{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:56:38Z","timestamp":1787165798022,"version":"build-2736575974"},"posted":{"date-parts":[[2023,12,28]]},"group-title":"Bioinformatics","reference-count":18,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2023,12,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>The emergence of large chemical repositories and combinatorial chemical spaces, coupled with high-throughput docking and generative AI, have greatly expanded the chemical diversity of small molecules for drug discovery. Selecting compounds for experimental validation requires filtering these molecules based on favourable druglike properties, such as Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET). We developed ADMET-AI, a machine learning platform that provides fast and accurate ADMET predictions both as a website and as a Python package. ADMET-AI has the highest average rank on the TDC ADMET Benchmark Group leaderboard, and it is currently the fastest web-based ADMET predictor, with a 45% reduction in time compared to the next fastest ADMET web server. ADMET-AI can also be run locally with predictions for one million molecules taking just 3.1 hours.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>\n                    The ADMET-AI platform is freely available both as a web server at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/admet.ai.greenstonebio.com\">admet.ai.greenstonebio.com<\/jats:ext-link>\n                    and as an open-source Python package for local batch prediction at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/github.com\/swansonk14\/admet_ai\">github.com\/swansonk14\/admet_ai<\/jats:ext-link>\n                    (also archived on Zenodo at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/doi.org\/10.5281\/zenodo.10372930\">doi.org\/10.5281\/zenodo.10372930<\/jats:ext-link>\n                    ). All data and models are archived on Zenodo at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/doi.org\/10.5281\/zenodo.10372418\">doi.org\/10.5281\/zenodo.10372418<\/jats:ext-link>\n                    .\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2023.12.28.573531","type":"posted-content","created":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T17:20:11Z","timestamp":1703784011000},"source":"Crossref","is-referenced-by-count":21,"title":["ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7385-7844","authenticated-orcid":false,"given":"Kyle","family":"Swanson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parker","family":"Walther","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy","family":"Leitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8355-3000","authenticated-orcid":false,"given":"Souhrid","family":"Mukherjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6068-8041","authenticated-orcid":false,"given":"Joseph C.","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rabindra V.","family":"Shivnaraine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8880-4764","authenticated-orcid":false,"given":"James","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2023123003251505000_2023.12.28.573531v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/s41589-022-01234-w"},{"key":"2023123003251505000_2023.12.28.573531v1.2","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1177\/10943420211010930","article-title":"Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models","volume":"35","year":"2021","journal-title":"Int. J. High Perform. Comput. Appl"},{"key":"2023123003251505000_2023.12.28.573531v1.3","doi-asserted-by":"crossref","first-page":"4799","DOI":"10.1038\/s41596-021-00597-z","article-title":"A practical guide to large-scale docking","volume":"16","year":"2021","journal-title":"Nat. Protoc"},{"key":"2023123003251505000_2023.12.28.573531v1.4","doi-asserted-by":"crossref","first-page":"8835","DOI":"10.1021\/acs.jmedchem.9b02187","article-title":"Improvement in ADMET Prediction with Multitask Deep Featurization","volume":"63","year":"2020","journal-title":"J. Med. Chem"},{"key":"2023123003251505000_2023.12.28.573531v1.5","unstructured":"Huang, K. et al. Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development. in Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (eds. Vanschoren, J. & Yeung, S. ) vol. 1 (Curran, 2021)."},{"key":"2023123003251505000_2023.12.28.573531v1.6","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00237"},{"key":"2023123003251505000_2023.12.28.573531v1.7","unstructured":"RDKit: Open-source cheminformatics."},{"key":"2023123003251505000_2023.12.28.573531v1.8","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/BF00058611","article-title":"Error reduction through learning multiple descriptions","volume":"24","year":"1996","journal-title":"Mach. Learn"},{"key":"2023123003251505000_2023.12.28.573531v1.9","unstructured":"Flask."},{"key":"2023123003251505000_2023.12.28.573531v1.10","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1037"},{"key":"2023123003251505000_2023.12.28.573531v1.11","unstructured":"WHO Collaborating Centre for Drug Statistics Methodology. https:\/\/www.whocc.no\/atc\/structure_and_principles\/. ATC: Structure and Principles (2022)."},{"key":"2023123003251505000_2023.12.28.573531v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/srep42717"},{"key":"2023123003251505000_2023.12.28.573531v1.13","doi-asserted-by":"crossref","first-page":"W5","DOI":"10.1093\/nar\/gkab255","article-title":"ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties","volume":"49","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023123003251505000_2023.12.28.573531v1.14","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.5b00104"},{"key":"2023123003251505000_2023.12.28.573531v1.15","doi-asserted-by":"crossref","first-page":"889","DOI":"10.3389\/fphar.2017.00889","article-title":"vNN Web Server for ADMET Predictions","volume":"8","year":"2017","journal-title":"Front. Pharmacol"},{"key":"2023123003251505000_2023.12.28.573531v1.16","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1007\/s00894-022-05373-8","article-title":"ADMETboost: a web server for accurate ADMET prediction","volume":"28","year":"2022","journal-title":"J. Mol. Model"},{"key":"2023123003251505000_2023.12.28.573531v1.17","unstructured":"Lee, S. K. , Lee, I. H. , Chang, H. J. , Chung, J. E. & No, K. T. The PreADME Approach: Web-based program for rapid prediction of physico-chemical, drug absorption and drug-like properties. EuroQSAR 2002 Des. Drugs Crop Prot. Process. Probl. Solut. 418\u2013420 (2003)."},{"key":"2023123003251505000_2023.12.28.573531v1.18","unstructured":"Lee, S. K. et al. The PreADME: PC-based program for batch prediction of ADME properties. EuroQSAR 2004 Des. Drugs Crop Prot. Process. Probl. Solut. 9\u201310 (2004)."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2023.12.28.573531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T05:44:13Z","timestamp":1768455853000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2023.12.28.573531"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,28]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1101\/2023.12.28.573531","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1093\/bioinformatics\/btae416","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2023,12,28]]},"subtype":"preprint"}}