{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:48:10Z","timestamp":1785336490411,"version":"3.55.0"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"vor","delay-in-days":56,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Human Genome Research Institute of the National Institutes of Health","award":["T32HG000046"],"award-info":[{"award-number":["T32HG000046"]}]},{"name":"National Library of Medicine of the National Institutes of Health","award":["R00LM013646"],"award-info":[{"award-number":["R00LM013646"]}]},{"name":"National Institute on Aging of the National Institutes of Health","award":["U01AG066833"],"award-info":[{"award-number":["U01AG066833"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurately determining the binding affinity of a ligand with a protein is important for drug design, development, and screening. With the advent of accessible protein structure prediction methods such as AlphaFold, predicted protein 3D structures are readily available; however, scalable methods for predicting binding affinity currently do not take full advantage of 3D protein information. Here, we present CASTER-DTA (Cross-Attention with Structural Target Equivariant Representations for Drug\u2013Target Affinity), which uses an equivariant graph neural network (GNN) to learn more robust protein representations alongside a standard GNN to learn molecular representations to predict DTA. We augment these representations by incorporating an attention-based mechanism between protein residues and drug atoms to improve interpretability. We show that CASTER-DTA represents a state-of-the-art improvement on multiple benchmarks for predicting DTA, and that it generates novel insights for several related tasks. We then apply CASTER-DTA to create a large resource of the binding affinities of every drug approved by the U.S. Food and Drug Administration (FDA) against every protein in the human proteome and make these predictions freely available for download. We also make available a web server for researchers to apply a pretrained CASTER-DTA model for predicting binding affinities between arbitrary proteins and drugs.<\/jats:p>","DOI":"10.1093\/bib\/bbaf554","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T11:47:45Z","timestamp":1759837665000},"source":"Crossref","is-referenced-by-count":8,"title":["CASTER-DTA: equivariant graph neural networks for predicting drug\u2013target affinity"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7736-3307","authenticated-orcid":false,"given":"Rachit","family":"Kumar","sequence":"first","affiliation":[{"name":"Medical Scientist Training Program , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]},{"name":"Genomics and Computational Biology Graduate Group , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]},{"name":"Institute for Biomedical Informatics , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7999-4399","authenticated-orcid":false,"given":"Joseph D","family":"Romano","sequence":"additional","affiliation":[{"name":"Institute for Biomedical Informatics , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]},{"name":"Center of Excellence in Environmental Toxicology , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]},{"name":"Department of Biostatistics , Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1208-1720","authenticated-orcid":false,"given":"Marylyn D","family":"Ritchie","sequence":"additional","affiliation":[{"name":"Institute for Biomedical Informatics , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]},{"name":"Department of Biostatistics , Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]},{"name":"Department of Genetics , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"2025102609224107500_ref1","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1080\/17460441.2019.1623202","article-title":"Binding affinity in drug design: experimental and computational techniques","volume":"14","author":"Kairys","year":"2019","journal-title":"Expert Opin Drug Discovery"},{"key":"2025102609224107500_ref2","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.3390\/molecules23081899","article-title":"Binding affinity via docking: fact and fiction","volume":"23","author":"Pantsar","year":"2018","journal-title":"Molecules"},{"key":"2025102609224107500_ref3","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa107","article-title":"Computationally predicting binding affinity in protein\u2013ligand complexes: free energy-based simulations and machine learning-based scoring functions","volume":"22","author":"Wang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025102609224107500_ref4","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TCBB.2022.3170365","article-title":"AttentionDTA: drug-target binding affinity prediction by sequence-based deep learning with attention