{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:43:51Z","timestamp":1782909831345,"version":"3.54.5"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    The vast majority of chemically plausible, drug-like molecules remain unexplored due to the combinatorial scale of chemical space and the limited throughput of experimental screening. This is complicated by the lack of data and the inability to extrapolate predictive models to chemotypes that are not represented well. We introduce a transformer-based molecular modeling framework for target-specific potency prediction, trained on curated BindingDB bioactivity data across Alzheimer\u2018s, diabetes, and cancer targets to deliver accurate pIC50 regression and binary activity classification. It uses curated bioactivity data from BindingDB to build target-specific datasets and uses a Byte Latent Transformer (BLT) that is trained directly on SMILES strings to predict changes in compound activity and potency based on quantitative structure\u2013activity relationships. The transformer captures both syntactic and higher-level chemical features of SMILES representations and performs byte-level predictions using a latent model trained on the same molecular information. Potency predictions are executed inside an engine of chemically described molecular search engine, which executes stochasticity, SMILES-based amount mutations benefit by the envisaged activity, drug-like rules, and adaptive seeking heuristics to prevent local minima. Optimized candidate molecules and local optima are generated through guided SMILES mutations, preserving structural diversity around high-potency leads. The framework delivers highly accurate pIC50 regression (\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    0.95\u20130.98) and binary activity classification across Alzheimer's, diabetes, and cancer targets, enabling robust virtual screening and lead prioritization for diverse biological targets.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1807340","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T11:46:07Z","timestamp":1782906367000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-driven drug discovery using transformer-based molecular representation learning"],"prefix":"10.3389","volume":"9","author":[{"given":"V.","family":"Karthik","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mukunda","family":"Hosangadi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumedh","family":"Kudale","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"OmKumar Chandra","family":"Umakanthan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1080\/1061186X.2024.2347358","article-title":"An extensive review on lung cancer therapeutics using machine learning techniques","volume":"32","author":"Ahmad","year":"2024","journal-title":"J. Drug Target."},{"key":"B2","doi-asserted-by":"publisher","first-page":"e01550","DOI":"10.1002\/adts.202501550","article-title":"DrLungker: a deep ensemble learning framework for predicting anti-lung cancer bioactivity","volume":"9","author":"Ahmad","year":"2026","journal-title":"Adv. Theory Simul."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1807","DOI":"10.1080\/1061186X.2025.2530656","article-title":"Machine learning for genomic profiling and drug discovery in personalised lung cancer therapeutics","volume":"33","author":"Ahmad","year":"2025","journal-title":"J. Drug Target."},{"key":"B4","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/s11030-013-9441-2","article-title":"Toward a general predictive QSAR model for gamma-secretase inhibitors","volume":"17","author":"Ajmani","year":"2013","journal-title":"Mol. Divers."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.20011","article-title":"AI model for predicting binding affinity of antidiabetic compounds targeting PPAR","author":"Aman","year":"2024","journal-title":"arXiv [Preprint]"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1550158","DOI":"10.3389\/fphar.2025.1550158","article-title":"New strategies to enhance the efficiency and precision of drug discovery","volume":"16","author":"An","year":"2025","journal-title":"Front. Pharmacol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/1062936X.2025.2478123","article-title":"Predictive modelling of peroxisome proliferator-activated receptor gamma (PPAR\u03b3) IC50 inhibition by emerging pollutants using light gradient boosting machine","volume":"36","author":"Awomutia","year":"2025","journal-title":"SAR QSAR Environ. Res."},{"key":"B8","doi-asserted-by":"publisher","first-page":"3588","DOI":"10.3390\/molecules28083588","article-title":"Development of activity rules and chemical fragment design for in silico discovery of AChE and BACE1 dual inhibitors against Alzheimer's disease","volume":"28","author":"Bao","year":"2023","journal-title":"Molecules"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-4550896\/v1","article-title":"Contribution to predicte of pIC50 using algorithms of deep learning","author":"Belaidi","year":"2024","journal-title":"Res. Sq."},{"key":"B10","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The properties of known drugs. 1. Molecular frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J. Med. Chem."},{"key":"B11","doi-asserted-by":"publisher","first-page":"D1467","DOI":"10.1093\/nar\/gkae1128","article-title":"Open Targets Platform: facilitating therapeutic hypotheses building in drug discovery","volume":"53","author":"Buniello","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"B12","first-page":"354","article-title":"\u201cInstructmol: multi-modal integration for building a versatile and reliable molecular assistant in drug discovery,\u201d","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Cao","year":"2025"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpha.2025.101248","article-title":"The future of pharmaceuticals: artificial intelligence in drug discovery and development","author":"Fu","year":"2025","journal-title":"J. Pharm. Anal."