{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:27:02Z","timestamp":1760059622616,"version":"build-2065373602"},"reference-count":27,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","award":["RGPIN-2024-05287"],"award-info":[{"award-number":["RGPIN-2024-05287"]}]},{"name":"AI in Health Research Chair at the Universit\u00e9 de Moncton","award":["RGPIN-2024-05287"],"award-info":[{"award-number":["RGPIN-2024-05287"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Background: The accurate prediction of gene expression is essential in breast cancer research. However, spatial transcriptomics technologies are usually too expensive. Recent studies have used whole-slide images combined with spatial transcriptomics data to predict breast cancer gene expression. To this end, we present EMGP-Net, a novel hybrid deep learning architecture developed by combining two state-of-the-art models, MambaVision and EfficientFormer. Method: EMGP-Net was first trained on the HER2+ dataset, containing data from eight patients using a leave-one-patient-out approach. To ensure generalizability, we conducted external validation and alternately trained EMGP-Net on the HER2+ dataset and tested it on the STNet dataset, containing data from 23 patients, and vice versa. We evaluated EMGP-Net\u2019s ability to predict the expression of 250 selected genes. EMGP-Net mixes features from both models, and uses attention mechanisms followed by fully connected layers. Results: Our model outperformed both EfficientFormer and MambaVision, which were trained separately on the HER2+ dataset, achieving the highest PCC of 0.7903 for the PTMA gene, with the top 14 genes having PCCs greater than 0.7, including other important breast cancer biomarkers such as GNAS and B2M. The external validation showed that it also outperformed models that were retrained with our approach. Conclusions: The results of EMGP-Net were better than those of existing models, showing that the combination of advanced models is an effective strategy to improve performance in this task.<\/jats:p>","DOI":"10.3390\/computers14070253","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T11:15:23Z","timestamp":1750936523000},"page":"253","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EMGP-Net: A Hybrid Deep Learning Architecture for Breast Cancer Gene Expression Prediction"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1437-6154","authenticated-orcid":false,"given":"Oumeima","family":"Th\u00e2albi","sequence":"first","affiliation":[{"name":"Perception, Robotics, and Intelligent Machines (PRIME), Department of Computer Science, Universit\u00e9 de Moncton, Moncton, NB E1A 3E9, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4378-2669","authenticated-orcid":false,"given":"Moulay A.","family":"Akhloufi","sequence":"additional","affiliation":[{"name":"Perception, Robotics, and Intelligent Machines (PRIME), Department of Computer Science, Universit\u00e9 de Moncton, Moncton, NB E1A 3E9, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e36905","DOI":"10.1097\/MD.0000000000036905","article-title":"Breast cancer: A review of risk factors and diagnosis","volume":"103","author":"Obeagu","year":"2024","journal-title":"Medicine"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Thaalbi, O., and Akhloufi, M.A. (2024). Deep learning for breast cancer diagnosis from histopathological images: Classification and gene expression: Review. Netw. Model. Anal. Health Inform. Bioinform., 13.","DOI":"10.1007\/s13721-024-00489-8"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Al-Jabbar, M., Alshahrani, M., Senan, E.M., and Ahmed, I.A. (2023). Multi-Method Diagnosis of Histopathological Images for Early Detection of Breast Cancer Based on Hybrid and Deep Learning. Mathematics, 11.","DOI":"10.3390\/math11061429"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Obayya, M., Maashi, M.S., Nemri, N., Mohsen, H., Motwakel, A., Osman, A.E., Alneil, A.A., and Alsaid, M.I. (2023). Hyperparameter Optimizer with Deep Learning-Based Decision-Support Systems for Histopathological Breast Cancer Diagnosis. Cancers, 15.","DOI":"10.3390\/cancers15030885"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Clement, D., Agu, E., Obayemi, J., Adeshina, S., and Soboyejo, W. (2022). Breast Cancer Tumor Classification Using a Bag of Deep Multi-Resolution Convolutional Features. Informatics, 9.","DOI":"10.3390\/informatics9040091"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Bagchi, A., Pramanik, P., and Sarkar, R. (2022). A Multi-Stage Approach to Breast Cancer Classification Using Histopathology Images. Diagnostics, 13.","DOI":"10.2139\/ssrn.4065219"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"18019","DOI":"10.1007\/s11042-022-14268-y","article-title":"Detection and classification of breast cancer availing deep canid optimization based deep CNN","volume":"82","author":"Bhausaheb","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1016\/j.jksuci.2023.01.017","article-title":"SECS: An effective CNN joint construction strategy for breast cancer histopathological image classification","volume":"35","author":"Yu","year":"2023","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_9","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":"ref_10","doi-asserted-by":"crossref","unstructured":"Rahaman, M.M., Millar, E.K., and Meijering, E. (2023). Breast cancer histopathology image-based gene expression prediction using spatial transcriptomics data and deep learning. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-40219-0"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Thaalbi, O., and Akhloufi, M.A. (2025). GeNetFormer: Transformer-Based Framework for Gene Expression Prediction in Breast Cancer. AI, 6.","DOI":"10.3390\/ai6030043"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pang, M., Su, K., and Li, M. (2021). Leveraging information in spatial transcriptomics to predict super-resolution gene expression from histology images in tumors. BioRxiv.","DOI":"10.1101\/2021.11.28.470212"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Mejia, G., C\u00e1rdenas, P., Ruiz, D., Castillo, A., and Arbel\u00e1ez, P. (2023, January 1\u20136). SEPAL: Spatial Gene Expression Prediction from Local Graphs. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCVW60793.2023.00243"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Wei, Z., Yu, W., Yin, R., Yuan, Y., Li, B., Tang, Z., Lu, Y., and Yang, Y. (2022). Spatial transcriptomics prediction from histology jointly through transformer and graph neural networks. Briefings Bioinform., 23.","DOI":"10.1093\/bib\/bbac297"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Jia, Y., Liu, J., Chen, L., Zhao, T., and Wang, Y. (2024). THItoGene: A deep learning method for predicting spatial transcriptomics from histological images. Briefings Bioinform., 25.","DOI":"10.1093\/bib\/bbad464"},{"key":"ref_16","unstructured":"Niu, Y., Liu, J., Zhan, Y., Shi, J., Zhang, D., Machado, I., Crispin-Ortuzar, M., Li, C., and Gao, Z. (2025). ST-Prompt Guided Histological Hypergraph Learning for Spatial Gene Expression Prediction. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, B., Zhang, Y., Wang, Q., Zhang, C., Li, M., Wang, G., and Song, Q. (2024). Gene expression prediction from histology images via hypergraph neural networks. Briefings Bioinform., 25.","DOI":"10.1093\/bib\/bbae500"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yang, Y., Hossain, M.Z., Stone, E.A., and Rahman, S. (2023, January 2\u20137). Exemplar guided deep neural network for spatial transcriptomics analysis of gene expression prediction. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV56688.2023.00501"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"109966","DOI":"10.1016\/j.patcog.2023.109966","article-title":"Spatial transcriptomics analysis of gene expression prediction using exemplar guided graph neural network","volume":"145","author":"Yang","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106091","DOI":"10.1016\/j.neunet.2023.12.045","article-title":"Are transformer-based models more robust than CNN-based models?","volume":"172","author":"Liu","year":"2024","journal-title":"Neural Netw."},{"key":"ref_21","unstructured":"Hatamizadeh, A., and Kautz, J. (2024). Mambavision: A hybrid mamba-transformer vision backbone. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chung, Y., Ha, J.H., Im, K.C., and Lee, J.S. (2024, January 16\u201322). Accurate Spatial Gene Expression Prediction by Integrating Multi-Resolution Features. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01101"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, C., Zhang, Z., Tang, P., Liu, X., and Huang, B. (2024). Edge-relational window-attentional graph neural network for gene expression prediction in spatial transcriptomics analysis. Comput. Biol. Med., 174.","DOI":"10.1016\/j.compbiomed.2024.108449"},{"key":"ref_24","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":"ref_25","unstructured":"Gu, A., and Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv."},{"key":"ref_26","first-page":"12934","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","unstructured":"Vaswani, A. (2017). Attention is all you need. arXiv."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/7\/253\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:59:20Z","timestamp":1760032760000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/7\/253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":27,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["computers14070253"],"URL":"https:\/\/doi.org\/10.3390\/computers14070253","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,6,26]]}}}