{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:38:17Z","timestamp":1776800297715,"version":"3.51.2"},"posted":{"date-parts":[[2026,4,18]]},"group-title":"Bioinformatics","reference-count":34,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T00:00:00Z","timestamp":1776470400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"crossref","award":["R01GM149646"],"award-info":[{"award-number":["R01GM149646"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"crossref","award":["R35GM150620"],"award-info":[{"award-number":["R35GM150620"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,4,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>We previously showed that AlphaFold2 can be used to screen for peptide-binding epitopes targeting the extraterminal (ET) domain of Bromodomain and Extraterminal (BET) proteins from candidate protein partners identified in pull-down experiments. However, such approaches require large numbers of AlphaFold2 calculations, making exhaustive screening impractical for larger datasets, such as viral proteomes that may target the ET domain. In many cases, identifying a substantial fraction of binders\u2014even without exhaustive coverage\u2014would already provide valuable biological insight into these interaction networks. Here, we show that an active learning strategy based on Thompson sampling (TS) can efficiently explore peptide sequence space. Using a library derived from BRD3 pull-down experiments, TS recovers 50% of all binders using 15% of the queries required by exhaustive sampling (3.3 times improvement over random sampling). Moreover, TS consistently identifies experimentally known binding epitopes with substantially fewer queries. Because the approach relies only on binary labels, it is readily transferable to other protein\u2013peptide systems where AF-based binding classification is applicable, as well as to peptide-property predictors for properties such as solubility or aggregation propensity.<\/jats:p>","DOI":"10.64898\/2026.04.16.718999","type":"posted-content","created":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T04:50:15Z","timestamp":1776574215000},"source":"Crossref","is-referenced-by-count":0,"title":["Efficient exploration of peptide libraries using active learning with AlphaFold-based screening"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7836-4539","authenticated-orcid":false,"given":"Jokent","family":"Gaza","sequence":"first","affiliation":[{"name":"Department of Chemistry, University of Florida, Gainesville, Florida 32611, United States"},{"name":"Quantum Theory Project, University of Florida, Gainesville, Florida 32611, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5500-8698","authenticated-orcid":false,"given":"Jherome Brylle Woody","family":"Santos","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Florida, Gainesville, Florida 32611, United States"},{"name":"Quantum Theory Project, University of Florida, Gainesville, Florida 32611, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3044-3588","authenticated-orcid":false,"given":"Bhumika","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Florida, Gainesville, Florida 32611, United States"},{"name":"Quantum Theory Project, University of Florida, Gainesville, Florida 32611, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2121-4449","authenticated-orcid":false,"given":"Ram\u00f3n Alain","family":"Miranda-Quintana","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Florida, Gainesville, Florida 32611, United States"},{"name":"Quantum Theory Project, University of Florida, Gainesville, Florida 32611, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5054-5338","authenticated-orcid":false,"given":"Alberto","family":"Perez","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Florida, Gainesville, Florida 32611, United States"},{"name":"Quantum Theory Project, University of Florida, Gainesville, Florida 32611, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026042111500812000_2026.04.16.718999v1.1","doi-asserted-by":"publisher","DOI":"10.1021\/cr400698c"},{"key":"2026042111500812000_2026.04.16.718999v1.2","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1002\/prot.21396","article-title":"Hot spots\u2014A review of the protein\u2013protein interface determinant amino-acid residues","volume":"68","year":"2007","journal-title":"Proteins:Struct., Funct., Bioinf"},{"key":"2026042111500812000_2026.04.16.718999v1.3","doi-asserted-by":"crossref","first-page":"3140","DOI":"10.1002\/prot.22785","article-title":"Can self-inhibitory peptides be derived from the interfaces of globular protein\u2013protein