{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T16:00:06Z","timestamp":1790092806316,"version":"4.0.1"},"reference-count":45,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62262069"],"award-info":[{"award-number":["62262069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Fund Project of Yunnan Education Department","award":["2026J0841"],"award-info":[{"award-number":["2026J0841"]}]},{"name":"Yunnan Fundamental Research Projects","award":["NO. 202601CI070001"],"award-info":[{"award-number":["NO. 202601CI070001"]}]},{"name":"the Practical Innovation Project of Postgraduate Students in the Professional Degree of Yunnan University","award":["ZC-252513616"],"award-info":[{"award-number":["ZC-252513616"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>High costs and operational complexity limit the clinical application of spatial transcriptomics (ST). Inferring ST from pathology images is a promising alternative, the core of which lies in effectively aligning image and gene expression features. However, existing models are mostly limited to single-scale and single-slice modeling. This not only fails to connect microscopic cells with macroscopic tissues but also restricts generalization due to the inability to extract cross-sample shared features. Furthermore, the inherent representational differences between modalities further exacerbate the difficulty of feature alignment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>To address these challenges, we propose HisCMCL, a multimodal framework. The model combines multi-scale features with a cross-attention mechanism to jointly capture local morphology and global context. Additionally, it fuses spatial location information and utilizes a contrastive learning strategy to facilitate the effective alignment of image and transcriptomic features. Evaluations on four public datasets demonstrate that HisCMCL outperforms existing baseline methods in predictive performance. It exhibits good structural consistency in identifying cancer and immune markers and delineating tumor regions, offering new insights for spatial expression inference.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The code of HisCMCL is available at https:\/\/github.com\/wenwenmin\/HisCMCL.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag342","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T11:39:54Z","timestamp":1779968394000},"source":"Crossref","is-referenced-by-count":0,"title":["HisCMCL: cross-modal contrastive learning with hierarchical multi-scale fusion for spatial expression prediction"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5760-1751","authenticated-orcid":false,"given":"Chengju","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University , Kunming, Yunnan 650500,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6798-2397","authenticated-orcid":false,"given":"Fangfang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Health and Nursing, Yunnan Open University , Kunming, Yunnan 650500,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2558-2911","authenticated-orcid":false,"given":"Wenwen","family":"Min","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University , Kunming, Yunnan 650500,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"2026092211020054900_btag342-B1","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":"2026092211020054900_btag342-B2","doi-asserted-by":"crossref","first-page":"2644","DOI":"10.1093\/bioinformatics\/btab164","article-title":"Sepal: identifying transcript profiles with spatial patterns by diffusion-based modeling","volume":"37","author":"Andersson","year":"2021","journal-title":"Bioinformatics"},{"key":"2026092211020054900_btag342-B3","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3390\/cancers11010025","article-title":"Stemness, pluripotentiality, and Wnt antagonism: sFRP4, a Wnt antagonist mediates pluripotency and stemness in glioblastoma","volume":"11","author":"Bhuvanalakshmi","year":"2018","journal-title":"Cancers (Basel)"},{"key":"2026092211020054900_btag342-B4","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1111\/j.1750-3639.2001.tb00383.x","article-title":"The pathobiology of myelin mutants reveal novel biological functions of the MBP and PLP genes","volume":"11","author":"Campagnoni","year":"2001","journal-title":"Brain Pathol"},{"key":"2026092211020054900_btag342-B5","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-grade computational pathology using weakly supervised deep learning on whole slide images","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat Med"},{"key":"2026092211020054900_btag342-B6","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":"2026092211020054900_btag342-B7","doi-asserted-by":"crossref","first-page":"btaf131","DOI":"10.1093\/bioinformatics\/btaf131","article-title":"Benchmarking