<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Atz K</submitter><funding>Swiss National Science Foundation</funding><funding>Scholarship Fund of the Swiss Chemical Industry</funding><pagination>3408</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC11035696</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>15(1)</volume><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 </pubmed_abstract><journal>Nature communications</journal><pubmed_title>Prospective de novo drug design with deep interactome learning.</pubmed_title><pmcid>PMC11035696</pmcid><funding_grant_id>202245</funding_grant_id><funding_grant_id>CRSII5_202245</funding_grant_id><funding_grant_id>205321</funding_grant_id><funding_grant_id>182176</funding_grant_id><pubmed_authors>Hiss JA</pubmed_authors><pubmed_authors>Grether U</pubmed_authors><pubmed_authors>Iff M</pubmed_authors><pubmed_authors>Hilleke M</pubmed_authors><pubmed_authors>Nippa DF</pubmed_authors><pubmed_authors>Schiebroek CCG</pubmed_authors><pubmed_authors>Focht D</pubmed_authors><pubmed_authors>Romeo V</pubmed_authors><pubmed_authors>Isert C</pubmed_authors><pubmed_authors>Schneider P</pubmed_authors><pubmed_authors>Ledergerber J</pubmed_authors><pubmed_authors>Hakansson M</pubmed_authors><pubmed_authors>Kuhn B</pubmed_authors><pubmed_authors>Schneider G</pubmed_authors><pubmed_authors>Atz K</pubmed_authors><pubmed_authors>Cotos L</pubmed_authors><pubmed_authors>Merk D</pubmed_authors></additional><is_claimable>false</is_claimable><name>Prospective de novo drug design with deep interactome learning.</name><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 </description><dates><release>2024-01-01T00:00:00Z</release><publication>2024 Apr</publication><modification>2026-06-01T19:59:22.189Z</modification><creation>2025-08-17T03:06:08.357Z</creation></dates><accession>S-EPMC11035696</accession><cross_references><pubmed>38649351</pubmed><doi>10.1038/s41467-024-47613-w</doi></cross_references></HashMap>