2. Academic Validation
  3. A deep learning and large language hybrid workflow for omics interpretation

A deep learning and large language hybrid workflow for omics interpretation

  • Nat Biomed Eng. 2026 Jan 8. doi: 10.1038/s41551-025-01576-5.
Dachao Tang # 1,  Chi Zhang # 1,  Weizhi Zhang # 1,  Funian Lu 2,  Leming Xiao 1,  Xinhe Huang 1,  Jiangyi Shao 3,  Dan Liu 1,  Shanshan Fu 1,  Miaoying Zhao 1,  Luoying Zhang 4,  Da Jia 5,  Han-Ming Shen 6,  Chaoyang Sun 2,  Gang Chen 2,  Bin Liu 3,  Di Peng 7,  Yu Xue 8 9
Affiliations

Affiliations

  • 1 Department of Bioinformatics and Systems Biology, MOE Key Laboratory of Molecular Biophysics, Hubei Bioinformatics and Molecular Imaging Key Laboratory, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • 2 National Clinical Research Center for Gynecology and Obstetrics and Cancer Biology Research Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • 3 School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.
  • 4 Key Laboratory of Molecular Biophysics of Ministry of Education, Hubei Bioinformatics and Molecular Imaging Key Laboratory, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • 5 Key Laboratory of Birth Defects and Related Diseases of Women and Children, Department of Paediatrics, West China Second University Hospital, State Key Laboratory of Biotherapy and Collaborative Innovation Center of Biotherapy, Sichuan University, Chengdu, China.
  • 6 Faculty of Health Sciences, Ministry of Education Frontiers Science Center for Precision Oncology, University of Macau, Macau, China.
  • 7 Department of Bioinformatics and Systems Biology, MOE Key Laboratory of Molecular Biophysics, Hubei Bioinformatics and Molecular Imaging Key Laboratory, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, China. [email protected].
  • 8 Department of Bioinformatics and Systems Biology, MOE Key Laboratory of Molecular Biophysics, Hubei Bioinformatics and Molecular Imaging Key Laboratory, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, China. [email protected].
  • 9 Hubei Hongshan Laboratory, Wuhan, China. [email protected].
  • # Contributed equally.
PMID: 41507521 DOI: 10.1038/s41551-025-01576-5
Abstract

Profiling molecular panorama from massive omics data identifies regulatory networks in cells but requires mechanistic interpretation and experimental follow up. Here we combine deep learning and large language model reasoning to develop a hybrid workflow for omics interpretation, called LyMOI. LyMOI incorporates GPT-3.5 for biological knowledge reasoning and a large graph model with graph convolutional networks (GCNs). The large graph model integrates evolutionarily conserved protein interactions and uses hierarchical fine-tuning to predict context-specific molecular regulators from multi-omics data. GPT-3.5 then generates machine chain-of-thought (CoT) to mechanistically interpret their roles in biological systems. Focusing on Autophagy, LyMOI mechanistically interprets 1.3 TB transcriptomic, proteomic and phosphoproteomic data and expands the knowledge of Autophagy regulators. We also show that LyMOI highlights two human oncoproteins, CTSL and FAM98A, for enhancing Autophagy upon treatment with disulfiram (DSF), an antitumour agent. Silencing these genes in vitro attenuates DSF-mediated Autophagy and suppresses Cancer cell proliferation. Strikingly, DSF treatment with Z-FY-CHO, a CTSL-specific inhibitor previously used for preventing SARS-CoV-2 Infection, potently inhibits tumour growth in vivo.

Figures
Products