{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:12:46Z","timestamp":1768263166066,"version":"3.49.0"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"vor","delay-in-days":56,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002808","name":"Carlsberg Foundation","doi-asserted-by":"publisher","award":["CF20-0248"],"award-info":[{"award-number":["CF20-0248"]}],"id":[{"id":"10.13039\/501100002808","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Deep learning (DL) methods have drastically advanced structure-based drug discovery by directly predicting protein structures from sequences. Recently, these methods have become increasingly accurate in predicting complexes formed by multiple protein chains. We evaluated these advancements to predict and accurately model the largest receptor family and its cognate peptide hormones. We benchmarked DL tools, including AlphaFold 2.3 (AF2), AlphaFold 3 (AF3), Chai-1, NeuralPLexer, RoseTTAFold-AllAtom, Peptriever, ESMFold, and D-SCRIPT, to predict interactions between G protein-coupled receptors (GPCRs) and their endogenous peptide ligands. Our results showed that structure-aware models outperformed language models in peptide binding classification, with the top-performing model achieving an area under the curve of 0.86 on a benchmark set of 124 ligands and 1240 decoys. Rescoring predicted structures on local interactions further improved the principal ligand discovery among decoy peptides, whereas DL-based approaches did not. We explored a competitive tournament approach for modeling multiple peptides simultaneously on a single GPCR, which accelerates the performance but reduces true-positive recovery. When evaluating the binding poses of 67 recent complexes, AF2 reproduced the correct binding modes in nearly all cases (94%), surpassing those of both AF3 and Chai-1. Confidence scores correlate with structural binding mode accuracy, which provides a guide for interpreting interface predictions. These results demonstrated that DL models can reliably rediscover peptide binders, aid peptide drug discovery, and guide the selection of optimal tools for GPCR-targeted therapies. To this end, we provided a practical guide for selecting the best models for specific applications and an independent benchmarking set for future model evaluation.<\/jats:p>","DOI":"10.1093\/bib\/bbaf186","type":"journal-article","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T04:29:53Z","timestamp":1745641793000},"source":"Crossref","is-referenced-by-count":5,"title":["Deep learning in GPCR drug discovery: benchmarking the path to accurate peptide binding"],"prefix":"10.1093","volume":"26","author":[{"given":"Luuk R","family":"Hoegen Dijkhof","sequence":"first","affiliation":[{"name":"Department of Drug Design and Pharmacology, University of Copenhagen , Jagtvej 160, 2100 \u00d8, Copenhagen ,","place":["Denmark"]},{"name":"Center for Pharmaceutical Data Science, University of Copenhagen ,","place":["Denmark"]}]},{"given":"Teemu K E","family":"R\u00f6nkk\u00f6","sequence":"additional","affiliation":[{"name":"Department of Drug Design and Pharmacology, University of Copenhagen , Jagtvej 160, 2100 \u00d8, Copenhagen ,","place":["Denmark"]},{"name":"Center for Pharmaceutical Data Science, University of Copenhagen ,","place":["Denmark"]}]},{"given":"Hans C","family":"von Vegesack","sequence":"additional","affiliation":[{"name":"Department of Drug Design and Pharmacology, University of Copenhagen , Jagtvej 160, 2100 \u00d8, Copenhagen ,","place":["Denmark"]},{"name":"Center for Pharmaceutical Data Science, University of Copenhagen ,","place":["Denmark"]}]},{"given":"Jacob","family":"Lenzing","sequence":"additional","affiliation":[{"name":"Department of Drug Design and Pharmacology, University of Copenhagen , Jagtvej 160, 2100 \u00d8, Copenhagen ,","place":["Denmark"]},{"name":"Center for Pharmaceutical Data Science, University of Copenhagen ,","place":["Denmark"]}]},{"given":"Alexander S","family":"Hauser","sequence":"additional","affiliation":[{"name":"Department of Drug Design and Pharmacology, University of Copenhagen , Jagtvej 160, 2100 \u00d8, Copenhagen ,","place":["Denmark"]},{"name":"Center for Pharmaceutical Data Science, University of