Synergistic integration of topology and machine learning for the predictions of protein-ligand binding affinities and mutation impacts

拓扑和机器学习的协同集成，用于预测蛋白质-配体结合亲和力和突变影响

基本信息

批准号：
9756427
负责人：
Guowei Wei
金额：
$ 31.93万
依托单位：
MICHIGAN STATE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2018
资助国家：
美国
起止时间：
2018-08-01 至 2022-07-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/9756427
关键词：
3-Dimensional Address Affinity Architecture Big Data Binding Binding Proteins Bioinformatics Biological Biological Sciences Biophysics Characteristics Chemicals Classification Complex Computer software DNA Sequence Data Data Analyses Data Science Data Set Databases Development Diagnosis Dimensions Drug Design Electrostatics Elements Free Energy Freedom Future Generations Geometry Handwriting Image Analysis Induced Mutation Ions Learning Ligand Binding Ligands Lipids Machine Learning Medical Membrane Membrane Proteins Metals Methodology Methods Mutation Physics Plant Roots Proteins Psychological Transfer Site Speech System Techniques Thermodynamics Work algebraic topology base cofactor data warehouse deep learning deep learning algorithm direct application high dimensionality improved innovation language processing learning algorithm learning strategy machine learning algorithm metallicity models and simulation multi-task learning multitask mutant neglect next generation search engine tool trend user-friendly

项目摘要

Project Summary Fundamental challenges that hinder the current understanding of biomolecular systems are their tremendous complexity, high dimensionality and excessively large data sets associated with their geometric modeling and simulations. These challenges call for innovative strategies for handling massive biomolecular datasets. Topology, in contrast to geometry, provides a unique tool for dimensionality reduction and data simplification. However, traditional topology typically incurs with excessive reduction in geometric information. Persistent homology is a new branch of topology that is able to bridge traditional topology and geometry, but suffers from neglecting biological information. Built upon PI’s recent work in the topological data analysis of biomolecules, this project will explore how to integrate topological data analysis and machine learning to significantly improve the current state-of-the-art predictions of protein-ligand binding and mutation impact established in the PI’s preliminary studies. These improvements will be achieved through developing physics-embedded topological methodologies and advanced deep learning architectures for tackling heterogeneous biomolecular data sets arising from a variety of physical and biological considerations. Finally, the PI will establish robust databases and online servers for the proposed predictions.

项目概要阻碍当前对生物分子系统的理解的基本挑战是它们与其相关的巨大复杂性、高维度和过大的数据集这些挑战需要创新的处理策略。与几何相比，大量生物分子数据集提供了一种独特的工具。然而，传统拓扑通常会带来降维和数据简化。几何信息的过度减少是拓扑学的一个新分支。它能够连接传统的拓扑学和几何学，但却忽视了生物学该信息基于 PI 最近在生物分子拓扑数据分析方面的工作。项目将探索如何将拓扑数据分析和机器学习结合起来，以显着改进当前对蛋白质配体结合和突变影响的最先进预测这些改进将通过 PI 的初步研究来实现。开发物理嵌入式拓扑方法和高级深度学习用于解决由各种物理产生的异质生物分子数据集的体系结构最后，PI 将建立强大的数据库和在线服务器。对于所提出的预测。