{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T04:58:47Z","timestamp":1790657927428,"version":"4.1.0"},"reference-count":65,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Molecular Informatics"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:p>Transformer\u2010based molecular language models have demonstrated strong capabilities for de novo molecular generation by modeling chemical structures as token sequences. However, controllable generation of molecules with desired physicochemical properties remains challenging without reinforcement learning (RL) or post\u2010generation filtering. In this study, we propose a property\u2010conditioned autoregressive transformer framework for molecular generation using the SELFIES representation. Continuous molecular descriptors, including logP, quantitative estimate of drug\u2010likeness, and molecular weight (MolWt), were normalized and embedded via a multilayer perceptron and injected into token embeddings to enable global conditioning during sequence modeling. The model was trained end\u2010to\u2010end using the maximum likelihood with cross\u2010entropy loss. Experiments conducted on the combined subsets of QM9, ZINC, and MOSES datasets demonstrated high validity (100%), strong uniqueness, and substantial novelty in the generated molecules. Furthermore, the generated property distributions closely aligned with the training data statistics. The proposed framework provides a computationally efficient and stable approach for controllable molecular generation without requiring RL or graph\u2010based modeling.<\/jats:p>","DOI":"10.1002\/minf.70055","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T04:39:05Z","timestamp":1790656745000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Property\u2010Conditioned Transformer Language Model for De Novo Molecular Generation Using Self\u2010Referencing Embedded Strings"],"prefix":"10.1002","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5773-3756","authenticated-orcid":false,"given":"Ashish","family":"Patel","sequence":"first","affiliation":[{"name":"Department of Pharmaceutical Chemistry Parul Institute of Pharmacy Parul University  Vadodara Gujarat India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2658-9517","authenticated-orcid":false,"given":"Rajesh A.","family":"Maheshwari","sequence":"additional","affiliation":[{"name":"Department of Pharmacy Sumandeep Vidyapeeth Deemed to be University  Vadodara Gujarat India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5697-2050","authenticated-orcid":false,"given":"Atul","family":"Patel","sequence":"additional","affiliation":[{"name":"Charotar University of Science and Technology, CHARUSAT\u2010Campus  Anand Gujarat India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5280-8082","authenticated-orcid":false,"given":"Ankit","family":"Faldu","sequence":"additional","affiliation":[{"name":"Smt. Chandaben Mohanbhai Patel Institute of Computer Applications Charotar University of Science and Technology  Anand Gujarat India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5768-7726","authenticated-orcid":false,"given":"Anjali","family":"Mahavar","sequence":"additional","affiliation":[{"name":"Charotar University of Science and Technology, CHARUSAT\u2010Campus  Anand Gujarat India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrd.2017.232"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10822\u2010020\u201000317\u2010x"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41573\u2010019\u20100024\u20105"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587\u2010019\u20100224\u2010x"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat2663"},{"key":"e_1_2_10_7_1","unstructured":"W.GaoandC. W.Coley The Synthesizability of Molecules Proposed by Generative Models 2020 arXiv [q\u2010Bio.QM] http:\/\/arxiv.org\/abs\/2002.07007."