},{"key":"B14","doi-asserted-by":"publisher","first-page":"3948","DOI":"10.1021\/acs.jmedchem.4c01257","article-title":"Artificial intelligence in natural product drug discovery: current applications and future perspectives","volume":"68","author":"Gangwal","year":"2025","journal-title":"J. Med. Chem."},{"key":"B15","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1186\/s12859-022-04913-6","article-title":"Topology-enhanced molecular graph representation for anti-breast cancer drug selection","volume":"23","author":"Gao","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"D1045","DOI":"10.1093\/nar\/gkv1072","article-title":"BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology","volume":"44","author":"Gilson","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"B17","doi-asserted-by":"publisher","first-page":"D1287","DOI":"10.1093\/nar\/gkae1050","article-title":"canSAR 2024-an update to the public drug discovery knowledgebase","volume":"53","author":"Gingrich","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.04738","article-title":"SMILES transformer: pre-trained molecular fingerprint for low data drug discovery","author":"Honda","year":"2019","journal-title":"arXiv [Preprint]"},{"key":"B19","doi-asserted-by":"publisher","first-page":"101081","DOI":"10.1016\/j.jpha.2024.101081","article-title":"A review of transformer models in drug discovery and beyond","volume":"15","author":"Jiang","year":"2025","journal-title":"J. Pharm. Anal."},{"key":"B20","doi-asserted-by":"publisher","author":"Lee","year":"2025","DOI":"10.48550\/arXiv.2501.06158"},{"key":"B21","unstructured":"Prediction of pIC50 bioactive values based on knowledge priors and attention neural networks\n          \n          \n            \n              Li\n              M.\n            \n            \n              Tang\n              W.\n            \n            \n              Wang\n              X.\n            \n            \n              Zhan\n              Y.\n            \n            \n              Chen\n              B.\n            \n          \n          SSRN\n          \n          2023"},{"key":"B22","first-page":"4252","article-title":"\u201cRevolutionizing drug discovery: integrating spatial transcriptomics with advanced computer vision techniques,\u201d","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Li","year":"2025"},{"key":"B23","doi-asserted-by":"publisher","first-page":"100013","DOI":"10.1124\/pharmrev.124.001297","article-title":"Promising tools for future drug discovery and development in antiarrhythmic therapy","volume":"77","author":"Mond\u00e9jar-Parre\u00f1o","year":"2025","journal-title":"Pharmacol. Rev."},{"key":"B24","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s40364-025-00758-2","article-title":"Integrating artificial intelligence in drug discovery and early drug development: a transformative approach","volume":"13","author":"Ocana","year":"2025","journal-title":"Biomark. Res."},{"key":"B25","doi-asserted-by":"crossref","first-page":"9238","DOI":"10.18653\/v1\/2025.acl-long.453","article-title":"\u201cByte latent transformer: patches scale better than tokens,\u201d","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Pagnoni","year":"2025"},{"key":"B26","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1021\/acs.jmedchem.4c03044","article-title":"Real-world applications and experiences of AI\/ML deployment for drug discovery","volume":"68","author":"Pitt","year":"2025","journal-title":"J. Med. Chem."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1016\/j.fmre.2024.04.021","article-title":"Role of artificial intelligence in revolutionizing drug discovery","volume":"5","author":"Rehman","year":"2025","journal-title":"Fundam. Res."},{"key":"B28","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1039\/D4PM00323C","article-title":"AI driven innovations in pharmaceuticals: optimizing drug discovery and industry operations","volume":"2","author":"Saini","year":"2025","journal-title":"RSC Pharm."},{"key":"B29","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1021\/acs.chemrestox.2c00283","article-title":"Validation of acetylcholinesterase inhibition machine learning models for multiple species","volume":"36","author":"Vignaux","year":"2023","journal-title":"Chem. Res. Toxicol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s11030-008-9080-1","article-title":"Prediction of binding affinity for estrogen receptor \u03b1 modulators using statistical learning approaches","volume":"12","author":"Wang","year":"2008","journal-title":"Mol. Divers."},{"key":"B31","doi-asserted-by":"publisher","first-page":"6857","DOI":"10.1021\/acs.est.0c07040","article-title":"Developing QSAR models with defined applicability domains on PPAR\u03b3 binding affinity using large data sets and machine learning algorithms","volume":"55","author":"Wang","year":"2021","journal-title":"Environ. Sci. Technol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-025-00963-z","article-title":"Fifteen years of ChEMBL and its role in cheminformatics and drug discovery","volume":"17","author":"Zdrazil","year":"2025","journal-title":"J. Cheminform."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1547131","DOI":"10.3389\/fphar.2025.1547131","article-title":"The role and application of bioinformatics techniques and tools in drug discovery","volume":"16","author":"Zhang","year":"2025","journal-title":"Front. Pharmacol."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1807340\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T11:46:15Z","timestamp":1782906375000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1807340\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":33,"alternative-id":["10.3389\/frai.2026.1807340"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1807340","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"article-number":"1807340"}}