{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:33:10Z","timestamp":1786365190115,"version":"build-2736575974"},"reference-count":48,"publisher":"American Chemical Society (ACS)","issue":"15","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976247"],"award-info":[{"award-number":["61976247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004536","name":"Southwest Jiaotong University","doi-asserted-by":"publisher","award":["2682024JX004"],"award-info":[{"award-number":["2682024JX004"]}],"id":[{"id":"10.13039\/501100004536","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004536","name":"Southwest Jiaotong University","doi-asserted-by":"publisher","award":["2682024KJ016"],"award-info":[{"award-number":["2682024KJ016"]}],"id":[{"id":"10.13039\/501100004536","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Balancing target-specific biological affinity with drug-likeness remains a central challenge in de novo molecular design, where existing generative models often exhibit limited controllability or reduced structural diversity. Here, we present DF-S4, a conditional molecular generation framework based on Structured State Space Models (S4), which addresses this limitation through a disentangled latent representation and hierarchical feature-wise linear modulation (FiLM). By decoupling structural and property variables and injecting conditional signals across multiple representation levels, DF-S4 enables fine-grained and stable multi-objective control beyond conventional input-level conditioning. Evaluated via a rigorous progressive multi-denominator auditing framework across three kinase targets (EGFR, BRAF, and FGFR1), DF-S4 exhibits robust target-steering performance, yielding favorable intradomain active ratios (74.2\u201383.9%) while maintaining high novelty (&amp;gt;95%) and competitive internal diversity (\u223c0.85). Furthermore, DF-S4 shifts the multi-objective Pareto Frontier toward regions of simultaneous high apparent affinity and drug-likeness, mitigating the distributional-trapping trade-offs commonly observed in prior approaches. Molecular docking analyses confirm the physical plausibility of generated candidates, yielding stronger binding affinities than reference inhibitors. Finally, comprehensive ablation studies and latent space dependence analyses mathematically validate that both explicit latent disentanglement and hierarchical FiLM modulation are critical for robust feature isolation, tighter property alignment, and generative stability.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c02064","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T14:32:56Z","timestamp":1784817176000},"page":"9045-9056","source":"Crossref","is-referenced-by-count":0,"title":["DF-S4: Disentangled\nFiLM-Conditioned Molecular Generation\nUsing the S4 Architecture"],"prefix":"10.1021","volume":"66","author":[{"given":"Yuecheng","family":"Peng","sequence":"first","affiliation":[{"name":"Southwest Jiaotong University , , , ,","place":["Chengdu, Sichuan, P. R. China, 610031"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1651-595X","authenticated-orcid":true,"given":"Yongquan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University , , , ,","place":["Chengdu, Sichuan, P. R. China, 610031"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoxue","family":"Quan","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University , , , ,","place":["Chengdu, Sichuan, P. R. China, 611756"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6611-4225","authenticated-orcid":true,"given":"Kuanping","family":"Gong","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University , , , ,","place":["Chengdu, Sichuan, P. R. China, 610031"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yang","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University , , , ,","place":["Chengdu, Sichuan, P. R. China, 610031"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"issue":"6","key":"2026081008094186800_cit1","doi-asserted-by":"publisher","first-page":"103992","DOI":"10.1016\/j.drudis.2024.103992","article-title":"Unleashing the Power of Generative AI in Drug Discovery","volume":"29","author":"Gangwal","year":"2024","journal-title":"Drug Discovery Today"},{"key":"2026081008094186800_cit2","doi-asserted-by":"publisher","first-page":"102575","DOI":"10.1016\/j.sbi.2023.102575","article-title":"Artificial Intelligence in Molecular\nde Novo Design: Integration with Experiment","volume":"80","author":"Janet","year":"2023","journal-title":"Curr. Opin. Struct. Biol."