripts in Single Cells and Reveals Robust Spatial Organization in the Hippocampus","author":"S Shah","year":"2017","journal-title":"Neuron"},{"issue":"7751","key":"pcbi.1014762.ref007","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1038\/s41586-019-1049-y","article-title":"Transcriptome-scale super-resolved imaging in tissues by RNA seqFISH","volume":"568","author":"C-HL Eng","year":"2019","journal-title":"Nature"},{"issue":"7879","key":"pcbi.1014762.ref008","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1038\/s41586-021-03705-x","article-title":"Spatially resolved cell atlas of the mouse primary motor cortex by MERFISH","volume":"598","author":"M Zhang","year":"2021","journal-title":"Nature"},{"issue":"6434","key":"pcbi.1014762.ref009","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":"SG Rodriques","year":"2019","journal-title":"Science"},{"issue":"3","key":"pcbi.1014762.ref010","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1038\/s41587-020-0739-1","article-title":"Highly sensitive spatial transcriptomics at near-cellular resolution with Slide-seqV2","volume":"39","author":"RR Stickels","year":"2021","journal-title":"Nat Biotechnol"},{"issue":"10","key":"pcbi.1014762.ref011","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1038\/s41592-019-0548-y","article-title":"High-definition spatial transcriptomics for in situ tissue profiling","volume":"16","author":"S Vickovic","year":"2019","journal-title":"Nat Methods"},{"key":"pcbi.1014762.ref012","doi-asserted-by":"crossref","unstructured":"Rahaman MM, Millar EKA, Meijering E. Breast cancer histopathology image based gene expression prediction using spatial transcriptomics data and deep learning. 2023.","DOI":"10.21203\/rs.3.rs-2983276\/v1"},{"key":"pcbi.1014762.ref013","article-title":"Spatial transcriptomic cell-type deconvolution using graph neural networks","author":"Y Li","year":"2023","journal-title":"bioRxiv"},{"issue":"8","key":"pcbi.1014762.ref014","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":"B He","year":"2020","journal-title":"Nat Biomed Eng"},{"key":"pcbi.1014762.ref015","author":"M Pang","year":"2021"},{"issue":"9","key":"pcbi.1014762.ref016","doi-asserted-by":"crossref","first-page":"2569","DOI":"10.3390\/cancers15092569","article-title":"hist2RNA: An Efficient Deep Learning Architecture to Predict Gene Expression from Breast Cancer Histopathology Images","volume":"15","author":"RK Mondol","year":"2023","journal-title":"Cancers (Basel)"},{"issue":"5","key":"pcbi.1014762.ref017","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac297","article-title":"Spatial transcriptomics prediction from histology jointly through Transformer and graph neural networks","volume":"23","author":"Y Zeng","year":"2022","journal-title":"Brief Bioinform"},{"key":"pcbi.1014762.ref018","article-title":"Spatially resolved gene expression prediction from H&E histology images via bi-modal contrastive learning","author":"R Xie"},{"issue":"19","key":"pcbi.1014762.ref019","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":"Y Wang","year":"2021","journal-title":"Cancer Res"},{"key":"pcbi.1014762.ref020","article-title":"Inference of single cell profiles from histology stains with the Single-Cell omics from Histology Analysis Framework (SCHAF). bioRxiv","author":"C Comiter","year":"2023"},{"key":"pcbi.1014762.ref021","unstructured":"Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 2014."},{"key":"pcbi.1014762.ref022","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: 2020."},{"issue":"1","key":"pcbi.1014762.ref023","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":"C Wang","year":"2025","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014762.ref024","doi-asserted-by":"crossref","first-page":"4452","DOI":"10.1038\/s41467-025-58989-8","article-title":"Combining spatial transcriptomics with tissue morphology","volume":"16","author":"E Chelebian","year":"2025","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014762.ref025","article-title":"THItoGene: a deep learning method for predicting spatial transcriptomics from histological images","volume":"25","author":"Y Jia","year":"2023","journal-title":"Brief Bioinform"},{"key":"pcbi.1014762.ref026","unstructured":"Dawo S, Nonchev K, Silina K. 10x Visium Spatial Transcriptomics Dataset: Kidney (3) and Lung (5) Cancer with Tertiary Lymphoid Structures. In: Preprint at Zenodo, 2025. https:\/\/doi.org\/10.5281\/zenodo.14620362"},{"key":"pcbi.1014762.ref027","unstructured":"Kipf TN, Welling M. Semi-Supervised Classification with Graph Convolutional Networks. In: 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings, 2016."},{"issue":"6294","key":"pcbi.1014762.ref028","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1126\/science.aaf2403","article-title":"Visualization and analysis of gene expression in tissue sections by spatial transcriptomics","volume":"353","author":"PL St\u00e5hl","year":"2016","journal-title":"Science"},{"key":"pcbi.1014762.ref029","doi-asserted-by":"crossref","unstructured":"Veli\u010dkovi\u0107 P, Casanova A, Li\u00f2 P, Cucurull G, Romero A, Bengio Y. Graph Attention Networks. In: 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings, 2017. https:\/\/doi.org\/10.1007\/978-3-031-01587-8_7","DOI":"10.1007\/978-3-031-01587-8_7"},{"issue":"11","key":"pcbi.1014762.ref030","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41592-021-01255-8","article-title":"SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network","volume":"18","author":"J Hu","year":"2021","journal-title":"Nat Methods"},{"issue":"12","key":"pcbi.1014762.ref031","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":"R Lopez","year":"2018","journal-title":"Nat Methods"},{"key":"pcbi.1014762.ref032","doi-asserted-by":"crossref","unstructured":"Boquet G, Vicario JL, Morell A, Serrano J. Missing Data in Traffic Estimation: A Variational Autoencoder Imputation Method. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019. 2882\u20136. https:\/\/doi.org\/10.1109\/icassp.2019.8683011","DOI":"10.1109\/ICASSP.2019.8683011"},{"issue":"1","key":"pcbi.1014762.ref033","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41379-021-00911-w","article-title":"Deep learning trained on hematoxylin and eosin tumor region of Interest predicts HER2 status and trastuzumab treatment response in HER2+ breast cancer","volume":"35","author":"S Farahmand","year":"2022","journal-title":"Mod Pathol"},{"issue":"1","key":"pcbi.1014762.ref034","doi-asserted-by":"crossref","first-page":"7848","DOI":"10.1038\/s41467-023-43629-w","article-title":"Integrating spatial and single-cell transcriptomics data using deep generative models with SpatialScope","volume":"14","author":"X Wan","year":"2023","journal-title":"Nat Commun"},{"issue":"9","key":"pcbi.1014762.ref035","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1038\/s41588-021-00911-1","article-title":"A single-cell and spatially resolved atlas of human breast cancers","volume":"53","author":"SZ Wu","year":"2021","journal-title":"Nat Genet"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014762","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T18:05:16Z","timestamp":1789149916000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014762"}},"subtitle":[],"editor":[{"given":"Zhixiang","family":"Lin","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong Faculty of Science","place":["HONG KONG"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":35,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014762","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]}}}