Large-language models facilitate discovery of the molecular signatures regulating sleep and activity

  • Nat Commun. 2024 May 1;15(1):3685. doi: 10.1038/s41467-024-48005-w.
Di Peng  #  1 ,  Liubin Zheng  #  1 ,  Dan Liu  #  1 ,  Cheng Han  #  1 ,  Xin Wang  1 ,  Yan Yang  1 ,  Li Song  1 ,  Miaoying Zhao  1 ,  Yanfeng Wei  1 ,  Jiayi Li  1 ,  Xiaoxue Ye  1 ,  Yuxiang Wei  1 ,  Zihao Feng  1 ,  Xinhe Huang  1 ,  Miaomiao Chen  1 ,  Yujie Gou  1 ,  Yu Xue  2  3 ,  Luoying Zhang  4  5
Affiliations
  • 1. 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, 430074, China.
  • 2. 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, 430074, China. [email protected].
  • 3. Nanjing University Institute of Artificial Intelligence Biomedicine, Nanjing, Jiangsu, 210031, China. [email protected].
  • 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, 430074, China. [email protected].
  • 5. Hubei Province Key Laboratory of Oral and Maxillofacial Development and Regeneration, Wuhan, Hubei, 430022, China. [email protected].
  • # Contributed equally.
PMID: 38693116 DOI: 10.1038/s41467-024-48005-w
Abstract

Sleep, locomotor and social activities are essential animal behaviors, but their reciprocal relationships and underlying mechanisms remain poorly understood. Here, we elicit information from a cutting-edge large-language model (LLM), generative pre-trained transformer (GPT) 3.5, which interprets 10.2-13.8% of Drosophila genes known to regulate the 3 behaviors. We develop an instrument for simultaneous video tracking of multiple moving objects, and conduct a genome-wide screen. We have identified 758 fly genes that regulate sleep and activities, including mre11 which regulates sleep only in the presence of conspecifics, and NELF-B which regulates sleep regardless of whether conspecifics are present. Based on LLM-reasoning, an educated signal web is modeled for understanding of potential relationships between its components, presenting comprehensive molecular signatures that control sleep, locomotor and social activities. This LLM-aided strategy may also be helpful for addressing Other complex scientific questions.

Products