{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:02:27Z","timestamp":1787022147002,"version":"build-2736575974"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>The battle against viral drug resistance highlights the need for innovative approaches to replace time-consuming and costly traditional methods. Deep generative models offer automation potential, especially in the fight against Human immunodeficiency virus (HIV), as they can synthesize diverse molecules effectively. In this paper, an application of an LSTM-based deep generative model named \u201cLSTM-ProGen\u201d is proposed to be tailored explicitly for the de novo design of drug candidate molecules that interact with a specific target protein (HIV-1 protease). LSTM-ProGen distinguishes itself by employing a long-short-term memory (LSTM) architecture, to generate novel molecules target specificity against the HIV-1 protease. Following a thorough training process involves fine-tuning LSTM-ProGen on a diverse range of compounds sourced from the ChEMBL database. The model was optimized to meet specific requirements, with multiple iterations to enhance its predictive capabilities and ensure it generates molecules that exhibit favorable target interactions. The training process encompasses an array of performance evaluation metrics, such as drug-likeness properties. Our evaluation includes extensive silico analysis using molecular docking and PCA-based visualization to explore the chemical space that the new molecules cover compared to those in the training set. These evaluations reveal that a subset of 12 de novo molecules generated by LSTM-ProGen exhibit a striking ability to interact with the target protein, rivaling or even surpassing the efficacy of native ligands. Extended versions with further refinement of LSTM-ProGen hold promise as versatile tools for designing efficacious and customized drug candidates tailored to specific targets, thus accelerating drug development and facilitating the discovery of new therapies for various diseases.<\/jats:p>","DOI":"10.1371\/journal.pone.0303597","type":"journal-article","created":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T13:22:50Z","timestamp":1718976170000},"page":"e0303597","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["LSTM-driven drug design using SELFIES for target-focused de novo generation of HIV-1 protease inhibitor candidates for AIDS treatment"],"prefix":"10.1371","volume":"19","author":[{"given":"M. Taleb","family":"Albrijawi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6657-9738","authenticated-orcid":true,"given":"Reda","family":"Alhajj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,6,21]]},"reference":[{"issue":"5112","key":"pone.0303597.ref001","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1126\/science.8493571","article-title":"How does HIV cause AIDS?","volume":"260","author":"RA Weiss","year":"1993","journal-title":"Science (New York, NY)"},{"issue":"6831","key":"pone.0303597.ref002","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1038\/35073639","article-title":"The global impact of HIV\/AIDS","volume":"410","author":"P Piot","year":"2001","journal-title":"Nature"},{"key":"pone.0303597.ref003","volume-title":"UNAIDS Global AIDS Update 2022","author":"Joint United Nations Programme on HIV\/AIDS (UNAIDS)","year":"2022"},{"issue":"11","key":"pone.0303597.ref004","first-page":"a006965","article-title":"HIV transmission","volume":"2","author":"GM Shaw","year":"2012","journal-title":"Cold Spring Harbor perspectives in medicine"},{"issue":"1","key":"pone.0303597.ref005","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/2045-3701-2-32","article-title":"Effects of HIV-1 protease on cellular functions and their potential applications in antiretroviral therapy","volume":"2","author":"H Yang","year":"2012","journal-title":"Cell & bioscience"},{"issue":"3","key":"pone.0303597.ref006","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1159\/000445852","article-title":"Human immunodeficiency virus (HIV)","volume":"43","author":"Blut) German Advisory Committee Blood (Arbeitskreis","year":"2016","journal-title":"Transfusion medicine and hemotherapy"},{"issue":"1","key":"pone.0303597.ref007","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1039\/b208248a","article-title":"HIV-1 protease: mechanism and drug discovery","volume":"1","author":"A Brik","year":"2003","journal-title":"Organic & biomolecular chemistry"},{"issue":"2","key":"pone.0303597.ref008","first-page":"162","article-title":"HIV protease inhibitors: their anti-HIV activity and potential role in treatment","volume":"6","author":"T Robins","year":"1993","journal-title":"Journal of acquired immune deficiency syndromes"},{"issue":"2","key":"pone.0303597.ref009","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s11904-007-0010-0","article-title":"Adherence-resistance relationships to combination HIV antiretroviral therapy","volume":"4","author":"DR Bangsberg","year":"2007","journal-title":"Current HIV\/AIDS reports"},{"issue":"8","key":"pone.0303597.ref010","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1016\/j.tips.2019.06.004","article-title":"Advancing drug discovery via artificial intelligence","volume":"40","author":"HCS Chan","year":"2019","journal-title":"Trends in pharmacological sciences"},{"issue":"12","key":"pone.0303597.ref011","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1038\/nrd4507","article-title":"New drugs cost USD 2.6 billion to develop","volume":"13","author":"A Mullard","year":"2014","journal-title":"Nature reviews Drug discovery"},{"issue":"8","key":"pone.0303597.ref012","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1007\/s10822-013-9672-4","article-title":"Estimation of the size of drug-like chemical space based on GDB-17 data","volume":"27","author":"PG Polishchuk","year":"2013","journal-title":"Journal of computer-aided molecular design"},{"issue":"10","key":"pone.0303597.ref013","first-page":"100588","article-title":"SELFIES and the future of molecular string representations","volume":"3","author":"M Krenn","year":"2022","journal-title":"Patterns (New York, NY)"},{"issue":"W1","key":"pone.0303597.ref014","doi-asserted-by":"crossref","first-page":"W612","DOI":"10.1093\/nar\/gkv352","article-title":"ChEMBL web