{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["20(9)"],"submitter":["Ray S"],"pubmed_abstract":["The COVID-19 pandemic has demanded urgent and accelerated action toward developing effective therapeutic strategies. Drug repurposing models (in silico) are in high demand and require accurate and reliable molecular interaction data. While experimentally verified viral-host interaction data (SARS-CoV-2-human interactions published on April 30, 2020) provide an invaluable resource, these datasets include only a limited number of high-confidence interactions. Here, we extend these resources using a deep learning-based multiview graph neural network approach, coupled with optimal transport-based integration. Our comprehensive validation strategy confirms 472 high-confidence predicted interactions between 280 host proteins and 27 SARS-CoV-2 proteins. The proposed model demonstrates robust pred"],"journal":["PloS one"],"pagination":["e0332794"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12463271"],"repository":["biostudies-literature"],"pubmed_title":["A graph neural network-based approach for predicting SARS-CoV-2-human protein interactions from multiview data."],"pmcid":["PMC12463271"],"pubmed_authors":["Schonhuth A","Alberuni S","Ray S"],"additional_accession":[]},"is_claimable":false,"name":"A graph neural network-based approach for predicting SARS-CoV-2-human protein interactions from multiview data.","description":"The COVID-19 pandemic has demanded urgent and accelerated action toward developing effective therapeutic strategies. Drug repurposing models (in silico) are in high demand and require accurate and reliable molecular interaction data. While experimentally verified viral-host interaction data (SARS-CoV-2-human interactions published on April 30, 2020) provide an invaluable resource, these datasets include only a limited number of high-confidence interactions. Here, we extend these resources using a deep learning-based multiview graph neural network approach, coupled with optimal transport-based integration. Our comprehensive validation strategy confirms 472 high-confidence predicted interactions between 280 host proteins and 27 SARS-CoV-2 proteins. The proposed model demonstrates robust pred","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025","modification":"2026-06-06T04:10:51.854Z","creation":"2026-05-25T03:12:11.809Z"},"accession":"S-EPMC12463271","cross_references":{"pubmed":["40997149"],"doi":["10.1371/journal.pone.0332794"]}}