{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Verma S"],"funding":["Friends for an Earlier Breast Cancer Test","National Biofilms Innovation Centre","The Alan Turing Institute","EPSRC","Engineering and Physical Sciences Research Council"],"pagination":["100817"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11294841"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["4(7)"],"pubmed_abstract":["Deep-learning tools that extract prognostic factors derived from multi-omics data have recently contributed to individualized predictions of survival outcomes. However, the limited size of integrated omics-imaging-clinical datasets poses challenges. Here, we propose two biologically interpretable and robust deep-learning architectures for survival prediction of non-small cell lung cancer (NSCLC) patients, learning simultaneously from computed tomography (CT) scan images, gene expression data, and clinical information. The proposed models integrate patient-specific clinical, transcriptomic, and imaging data and incorporate Kyoto Encyclopedia of Genes and Genomes (KEGG) and Reactome pathway information, adding biological knowledge within the learning process to extract prognostic gene biomar"],"journal":["Cell reports methods"],"pubmed_title":["Cross-attention enables deep learning on limited omics-imaging-clinical data of 130 lung cancer patients."],"pmcid":["PMC11294841"],"funding_grant_id":["TNDC2-100022","EP/Y001613/1","D-ELA-013"],"pubmed_authors":["Verma S","Magazzu G","Lou T","Angione C","Occhipinti A","Eftekhari N","Gilhespy A"],"additional_accession":[]},"is_claimable":false,"name":"Cross-attention enables deep learning on limited omics-imaging-clinical data of 130 lung cancer patients.","description":"Deep-learning tools that extract prognostic factors derived from multi-omics data have recently contributed to individualized predictions of survival outcomes. However, the limited size of integrated omics-imaging-clinical datasets poses challenges. Here, we propose two biologically interpretable and robust deep-learning architectures for survival prediction of non-small cell lung cancer (NSCLC) patients, learning simultaneously from computed tomography (CT) scan images, gene expression data, and clinical information. The proposed models integrate patient-specific clinical, transcriptomic, and imaging data and incorporate Kyoto Encyclopedia of Genes and Genomes (KEGG) and Reactome pathway information, adding biological knowledge within the learning process to extract prognostic gene biomar","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Jul","modification":"2026-06-03T00:56:54.779Z","creation":"2025-02-19T02:28:52.837Z"},"accession":"S-EPMC11294841","cross_references":{"pubmed":["38981473"],"doi":["10.1016/j.crmeth.2024.100817"]}}