{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Atz K"],"funding":["Swiss National Science Foundation","Scholarship Fund of the Swiss Chemical Industry"],"pagination":["3408"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11035696"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["15(1)"],"pubmed_abstract":["De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes on the unique strengths of both graph neural networks and chemical language models, offering an alternative to the need for application-specific reinforcement, transfer, or few-shot learning. It enables the \"zero-shot\" construction of compound libraries tailored to possess specific bioactivity, synthesizability, and structural novelty. In order to proactively evaluate the deep interactome learning framework for protein structure-based drug design, potential new ligands targeting the binding site of the "],"journal":["Nature communications"],"pubmed_title":["Prospective de novo drug design with deep interactome learning."],"pmcid":["PMC11035696"],"funding_grant_id":["202245","CRSII5_202245","205321","182176"],"pubmed_authors":["Hiss JA","Grether U","Iff M","Hilleke M","Nippa DF","Schiebroek CCG","Focht D","Romeo V","Isert C","Schneider P","Ledergerber J","Hakansson M","Kuhn B","Schneider G","Atz K","Cotos L","Merk D"],"additional_accession":[]},"is_claimable":false,"name":"Prospective de novo drug design with deep interactome learning.","description":"De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes on the unique strengths of both graph neural networks and chemical language models, offering an alternative to the need for application-specific reinforcement, transfer, or few-shot learning. It enables the \"zero-shot\" construction of compound libraries tailored to possess specific bioactivity, synthesizability, and structural novelty. In order to proactively evaluate the deep interactome learning framework for protein structure-based drug design, potential new ligands targeting the binding site of the ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Apr","modification":"2026-06-01T19:59:22.189Z","creation":"2025-08-17T03:06:08.357Z"},"accession":"S-EPMC11035696","cross_references":{"pubmed":["38649351"],"doi":["10.1038/s41467-024-47613-w"]}}