Distance-based ab initio protein structure prediction

基于距离的从头算蛋白质结构预测

基本信息

批准号：
10251061
负责人：
Jianlin Cheng
金额：
$ 34.22万
依托单位：
UNIVERSITY OF MISSOURI-COLUMBIA
依托单位国家：
美国
项目类别：
财政年份：
2010
资助国家：
美国
起止时间：
2010-06-01 至 2024-05-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10251061
关键词：
3-Dimensional Amino Acid Sequence Architecture Area Artificial Intelligence Attention Biomedical Research C-terminal Collaborations Communities Complex Computational Biology Computing Methodologies Conflict (Psychology)Dependence Development Genome Hereditary Disease Homo Maps Methods Modeling Modernization Mutate Performance Play Problem Solving Protein Engineering Protein Region Proteins Recurrence Renaissance Residual state Role Scientist Sequence Alignment Signal Transduction Site Structural Models Structural Protein Structure Techniques Technology Tertiary Protein Structure Weight X-Ray Crystallography base biophysical techniques comparative convolutional neural network cost deep learning design drug development empowered experience experimental study improved learning network learning strategy long short term memory monomer novel novel strategies open source tool protein data bank protein function protein protein interaction protein structure protein structure prediction reconstruction recurrent neural network self assembly structural biology success three dimensional structure three-dimensional modeling tool

项目摘要

Project Summary Predicting the three-dimensional structures of proteins without using known structures from the Protein Data Bank (PDB) as templates (ab initio) remains a grand challenge of computational biology. Whereas template-based modeling is now a mature field, ab initio modeling is a comparatively nascent one, especially for large proteins with complex topologies and multiple domains. The need for advances in ab initio modeling is evident. A lot of protein sequences do not have (recognizable) templates in the PDB, and the pace of experimental structure determination is incommensurate with the scale of the problem. Herein, we propose a new approach to ab initio modeling that consists of novel deep learning architectures to predict inter- residue distances and domain boundaries as well as robust, iterative optimization methods to construct tertiary structures from the predicted distances. This project builds on the success of our current R01, particularly the outstanding performance of the Cheng group in the 2018 worldwide protein structure prediction experiment – CASP13 – where our MULTICOM suite ranked among the top three tertiary structure predictors, alongside Google DeepMind’s AlphaFold. The methods will be implemented as open-source tools for the emerging field of distance-based ab initio protein structure modeling. We will apply the methods to study protein homo-oligomers and self-assemblies, based on our novel discovery that the quaternary structure contacts within homo-oligomers can be predicted by deep learning methods from the co-evolutionary signals embedded in multiple sequence alignments of protein monomers. Furthermore, we will apply the methods to predict the folds, functional sites, superfamilies, and protein-protein interactions of proteins that contain “essential Domains of Unknown Function” (eDUFs), a group of evolutionarily conserved, essential proteins that represents an important uncharted region of protein function/fold space. The predictions for a diverse and representative subset of eDUFs will be experimentally validated through a unique collaboration with the structural biology group of Dr. Tanner.

项目概要不使用已知结构来预测蛋白质的三维结构蛋白质数据库（PDB）作为模板（从头开始）仍然是计算的巨大挑战随着基于模板的建模现已成为一个成熟的领域，从头开始建模是一个成熟的领域。相对新生的一种，特别是对于具有复杂拓扑和多个的大蛋白质许多蛋白质序列都需要从头开始建模。 PDB 中没有（可识别的）模板，以及实验结构的步伐决心与问题的规模不相称，在此，我们提出了一个新的方案。从头开始建模的方法，由新颖的深度学习架构组成，用于预测交互残差距离和域边界以及稳健的迭代优化方法该项目建立在预测距离的成功基础上。我们现在的R01，特别是程氏集团2018年的出色表现全球蛋白质结构预测实验 – CASP13 – 我们的 MULTICOM 套件与 Google DeepMind 的 AlphaFold 一起跻身三级结构预测器前三名。这些方法将作为基于距离的新兴领域的开源工具来实施我们将应用这些方法来研究蛋白质同源寡聚物。和自组装，基于我们的新发现，即四级结构在内部接触可以通过深度学习方法从共同进化信号中预测同源寡聚物嵌入蛋白质单体的多个序列比对中，此外，我们将应用预测折叠、功能位点、超家族和蛋白质-蛋白质相互作用的方法含有“未知功能的必需结构域”（eDUF）的蛋白质，这是一组进化上的蛋白质保守的必需蛋白质，代表蛋白质的重要未知区域函数/折叠空间的多样化且具有代表性的 eDUF 子集的预测将是通过与 Dr. 的结构生物学小组的独特合作进行了实验验证。皮匠。