mechanism","volume":"20","author":"Zhao","year":"2023","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025102609224107500_ref5","doi-asserted-by":"publisher","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug\u2013target binding affinity prediction","volume":"34","author":"\u00d6zt\u00fcrk","year":"2018","journal-title":"Bioinformatics"},{"key":"2025102609224107500_ref6","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA: predicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2025102609224107500_ref7","doi-asserted-by":"publisher","first-page":"20701","DOI":"10.1039\/D0RA02297G","article-title":"Drug\u2013target affinity prediction using graph neural network and contact maps","volume":"10","author":"Jiang","year":"2020","journal-title":"RSC Adv"},{"key":"2025102609224107500_ref8","article-title":"Equivariant graph neural networks for 3D macromolecular structure","author":"Jing"},{"key":"2025102609224107500_ref9","article-title":"Learning from protein structure with geometric vector perceptrons","author":"Jing"},{"key":"2025102609224107500_ref10","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1038\/s41467-023-36699-3","article-title":"Predicting locations of cryptic pockets from single protein structures using the PocketMiner graph neural network","volume":"14","author":"Meller","year":"2023","journal-title":"Nat Commun"},{"key":"2025102609224107500_ref11","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1038\/nbt.1990","article-title":"Comprehensive analysis of kinase inhibitor selectivity","volume":"29","author":"Davis","year":"2011","journal-title":"Nat Biotechnol"},{"key":"2025102609224107500_ref12","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1021\/ci400709d","article-title":"Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis","volume":"54","author":"Tang","year":"2014","journal-title":"J Chem Inf Model"},{"key":"2025102609224107500_ref13","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1038\/nchembio.530","article-title":"Navigating the kinome","volume":"7","author":"Metz","year":"2011","journal-title":"Nat Chem Biol"},{"key":"2025102609224107500_ref14","first-page":"gkae1075","article-title":"Bindingdb in 2024: a fair knowledgebase of protein-small molecule binding data","author":"Liu","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2025102609224107500_ref15","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data Bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2025102609224107500_ref16","doi-asserted-by":"publisher","first-page":"D368","DOI":"10.1093\/nar\/gkad1011","article-title":"AlphaFold protein structure database in 2024: providing structure coverage for over 214 million protein sequences","volume":"52","author":"Varadi","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2025102609224107500_ref17","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2025102609224107500_ref18","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1038\/s41592-022-01488-1","article-title":"ColabFold: making protein folding accessible to all","volume":"19","author":"Mirdita","year":"2022","journal-title":"Nat Methods"},{"key":"2025102609224107500_ref19","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1038\/s41589-024-01638-w","article-title":"The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins","volume":"20","author":"Agarwal","year":"2024","journal-title":"Nat Chem Biol"},{"key":"2025102609224107500_ref20","doi-asserted-by":"publisher","first-page":"985","DOI":"10.3390\/biom12070985","article-title":"Benchmarking the accuracy of AlphaFold 2 in loop structure prediction","volume":"12","author":"Stevens","year":"2022","journal-title":"Biomolecules"},{"key":"2025102609224107500_ref21","doi-asserted-by":"crossref","first-page":"2464","DOI":"10.1038\/s41467-024-46715-9","article-title":"High-throughput prediction of protein conformational distributions with subsampled AlphaFold2","volume":"15","author":"Monteiro","year":"2024","journal-title":"Nat Commun"},{"key":"2025102609224107500_ref22","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1038\/s41586-023-06832-9","article-title":"Predicting multiple conformations via sequence clustering and AlphaFold2","volume":"625","author":"Wayment-Steele","year":"2024","journal-title":"Nature"},{"key":"2025102609224107500_ref23","unstructured":"RDKit: Open-source cheminformatics. http:\/\/www.rdkit.org. [Online]. 