Copenhagen ,","place":["Denmark"]}]}],"member":"286","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"2025042600294764300_ref1","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1002\/prot.26617","article-title":"Critical assessment of methods of protein structure prediction (CASP)-round XV","volume":"91","author":"Kryshtafovych","year":"2023","journal-title":"Proteins"},{"key":"2025042600294764300_ref2","doi-asserted-by":"publisher","first-page":"102594","DOI":"10.1016\/j.sbi.2023.102594","article-title":"Progress at protein structure prediction, as seen in CASP15","volume":"80","author":"Elofsson","year":"2023","journal-title":"Curr Opin Struct Biol"},{"key":"2025042600294764300_ref3","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":"2025042600294764300_ref4","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1146\/annurev-biophys-102622-084607","article-title":"Critical assessment of methods for predicting the 3D structure of proteins and protein complexes","volume":"52","author":"Wodak","year":"2023","journal-title":"Annu Rev Biophys"},{"key":"2025042600294764300_ref5","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1038\/nrd.2017.178","article-title":"Trends in GPCR drug discovery: new agents, targets and indications","volume":"16","author":"Hauser","year":"2017","journal-title":"Nat Rev Drug Discov"},{"key":"2025042600294764300_ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-025-01139-y","article-title":"GPCR drug discovery: new agents, targets and indications","author":"Lorente","journal-title":"Nat Rev Drug Discov."},{"key":"2025042600294764300_ref7","doi-asserted-by":"publisher","DOI":"10.1101\/2023.07.28.551063","article-title":"Reliable protein-protein docking with AlphaFold, Rosetta, and replica-exchange","author":"Harmalkar","year":"2023","journal-title":"bioRxiv"},{"key":"2025042600294764300_ref8","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1016\/j.cell.2019.10.010","article-title":"Discovery of human signaling systems: pairing peptides to G protein-coupled receptors","volume":"179","author":"Foster","year":"2019","journal-title":"Cell"},{"key":"2025042600294764300_ref9","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1021\/acs.jcim.5b00234","article-title":"LEADS-PEP: a benchmark data set for assessment of peptide docking performance","volume":"56","author":"Hauser","year":"2016","journal-title":"J Chem Inf Model"},{"key":"2025042600294764300_ref10","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae303","article-title":"Peptriever: a bi-encoder approach for large-scale protein-peptide binding search","volume":"40","author":"Gurvich","year":"2024","journal-title":"Bioinformatics"},{"key":"2025042600294764300_ref11","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1016\/j.cels.2021.08.010","article-title":"D-SCRIPT translates genome to phenome with sequence-based, structure-aware, genome-scale predictions of protein-protein interactions","volume":"12","author":"Sledzieski","year":"2021","journal-title":"Cell Syst"},{"key":"2025042600294764300_ref12","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1002\/pro.2187","article-title":"A comparison of successful and failed protein interface designs highlights the challenges of designing buried hydrogen bonds","volume":"22","author":"Stranges","year":"2013","journal-title":"Protein Sci"},{"key":"2025042600294764300_ref13","doi-asserted-by":"publisher","DOI":"10.1101\/2024.02.19.580970","author":"Kim","year":"2024","journal-title":"Enhanced Protein-Protein Interaction Discovery Via AlphaFold-Multimer"},{"key":"2025042600294764300_ref14","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1016\/j.ymthe.2024.04.003","article-title":"Fast, accurate ranking of engineered proteins by receptor binding propensity using structure modeling","volume":"36","author":"Ding","year":"2024","journal-title":"Molecular Therapy"},{"key":"2025042600294764300_ref15","doi-asserted-by":"publisher","first-page":"647915","DOI":"10.3389\/fmolb.2021.647915","article-title":"Protein docking model evaluation by graph neural networks","volume":"8","author":"Wang","year":"2021","journal-title":"Front Mol