},{"issue":"6","key":"2026081008094186800_cit3","doi-asserted-by":"publisher","first-page":"891","DOI":"10.3390\/ph16060891","article-title":"The Role of\nAI in Drug Discovery: Challenges, Opportunities, and Strategies","volume":"16","author":"Blanco-Gonza\u0301lez","year":"2023","journal-title":"Pharmaceuticals"},{"issue":"2","key":"2026081008094186800_cit4","doi-asserted-by":"publisher","first-page":"100678","DOI":"10.1016\/j.patter.2023.100678","article-title":"Computer-Aided Multi-Objective\nOptimization in Small\nMolecule Discovery","volume":"4","author":"Fromer","year":"2023","journal-title":"Patterns"},{"key":"2026081008094186800_cit5","doi-asserted-by":"publisher","first-page":"3235","DOI":"10.2147\/DDDT.S257494","article-title":"Potential Impact of the Multi-Target\nDrug Approach\nin the Treatment of Some Complex Diseases","volume":"14","author":"Makhoba","year":"2020","journal-title":"Drug\nDes. Devel. Ther."},{"issue":"20","key":"2026081008094186800_cit6","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e39038","article-title":"Transformer-Based\nModels for Chemical SMILES Representation:\nA Comprehensive Literature Review","volume":"10","author":"Mswahili","year":"2024","journal-title":"Heliyon"},{"issue":"5","key":"2026081008094186800_cit7","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1608","article-title":"Generative Models\nfor Molecular Discovery: Recent Advances and Challenges","volume":"12","author":"Bilodeau","year":"2022","journal-title":"WIREs Comput. Mol. Sci."},{"key":"2026081008094186800_cit8","doi-asserted-by":"publisher","first-page":"arXiv.1802.08786","DOI":"10.48550\/arXiv.1802.08786","article-title":"Syntax-Directed\nVariational Autoencoder for Structured Data","author":"Dai","year":"2018","journal-title":"arXiv"},{"issue":"1","key":"2026081008094186800_cit9","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1021\/acs.jcim.8b00263","article-title":"Conditional Molecular Design with\nDeep Generative Models","volume":"59","author":"Kang","year":"2019","journal-title":"J. Chem. Inf. Model."},{"issue":"9","key":"2026081008094186800_cit10","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1021\/acs.jcim.1c00600","article-title":"MolGPT:\nMolecular Generation Using a Transformer-Decoder Model","volume":"62","author":"Bagal","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026081008094186800_cit11","unstructured":"Hoogeboom, E.; Satorras, V. G.; Vignac, C.; Welling, M.\n          Equivariant\nDiffusion\nfor Molecule Generation in 3d. In  International\nConference on Machine Learning; PMLR, 2022; pp 8867\u20138887."},{"key":"2026081008094186800_cit12","unstructured":"Xu, M.; Powers, A. S.; Dror, R. O.; Ermon, S.; Leskovec, J.\n          Geometric\nLatent\nDiffusion Models for 3d Molecule Generation. In  International Conference on Machine Learning; PMLR, 2023; pp 38592\u201338610."},{"issue":"4","key":"2026081008094186800_cit13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3626235","article-title":"Diffusion\nModels: A Comprehensive Survey of Methods and Applications","volume":"56","author":"Yang","year":"2024","journal-title":"ACM Comput. Surv."},{"issue":"12","key":"2026081008094186800_cit14","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1038\/s43588-024-00737-x","article-title":"Structure-Based Drug\nDesign with Equivariant Diffusion Models","volume":"4","author":"Schneuing","year":"2024","journal-title":"Nat.\nComput. Sci."},{"issue":"1","key":"2026081008094186800_cit15","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s13321-021-00498-z","article-title":"Diversity Oriented\nDeep Reinforcement Learning for Targeted Molecule Generation","volume":"13","author":"Pereira","year":"2021","journal-title":"J. Cheminformatics"},{"issue":"1","key":"2026081008094186800_cit16","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1186\/s13321-020-00473-0","article-title":"Memory-Assisted Reinforcement\nLearning for Diverse Molecular de Novo Design","volume":"12","author":"Blaschke","year":"2020","journal-title":"J. Cheminformatics"},{"issue":"1","key":"2026081008094186800_cit17","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-024-00812-5","article-title":"Reinvent 4:\nModern AI\u2013Driven Generative Molecule\nDesign","volume":"16","author":"Loeffler","year":"2024","journal-title":"J. Cheminformatics"},{"issue":"19","key":"2026081008094186800_cit18","doi-asserted-by":"publisher","first-page":"10054","DOI":"10.1021\/acs.jcim.5c01541","article-title":"CNSGT: Generative\nTransformer for De Novo Drug Design Targeting the Central Nervous\nSystem","volume":"65","author":"Chen","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"20","key":"2026081008094186800_cit19","doi-asserted-by":"publisher","first-page":"10918","DOI":"10.1021\/acs.jcim.5c01606","article-title":"A Versatile Generative Architecture\nfor Bioactive Molecules\nacross Multiple Therapeutic Targets","volume":"65","author":"Delre","year":"2025","journal-title":"J. Chem.