{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T12:47:58Z","timestamp":1788871678411,"version":"build-2803163510"},"reference-count":25,"publisher":"American Chemical Society (ACS)","issue":"15","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"publisher","award":["R01DK137299PI"],"award-info":[{"award-number":["R01DK137299PI"]}],"id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005010","name":"Associazione Italiana per la Ricerca sul Cancro","doi-asserted-by":"publisher","award":["IG 2021-ID 25865"],"award-info":[{"award-number":["IG 2021-ID 25865"]}],"id":[{"id":"10.13039\/501100005010","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Targeting protein\u2013protein interactions (PPIs) with small molecules is historically challenging due to shallow, solvent-exposed interfaces that lack classical binding pockets. Furthermore, employing traditional structure-based virtual screening (SBVS) across ultralarge chemical spaces to find novel chemotypes imposes prohibitive computational bottlenecks. Here, we report the first prospective, real-world application of the PyRMD2Dock platform, an AI-enforced SBVS workflow that integrates machine learning and standard docking available within the PyRMD Studio suite. To target the structurally demanding immune receptor CD28, a chemically diverse subset of 2.4 million molecules from the Enamine REAL Diversity Space was docked into a cleft adjacent to the canonical ligand interface. These data were used to train 672 classification models, and the optimized model rapidly screened the remaining \u223c46 million compounds. Following interaction filtering and clustering, 232 highly prioritized ligands were identified. Experimental validation of 150 purchased candidates yielded a strong hit rate, identifying multiple direct CD28 binders. Lead compounds 100 and 104 exhibited submicromolar affinity (Kd = 343.8 nM and 407.1 nM, respectively), potent CD28-CD80 disruption, and functional blockade in cellular reporter assays. Furthermore, these compounds successfully reduced cytokine secretion in primary human tumor-PBMC and epithelial tissue coculture models. This study validates PyRMD2Dock as a highly scalable, effective protocol for mining massive chemical libraries to discover small-molecule modulators of challenging immune receptor interfaces.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c00859","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T09:43:52Z","timestamp":1781171032000},"page":"8805-8819","source":"Crossref","is-referenced-by-count":1,"title":["AI-Enforced Ultra-Large\nVirtual Screening Discovers\nPotent CD28 Binders"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9394-7321","authenticated-orcid":true,"given":"Saurabh","family":"Upadhyay","sequence":"first","affiliation":[{"name":"Weill Cornell Medicine , , , ,","place":["New York, New York, United States, 10065"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3860-2502","authenticated-orcid":true,"given":"Michele","family":"Roggia","sequence":"additional","affiliation":[{"name":"University of Campania Luigi Vanvitelli , , ,","place":["Caserta, Italy, 81100"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoren","family":"Yuan","sequence":"additional","affiliation":[{"name":"Weill Cornell Medicine , , , ,","place":["New York, New York, United States, 10065"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8900-0968","authenticated-orcid":true,"given":"Sandro","family":"Cosconati","sequence":"additional","affiliation":[{"name":"University of Campania Luigi Vanvitelli , , ,","place":["Caserta, Italy, 81100"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9074-3331","authenticated-orcid":true,"given":"Moustafa T.","family":"Gabr","sequence":"additional","affiliation":[{"name":"Weill Cornell Medicine , , , ,","place":["New York, New York, United States, 10065"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"issue":"3","key":"2026081008110737400_cit1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms23031550","article-title":"Challenges in Discovering Drugs That Target the Protein-Protein\nInteractions of Disordered Proteins","volume":"23","author":"Ola\u0301h","year":"2022","journal-title":"Int. J.\nMol. Sci."},{"issue":"9","key":"2026081008110737400_cit2","doi-asserted-by":"publisher","first-page":"1102","DOI":"10.1016\/j.chembiol.2014.09.001","article-title":"Small-Molecule Inhibitors of Protein-Protein\nInteractions: Progressing toward the Reality","volume":"21","author":"Arkin","year":"2014","journal-title":"Chem. Biol."},{"key":"2026081008110737400_cit3","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.copbio.2015.04.006","article-title":"Alternative modulation of protein-protein\ninteractions by small molecules","volume":"35","author":"Fischer","year":"2015","journal-title":"Curr. Opin.\nBiotechnol."},{"key":"2026081008110737400_cit4","doi-asserted-by":"publisher","DOI":"10.1017\/erm.2012.10","article-title":"Features of protein-protein interactions that translate\ninto potent inhibitors: topology, surface area and affinity","volume":"14","author":"Smith","year":"2012","journal-title":"Expert Rev. Mol. Med."},{"key":"2026081008110737400_cit5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmcl.2025.130310","article-title":"CD28 and ICOS in immune regulation:\nStructural insights and therapeutic targeting","volume":"127","author":"Upadhyay","year":"2025","journal-title":"Bioorg. Med. Chem. Lett."},{"issue":"3","key":"2026081008110737400_cit6","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1038\/ni1170","article-title":"Crystal\nstructure of a soluble CD28-Fab complex","volume":"6","author":"Evans","year":"2005","journal-title":"Nat.\nImmunol."},{"issue":"23","key":"2026081008110737400_cit7","doi-asserted-by":"publisher","first-page":"25112","DOI":"10.1021\/acs.jmedchem.5c02136","article-title":"Discovery of CD28-Targeted Small\nMolecule Inhibitors of T Cell Co-Stimulation Using Affinity Selection-Mass\nSpectrometry (AS-MS) and Ex Vivo Validation","volume":"68","author":"Upadhyay","year":"2025","journal-title":"J. Med. Chem."