{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:50:53Z","timestamp":1792785053396,"version":"4.5.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T00:00:00Z","timestamp":1792368000000},"content-version":"vor","delay-in-days":93,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Manipal University Jaipur","id":[{"id":"https:\/\/ror.org\/040h76494","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-61237-8","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:25:58Z","timestamp":1784334358000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A lightweight, integrated generative AI assistant for accelerated early-stage drug discovery on constrained-resource hardware"],"prefix":"10.1038","volume":"16","author":[{"given":"Tarandeep Kaur","family":"Bhatia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun Singh","family":"Thakur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keshav","family":"Kaushik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renu","family":"Kumawat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"issue":"19-20","key":"61237_CR1","doi-asserted-by":"publisher","first-page":"1088","DOI":"10.1016\/j.drudis.2012.05.007","volume":"17","author":"I Khanna","year":"2012","unstructured":"Khanna, I. Drug discovery in pharmaceutical industry: Productivity challenges and trends. Drug Discov. Today 17(19\u201320), 1088\u20131102 (2012).","journal-title":"Drug Discov. Today"},{"issue":"3","key":"61237_CR2","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/nrd3078","volume":"9","author":"SM Paul","year":"2010","unstructured":"Paul, S. M. et al. How to improve R&D productivity: the pharmaceutical industry\u2019s grand challenge. Nat. Rev. Drug Discovery 9(3), 203\u2013214 (2010).","journal-title":"Nat. Rev. Drug Discovery"},{"issue":"1","key":"61237_CR3","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-024-00916-y","volume":"16","author":"H Flores-Hernandez","year":"2024","unstructured":"Flores-Hernandez, H. & Martinez-Ledesma, E. A systematic review of deep learning chemical language models in recent era. J. Cheminform. 16(1), 129 (2024).","journal-title":"J. Cheminform."},{"issue":"6","key":"61237_CR4","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.70057","volume":"15","author":"A Banerjee","year":"2025","unstructured":"Banerjee, A. et al. From feature\u2010based chemical similarity to chemical language models\u2014A paradigm shift in computer\u2010aided molecular design and property predictions. WIREs Comput. Mol. Sci. 15(6), e70057 (2025).","journal-title":"WIREs Comput. Mol. Sci."},{"issue":"4","key":"61237_CR5","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1021\/acschemneuro.5c00861","volume":"17","author":"Y Chen","year":"2026","unstructured":"Chen, Y. & Xue, W. Machine learning for de novo molecular generation: A comprehensive review. ACS Chem. Neurosci. 17(4), 666\u2013680 (2026).","journal-title":"ACS Chem. Neurosci."},{"issue":"3","key":"61237_CR6","doi-asserted-by":"publisher","first-page":"257","DOI":"10.2174\/0115734099287389240126072433","volume":"21","author":"H Shi","year":"2025","unstructured":"Shi, H. et al. Status and prospects of research on deep learning-based de novo generation of drug molecules. Curr. Comput. Aided Drug Des. 21(3), 257\u2013269 (2025).","journal-title":"Curr. Comput. Aided Drug Des."},{"issue":"7958","key":"61237_CR7","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1038\/s41586-023-05905-z","volume":"616","author":"AV Sadybekov","year":"2023","unstructured":"Sadybekov, A. V. & Katritch, V. Computational approaches streamlining drug discovery. Nature 616(7958), 673\u2013685 (2023).","journal-title":"Nature"},{"issue":"4","key":"61237_CR8","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1080\/17460441.2025.2481259","volume":"20","author":"V Kumar","year":"2025","unstructured":"Kumar, V. & Roy, K. Embracing the changes and challenges with modern early drug discovery. Expert Opin. Drug Discov. 20(4), 419\u2013431 (2025).","journal-title":"Expert Opin. Drug Discov."