{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Stevenson GA"],"funding":["American Heart Association","Lawrence Livermore National Laboratory"],"pagination":["6655-6666"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10647021"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["63(21)"],"pubmed_abstract":["Protein-ligand interactions are essential to drug discovery and drug development efforts. Desirable on-target or multitarget interactions are the first step in finding an effective therapeutic, while undesirable off-target interactions are the first step in assessing safety. In this work, we introduce a novel ligand-based featurization and mapping of human protein pockets to identify closely related protein targets and to project novel drugs into a hybrid protein-ligand feature space to identify their likely protein interactions. Using structure-based template matches from PDB, protein pockets are featured by the ligands that bind to their best co-complex template matches. The simplicity and interpretability of this approach provide a granular characterization of the human proteome at the protein-pocket level instead of the traditional protein-level characterization by family, function, or pathway. We demonstrate the power of this featurization method by clustering a subset of the human proteome and evaluating the predicted cluster associations of over 7000 compounds."],"journal":["Journal of chemical information and modeling"],"pubmed_title":["Clustering Protein Binding Pockets and Identifying Potential Drug Interactions: A Novel Ligand-Based Featurization Method."],"pmcid":["PMC10647021"],"funding_grant_id":["TC02274","DE- AC52-07NA27344"],"pubmed_authors":["Zemla A","Wong SE","Kim H","Bennett WFD","Torres MW","Kirshner D","Epstein A","Allen JE","Stevenson GA","Jones D","Lightstone FC","Yang Y","Zhang X","Bennion BJ"],"additional_accession":[]},"is_claimable":false,"name":"Clustering Protein Binding Pockets and Identifying Potential Drug Interactions: A Novel Ligand-Based Featurization Method.","description":"Protein-ligand interactions are essential to drug discovery and drug development efforts. Desirable on-target or multitarget interactions are the first step in finding an effective therapeutic, while undesirable off-target interactions are the first step in assessing safety. In this work, we introduce a novel ligand-based featurization and mapping of human protein pockets to identify closely related protein targets and to project novel drugs into a hybrid protein-ligand feature space to identify their likely protein interactions. Using structure-based template matches from PDB, protein pockets are featured by the ligands that bind to their best co-complex template matches. The simplicity and interpretability of this approach provide a granular characterization of the human proteome at the protein-pocket level instead of the traditional protein-level characterization by family, function, or pathway. We demonstrate the power of this featurization method by clustering a subset of the human proteome and evaluating the predicted cluster associations of over 7000 compounds.","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Nov","modification":"2024-10-18T05:23:53.785Z","creation":"2024-10-18T05:23:53.785Z"},"accession":"S-EPMC10647021","cross_references":{"pubmed":["37847557"],"doi":["10.1021/acs.jcim.3c00722"]}}