},{"issue":"44","key":"2026081008110737400_cit8","doi-asserted-by":"publisher","first-page":"53612","DOI":"10.1021\/acsomega.5c10222","article-title":"Surface Plasmon\nResonance (SPR)-Based Workflow for High-Throughput Discovery of CD28-Targeted\nSmall Molecules","volume":"10","author":"Calvo-Barreiro","year":"2025","journal-title":"ACS Omega"},{"issue":"6","key":"2026081008110737400_cit9","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/j.str.2022.03.004","article-title":"Structural characterization\nof a dimerization interface in the CD28 transmembrane domain","volume":"30","author":"Wu","year":"2022","journal-title":"Structure"},{"issue":"3\u20134","key":"2026081008110737400_cit10","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.drudis.2008.10.009","article-title":"Predicting druggable\nbinding sites\nat the protein-protein interface","volume":"14","author":"Fuller","year":"2009","journal-title":"Drug Discovery\nToday"},{"issue":"7743","key":"2026081008110737400_cit11","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1038\/s41586-019-0917-9","article-title":"Ultra-large library docking for discovering\nnew chemotypes","volume":"566","author":"Lyu","year":"2019","journal-title":"Nature"},{"issue":"7","key":"2026081008110737400_cit12a","doi-asserted-by":"publisher","first-page":"2143","DOI":"10.1021\/acs.jcim.3c00647","article-title":"Streamlining Large Chemical Library\nDocking with Artificial Intelligence: the PyRMD2Dock Approach","volume":"64","author":"Roggia","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026081008110737400_cit12b","doi-asserted-by":"crossref","unstructured":"(b)\n          \n            \n              Natale, B.; Waqas, M.; Roggia, M.; Di Maro, S.; Cosconati, S.\n          PyRMD Studio: A unified Suite\nfor Next-Generation, AI-Powered Virtual Screening\n          J. Chem. Inf. Model.\n          2026\n          10.1021\/acs.jcim.6c00648.","DOI":"10.1021\/acs.jcim.6c00648"},{"issue":"8","key":"2026081008110737400_cit13","doi-asserted-by":"publisher","first-page":"3835","DOI":"10.1021\/acs.jcim.1c00653","article-title":"PyRMD: A New Fully Automated AI-Powered Ligand-Based\nVirtual Screening Tool","volume":"61","author":"Amendola","year":"2021","journal-title":"J. Chem. Inf. Model."},{"issue":"2","key":"2026081008110737400_cit14","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1021\/acs.jctc.0c01006","article-title":"Accelerating AutoDock4 with GPUs and Gradient-Based Local Search","volume":"17","author":"Santos-Martins","year":"2021","journal-title":"J. Chem. Theory Comput."},{"issue":"6","key":"2026081008110737400_cit15","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1002\/qsar.200290002","article-title":"Identification\nof Diverse Database Subsets using Property-Based and Fragment-Based\nMolecular Descriptions","volume":"21","author":"Ashton","year":"2002","journal-title":"Quant. Struct.-Act.\nRelat."},{"issue":"1","key":"2026081008110737400_cit16","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13354","article-title":"Structural basis of checkpoint blockade by monoclonal\nantibodies in cancer immunotherapy","volume":"7","author":"Lee","year":"2016","journal-title":"Nat. Commun."},{"issue":"6","key":"2026081008110737400_cit17","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1517\/17460441.2010.484460","article-title":"Virtual Screening\nwith AutoDock: Theory and Practice","volume":"5","author":"Cosconati","year":"2010","journal-title":"Expert Opin.\nDrug Discovery"},{"key":"2026081008110737400_cit18","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopha.2025.118937","article-title":"Overcoming\nthe undruggable\nbarrier: Structure-guided discovery of a potent small molecule CD28\nantagonist with translational potential","volume":"194","author":"Upadhyay","year":"2026","journal-title":"Biomed.\nPharmacother."},{"issue":"3","key":"2026081008110737400_cit19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10822-013-9644-8","article-title":"Protein and ligand preparation: parameters, protocols,\nand influence on virtual screening enrichments","volume":"27","author":"Sastry","year":"2013","journal-title":"J. Comput. Aided Mol. Des"},{"issue":"16","key":"2026081008110737400_cit20","doi-asserted-by":"publisher","first-page":"2785","DOI":"10.1002\/jcc.21256","article-title":"AutoDock4\nand AutoDockTools4: Automated\ndocking with selective receptor flexibility","volume":"30","author":"Morris","year":"2009","journal-title":"J. Comput. Chem."},{"key":"2026081008110737400_cit21","unstructured":"LigPrep: New York, NY; 2024."},{"issue":"1","key":"2026081008110737400_cit22","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-018-0321-8","article-title":"A probabilistic molecular fingerprint for big data\nsettings","volume":"10","author":"Probst","year":"2018","journal-title":"J. Cheminf."},{"key":"2026081008110737400_cit23","doi-asserted-by":"publisher","DOI":"10.1016\/j.slasd.2025.100256","article-title":"Temperature-related\nintensity change\n(TRIC)-based high-throughput screening enables the discovery of small\nmolecule CD28 binders","volume":"35","author":"Calvo-Barreiro","year":"2025","journal-title":"SLAS Discovery"},{"key":"2026081008110737400_cit24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmech.2025.118194","article-title":"Structure-based\nvirtual screening identifies potent CD28 inhibitors that suppress\nT cell co-stimulation in cellular and mucosal models","volume":"300","author":"Upadhyay","year":"2025","journal-title":"Eur. J. Med. Chem."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00859","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/8805\/66257678\/acs.jcim.6c00859.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/8805\/66257678\/acs.jcim.6c00859.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:23:48Z","timestamp":1786364628000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/15\/8805\/5232518\/AI-Enforced-Ultra-Large-Virtual-Screening"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":25,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,6,11]]},"published-print":{"date-parts":[[2026,8,10]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00859","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]}}}