},{"issue":"6","key":"61237_CR9","doi-asserted-by":"publisher","DOI":"10.3390\/molecules25061375","volume":"25","author":"X Lin","year":"2020","unstructured":"Lin, X., Li, X. & Lin, X. A review on applications of computational methods in drug screening and design. Molecules 25(6), 1375 (2020).","journal-title":"Molecules"},{"issue":"8","key":"61237_CR10","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1002\/ddr.22115","volume":"84","author":"PC Tiwari","year":"2023","unstructured":"Tiwari, P. C., Pal, R., Chaudhary, M. J. & Nath, R. Artificial intelligence revolutionizing drug development: Exploring opportunities and challenges. Drug Dev. Res. 84(8), 1652\u20131663 (2023).","journal-title":"Drug Dev. Res."},{"issue":"9","key":"61237_CR11","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1038\/nrd.2016.109","volume":"15","author":"DA Erlanson","year":"2016","unstructured":"Erlanson, D. A., Fesik, S. W., Hubbard, R. E., Jahnke, W. & Jhoti, H. Twenty years on: The impact of fragments on drug discovery. Nat. Rev. Drug Discov. 15(9), 605\u2013619 (2016).","journal-title":"Nat. Rev. Drug Discov."},{"issue":"3","key":"61237_CR12","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/nrd2220","volume":"6","author":"PJ Hajduk","year":"2007","unstructured":"Hajduk, P. J. & Greer, J. A decade of fragment-based drug design: Strategic advances and lessons learned. Nat. Rev. Drug Discov. 6(3), 211\u2013219 (2007).","journal-title":"Nat. Rev. Drug Discov."},{"issue":"2","key":"61237_CR13","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.70072","volume":"16","author":"A Gangwal","year":"2026","unstructured":"Gangwal, A. & Lavecchia, A. IMPACT framework: Establishing global standards for artificial intelligence implementation, methodology, and translation in drug discovery. WIREs Comput. Mol. Sci. 16(2), e70072 (2026).","journal-title":"WIREs Comput. Mol. Sci."},{"issue":"3","key":"61237_CR14","doi-asserted-by":"publisher","DOI":"10.1177\/00368504251344145","volume":"108","author":"S Bridio","year":"2025","unstructured":"Bridio, S., Deceuninck, P., Whelan, M. & Worth, A. The computational model lifecycle: Opportunities and challenges for computational medicine in the healthcare ecosystem. Sci. Prog. 108(3), 00368504251344145 (2025).","journal-title":"Sci. Prog."},{"key":"61237_CR15","doi-asserted-by":"crossref","unstructured":"Chen, T. & Carlos, G. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785\u2013794 (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"61237_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100588","author":"M Krenn","year":"2022","unstructured":"Krenn, M. et al. SELFIES and the future of molecular string representations. Patterns https:\/\/doi.org\/10.1016\/j.patter.2022.100588 (2022).","journal-title":"Patterns"},{"key":"61237_CR17","doi-asserted-by":"crossref","unstructured":"Polykovskiy, D. et al. Molecular sets (MOSES): A benchmarking platform for molecular generation models. Front. Pharmacol. 11, 565644 (2020).","DOI":"10.3389\/fphar.2020.565644"},{"issue":"12","key":"61237_CR18","doi-asserted-by":"publisher","first-page":"6065","DOI":"10.1021\/acs.jcim.0c00675","volume":"60","author":"JJ Irwin","year":"2020","unstructured":"Irwin, J. J. et al. ZINC20\u2014A free ultralarge-scale chemical database for ligand discovery. J. Chem. Inf. Model. 60(12), 6065\u20136073 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"61237_CR19","doi-asserted-by":"crossref","unstructured":"Krenn, M., Florian, H., Nigam, A., Friederich, P., & Aspuru-Guzik, A. SELFIES: a robust representation of semantically constrained graphs with an example application in chemistry. arXiv preprint arXiv:1905.13741 1(3) (2019).","DOI":"10.1088\/2632-2153\/aba947"},{"issue":"8","key":"61237_CR20","doi-asserted-by":"publisher","first-page":"11218","DOI":"10.1109\/TNNLS.2023.3250324","volume":"35","author":"Q Lv","year":"2023","unstructured":"Lv, Q., Chen, G., Yang, Z., Zhong, W. & Chen, C.-C. Meta learning with graph attention networks for low-data drug discovery. IEEE Trans. Neural Netw. Learn. Syst. 35(8), 11218\u201311230 (2023).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"61237_CR21","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1039\/C9ME00039A","volume":"4","author":"DC Elton","year":"2019","unstructured":"Elton, D. C., Boukouvalas, Z., Fuge, M. D. & Chung, P. W. Deep learning for molecular design\u2014a review of the state of the art. Mol. Syst. Des. Eng. 4(4), 828\u2013849 (2019).","journal-title":"Mol. Syst. Des. Eng."