{ "abstract": "Gene expression profiles capture system-level drug responses and offer a promising basis for de novo molecular generation. However, their application is limited by data sparsity and experimental noise, which hinder the reliable mapping between disease-associated transcriptomic perturbations and chemically valid therapeutic molecules. Here, we present AET5, a de novo molecular generation framework that conditions molecular design on disease-reversal gene expression profiles. AET5 integrates contrastive self-supervised learning with pre-trained sequence-to-sequence models to learn robust associations between transcriptomic signatures and molecular structures by deriving noise-tolerant transcriptomic representations and aligning them with molecular sequence space. Across the L1000 dataset, AET5 outperforms existing expression-guided generation methods in generation quality and distributional characteristics, while maintaining favorable physicochemical and drug-related properties. We further apply AET5 to generate candidate compounds for SARS-CoV-2 infection and prostate cancer. Molecular docking and dynamics simulations indicate stable target binding, supporting the biological relevance of the generated molecules. These results demonstrate that disease-reversal expression profiles can effectively guide de novo molecular generation, providing a general framework for biologically informed drug design under noisy transcriptomic conditions. Author summary: Gene expression profiles provide a system-level view of how cells respond to diseases and drug treatments, making them valuable for computational drug discovery. However, directly using transcriptomic data to guide de novo molecular generation remains challenging because these data are often sparse, noisy, and difficult to map reliably to valid chemical structures. In this study, we propose AET5, an expression-guided molecular generation framework that designs molecules conditioned on disease-reversal gene expression profiles. AET5 combines contrastive self-supervised learning with a pre-trained sequence-to-sequence molecular generator to learn robust associations between transcriptomic signatures and molecular structures, thereby reducing the influence of experimental noise and improving the alignment between biological perturbation information and chemical space. Experiments on the L1000 dataset show that AET5 achieves improved overall generation performance compared with existing expression-guided methods and produces molecules with favorable structural, distributional, and physicochemical characteristics. Case studies on SARS-CoV-2 infection and prostate cancer further suggest that the generated compounds may have biologically relevant target-binding potential. Overall, AET5 provides a scalable and biologically informed strategy for transcriptome-guided molecular design.", "abstract_shown": true, "affiliations": [ "School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu, China", "Hangzhou Institute of Medicine, Chinese Academy of Sciences, Hangzhou, Zhejiang, China", "School of Computer Science and Technology, Zhejiang Normal University, Jinhua, Zhejiang, China", "Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang, China", "University of Oxford, Oxford, Oxfordshire, United Kingdom", "Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang, China", "School of Information Technology, Halmstad University, Halmstad, Sweden", "Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong SAR, China" ], "article_type": "Research Article", "arxiv": null, "author_total": 9, "authors": [ { "affs": [ 0 ], "name": "Zhikang Yuan" }, { "affs": [ 1 ], "name": "Xin Zhang" }, { "affs": [ 2 ], "name": "Gaoming Lin" }, { "affs": [ 3 ], "name": "Quan Zou" }, { "affs": [ 4 ], "name": "Subhashisa Swain" }, { "affs": [ 5 ], "name": "Yijie Ding" }, { "affs": [ 6 ], "name": "Prayag Tiwari" }, { "affs": [ 7 ], "name": "Shuofeng Yuan" }, { "name": "Xiaoyi Guo" } ], "bibtex": "https://research.draconitic.com/paper/et0y1rgafet5q.bib", "cited_by": 0, "doi": "10.1371/journal.pcbi.1014703", "fulltext_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014703", "id": "et0y1rgafet5q", "issns": [ "1553-7358" ], "landing_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014703", "language": null, "licence": "CC-BY-4.0", "licence_label": "CC BY 4.0", "licence_source": "journal", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [ [ "openalex", "1703|Computational Drug Discovery Methods" ], [ "plos", "/Biology and life sciences/Computational biology/Genome analysis/Transcriptome analysis" ], [ "plos", "/Biology and life sciences/Genetics/Gene expression" ], [ "plos", "/Biology and life sciences/Genetics/Genomics/Genome analysis/Transcriptome analysis" ], [ "plos", "/Biology and life sciences/Microbiology/Medical microbiology/Microbial pathogens/Viral pathogens/Coronaviruses/SARS coronavirus/SARS CoV 2" ], [ "plos", "/Biology and life sciences/Organisms/Viruses/RNA viruses/Coronaviruses/SARS coronavirus/SARS CoV 2" ], [ "plos", "/Biology and life sciences/Organisms/Viruses/Viral pathogens/Coronaviruses/SARS coronavirus/SARS CoV 2" ], [ "plos", "/Biology and life sciences/Physiology/Physiological processes/Molting" ], [ "plos", "/Medicine and health sciences/Oncology/Cancers and neoplasms/Genitourinary tract tumors/Prostate cancer" ], [ "plos", "/Medicine and health sciences/Pathology and laboratory medicine/Pathogens/Microbial pathogens/Viral pathogens/Coronaviruses/SARS coronavirus/SARS CoV 2" ], [ "plos", "/Medicine and health sciences/Urology/Prostate diseases/Prostate cancer" ], [ "plos", "/Physical sciences/Chemistry/Chemical physics/Molecular structure" ], [ "plos", "/Physical sciences/Mathematics/Statistics/Statistical noise/Gaussian noise" ], [ "plos", "/Physical sciences/Physics/Chemical physics/Molecular structure" ], [ "plos", "/Research and analysis methods/Chemical characterization/Binding analysis" ] ], "openalex": "W7212189401", "pdf_url": "https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1014703&type=printable", "pmcid": null, "pmid": null, "published": "2026-09-10", "publisher": "Public Library of Science", "ris": "https://research.draconitic.com/paper/et0y1rgafet5q.ris", "sources": [ { "first_seen": "2026-10-30T12:17:56Z", "native_id": "10.1371/journal.pcbi.1014703", "source": "plos", "url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014703" } ], "subjects": [ { "field": "biochemistry", "origin": "plos:gene expression", "subfield": "molecular-biology" }, { "field": "biology", "origin": "plos:computational biology", "subfield": "bioinformatics" }, { "field": "chemistry", "origin": "plos:chemical physics", "subfield": "physical" } ], "title": "AET5: A transcriptome-guided molecular generation framework with contrastive self-supervised learning", "title_text": "AET5: A transcriptome-guided molecular generation framework with contrastive self-supervised learning", "type": "peer-reviewed", "updated_at": "2026-10-30T12:17:56Z", "url": "https://research.draconitic.com/paper/et0y1rgafet5q", "venue": "PLOS Computational Biology", "versions": [] }