},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587\u2010020\u20100418\u20102"},{"key":"e_1_2_10_9_1","first-page":"56","volume-title":"Advances in Intelligent Systems Research","author":"Djennad A.","year":"2025"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2023.103516"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.55041\/ijsrem52104"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.medidd.2025.100213"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.55549\/epstem.1248"},{"key":"e_1_2_10_14_1","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine Learning for Molecular and Materials Science","volume":"559","author":"Butler K. T.","year":"2018","journal-title":"Nature"},{"key":"e_1_2_10_15_1","first-page":"1","article-title":"Machine Learning for Chemical Discovery","volume":"11","author":"Tkatchenko A.","year":"2023","journal-title":"Nature Communications"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2026.104634"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/molecules31030440"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1039\/c9me00039a"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemmater.5c02194"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.2174\/1570163817666200806165934"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c00536"},{"key":"e_1_2_10_22_1","first-page":"2125","article-title":"Autoregressive Language Models for Molecular Generation","volume":"64","author":"Wang J.","year":"2024","journal-title":"Journal of Chemical Information and Modeling"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ailsci.2026.100159"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"A.Y\u00fcksel E.Ulusoy A.\u00dcnl\u00fc andT.Do\u011fan SELFormer: Molecular Representation Learning via SELFIES Language Models 2023 arXiv [q\u2010Bio.QM] https:\/\/doi.org\/10.48550\/arXiv.2304.04662.","DOI":"10.1088\/2632-2153\/acdb30"},{"key":"e_1_2_10_25_1","doi-asserted-by":"crossref","unstructured":"D.Huang andS.Tu \u201cMulMol: Transformer\u2010based Multi\u2010Task Molecular Representation Learning \u201d in2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (IEEE 2024) 681\u2013686 https:\/\/doi.org\/10.1109\/BIBM62325.2024.10822716.","DOI":"10.1109\/BIBM62325.2024.10822716"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010025\u201063245\u20100"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1725"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.molstruc.2024.139574"},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","unstructured":"A.Sultan M.Rausch\u2010Dupont S.Khan O.Kalinina D.Klakow andA.Volkamer A. Transformers for Molecular Property Prediction: Domain Adaptation Efficiently Improves Performance 2025 arXiv [cs.LG] https:\/\/doi.org\/10.48550\/arXiv.2503.03360.","DOI":"10.1186\/s13321-026-01252-z"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c00600"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1651"},{"key":"e_1_2_10_32_1","unstructured":"H.Ma Y.Bian Y.Rong et al. Multi\u2010View Graph Neural Networks for Molecular Property Prediction 2020 arXiv [q\u2010Bio.QM] http:\/\/arxiv.org\/abs\/2005.13607."},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf555"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpha.2025.101508"},{"key":"e_1_2_10_35_1","unstructured":"K.BerryandL.Cheng A Survey of Graph Neural Networks for Drug Discovery: Recent Developments and Challenges 2025 arXiv [cs.LG] http:\/\/arxiv.org\/abs\/2509.07887."},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms25126583"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf117"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad235"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3769677"},{"key":"e_1_2_10_40_1","doi-asserted-by":"crossref","unstructured":"W. Y.Kim H.Kim S.Moon W.Zhung andJ.Lim DeepBioisostere: Deep Learning\u2010Based Bioisosteric Replacements for Optimization of Multiple Molecular Properties 2024 Research Square https:\/\/doi.org\/10.21203\/rs.3.rs\u20104225249\/v1.","DOI":"10.21203\/rs.3.rs-4225249\/v1"},{"key":"e_1_2_10_41_1","unstructured":"A. A.Singh Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design 2025 arXiv [physics.atom\u2010Ph] http:\/\/arxiv.org\/abs\/2505.12848."