},{"issue":"3","key":"61237_CR22","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s42256-020-0160-y","volume":"2","author":"M Moret","year":"2020","unstructured":"Moret, M., Friedrich, L., Grisoni, F., Merk, D. & Schneider, G. Generative molecular design in low data regimes. Nat. Mach. Intell. 2(3), 171\u2013180 (2020).","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"61237_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms10425","volume":"7","author":"R Huang","year":"2016","unstructured":"Huang, R. et al. Modelling the Tox21 10 K chemical profiles for in vivo toxicity prediction and mechanism characterization. Nat. Commun. 7(1), 10425 (2016).","journal-title":"Nat. Commun."},{"issue":"3","key":"61237_CR24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","volume":"10","author":"T Saito","year":"2015","unstructured":"Saito, T. & Rehmsmeier, M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE 10(3), e0118432 (2015).","journal-title":"PLoS ONE"},{"issue":"3","key":"61237_CR25","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1021\/ci034243x","volume":"44","author":"JS Delaney","year":"2004","unstructured":"Delaney, J. S. ESOL: Estimating aqueous solubility directly from molecular structure. J. Chem. Inf. Comput. Sci. 44(3), 1000\u20131005 (2004).","journal-title":"J. Chem. Inf. Comput. Sci."},{"issue":"10","key":"61237_CR26","doi-asserted-by":"publisher","first-page":"4310","DOI":"10.1021\/acs.jcim.3c02061","volume":"64","author":"G Cordoves-Delgado","year":"2024","unstructured":"Cordoves-Delgado, G. & Garc\u00eda-Jacas, C\u00e9sar. R. Predicting antimicrobial peptides using ESMFold-predicted structures and ESM-2-based amino acid features with graph deep learning. J. Chem. Inf. Model. 64(10), 4310\u20134321 (2024).","journal-title":"J. Chem. Inf. Model."},{"issue":"12","key":"61237_CR27","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a041473","volume":"15","author":"L Lannelongue","year":"2023","unstructured":"Lannelongue, L. & Inouye, M. Environmental impacts of machine learning applications in protein science. Cold Spring Harb. Perspect. Biol. 15(12), a041473 (2023).","journal-title":"Cold Spring Harb. Perspect. Biol."},{"key":"61237_CR28","doi-asserted-by":"publisher","DOI":"10.3389\/fenvs.2015.00085","volume":"3","author":"R Huang","year":"2016","unstructured":"Huang, R. et al. Tox21Challenge to build predictive models of nuclear receptor and stress response pathways as mediated by exposure to environmental chemicals and drugs. Front. Environ. Sci. 3, 85 (2016).","journal-title":"Front. Environ. Sci."},{"issue":"4","key":"61237_CR29","doi-asserted-by":"publisher","DOI":"10.3390\/buildings15040630","volume":"15","author":"S Mazzetto","year":"2025","unstructured":"Mazzetto, S. Hybrid predictive maintenance for building systems: Integrating rule-based and machine learning models for fault detection using a high-resolution Danish dataset. Buildings 15(4), 630 (2025).","journal-title":"Buildings"},{"issue":"10","key":"61237_CR30","doi-asserted-by":"publisher","first-page":"5465","DOI":"10.3390\/app15105465","volume":"15","author":"J Garcia","year":"2025","unstructured":"Garcia, J., Rios-Colque, L., Pe\u00f1a, A. & Rojas, L. Condition monitoring and predictive maintenance in industrial equipment: An NLP-assisted review of signal processing, hybrid models, and implementation challenges. Appl. Sci. 15(10), 5465 (2025).","journal-title":"Appl. Sci."},{"issue":"4","key":"61237_CR31","doi-asserted-by":"publisher","DOI":"10.1002\/slct.202403269","volume":"10","author":"S Verma","year":"2025","unstructured":"Verma, S., Dubey, A., Singh, R., Tayade, R. & Mishra, V. K. In\u2010silico screening, molecular dynamics, and DFT analysis of ZINC and ChEMBL library compounds for SARS\u2010CoV\u20102 main protease inhibition. ChemistrySelect 10(4), e202403269 (2025).","journal-title":"ChemistrySelect"},{"issue":"11","key":"61237_CR32","doi-asserted-by":"publisher","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","volume":"55","author":"T Sterling","year":"2015","unstructured":"Sterling, T. & Irwin, J. J. ZINC 15\u2013ligand discovery for everyone. J. Chem. Inf. Model. 