<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Peng D</submitter><funding>Ministry of Science and Technology of the People’s Republic of China</funding><funding>National Natural Science Foundation of China</funding><funding>Ministry of Science and Technology of the People's Republic of China (Chinese Ministry of Science and Technology)</funding><funding>National Natural Science Foundation of China (National Science Foundation of China)</funding><pagination>3685</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC11063160</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>15(1)</volume><pubmed_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 rel</pubmed_abstract><journal>Nature communications</journal><pubmed_title>Large-language models facilitate discovery of the molecular signatures regulating sleep and activity.</pubmed_title><pmcid>PMC11063160</pmcid><funding_grant_id>32341021</funding_grant_id><funding_grant_id>32022035</funding_grant_id><funding_grant_id>2021ZD0203200-02</funding_grant_id><pubmed_authors>Li J</pubmed_authors><pubmed_authors>Feng Z</pubmed_authors><pubmed_authors>Chen M</pubmed_authors><pubmed_authors>Zhang L</pubmed_authors><pubmed_authors>Wei Y</pubmed_authors><pubmed_authors>Ye X</pubmed_authors><pubmed_authors>Xue Y</pubmed_authors><pubmed_authors>Song L</pubmed_authors><pubmed_authors>Zhao M</pubmed_authors><pubmed_authors>Yang Y</pubmed_authors><pubmed_authors>Peng D</pubmed_authors><pubmed_authors>Zheng L</pubmed_authors><pubmed_authors>Huang X</pubmed_authors><pubmed_authors>Gou Y</pubmed_authors><pubmed_authors>Wang X</pubmed_authors><pubmed_authors>Liu D</pubmed_authors><pubmed_authors>Han C</pubmed_authors></additional><is_claimable>false</is_claimable><name>Large-language models facilitate discovery of the molecular signatures regulating sleep and activity.</name><description>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 rel</description><dates><release>2024-01-01T00:00:00Z</release><publication>2024 May</publication><modification>2026-06-01T05:37:41.385Z</modification><creation>2026-04-08T09:41:07.742Z</creation></dates><accession>S-EPMC11063160</accession><cross_references><pubmed>38693116</pubmed><doi>10.1038/s41467-024-48005-w</doi></cross_references></HashMap>