{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T13:00:05Z","timestamp":1790600405061,"version":"4.1.0"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":27,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-00519063"],"award-info":[{"award-number":["RS-2025-00519063"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["IITP-2026)-RS-2026-25615334"],"award-info":[{"award-number":["IITP-2026)-RS-2026-25615334"]}],"id":[{"id":"https:\/\/ror.org\/01g0hqq23","id-type":"ROR","asserted-by":"crossref"}]},{"name":"AI Star Fellowship Support Program","award":["2019-0-01842"],"award-info":[{"award-number":["2019-0-01842"]}]},{"name":"Artificial Intelligence Graduate School Program"},{"DOI":"10.13039\/501100002582","name":"Gwangju Institute of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002582","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Government of the Republic of Korea","id":[{"id":"https:\/\/ror.org\/019xm3p48","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Spatial transcriptomics (ST) enables the spatial mapping of gene expression by combining tissue images with spot-level gene expression profiles, allowing for the analysis of gene distribution and interactions between adjacent regions. Although numerous deep learning models have been developed for ST, most existing approaches are task-specific, and multimodal foundation models with broad knowledge of ST remain scarce. While a few ST multimodal models currently exist, they have been either trained on low-resolution tissue images or developed for a specific platform, thereby limiting their generalizability when applied to diverse ST data. To address this gap, we propose ST-ConMa, a multimodal foundation model pretrained on large-scale spot-level tissue images paired with corresponding gene expression profiles using contrastive and matching learning. While conventional task-specific and foundation models generate modality-specific embeddings for images and genes separately, our model jointly learns image\u2013gene fusion representations using a multimodal encoder equipped with cross-attention and a matching objective. Through extensive evaluations on histopathology image classification benchmarks and domain-specific tasks including gene expression prediction and spatial clustering, we demonstrate that ST-ConMa learns high-quality multimodal representations and consistently outperforms existing methods. These results indicate that ST-ConMa serves as a generalizable backbone for diverse ST approaches.<\/jats:p>","DOI":"10.1093\/bib\/bbag535","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:02:40Z","timestamp":1789473760000},"source":"Crossref","is-referenced-by-count":0,"title":["ST-ConMa: a multimodal foundation framework for spatial transcriptomics via image\u2013gene contrastive and matching learning"],"prefix":"10.1093","volume":"27","author":[{"given":"Taelim","family":"Yeom","sequence":"first","affiliation":[{"name":"Department of AI, College of Artificial Intelligence, Gwangju Institute of Science and Technology , 123 Cheomdangwagi-ro, Buk-gu, Gwangju 61005 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongha","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of AI, College of Artificial Intelligence, Gwangju Institute of Science and Technology , 123 Cheomdangwagi-ro, Buk-gu, Gwangju 61005 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2389-7183","authenticated-orcid":false,"given":"Hyunju","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of AI, College of Artificial Intelligence, Gwangju Institute of Science and Technology , 123 Cheomdangwagi-ro, Buk-gu, Gwangju 61005 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"2026092808250215200_ref1","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1016\/j.cell.2015.05.002","article-title":"Highly parallel genome-wide expression profiling of individual cells using nanoliter droplets","volume":"161","author":"Macosko","year":"2015","journal-title":"Cell"},{"key":"2026092808250215200_ref2","doi-asserted-by":"crossref","first-page":"14049","DOI":"10.1038\/ncomms14049","article-title":"Massively parallel digital transcriptional profiling of single cells","volume":"8","author":"Zheng","year":"2017","journal-title":"Nat Commun"},{"key":"2026092808250215200_ref3","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1126\/science.aad0501","article-title":"Dissecting the multicellular ecosystem of metastatic melanoma by single-cell RNA-seq","volume":"352","author":"Tirosh","year":"2016","journal-title":"Science"},{"key":"2026092808250215200_ref4","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1186\/s13073-018-0567-9","article-title":"Single-cell transcriptome analysis of lineage diversity in high-grade glioma","volume":"10","author":"Yuan","year":"2018","journal-title":"Genome Med"},{"key":"2026092808250215200_ref5","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":"St\u00e5hl","year":"2016","journal-title":"Science"},{"key":"2026092808250215200_ref6","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":"2026092808250215200_ref7","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1038\/s41592-022-01459-6","article-title":"Alignment and integration of spatial transcriptomics data","volume":"19","author":"Zeira","year":"2022","journal-title":"Nat Methods"},{"key":"2026092808250215200_ref8","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1038\/s41592-023-01972-2","article-title":"Alignment of spatial genomics data using deep gaussian processes","volume":"20","author":"Andrew Jones","year":"2023","journal-title":"Nat Methods"},{"key":"2026092808250215200_ref9","doi-asserted-by":"crossref","first-page":"btac825","DOI":"10.1093\/bioinformatics\/btac825","article-title":"EnDecon: cell type deconvolution of spatially resolved transcriptomics data via ensemble learning","volume":"39","author":"Jia-Juan","year":"2023","journal-title":"Bioinformatics"},{"key":"2026092808250215200_ref10","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1186\/s13059-024-03353-0","article-title":"STdGCN: spatial transcriptomic cell-type deconvolution using graph convolutional networks","volume":"25","author":"Li","year":"2024","journal-title":"Genome Biol"},{"key":"2026092808250215200_ref11","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":"Jian","year":"2021","journal-title":"Nat Methods"},{"key":"2026092808250215200_ref12","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1038\/s41467-022-29439-6","article-title":"Deciphering spatial domains from spatially resolved transcriptomics with an adaptive graph attention auto-encoder","volume":"13","author":"Dong","year":"2022","journal-title":"Nat Commun"},{"key":"2026092808250215200_ref13","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":"Andersson","year":"2021","journal-title":"Nat Commun"},{"key":"2026092808250215200_ref14","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":"Zeng","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026092808250215200_ref15","doi-asserted-by":"crossref","DOI":"10.52202\/079017-1704","article-title":"HEST-1k: a dataset for spatial transcriptomics and histology image analysis","volume-title":"Advances in Neural Information Processing Systems","author":"Jaume"},{"key":"2026092808250215200_ref16","doi-asserted-by":"crossref","DOI":"10.52202\/079017-1129","article-title":"STimage-1k4m: a histopathology image-gene expression dataset for spatial transcriptomics","volume-title":"Advances in Neural Information Processing Systems","author":"Chen"},{"key":"2026092808250215200_ref17","doi-asserted-by":"crossref","DOI":"10.1038\/s41592-025-02707-1","article-title":"A visual\u2013omics foundation model to bridge histopathology with spatial transcriptomics","volume":"22","author":"Chen","year":"2025","journal-title":"Nat Methods"},{"key":"2026092808250215200_ref18","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"2026092808250215200_ref19","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Jia"},{"key":"2026092808250215200_ref20","article-title":"Towards unified molecule-enhanced pathology image representation learning via integrating spatial transcriptomics","volume":"172","author":"Han","journal-title":"Pattern Recogn"},{"key":"2026092808250215200_ref21","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Chen"},{"key":"2026092808250215200_ref22","article-title":"ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Advances in Neural Information Processing Systems","author":"Lu"},{"key":"2026092808250215200_ref23","article-title":"Align before fuse: vision and language representation learning with momentum distillation","volume-title":"Advances in Neural Information Processing Systems","author":"Li"},{"key":"2026092808250215200_ref24","first-page":"15638","article-title":"FLAVA: a foundational language and vision alignment model","author":"Singh","year":"2022","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"2026092808250215200_ref25","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s13059-016-0953-9","article-title":"High-performance web services for querying gene and variant annotation","volume":"17","author":"Xin","year":"2016","journal-title":"Genome Biol"},{"key":"2026092808250215200_ref26","doi-asserted-by":"crossref","first-page":"D886","DOI":"10.1093\/nar\/gkae1142","article-title":"CZ CELLxGENE discover: a single-cell data platform for scalable exploration, analysis and modeling of aggregated data","volume":"53","author":"Cell Science Program","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026092808250215200_ref27","doi-asserted-by":"crossref","first-page":"103289","DOI":"10.1016\/j.media.2024.103289","article-title":"PathoDuet: foundation models for pathological slide analysis of H&E and IHC stains","volume":"97","author":"Hua","year":"2024","journal-title":"Med Image Anal"},{"key":"2026092808250215200_ref28","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy"},{"key":"2026092808250215200_ref29","article-title":"Pythia: a suite for analyzing large language models across training and scaling","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Biderman"},{"key":"2026092808250215200_ref30","doi-asserted-by":"crossref","article-title":"Scaling large language models for next-generation single-cell analysis","author":"Rizvi","DOI":"10.1101\/2025.04.14.648850"},{"key":"2026092808250215200_ref31","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01522","article-title":"Vision-language pre-training with triple contrastive learning","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yang"},{"key":"2026092808250215200_ref32","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani"},{"key":"2026092808250215200_ref33","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord"},{"key":"2026092808250215200_ref34","article-title":"Decoupled weight decay regularization","author":"Loshchilov"},{"key":"2026092808250215200_ref35","article-title":"From detection of individual metastases to classification of lymph node status at the patient level: the CAMELYON17 challenge","volume":"38","author":"Bandi","journal-title":"IEEE Trans Med Imaging"},{"key":"2026092808250215200_ref36","article-title":"100,000 histological images of human colorectal cancer and healthy tissue","author":"Kather","year":"2018"},{"key":"2026092808250215200_ref37","article-title":"WSSS4LUAD: grand challenge on weakly-supervised tissue semantic segmentation for lung