algorithms for spatially variable gene identification in spatial transcriptomics","volume":"41","author":"Chen","year":"2025","journal-title":"Bioinformatics"},{"key":"2026092211020054900_btag342-B8","doi-asserted-by":"publisher","author":"Chung","DOI":"10.1109\/CVPR52733.2024.01101"},{"key":"2026092211020054900_btag342-B9","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s43586-024-00294-7","article-title":"Graph neural networks","volume":"4","author":"Corso","year":"2024","journal-title":"Nat Rev Methods Primers"},{"key":"2026092211020054900_btag342-B10","doi-asserted-by":"crossref","first-page":"264","DOI":"10.3389\/fmed.2019.00264","article-title":"Deep learning for whole slide image analysis: an overview","volume":"6","author":"Dimitriou","year":"2019","journal-title":"Front Med"},{"key":"2026092211020054900_btag342-B11","doi-asserted-by":"crossref","first-page":"3749","DOI":"10.1038\/s41591-025-03982-3","article-title":"A multimodal whole-slide foundation model for pathology","volume":"31","author":"Ding","year":"2025","journal-title":"Nat Med"},{"key":"2026092211020054900_btag342-B12","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1038\/s41596-024-01047-2","article-title":"From whole-slide image to biomarker prediction: end-to-end weakly supervised deep learning in computational pathology","volume":"20","author":"El Nahhas","year":"2025","journal-title":"Nat Protoc"},{"key":"2026092211020054900_btag342-B13","doi-asserted-by":"crossref","first-page":"15611","DOI":"10.1109\/CVPR52734.2025.01455","article-title":"MERGE: multi-faceted hierarchical graph-based GNN for gene expression prediction from whole slide histopathology images","author":"Ganguly","year":"2025","journal-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA"},{"key":"2026092211020054900_btag342-B14","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026092211020054900_btag342-B15","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1189\/jlb.2MR0815-380R","article-title":"Common and biased signaling pathways of the chemokine receptor CCR7 elicited by its ligands CCL19 and CCL21 in leukocytes","volume":"99","author":"Hauser","year":"2016","journal-title":"J Leucocyte Biol"},{"key":"2026092211020054900_btag342-B16","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":"2026092211020054900_btag342-B17","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1038\/s41746-025-02020-3","article-title":"STPath: a generative foundation model for integrating spatial transcriptomics and whole-slide images","volume":"8","author":"Huang","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2026092211020054900_btag342-B18","doi-asserted-by":"crossref","first-page":"8353","DOI":"10.1038\/s41467-023-43458-x","article-title":"High resolution mapping of the tumor microenvironment using integrated single-cell, spatial and in situ analysis","volume":"14","author":"Janesick","year":"2023","journal-title":"Nat Commun"},{"key":"2026092211020054900_btag342-B19","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":"2026092211020054900_btag342-B20","doi-asserted-by":"crossref","first-page":"464","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":"Brief Bioinform"},{"key":"2026092211020054900_btag342-B21","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1007\/s12094-019-02042-w","article-title":"Elevated expression of GNAS promotes breast cancer cell proliferation and migration via the PI3K\/AKT\/Snail1\/E-cadherin axis","volume":"21","author":"Jin","year":"2019","journal-title":"Clin Transl Oncol"},{"key":"2026092211020054900_btag342-B22","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026092211020054900_btag342-B23","doi-asserted-by":"crossref","first-page":"656908","DOI":"10.3389\/fimmu.2021.656908","article-title":"The role of tumor necrosis factor in manipulating the immunological response of tumor microenvironment","volume":"12","author":"Laha","year":"2021","journal-title":"Front Immunol"},{"key":"2026092211020054900_btag342-B24","doi-asserted-by":"crossref","first-page":"4843","DOI":"10.1093\/nar\/gkae294","article-title":"High-density generation of spatial transcriptomics with stage","volume":"52","author":"Li","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092211020054900_btag342-B25","doi-asserted-by":"crossref","first-page":"btag059","DOI":"10.1093\/bioinformatics\/btag059","article-title":"transFusion: a novel comprehensive platform for integration analysis of Single-Cell and spatial transcriptomics","volume":"42","author":"Lin","year":"2026","journal-title":"Bioinformatics"},{"key":"2026092211020054900_btag342-B26","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":"2026092211020054900_btag342-B27","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nat