{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:39:30Z","timestamp":1787510370135,"version":"build-2736575974"},"reference-count":43,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan","doi-asserted-by":"crossref","award":["222300420278"],"award-info":[{"award-number":["222300420278"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"crossref"}]},{"name":"General Research Projects of Xuchang University","award":["2024YB017"],"award-info":[{"award-number":["2024YB017"]}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"crossref","award":["232102310486"],"award-info":[{"award-number":["232102310486"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Traditional drug discovery methods, such as high-throughput screening (HTS), are often inefficient and costly, especially in complex areas like oncology. The BRAF V600E mutation is a validated therapeutic target in cancers such as melanoma, thyroid carcinoma, and colorectal cancer. However, existing BRAF inhibitors face challenges like acquired resistance and off-target toxicity. Artificial intelligence (AI) has emerged as a transformative tool for designing novel inhibitors more efficiently.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study employed REINVENT 4, an advanced machine learning (ML) framework using recurrent neural networks and transformer architectures, for targeted generation and property optimization of BRAF V600E inhibitors, integrating reinforcement learning (RL) for drug-likeness optimization and transfer learning (TL) for mutation-specific design. Molecular docking and dynamics simulations were used to evaluate binding affinity and stability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The AI-driven approach generated 41,721 novel BRAF V600E inhibitor candidates with enhanced drug-likeness (mean Quantitative Estimate of Drug-likeness (QED) score: 0.61 \u00b1 0.17\n                      <jats:italic>vs<\/jats:italic>\n                      . the training set 0.40 \u00b1 0.13) and predicted inhibitory activity (83.8% with predicted pIC50 &gt; 6). The generated compounds showed a 32% reduction in mean molecular weight (326.8 \u00b1 45.6 g\/mol\n                      <jats:italic>vs<\/jats:italic>\n                      . 480.8 \u00b1 84.2 g\/mol in the training set) while maintaining inhibitory potency. Pharmacokinetic analysis revealed that 99.7% of generated compounds satisfied Lipinski\u2019s Rule of Five criteria, suggesting favorable absorption and distribution profiles. Molecular docking analysis of selected compounds revealed strong binding affinities, with an average free energy of \u22128.03 \u00b1 1.12 kcal\/mol and top-performing compounds reaching \u221211.5 kcal\/mol. Molecular dynamics simulations conducted over 200 ns confirmed complex stability, demonstrating protein backbone RMSD values of 0.35\u20130.55 nm and ligand RMSD values of 0.086\u20130.161 nm. Structural novelty assessment using Tanimoto similarity coefficients showed values below 0.45 when compared with FDA-approved BRAF inhibitors (including Sorafenib and Vemurafenib).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This work highlights a reproducible, integrated AI-driven workflow demonstration for targeted inhibitor generation. The generated inhibitors exhibit favorable drug-like properties and inhibitory activity, offering a scalable solution for designing safer cancer therapies. Experimental validation is needed to address potential discrepancies between computational predictions and biological behavior.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj.20541","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T08:53:42Z","timestamp":1767344022000},"page":"e20541","source":"Crossref","is-referenced-by-count":3,"title":["AI-driven\n                    <i>de novo<\/i>\n                    design of BRAF inhibitors with enhanced binding affinity and optimized drug-likeness"],"prefix":"10.7717","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4340-0376","authenticated-orcid":true,"given":"Zuokun","family":"Lu","sequence":"first","affiliation":[{"name":"Food and Pharmacy College, Xuchang University, Xuchang, Henan, China"},{"name":"Key Laboratory of Biomarker-Based Rapid Detection Technology for Food Safety, Xuchang University, Xuchang, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aili","family":"Zhang","sequence":"additional","affiliation":[{"name":"Food and Pharmacy College, Xuchang University, Xuchang, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"10.7717\/peerj.20541\/ref-1","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.softx.2015.06.001","article-title":"GROMACS: high performance molecular simulations through multi-level parallelism from laptops to supercomputers","volume":"1\u20132","author":"Abraham","year":"2015","journal-title":"SoftwareX"},{"issue":"W1","key":"10.7717\/peerj.20541\/ref-2","doi-asserted-by":"publisher","first-page":"W530","DOI":"10.1093\/nar\/gkab294","article-title":"PLIP 2021: expanding the scope of the protein-ligand interaction profiler to DNA and RNA","volume":"49","author":"Adasme","year":"2021","journal-title":"Nucleic Acids Research"},{"issue":"7","key":"10.7717\/peerj.20541\/ref-3","doi-asserted-by":"publisher","first-page":"5975","DOI":"10.1007\/s10462-022-10306-1","article-title":"Deep learning in drug discovery: an integrative review and future challenges","volume":"56","author":"Askr","year":"2023","journal-title":"Artificial Intelligence Review"},{"issue":"2","key":"10.7717\/peerj.20541\/ref-4","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying the chemical beauty of drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nature Chemistry"},{"issue":"10","key":"10.7717\/peerj.20541\/ref-5","doi-asserted-by":"publisher","first-page":"1807","DOI":"10.1016\/j.drudis.2020.07.024","article-title":"High-throughput screening: today\u2019s biochemical and cell-based approaches","volume":"25","author":"Blay","year":"2020","journal-title":"Drug Discovery Today"},{"issue":"26","key":"10.7717\/peerj.20541\/ref-6","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1056\/NEJMoa1103782","article-title":"Improved survival with vemurafenib in melanoma with BRAF V600E mutation","volume":"364","author":"Chapman","year":"2025","journal-title":"New England Journal of Medicine"},{"issue":"24","key":"10.7717\/peerj.20541\/ref-7","doi-asserted-by":"publisher","first-page":"3183","DOI":"10.1038\/s41388-018-0171-x","article-title":"Classifying BRAF alterations in cancer: new rational therapeutic strategies for actionable mutations","volume":"37","author":"Dankner","year":"2018","journal-title":"Oncogene"},{"issue":"8","key":"10.7717\/peerj.20541\/ref-8","doi-asserted-by":"publisher","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock vina 1.2.0: new docking methods, expanded force field, and python bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"23","key":"10.7717\/peerj.20541\/ref-9","doi-asserted-by":"publisher","first-page":"23889","DOI":"10.1021\/acsomega.5c00549","article-title":"AI-driven drug discovery: a comprehensive review","volume":"10","author":"Ferreira","year":"2025","journal-title":"ACS Omega"},{"key":"10.7717\/peerj.20541\/ref-10","doi-asserted-by":"publisher","first-page":"1700111","DOI":"10.1002\/minf.201700111","article-title":"Generative recurrent networks for de novo drug design","volume":"37","author":"Gupta","year":"2018","journal-title":"Molecular Informatics"},{"issue":"3","key":"10.7717\/peerj.20541\/ref-11","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1007\/s11030-021-10217-3","article-title":"Artificial intelligence to deep learning: machine intelligence approach for drug discovery","volume":"25","author":"Gupta","year":"2021","journal-title":"Molecular Diversity"},{"key":"10.7717\/peerj.20541\/ref-12","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1146\/annurev-pharmtox-040323-040828","article-title":"Artificial intelligence for drug discovery: are we there yet?","volume":"64","author":"Hasselgren","year":"2025","journal-title":"Annual Review of Pharmacology and Toxicology"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-13","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop: a machine learning package for chemical property prediction","volume":"64","author":"Heid","year":"2024","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"7","key":"10.7717\/peerj.20541\/ref-14","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1038\/nrc3760","article-title":"Targeting RAF kinases for cancer therapy: BRAF-mutated melanoma and beyond","volume":"14","author":"Holderfield","year":"2014","journal-title":"Nature Reviews Cancer"},{"issue":"3","key":"10.7717\/peerj.20541\/ref-15","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1021\/acs.jcim.2c01191","article-title":"Chemistry42: an AI-driven platform for molecular design and optimization","volume":"63","author":"Ivanenkov","year":"2023","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"2","key":"10.7717\/peerj.20541\/ref-16","doi-asserted-by":"publisher","first-page":"111612","DOI":"10.1016\/j.commatsci.2022.111612","article-title":"Recent progress in generative adversarial networks applied to inversely designing inorganic materials: a brief review","volume":"213","author":"Jabbar","year":"2022","journal-title":"Computational Materials Science"},{"issue":"2","key":"10.7717\/peerj.20541\/ref-17","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1038\/nbt1284","article-title":"Relating protein pharmacology by ligand chemistry","volume":"25","author":"Keiser","year":"2007","journal-title":"Nature Biotechnology"},{"issue":"9","key":"10.7717\/peerj.20541\/ref-18","doi-asserted-by":"publisher","first-page":"4435","DOI":"10.3390\/ijms22094435","article-title":"Deep learning in virtual screening: recent applications and developments","volume":"22","author":"Kimber","year":"2021","journal-title":"International Journal of Molecular Sciences"},{"issue":"5","key":"10.7717\/peerj.20541\/ref-19","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1038\/s42256-020-0174-5","article-title":"Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks","volume":"2","author":"Kotsias","year":"2020","journal-title":"Nature Machine Intelligence"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-20","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s13321-018-0286-7","article-title":"Molecular generative model based on conditional variational autoencoder for de novo molecular design","volume":"10","author":"Lim","year":"2018","journal-title":"Journal of Cheminformatics"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-21","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/s1056-8719(00)00107-6","article-title":"Drug-like properties and the causes of poor solubility and poor permeability","volume":"44","author":"Lipinski","year":"2000","journal-title":"Journal of Pharmacological and Toxicological Methods"},{"issue":"4","key":"10.7717\/peerj.20541\/ref-22","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1134\/S0026893308040195","article-title":"Radius of gyration as an indicator of protein structure compactness","volume":"42","author":"Lobanov","year":"2008","journal-title":"Molecular Biology"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-23","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-024-00812-5","article-title":"Reinvent 4: modern AI-driven generative molecule design","volume":"16","author":"Loeffler","year":"2024","journal-title":"Journal of Cheminformatics"},{"issue":"5","key":"10.7717\/peerj.20541\/ref-24","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/s13205-022-03165-8","article-title":"Deep learning tools for advancing drug discovery and