\nInf. Model."},{"key":"2026081008094186800_cit20","doi-asserted-by":"publisher","first-page":"chemrxiv-2025-1zs8j","DOI":"10.26434\/chemrxiv-2025-1zs8j","article-title":"Generative Deep Learning\nfor de Novo Drug Design \u2013 a Chemical Space Odyssey","author":"O\u0308zc\u0327elik","year":"2025","journal-title":"chemrxiv"},{"issue":"12","key":"2026081008094186800_cit21","doi-asserted-by":"publisher","first-page":"3200","DOI":"10.1093\/bioinformatics\/btac296","article-title":"Small Molecule Generation\nvia Disentangled Representation Learning","volume":"38","author":"Du","year":"2022","journal-title":"Bioinformatics"},{"key":"2026081008094186800_cit22","doi-asserted-by":"crossref","first-page":"78435","DOI":"10.52202\/075280-3429","article-title":"Learning Invariant Molecular Representation\nin Latent Discrete Space","volume":"36","author":"Zhuang","year":"2023","journal-title":"Adv. Neural Inf. Process.\nSyst."},{"issue":"1","key":"2026081008094186800_cit23","doi-asserted-by":"publisher","first-page":"6176","DOI":"10.1038\/s41467-024-50469-9","article-title":"Chemical Language Modeling\nwith Structured State Space Sequence Models","volume":"15","author":"O\u0308zc\u0327elik","year":"2024","journal-title":"Nat. Commun."},{"issue":"1","key":"2026081008094186800_cit24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671","article-title":"FiLM:\nVisual Reasoning with\na General Conditioning Layer","volume":"32","author":"Perez","year":"2018","journal-title":"Proc. AAAI Conf.\nArtif. Intell."},{"key":"2026081008094186800_cit25","unstructured":"Brockschmidt, M.\n          \n          Gnn-Film:\nGraph Neural Networks with Feature-Wise Linear Modulation. In  International Conference on Machine Learning; PMLR, 2020; pp 1144\u20131152."},{"key":"2026081008094186800_cit26","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"2026081008094186800_cit27","doi-asserted-by":"publisher","first-page":"4430","DOI":"10.3390\/molecules28114430","article-title":"cMolGPT: A Conditional\nGenerative Pre-Trained Transformer for Target-Specific De Novo Molecular\nGeneration","volume":"28","author":"Wang","year":"2023","journal-title":"Molecules"},{"issue":"1","key":"2026081008094186800_cit28","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1021\/ci049714+","article-title":"ZINC \u2013 A Free Database of\nCommercially Available\nCompounds for Virtual Screening","volume":"45","author":"Irwin","year":"2005","journal-title":"J. Chem. Inf.\nModel."},{"issue":"D1","key":"2026081008094186800_cit29","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL:\nA Large-Scale Bioactivity Database for Drug Discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2026081008094186800_cit30","doi-asserted-by":"publisher","first-page":"565644","DOI":"10.3389\/fphar.2020.565644","article-title":"Molecular Sets (MOSES): A Benchmarking Platform for\nMolecular Generation Models","volume":"11","author":"Polykovskiy","year":"2020","journal-title":"Front. Pharmacol."},{"key":"2026081008094186800_cit31","unstructured":"Landrum, G.\n          \n          Rdkit Documentation\nRelease, 2013, 1(1\u201379), 4."},{"issue":"2","key":"2026081008094186800_cit32","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying\nthe Chemical Beauty of Drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nat. Chem."},{"issue":"14","key":"2026081008094186800_cit33","doi-asserted-by":"publisher","first-page":"6582","DOI":"10.1021\/jm300687e","article-title":"Directory of Useful\nDecoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking","volume":"55","author":"Mysinger","year":"2012","journal-title":"J. Med. Chem."},{"key":"2026081008094186800_cit34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41587-026-03090-8","article-title":"Comprehensive\nProfiling of Clinically Approved Kinase Inhibitors Reveals Mutation-Specific\nInhibitors and Opportunities for Drug Repurposing","author":"Saifudeen","year":"2026","journal-title":"Nat. Biotechnol."