},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43246\u2010022\u201000315\u20106"},{"key":"e_1_2_10_43_1","doi-asserted-by":"crossref","unstructured":"K.Zhang X.Wen J.Xiang X.Wang Y.Gao andR.Cao \u201cMulti\u2010Representation Local\u2010Global Deep Learning Architecture for Molecular Property Prediction \u201d in2025 International Joint Conference on Neural Networks (IJCNN) (IEEE 2025) 1\u20138 https:\/\/doi.org\/10.1109\/IJCNN64981.2025.11228160.","DOI":"10.1109\/IJCNN64981.2025.11228160"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.3390\/chemistry8030032"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.565644"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00675"},{"key":"e_1_2_10_47_1","first-page":"045024","article-title":"SELFIES: A Robust Representation of Semantically Constrained Graphs With an Example Application in Chemistry","volume":"1","author":"Krenn M.","year":"2022","journal-title":"Machine Learning: Science and Technology"},{"key":"e_1_2_10_48_1","first-page":"3450","article-title":"RDKit: Open\u2010Source Cheminformatics Software","volume":"63","author":"Landrum G.","year":"2023","journal-title":"Journal of Chemical Information and Modeling"},{"key":"e_1_2_10_49_1","unstructured":"A.Paszke S.Gross F.Massa et al. PyTorch: An Imperative Style High\u2010Performance Deep Learning Library 2019 arXiv [cs.LG] http:\/\/arxiv.org\/abs\/1912.01703."},{"key":"e_1_2_10_50_1","unstructured":"D. P.KingmaandJ.Ba Adam: A Method for Stochastic Optimization 2014 arXiv [cs.LG] https:\/\/doi.org\/10.48550\/arXiv.1412.6980."},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256\u2010024\u201000843\u20105"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.5c10621"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201083090\u20103"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae189"},{"key":"e_1_2_10_55_1","doi-asserted-by":"crossref","unstructured":"J.Ding S.Jin Y.Meng Q.Jin andJ.Xu \u201cTransFVAE: A Transformer\u2010Based Flow Variational Autoencoder Model for Molecular Graph Generation \u201c in2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (IEEE 2025) 645\u2013651 https:\/\/doi.org\/10.1109\/BIBM66473.2025.11356197.","DOI":"10.1109\/BIBM66473.2025.11356197"},{"key":"e_1_2_10_56_1","doi-asserted-by":"crossref","unstructured":"N.JoshiandE.Guven Improved Molecular Generation Through Attribute\u2010Driven Integrative Embeddings and GAN Selectivity 2025 arXiv [cs.LG] https:\/\/doi.org\/10.48550\/arXiv.2504.19040.","DOI":"10.1109\/CAI64502.2025.00085"},{"key":"e_1_2_10_57_1","doi-asserted-by":"crossref","unstructured":"D.Manu J.Yao W.Liu andX.Sun GraphGANFed: A Federated Generative Framework for Graph\u2010Structured Molecules Towards Efficient Drug Discovery 2023 arXiv [cs.LG] https:\/\/doi.org\/10.48550\/arXiv.2304.05498.","DOI":"10.1109\/TCBB.2024.3349990"},{"key":"e_1_2_10_58_1","doi-asserted-by":"crossref","unstructured":"P.Gai\u0144ski M.Koziarski J.Tabor andM.\u015amieja ChiENN: Embracing Molecular Chirality With Graph Neural Networks 2023 arXiv [cs.LG] https:\/\/doi.org\/10.48550\/arXiv.2307.02198.","DOI":"10.1007\/978-3-031-43418-1_3"},{"key":"e_1_2_10_59_1","unstructured":"J.WeeandJ.Jiang A Review of Topological Data Analysis and Topological Deep Learning in Molecular Sciences 2025 arXiv [q\u2010Bio.BM] http:\/\/arxiv.org\/abs\/2509.16877."},{"key":"e_1_2_10_60_1","doi-asserted-by":"publisher","DOI":"10.1039\/d4md00196f"},{"key":"e_1_2_10_61_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c02234"},{"key":"e_1_2_10_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/foods14173114"},{"key":"e_1_2_10_63_1","doi-asserted-by":"crossref","unstructured":"H.Wang Z.Zhang andH.Gong qcMol: A Large\u2010Scale Dataset of 1.2 Million Molecules With High\u2010Quality Quantum Chemical Annotations for Molecular Representation Learning 2025 bioRxiv https:\/\/doi.org\/10.1101\/2025.09.07.674462.","DOI":"10.1101\/2025.09.07.674462"},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010026\u201010131\u20104"},{"key":"e_1_2_10_65_1","doi-asserted-by":"publisher","DOI":"10.3390\/jdad3020019"},{"key":"e_1_2_10_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2024.04.030"}],"container-title":["Molecular Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/minf.70055","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/minf.70055","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/minf.70055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T04:39:18Z","timestamp":1790656758000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/minf.70055"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":65,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/minf.70055"],"URL":"https:\/\/doi.org\/10.1002\/minf.70055","archive":["Portico"],"relation":{},"ISSN":["1868-1743","1868-1751"],"issn-type":[{"value":"1868-1743","type":"print"},{"value":"1868-1751","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"2026-03-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70055"}}