Machine learning of time-series single-cell drug screening to elucidate HIV latency control mechanisms

时间序列单细胞药物筛选的机器学习阐明 HIV 潜伏期控制机制

• 批准号: 10402668
• 负责人: Diwakar Shukla
• 金额: $ 22.13万
• 依托单位: UNIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10402668
• 关键词: Accounting; Affect; Area; Biochemistry; Biological; Biology; Biomedical Engineering; Biophysics; Career Transition Award; Cells; Chemical Agents; Chemical Models; Chemical Structure; Chemicals; Clinical; Communities; Data; Data Set; Decision Making; Disease; Drug Compounding; Drug Screening; Drug Targeting; Engineering; Etiology; Excision; FDA approved; Faculty; Feedback; Fluorescence Microscopy; Foundations; Funding; Gene Expression; Genes; Goals; HIV; Health; Hour; Human; Image; Lead; Learning; Libraries; Literature; Machine Learning; Microscopy; Mission; Modeling; National Institute of Allergy and Infectious Disease; Noise; Outcome; Pharmaceutical Preparations; Pharmacologic Substance; Pharmacotherapy; Publishing; Research; Research Assistant; Science; Series; Shock; Structure; Structure-Activity Relationship; Systems Biology; T-Lymphocyte; Therapeutic; Time; Training; Training Support; United States National Institutes of Health; Validation; Variant; Virus; Work; autoencoder; base; computational pipelines; computer science; deep learning; deep neural network; design; drug development; drug discovery; drug repurposing; experimental study; generative adversarial network; in silico; insight; integration site; interest; latent HIV reservoir; learning strategy; machine learning pipeline; mathematical sciences; member; novel; novel therapeutics; protein expression; reactivation from latency; response; small molecule; small molecule libraries; success; time use; tool; treatment strategy; virology

PROJECT SUMMARY Gene expression dynamics yield a wealth of insight into the underlying structure-function relationships of gene circuitry and the blueprints of disease. This is especially true for viruses whose decision-making is highly dependent on their gene expression dynamics. Time-series gene expression perturbation data elucidates biological causality and is essential to identify biological mechanisms, perform chemical biology analyses, and for the discovery of novel drugs. However, a pipeline to comprehensively and effectively analyze such time-series perturbation data does not exist. In this work, we propose to apply machine learning to unravel the hidden (latent) structure of human immunodeficiency virus (HIV) time- series gene expression when affected by chemical perturbations. This highly interdisciplinary effort includes scientific areas relevant to the mission of the NIH such as biological, clinical, physical, chemical, computational, engineering, and mathematical sciences. The proposed areas of research combine machine learning, virology, systems biology, chemical sciences, single-cell biophysics, and pharmaceutical sciences. The research will train and support two faculty members and two graduate research assistants for the two-year term.

项目摘要 基因表达动态产生了丰富的洞察潜在的结构-功能关系 基因电路和疾病蓝图的关系。对于那些决策过程 高度依赖于它们的基因表达动态。时间序列基因表达扰动数据 阐明生物因果关系，对于确定生物机制、进行化学反应至关重要 生物学分析和新药的发现。然而，一个全面和 有效地分析这样时间序列扰动数据是不存在的。在这项工作中，我们建议应用 机器学习解开人类免疫缺陷病毒（HIV）时间的隐藏（潜伏）结构- 一系列基因表达受到化学扰动时。这种高度跨学科的努力 包括与NIH的使命相关的科学领域，如生物学，临床，物理学， 化学、计算、工程和数学科学。拟议的研究领域 联合收割机结合机器学习、病毒学、系统生物学、化学科学、单细胞生物物理学， 制药科学该研究将培训和支持两名教师和两名研究生 研究助理任期两年。