development","volume":"12","author":"Nag","year":"2022","journal-title":"3 Biotech"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-25","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-017-0235-x","article-title":"Molecular de-novo design through deep reinforcement learning","volume":"9","author":"Olivecrona","year":"2017","journal-title":"Journal of Cheminformatics"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-26","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open babel: an open chemical toolbox","volume":"3","author":"O\u2019Boyle","year":"2011","journal-title":"Journal of Cheminformatics"},{"issue":"3","key":"10.7717\/peerj.20541\/ref-27","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1038\/s42256-020-00285-9","article-title":"A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing","volume":"3","author":"Pham","year":"2021","journal-title":"Nature Machine Intelligence"},{"issue":"7","key":"10.7717\/peerj.20541\/ref-28","doi-asserted-by":"publisher","first-page":"eaap7885","DOI":"10.1126\/sciadv.aap7885","article-title":"Deep reinforcement learning for de novo drug design","volume":"4","author":"Popova","year":"2025","journal-title":"Science Advances"},{"issue":"21","key":"10.7717\/peerj.20541\/ref-29","doi-asserted-by":"publisher","first-page":"4618","DOI":"10.1158\/1078-0432.CCR-21-2138","article-title":"Molecular pathways and mechanisms of BRAF in cancer therapy","volume":"28","author":"Poulikakos","year":"2022","journal-title":"Clinical Cancer Research"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-30","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1097\/cco.0000000000000797","article-title":"BRAF mutations in thyroid cancer","volume":"34","author":"Scheffel","year":"2022","journal-title":"Current Opinion in Oncology"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-31","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","article-title":"Generating focused molecule libraries for drug discovery with recurrent neural networks","volume":"4","author":"Segler","year":"2018","journal-title":"ACS Central Science"},{"issue":"12","key":"10.7717\/peerj.20541\/ref-32","doi-asserted-by":"publisher","first-page":"3629","DOI":"10.1021\/acs.jcim.3c00434","article-title":"DrugEx: deep learning models and tools for exploration of drug-like chemical space","volume":"63","author":"\u0160\u00edcho","year":"2023","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-33","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1186\/1756-0500-5-367","article-title":"ACPYPE-AnteChamber PYthon Parser interfacE","volume":"5","author":"Sousa da Silva","year":"2012","journal-title":"BMC Research Notes"},{"issue":"14","key":"10.7717\/peerj.20541\/ref-34","doi-asserted-by":"publisher","first-page":"1710","DOI":"10.1093\/bioinformatics\/btl150","article-title":"Molecular complexes at a glance: automated generation of two-dimensional complex diagrams","volume":"22","author":"Stierand","year":"2006","journal-title":"Bioinformatics"},{"issue":"4","key":"10.7717\/peerj.20541\/ref-35","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A deep learning approach to antibiotic discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"issue":"6","key":"10.7717\/peerj.20541\/ref-36","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1016\/j.ejca.2012.11.019","article-title":"Resistance to BRAF-targeted therapy in melanoma","volume":"49","author":"Sullivan","year":"2013","journal-title":"European Journal of Cancer"},{"issue":"2","key":"10.7717\/peerj.20541\/ref-37","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"Journal of Computational Chemistry"},{"issue":"10","key":"10.7717\/peerj.20541\/ref-38","doi-asserted-by":"publisher","first-page":"6281","DOI":"10.1021\/acs.jctc.1c00645","article-title":"gmx_MMPBSA: a new tool to perform end-state free energy calculations with GROMACS","volume":"17","author":"Vald\u00e9s-Tresanco","year":"2021","journal-title":"Journal of Chemical Theory and Computation"},{"issue":"2","key":"10.7717\/peerj.20541\/ref-39","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1021\/acs.accounts.0c00699","article-title":"Applications of deep learning in molecule generation and molecular property prediction","volume":"54","author":"Walters","year":"2021","journal-title":"Accounts of Chemical Research"},{"issue":"8","key":"10.7717\/peerj.20541\/ref-40","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1038\/s43588-024-00679-4","article-title":"Deep learning large-scale drug discovery and repurposing","volume":"4","author":"Yu","year":"2024","journal-title":"Nature Computational Science"},{"issue":"8","key":"10.7717\/peerj.20541\/ref-41","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.3390\/cancers11081197","article-title":"Targeting oncogenic BRAF: past, present, and future","volume":"11","author":"Zaman","year":"2019","journal-title":"Cancers"},{"issue":"1","key":"10.7717\/peerj.20541\/ref-42","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/s41591-024-03434-4","article-title":"Artificial intelligence in drug development","volume":"31","author":"Zhang","year":"2025","journal-title":"Nature Medicine"},{"issue":"9","key":"10.7717\/peerj.20541\/ref-43","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nature Biotechnology"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/20541.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20541.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20541.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20541.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T08:53:45Z","timestamp":1767344025000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/20541"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":43,"alternative-id":["10.7717\/peerj.20541"],"URL":"https:\/\/doi.org\/10.7717\/peerj.20541","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,2]]},"article-number":"e20541"}}