Med"},{"key":"2026092211020054900_btag342-B28","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1038\/s41593-020-00787-0","article-title":"Transcriptome-scale spatial gene expression in the human dorsolateral prefrontal cortex","volume":"24","author":"Maynard","year":"2021","journal-title":"Nat Neurosci"},{"key":"2026092211020054900_btag342-B29","doi-asserted-by":"crossref","first-page":"e1012881","DOI":"10.1371\/journal.pcbi.1012881","article-title":"SpaMask: dual masking graph autoencoder with contrastive learning for spatial transcriptomics","volume":"21","author":"Min","year":"2025","journal-title":"PLoS Comput Biol"},{"key":"2026092211020054900_btag342-B30","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":"2026092211020054900_btag342-B31","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":"Mondol","year":"2023","journal-title":"Cancers"},{"key":"2026092211020054900_btag342-B32","article-title":"Leveraging information in spatial transcriptomics to predict super-resolution gene expression from histology images in tumors","author":"Pang","year":"2021","journal-title":"BioRxiv"},{"key":"2026092211020054900_btag342-B33","doi-asserted-by":"crossref","first-page":"3460","DOI":"10.21437\/Interspeech.2024-40","volume-title":"Interspeech 2024, Kos, Greece","author":"Parcollet","year":"2024"},{"key":"2026092211020054900_btag342-B34","first-page":"8748","author":"Radford","year":"2021"},{"key":"2026092211020054900_btag342-B35","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1038\/s41586-021-03634-9","article-title":"Exploring tissue architecture using spatial transcriptomics","volume":"596","author":"Rao","year":"2021","journal-title":"Nature"},{"key":"2026092211020054900_btag342-B36","doi-asserted-by":"publisher","author":"Shi","DOI":"10.1109\/CVPR52734.2025.01938"},{"key":"2026092211020054900_btag342-B37","doi-asserted-by":"crossref","first-page":"112647","DOI":"10.1016\/j.engappai.2025.112647","article-title":"Geometry-informed multimodal fusion network for enhancing high-density spatial transcriptomics from histology images","volume":"162","author":"Shi","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"2026092211020054900_btag342-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":"2026092211020054900_btag342-B39","doi-asserted-by":"crossref","first-page":"628480","DOI":"10.3389\/fonc.2021.628480","article-title":"Proteomic analysis reveals that placenta-specific protein 9 inhibits proliferation and stimulates motility of human bronchial epithelial cells","volume":"11","author":"Wang","year":"2021","journal-title":"Front Oncol"},{"key":"2026092211020054900_btag342-B40","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1038\/s42003-020-01341-1","article-title":"From whole-mount to single-cell spatial assessment of gene expression in 3D","volume":"3","author":"Waylen","year":"2020","journal-title":"Commun Biol"},{"key":"2026092211020054900_btag342-B41","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1186\/s13073-022-01075-1","article-title":"An introduction to spatial transcriptomics for biomedical research","volume":"14","author":"Williams","year":"2022","journal-title":"Genome Med"},{"key":"2026092211020054900_btag342-B42","first-page":"70626","article-title":"Spatially resolved gene expression prediction from histology images via bi-modal contrastive learning","volume":"36","author":"Xie"},{"key":"2026092211020054900_btag342-B43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2407-6-88","article-title":"Expression analysis of mammaglobin A (SCGB2A2) and lipophilin B (SCGB1D2) in more than 300 human tumors and matching normal tissues reveals their co-expression in gynecologic malignancies","volume":"6","author":"Zafrakas","year":"2006","journal-title":"BMC Cancer"},{"key":"2026092211020054900_btag342-B44","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":"2026092211020054900_btag342-B45","doi-asserted-by":"crossref","first-page":"1375","DOI":"10.1038\/s41587-021-00935-2","article-title":"Spatial transcriptomics at subspot resolution with BayesSpace","volume":"39","author":"Zhao","year":"2021","journal-title":"Nat Biotechnol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag342\/68431864\/btag342.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag342\/68431864\/btag342.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag342\/68431864\/btag342.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T15:03:19Z","timestamp":1790089399000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag342\/8698030"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":45,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag342","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,5,29]]},"article-number":"btag342"}}