Biosci"},{"key":"2025042600294764300_ref16","doi-asserted-by":"publisher","first-page":"vbad191","DOI":"10.1093\/bioadv\/vbad191","article-title":"DeepRank-GNN-esm: a graph neural network for scoring protein\u2013protein models using protein language model","volume":"4","author":"Xu","year":"2024","journal-title":"Bioinform Adv"},{"key":"2025042600294764300_ref17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae586","volume":"40","author":"Mirabello","journal-title":"DockQ v2: Improved Automatic Quality Measure for Protein Multimers, Nucleic Acids, and Small Molecules"},{"key":"2025042600294764300_ref18","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.csbj.2022.11.057","article-title":"Evaluating GPCR modeling and docking strategies in the era of deep learning-based protein structure prediction","volume":"21","author":"Lee","year":"2023","journal-title":"Comput Struct Biotechnol J"},{"key":"2025042600294764300_ref19","doi-asserted-by":"publisher","first-page":"10139","DOI":"10.3390\/ijms251810139","article-title":"Reliability of AlphaFold2 models in virtual drug screening: a focus on selected class a GPCRs","volume":"25","author":"Alhumaid","year":"2024","journal-title":"Int J Mol Sci"},{"key":"2025042600294764300_ref20","doi-asserted-by":"publisher","first-page":"btad424","DOI":"10.1093\/bioinformatics\/btad424","article-title":"Evaluation of AlphaFold-Multimer prediction on multi-chain protein complexes","volume":"39","author":"Zhu","year":"2023","journal-title":"Bioinformatics"},{"key":"2025042600294764300_ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41401-022-00938-y","article-title":"AlphaFold2 versus experimental structures: evaluation on G protein-coupled receptors","volume":"44","author":"He","year":"2023","journal-title":"Acta Pharmacol Sin"},{"key":"2025042600294764300_ref22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41401-024-01429-y","article-title":"AlphaFold3 versus experimental structures: assessment of the accuracy in ligand-bound G protein-coupled receptors","volume":"46","author":"He","year":"2024","journal-title":"Acta Pharmacol Sin"},{"key":"2025042600294764300_ref23","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2025042600294764300_ref24","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1038\/s41467-023-44288-7","article-title":"From interaction networks to interfaces, scanning intrinsically disordered regions using AlphaFold2","volume":"15","author":"Bret","year":"2024","journal-title":"Nat Commun"},{"key":"2025042600294764300_ref25","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.str.2022.11.012","article-title":"Benchmarking AlphaFold2 on peptide structure prediction","volume":"31","author":"McDonald","year":"2023","journal-title":"Structure"},{"key":"2025042600294764300_ref26","doi-asserted-by":"publisher","DOI":"10.1111\/bph.17314","article-title":"The path to the G protein-coupled receptor structural landscape: major milestones and future directions","author":"Kogut-G\u00fcnthel","journal-title":"Br J Pharmacol"},{"key":"2025042600294764300_ref27","first-page":"2017.603980","article-title":"PINDER: the protein interaction dataset and evaluation resource","volume":"2024.2007","author":"Kovtun","year":"2024","journal-title":"bioRxiv"},{"key":"2025042600294764300_ref28","doi-asserted-by":"publisher","first-page":"bbae076","DOI":"10.1093\/bib\/bbae076","article-title":"Cracking the black box of deep sequence-based protein\u2013protein interaction prediction","volume":"25","author":"Bernett","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025042600294764300_ref29","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s42256-024-00792-z","article-title":"State-specific protein\u2013ligand complex structure prediction with a multiscale deep generative model","volume":"6","author":"Qiao","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2025042600294764300_ref30","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1038\/d41586-019-00145-6","volume":"566","author":"Gloriam","journal-title":"Bigger Is Better in Virtual Drug Screens"},{"key":"2025042600294764300_ref31","doi-asserted-by":"publisher","first-page":"2105","DOI":"10.1093\/bioinformatics\/btz863","article-title":"DeepMSA: constructing deep multiple sequence alignment to improve contact prediction and