interactions?","volume":"78","year":"2010","journal-title":"Proteins:Struct., Funct., Bioinf"},{"key":"2026042111500812000_2026.04.16.718999v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.copbio.2006.08.002"},{"key":"2026042111500812000_2026.04.16.718999v1.5","doi-asserted-by":"crossref","first-page":"3302","DOI":"10.1039\/C4CC08565E","article-title":"Modulating protein\u2013protein interactions: the potential of peptides","volume":"51","year":"2015","journal-title":"Chem. Commun"},{"key":"2026042111500812000_2026.04.16.718999v1.6","doi-asserted-by":"publisher","DOI":"10.1002\/anie.201412070"},{"key":"2026042111500812000_2026.04.16.718999v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmech.2015.01.014"},{"key":"2026042111500812000_2026.04.16.718999v1.8","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201400040"},{"key":"2026042111500812000_2026.04.16.718999v1.9","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.9b01208"},{"key":"2026042111500812000_2026.04.16.718999v1.10","doi-asserted-by":"publisher","DOI":"10.3390\/ijms10062763"},{"key":"2026042111500812000_2026.04.16.718999v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/nprot.2011.452"},{"key":"2026042111500812000_2026.04.16.718999v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth0206-135"},{"key":"2026042111500812000_2026.04.16.718999v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-021-03819-2"},{"key":"2026042111500812000_2026.04.16.718999v1.14","doi-asserted-by":"crossref","unstructured":"Tsaban, T. ; Varga, J. K. ; Avraham, O. ; Ben-Aharon, Z. ; Khramushin, A. ; SchuelerFurman, O . Harnessing protein folding neural networks for peptide\u2013protein docking. Nat. Commun. 2022, 13, 176.","DOI":"10.1038\/s41467-021-27838-9"},{"key":"2026042111500812000_2026.04.16.718999v1.15","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202213362"},{"key":"2026042111500812000_2026.04.16.718999v1.16","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202405767"},{"key":"2026042111500812000_2026.04.16.718999v1.17","doi-asserted-by":"crossref","unstructured":"Gittins, J. ; Glazebrook, K. ; Weber, R. Multi-armed bandit allocation indices; John Wiley & Sons, 2011.","DOI":"10.1002\/9780470980033"},{"key":"2026042111500812000_2026.04.16.718999v1.18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"2026042111500812000_2026.04.16.718999v1.19","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"2026042111500812000_2026.04.16.718999v1.20","unstructured":"Chapelle, O. ; Li, L. An empirical evaluation of thompson sampling. NeurIPS 2011, 24."},{"key":"2026042111500812000_2026.04.16.718999v1.21","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c01790"},{"key":"2026042111500812000_2026.04.16.718999v1.22","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1186\/s13321-025-01105-1","article-title":"Enhanced Thompson Sampling by Roulette Wheel Selection for Screening Ultra-Large Combinatorial Libraries","volume":"17","year":"2025","journal-title":"J. Cheminf"},{"key":"2026042111500812000_2026.04.16.718999v1.23","doi-asserted-by":"publisher","DOI":"10.1128\/MCB.01341-10"},{"key":"2026042111500812000_2026.04.16.718999v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2021.01.010"},{"key":"2026042111500812000_2026.04.16.718999v1.25","first-page":"1","article-title":"Introduction to Multi-Armed Bandits","volume":"12","year":"2019","journal-title":"Found. Trends Mach. Learn"},{"key":"2026042111500812000_2026.04.16.718999v1.26","doi-asserted-by":"publisher","DOI":"10.1074\/jbc.RA117.000678"},{"key":"2026042111500812000_2026.04.16.718999v1.27","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkh131"},{"key":"2026042111500812000_2026.04.16.718999v1.28","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1010"},{"key":"2026042111500812000_2026.04.16.718999v1.29","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01595"},{"key":"2026042111500812000_2026.04.16.718999v1.30","doi-asserted-by":"publisher","DOI":"10.1038\/S41592-022-01488-1"},{"key":"2026042111500812000_2026.04.16.718999v1.31","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl158"},{"key":"2026042111500812000_2026.04.16.718999v1.32","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04964-5"},{"key":"2026042111500812000_2026.04.16.718999v1.33","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"2026042111500812000_2026.04.16.718999v1.34","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab801"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.04.16.718999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T18:50:17Z","timestamp":1776797417000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.04.16.718999"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,18]]},"references-count":34,"URL":"https:\/\/doi.org\/10.64898\/2026.04.16.718999","relation":{},"subject":[],"published":{"date-parts":[[2026,4,18]]},"subtype":"preprint"}}