10.5281\/zenodo.10633624"},{"key":"2025102609224107500_ref24","article-title":"How powerful are graph neural networks?","author":"Xu"},{"key":"2025102609224107500_ref25","article-title":"Strategies for pre-training graph neural networks","author":"Hu"},{"key":"2025102609224107500_ref26","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107"},{"key":"2025102609224107500_ref27","article-title":"How attentive are graph attention networks?","author":"Brody"},{"key":"2025102609224107500_ref28","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Xiong","year":"2020","journal-title":"J Med Chem"},{"key":"2025102609224107500_ref29","doi-asserted-by":"publisher","first-page":"D1096","DOI":"10.1093\/nar\/gks966","article-title":"Biolip: a semi-manually curated database for biologically relevant ligand-protein interactions","volume":"41","author":"Yang","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2025102609224107500_ref30","doi-asserted-by":"publisher","first-page":"e226","DOI":"10.1002\/cpz1.226","article-title":"Pharmgkb, an integrated resource of pharmacogenomic knowledge","volume":"1","author":"Gong","year":"2021","journal-title":"Curr Protoc"},{"key":"2025102609224107500_ref31","doi-asserted-by":"publisher","first-page":"6065","DOI":"10.1021\/acs.jcim.0c00675","article-title":"ZINC20-a free Ultralarge-scale chemical database for ligand discovery","volume":"60","author":"Irwin","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2025102609224107500_ref32","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1160\/TH12-03-0151","article-title":"Effect of the VKORC1 D36Y variant on warfarin dose requirement and pharmacogenetic dose prediction","volume":"108","author":"Kurnik","year":"2012","journal-title":"Thromb Haemost"},{"key":"2025102609224107500_ref33","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1001\/jama.293.12.1485","article-title":"Thiopurine methyltransferase (TPMT) genotype and early treatment response to mercaptopurine in childhood acute lymphoblastic leukemia","volume":"293","author":"Stanulla","year":"2005","journal-title":"JAMA"},{"key":"2025102609224107500_ref34","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1002\/cpt.2527","article-title":"SLCO1B1${\\ast }$5 allele is associated with atorvastatin discontinuation and adverse muscle symptoms in the context of routine care","volume":"111","author":"Voora","year":"2022","journal-title":"Clin Pharmacol Ther"},{"key":"2025102609224107500_ref35","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1038\/s41397-021-00208-w","article-title":"A systematic review and meta-analysis of genotype-based and individualized data analysis of SLCO1B1 gene and statin-induced myopathy","volume":"21","author":"Turongkaravee","year":"2021","journal-title":"Pharmacogenomics J"},{"key":"2025102609224107500_ref36","doi-asserted-by":"publisher","first-page":"E200","DOI":"10.1073\/pnas.1615613114","article-title":"Systematic development of small molecules to inhibit specific microscopic steps of abeta42 aggregation in Alzheimer\u2019s disease","volume":"114","author":"Habchi","year":"2017","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025102609224107500_ref37","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1007\/s11481-011-9304-5","article-title":"The effect of hiv protease inhibitors on amyloid-beta peptide degradation and synthesis in human cells and Alzheimer\u2019s disease animal model","volume":"7","author":"Lan","year":"2012","journal-title":"J Neuroimmune Pharmacol"},{"key":"2025102609224107500_ref38","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1089\/rej.2018.2070","article-title":"Rapamycin confers neuroprotection against aging-induced oxidative stress, mitochondrial dysfunction, and neurodegeneration in old rats through activation of autophagy","volume":"22","author":"Singh","year":"2019","journal-title":"Rejuvenation Res"},{"key":"2025102609224107500_ref39","doi-asserted-by":"publisher","first-page":"3438","DOI":"10.1002\/anie.201511361","article-title":"Drug repurposing identifies inhibitors of oseltamivir-resistant influenza viruses","volume":"55","author":"Bao","year":"2016","journal-title":"Angew Chem Int Ed"},{"key":"2025102609224107500_ref40","doi-asserted-by":"publisher","first-page":"e13169","DOI":"10.1371\/journal.pone.0013169","article-title":"Gene expression signature-based screening identifies new broadly effective influenza a antivirals","volume":"5","author":"Josset","year":"2010","journal-title":"PLoS One"},{"key":"2025102609224107500_ref41","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.3390\/v15051128","article-title":"DHFR inhibitors display a pleiotropic anti-viral activity against SARS-COV-2: insights into the mechanisms of action","volume":"15","author":"Iaconis","year":"2023","journal-title":"Viruses"},{"key":"2025102609224107500_ref42","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1038\/nrd4163","article-title":"The role of ligand efficiency metrics in drug discovery","volume":"13","author":"Hopkins","year":"2014","journal-title":"Nat Rev Drug Discov"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf554\/64948755\/bbaf554.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf554\/64948755\/bbaf554.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T13:22:48Z","timestamp":1761484968000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf554\/8303310"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf554","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,8,31]]},"article-number":"bbaf554"}}