fold-recognition for distant-homology proteins","volume":"36","author":"Zhang","year":"2020","journal-title":"Bioinformatics"},{"key":"2025042600294764300_ref32","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s41592-023-02130-4","article-title":"Improving deep learning protein monomer and complex structure prediction using DeepMSA2 with huge metagenomics data","volume":"21","author":"Zheng","year":"2024","journal-title":"Nat Methods"},{"key":"2025042600294764300_ref33","first-page":"2010.615955","article-title":"Chai-1: decoding the molecular interactions of life","volume":"2024.2010","author":"Team CD","year":"2024","journal-title":"bioRxiv"},{"key":"2025042600294764300_ref34","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2025042600294764300_ref35","first-page":"2010.2001.615885","article-title":"Computing the human interactome","volume":"2024","author":"Zhang","year":"2024","journal-title":"bioRxiv"},{"key":"2025042600294764300_ref36","doi-asserted-by":"publisher","DOI":"10.1101\/2024.11.19.624167","article-title":"Boltz-1: Democratizing Biomolecular Interaction Modeling","volume":"2024.11","author":"Wohlwend","year":"2024","journal-title":"bioRxiv"},{"key":"2025042600294764300_ref37","doi-asserted-by":"publisher","first-page":"eadl2528","DOI":"10.1126\/science.adl2528","article-title":"Generalized biomolecular modeling and design with RoseTTAFold all-atom","volume":"384","author":"Krishna","year":"2024","journal-title":"Science"},{"key":"2025042600294764300_ref38","doi-asserted-by":"publisher","first-page":"7328","DOI":"10.1038\/s41467-024-51507-2","article-title":"Structure prediction of alternative protein conformations","volume":"15","author":"Bryant","year":"2024","journal-title":"Nat Commun"},{"key":"2025042600294764300_ref39","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1080\/10408363.2023.2286606","article-title":"G protein-coupled receptor (GPCR) gene variants and human genetic disease","volume":"61","author":"Thompson","year":"2024","journal-title":"Crit Rev Clin Lab Sci"},{"key":"2025042600294764300_ref40","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1080\/10408363.2024.2358304","article-title":"G protein-coupled receptor (GPCR) pharmacogenomics","volume":"61","author":"Thompson","year":"2024","journal-title":"Crit Rev Clin Lab Sci"},{"key":"2025042600294764300_ref41","doi-asserted-by":"publisher","first-page":"D1438","DOI":"10.1093\/nar\/gkad944","article-title":"The IUPHAR\/BPS guide to PHARMACOLOGY in 2024","volume":"52","author":"Harding","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2025042600294764300_ref42","doi-asserted-by":"publisher","first-page":"D395","DOI":"10.1093\/nar\/gkac1013","article-title":"GPCRdb in 2023: state-specific structure models using AlphaFold2 and new ligand resources","volume":"51","author":"Pandy-Szekeres","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025042600294764300_ref43","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1093\/bioinformatics\/btu739","article-title":"UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches","volume":"31","author":"Suzek","year":"2015","journal-title":"Bioinformatics"},{"key":"2025042600294764300_ref44","doi-asserted-by":"publisher","first-page":"D753","DOI":"10.1093\/nar\/gkac1080","article-title":"MGnify: the microbiome sequence data analysis resource in 2023","volume":"51","author":"Richardson","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025042600294764300_ref45","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":"2025042600294764300_ref46","doi-asserted-by":"publisher","first-page":"D302","DOI":"10.1093\/nar\/gkj120","article-title":"The RCSB PDB information portal for structural genomics","volume":"34","author":"Kouranov","year":"2006","journal-title":"Nucleic Acids Res"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf186\/63012484\/bbaf186.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf186\/63012484\/bbaf186.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T04:29:54Z","timestamp":1745641794000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf186\/8120239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf186","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,3]]},"article-number":"bbaf186"}}