adenocarcinoma","author":"Han"},{"key":"2026092808250215200_ref38","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-77211-6_2","article-title":"A petri dish for histopathology image analysis","volume-title":"Artificial Intelligence in Medicine: 19th International Conference on Artificial Intelligence in Medicine, AIME 2021","author":"Wei"},{"key":"2026092808250215200_ref39","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":"2026092808250215200_ref40","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1016\/j.jhep.2023.12.023","article-title":"Single-cell, single-nucleus, and spatial transcriptomics characterization of the immunological landscape in the healthy and PSC human liver","volume":"80","author":"Andrews","year":"2024","journal-title":"J Hepatol"},{"key":"2026092808250215200_ref41","doi-asserted-by":"crossref","article-title":"Leveraging information in spatial transcriptomics to predict super-resolution gene expression from histology images in tumors","author":"Pang","DOI":"10.1101\/2021.11.28.470212"},{"key":"2026092808250215200_ref42","article-title":"THItoGene: a deep learning method for predicting spatial transcriptomics from histological images","volume":"25","author":"Jia","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026092808250215200_ref43","doi-asserted-by":"crossref","DOI":"10.52202\/075280-3095","article-title":"Spatially resolved gene expression prediction from histology images via bi-modal contrastive learning","volume-title":"Advances in Neural Information Processing Systems","author":"Xie"},{"key":"2026092808250215200_ref44","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":"Brief Bioinform"},{"key":"2026092808250215200_ref45","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1186\/s12864-022-08601-w","article-title":"spatialLIBD: an r\/bioconductor package to visualize spatially-resolved transcriptomics data","volume":"23","author":"Pardo","year":"2022","journal-title":"BMC Genomics"},{"key":"2026092808250215200_ref46","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s13073-024-01283-x","article-title":"Unsupervised spatially embedded deep representation of spatial transcriptomics","volume":"16","author":"Hang","year":"2024","journal-title":"Genome Med"},{"key":"2026092808250215200_ref47","doi-asserted-by":"crossref","first-page":"e131","DOI":"10.1093\/nar\/gkac901","article-title":"DeepST: identifying spatial domains in spatial transcriptomics by deep learning","volume":"50","author":"Chang","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026092808250215200_ref48","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1038\/s41467-023-36796-3","article-title":"Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST.","volume":"14","author":"Long","year":"2023","journal-title":"Nat Commun"},{"key":"2026092808250215200_ref49","doi-asserted-by":"crossref","first-page":"bbae255","DOI":"10.1093\/bib\/bbae255","article-title":"A multi-view graph contrastive learning framework for deciphering spatially resolved transcriptomics data","volume":"25","author":"Zhang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026092808250215200_ref50","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1038\/s41467-025-56276-0","article-title":"STAIG: spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration","volume":"16","author":"Yang","year":"2025","journal-title":"Nat Commun"},{"key":"2026092808250215200_ref51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/cpbi.5","article-title":"The GeneCards suite: from gene data mining to disease genome sequence analyses","volume":"54","author":"Stelzer","year":"2016","journal-title":"Curr Protoc Bioinformatics"},{"key":"2026092808250215200_ref52","doi-asserted-by":"crossref","first-page":"6102","DOI":"10.1038\/sj.onc.1203973","article-title":"Molecular mechanisms underlying ErbB2\/HER2 action in breast cancer","volume":"19","author":"Harari","year":"2000","journal-title":"Oncogene"},{"key":"2026092808250215200_ref53","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1111\/cas.12427","article-title":"Expression of CD 24 is associated with HER2 expression and supports HER2-Akt signaling in HER2-positive breast cancer cells","volume":"105","author":"Hosonaga","year":"2014","journal-title":"Cancer Sci"},{"key":"2026092808250215200_ref54","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s00262-015-1788-z","article-title":"Galectin-1 is associated with poor prognosis in patients with cutaneous head and neck cancer with perineural spread","volume":"65","author":"Chawla","year":"2016","journal-title":"Cancer Immunol Immunother"},{"key":"2026092808250215200_ref55","first-page":"8279","article-title":"Cancer-associated fibroblast-derived gene signature discriminates distinct prognoses by integrated single-cell and bulk RNA-seq analyses in breast cancer","volume":"16","author":"Fang","year":"2024","journal-title":"Aging (Albany NY)"},{"key":"2026092808250215200_ref56","doi-asserted-by":"crossref","first-page":"1304853","DOI":"10.3389\/fgene.2024.1304853","article-title":"Fibroblast heterogeneity and functions: insights from single-cell sequencing in wound healing, breast cancer, ovarian cancer and melanoma","volume":"15","author":"Olazaba","year":"2024","journal-title":"Front Genet"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag535\/71438171\/bbag535.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag535\/71438171\/bbag535.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T12:25:22Z","timestamp":1790598322000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag535\/8841209"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":56,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag535","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag535"}}