},{"key":"2026081008094186800_cit35","doi-asserted-by":"publisher","first-page":"arXiv.1803.09518","DOI":"10.48550\/arXiv.1803.09518","article-title":"Fre\u0301chet ChemNet Distance:\nA Metric for Generative\nModels for Molecules in Drug Discovery","author":"Preuer","year":"2018","journal-title":"arXiv"},{"key":"2026081008094186800_cit36","doi-asserted-by":"publisher","first-page":"arXiv.2501.05457","DOI":"10.48550\/arXiv.2501.05457","article-title":"How Evaluation Choices\nDistort the Outcome of Generative\nDrug Discovery","author":"O\u0308zc\u0327elik","year":"2024","journal-title":"arXiv"},{"key":"2026081008094186800_cit37","doi-asserted-by":"publisher","first-page":"5189","DOI":"10.1021\/acs.jcim.6c00535","article-title":"VeGA-RX and VeGA-SCX: Controllable SMARTS-Guided\nGenerative Transformers\nfor Precision-Driven De Novo Drug Design","volume":"66","year":"2026","journal-title":"J. Chem. Inf. Model."},{"issue":"7019","key":"2026081008094186800_cit38","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1038\/nature03197","article-title":"Virtual\nScreening of Chemical Libraries","volume":"432","author":"Shoichet","year":"2004","journal-title":"Nature"},{"issue":"11","key":"2026081008094186800_cit39","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/S1359-6446(02)02290-0","article-title":"Structural\nBiology in Drug Design: Selective Protein Kinase Inhibitors","volume":"7","author":"Scapin","year":"2002","journal-title":"Drug Discovery Today"},{"issue":"1","key":"2026081008094186800_cit40","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-017-0235-x","article-title":"Molecular\nDe-Novo Design\nthrough Deep Reinforcement Learning","volume":"9","author":"Olivecrona","year":"2017","journal-title":"J. Cheminformatics"},{"issue":"16","key":"2026081008094186800_cit41","doi-asserted-by":"publisher","first-page":"5107","DOI":"10.1021\/acs.jcim.3c00963","article-title":"GENERA:\nA Combined Genetic\/Deep-Learning\nAlgorithm for Multiobjective Target-Oriented De Novo Design","volume":"63","author":"Lamanna","year":"2023","journal-title":"J. Chem. Inf. Model."},{"issue":"5","key":"2026081008094186800_cit42","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1093\/bfgp\/elae011","article-title":"DockingGA: Enhancing\nTargeted Molecule Generation Using Transformer Neural Network and\nGenetic Algorithm with Docking Simulation","volume":"23","author":"Gao","year":"2024","journal-title":"Brief.\nFunct. Genomics"},{"issue":"8","key":"2026081008094186800_cit43","doi-asserted-by":"publisher","first-page":"4576","DOI":"10.1021\/acs.jcim.6c00397","article-title":"A Reinforcement Learning-Guided Genetic Algorithm Integrating\nMedicinal Chemistry-Inspired Molecular Transformations","volume":"66","author":"Alberga","year":"2026","journal-title":"J. Chem. Inf. Model."},{"issue":"8","key":"2026081008094186800_cit44","doi-asserted-by":"publisher","first-page":"3041","DOI":"10.1073\/pnas.0711741105","article-title":"Discovery of a Selective Inhibitor\nof Oncogenic B-Raf Kinase with Potent Antimelanoma Activity","volume":"105","author":"Tsai","year":"2008","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"issue":"3","key":"2026081008094186800_cit45","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.ccr.2006.12.017","article-title":"Structures of Lung\nCancer-Derived\nEGFR Mutants and Inhibitor Complexes: Mechanism of Activation and\nInsights into Differential Inhibitor Sensitivity","volume":"11","author":"Yun","year":"2007","journal-title":"Cancer Cell"},{"issue":"5314","key":"2026081008094186800_cit46","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1126\/science.276.5314.955","article-title":"Structures\nof the Tyrosine Kinase Domain of Fibroblast Growth Factor Receptor\nin Complex with Inhibitors","volume":"276","author":"Mohammadi","year":"1997","journal-title":"Science"},{"key":"2026081008094186800_cit47","first-page":"5777","article-title":"Latent\nInceptionism for Targeted Molecule Generation","volume":"162","author":"Eckmann","year":"2022","journal-title":"Proc. Mach. Learn. Res."},{"issue":"7","key":"2026081008094186800_cit48","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e17575","article-title":"AI in Drug Discovery and Its Clinical\nRelevance","volume":"9","author":"Qureshi","year":"2023","journal-title":"Heliyon"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c02064","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/9045\/66236695\/acs.jcim.6c02064.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/9045\/66236695\/acs.jcim.6c02064.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:15:12Z","timestamp":1786364112000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/15\/9045\/5231202\/DF-S4-Disentangled-FiLM-Conditioned-Molecular"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":48,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,7,23]]},"published-print":{"date-parts":[[2026,8,10]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c02064","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]}}}