55(11), 2324\u20132337 (2015).","journal-title":"J. Chem. Inf. Model."},{"issue":"3","key":"61237_CR33","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","volume":"59","author":"N Brown","year":"2019","unstructured":"Brown, N., Fiscato, M., Segler, M. H. S. & Vaucher, A. C. GuacaMol: Benchmarking models for de novo molecular design. J. Chem. Inf. Model. 59(3), 1096\u20131108 (2019).","journal-title":"J. Chem. Inf. Model."},{"issue":"7","key":"61237_CR34","doi-asserted-by":"publisher","first-page":"2174","DOI":"10.1021\/acs.jcim.3c01496","volume":"64","author":"C Pang","year":"2023","unstructured":"Pang, C., Qiao, J., Zeng, X., Zou, Q. & Wei, L. Deep generative models in de novo drug molecule generation. J. Chem. Inf. Model. 64(7), 2174\u20132194 (2023).","journal-title":"J. Chem. Inf. Model."},{"issue":"1","key":"61237_CR35","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-024-01444-x","volume":"10","author":"H Du","year":"2024","unstructured":"Du, H., Wang, J., Hui, J., Zhang, L. & Wang, H. DenseGNN: Universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules. NPJ Comput. Mater. 10(1), 292 (2024).","journal-title":"NPJ Comput. Mater."},{"issue":"1","key":"61237_CR36","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1080\/1062936X.2023.2301327","volume":"35","author":"T Ehiro","year":"2024","unstructured":"Ehiro, T. Descriptor generation from Morgan fingerprint using persistent homology. SAR QSAR Environ. Res. 35(1), 31\u201351 (2024).","journal-title":"SAR QSAR Environ. Res."},{"key":"61237_CR37","unstructured":"Dickson, M. & Gagnon, J.P. The cost of new drug discovery and development. Discov. Med. 4(22), 172\u2013179 (2009)."},{"issue":"2","key":"61237_CR38","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1038\/nrd.2017.232","volume":"17","author":"G Schneider","year":"2018","unstructured":"Schneider, G. Automating drug discovery. Nat. Rev. Drug Discov. 17(2), 97\u2013113 (2018).","journal-title":"Nat. Rev. Drug Discov."},{"key":"61237_CR39","unstructured":"Lin, T.-Y., Priya, G., Ross, G., Kaiming, H. & Doll\u00e1r, P. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, 2980\u20132988 (2017)."},{"key":"61237_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.medidd.2020.100075","volume":"9","author":"FD Makurvet","year":"2021","unstructured":"Makurvet, F. D. Biologics vs. small molecules: Drug costs and patient access. Med. Drug Discov. 9, 100075 (2021).","journal-title":"Med. Drug Discov."},{"issue":"3","key":"61237_CR41","doi-asserted-by":"publisher","first-page":"4849","DOI":"10.1109\/TNNLS.2024.3359657","volume":"36","author":"Q Lv","year":"2024","unstructured":"Lv, Q., Chen, G., Yang, Z., Zhong, W. & Chen, C.-C. Meta-molnet: A cross-domain benchmark for few examples drug discovery. IEEE Trans. Neural Netw. Learn. Syst. 36(3), 4849\u20134863 (2024).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"61237_CR42","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.neunet.2023.05.039","volume":"165","author":"Q Lv","year":"2023","unstructured":"Lv, Q., Zhou, J., Yang, Z., He, H. & Chen, C.-C. 3D graph neural network with few-shot learning for predicting drug\u2013drug interactions in scaffold-based cold start scenario. Neural Netw. 165, 94\u2013105 (2023).","journal-title":"Neural Netw."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61237-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61237-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61237-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T17:02:11Z","timestamp":1792429331000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61237-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,18]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["61237"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-61237-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,18]]},"assertion":[{"value":"10 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable. This study involves in silico computational modelling using publicly available chemical datasets (Delaney\/ESOL and Tox21) and does not involve any experiments on human participants or vertebrate animals.","order":1,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"32814"}}