services: streamlining access to drug discovery data and utilities","volume":"43","author":"M Davies","year":"2015","journal-title":"Nucleic acids research"},{"issue":"D1","key":"pone.0303597.ref015","doi-asserted-by":"crossref","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"DrugBank 5.0: a major update to the DrugBank database for 2018","volume":"46","author":"DS Wishart","year":"2018","journal-title":"Nucleic acids research"},{"issue":"9","key":"pone.0303597.ref016","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1021\/cn3000422","article-title":"Exploring chemical space for drug discovery using the chemical universe database","volume":"3","author":"JL Reymond","year":"2012","journal-title":"ACS chemical neuroscience"},{"issue":"2","key":"pone.0303597.ref017","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"R Gomez-Bombarelli","year":"2018","journal-title":"ACS central science"},{"key":"pone.0303597.ref018","doi-asserted-by":"crossref","first-page":"8732","DOI":"10.1021\/ja902302h","article-title":"970 Million Druglike Small Molecules for Virtual Screening in the Chemical Universe","volume":"131","author":"LC B","year":"2009","journal-title":"J Am Chem Soc"},{"key":"pone.0303597.ref019","unstructured":"Jin W, Barzilay R, Jaakkola T. Junction tree variational autoencoder for molecular graph generation. arXiv [csLG]. 2018;."},{"issue":"1","key":"pone.0303597.ref020","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s13321-019-0397-9","article-title":"A de novo molecular generation method using latent vector based generative adversarial network","volume":"11","author":"O Prykhodko","year":"2019","journal-title":"Journal of cheminformatics"},{"issue":"D1","key":"pone.0303597.ref021","doi-asserted-by":"crossref","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: a large-scale bioactivity database for drug discovery","volume":"40","author":"A Gaulton","year":"2012","journal-title":"Nucleic acids research"},{"key":"pone.0303597.ref022","unstructured":"Cao ND, Kipf T. MolGAN: An implicit generative model for small molecular graphs. arXiv [statML]. 2018;."},{"issue":"1","key":"pone.0303597.ref023","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","article-title":"Generating focused molecule libraries for drug discovery with recurrent neural networks","volume":"4","author":"MHS Segler","year":"2018","journal-title":"ACS central science"},{"key":"pone.0303597.ref024","unstructured":"Bjerrum EJ. SMILES Enumeration as Data Augmentation for Neural Network. arXiv [csLG]. 2017;."},{"key":"pone.0303597.ref025","unstructured":"Landrum G. RDKit Website; Accessed 2023. Available from: https:\/\/www.rdkit.org\/."},{"issue":"1-2","key":"pone.0303597.ref026","article-title":"Generative recurrent networks for DE Novo drug design","volume":"37","author":"A Gupta","year":"2018","journal-title":"Molecular informatics"},{"key":"pone.0303597.ref027","unstructured":"Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. arXiv [csCL]. 2013;."},{"issue":"12","key":"pone.0303597.ref028","doi-asserted-by":"crossref","first-page":"310","DOI":"10.33564\/IJEAST.2020.v04i12.054","article-title":"ACTIVATION FUNCTIONS IN NEURAL NETWORKS","volume":"4","author":"S Sharma","year":"2017","journal-title":"International Journal of Engineering Applied Sciences and Technology"},{"key":"pone.0303597.ref029","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv [csLG]. 2014;."},{"issue":"1","key":"pone.0303597.ref030","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open Babel: An open chemical toolbox","volume":"3","author":"NM O\u2019Boyle","year":"2011","journal-title":"Journal of cheminformatics"},{"key":"pone.0303597.ref031","unstructured":"Bank RPD. RCSB Protein Data Bank\u20144HLA; Accessed 2023. Available from: https:\/\/www.rcsb.org\/structure\/4hla."},{"key":"pone.0303597.ref032","unstructured":"3S45\u2014RCSB Protein Data Bank; Accessed 2023. Available from: https:\/\/www.rcsb.org\/structure\/3s45."},{"key":"pone.0303597.ref033","unstructured":"BIOVIA DS. Discovery Studio Modeling Environment, Release 2017; 2016."},{"key":"pone.0303597.ref034","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/978-1-4939-2269-7_19","article-title":"Small-molecule library screening by docking with PyRx","volume":"1263","author":"S Dallakyan","year":"2015","journal-title":"Methods in molecular biology (Clifton, NJ)"},{"issue":"1","key":"pone.0303597.ref035","doi-asserted-by":"crossref","DOI":"10.1002\/0471250953.bi0814s24","article-title":"Using AutoDock for ligand-receptor docking","volume":"8","author":"GM Morris","year":"2008","journal-title":"Current protocols in bioinformatics"},{"issue":"2","key":"pone.0303597.ref036","doi-asserted-by":"crossref","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":"O Trott","year":"2010","journal-title":"Journal of computational chemistry"},{"issue":"1-3","key":"pone.0303597.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0010-4655(95)00041-D","article-title":"AMBER, a package of computer programs for applying molecular mechanics, normal mode analysis, molecular dynamics and free energy calculations to simulate the structural and energetic properties of molecules","volume":"91","author":"DA Pearlman","year":"1995","journal-title":"Computer physics communications"},{"key":"pone.0303597.ref038","unstructured":"Schr\u00f6dinger. The PyMOL Molecular Graphics System, Version 1.8; 2015. https:\/\/pymol.org\/2\/."},{"key":"pone.0303597.ref039","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. arXiv [csDC]. 2016;."},{"issue":"15","key":"pone.0303597.ref040","doi-asserted-by":"crossref","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The properties of known drugs. 1. Molecular frameworks","volume":"39","author":"GW Bemis","year":"1996","journal-title":"Journal of medicinal chemistry"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0303597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T13:23:26Z","timestamp":1718976206000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0303597"}},"subtitle":[],"editor":[{"given":"Soumendranath","family":"Bhakat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,6,21]]},"references-count":40,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0303597","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,21]]}}}