Predicting Protein Structure with Guided Conformation Space Search

描述（申请人提供）：蛋白质结构预测是结构生物学中最大的挑战之一。准确预测蛋白质三维结构的能力将带来重大的科学进步，并将有助于找到许多疾病的治疗方法。我们提出了一个新的蛋白质结构预测的计算框架。该框架的新奇之处在于其构象空间搜索的方法。构象空间搜索被认为是实现一致的高分辨率预测的主要瓶颈。所提出的构象空间搜索方法代表了蛋白质结构预测的重大概念转变，通过将机器人和机器学习的见解和算法与分子生物学技术以创新的方式相结合而成为可能。关键的创新来自于这样的见解，即目标特异性信息可以有效地引导构象空间搜索到生物相关区域。我们建议开发一个框架，蛋白质结构预测，实现生物学的准确性和计算效率，通过指导构象空间搜索使用目标特定的信息。所提出的框架利用两个来源的目标特定的信息：1）在搜索过程中连续获得的目标的能量景观的特征的信息，和2）从NMR实验获得的目标的结构的空间约束。随着搜索的进行，这些信息源的持续整合将使构象空间搜索适应目标的特定特征。这种定制的构象空间探索可以克服当前的瓶颈，产生高度准确和高效的结构预测。蛋白质代表了每个细胞内的分子机制，确定蛋白质三维结构的能力将大大有助于找到许多疾病的治疗方法。这项研究工作将开发一种新的，有效的，生物学上准确的计算方法来确定蛋白质的三维结构。

DESCRIPTION (provided by applicant): Protein structure prediction is one of the great challenges in structural biology. The ability to accurately predict the three-dimensional structure of proteins would bring about significant scientific advances and would facilitate finding cures and treatments for many diseases. We propose a novel computational framework for protein structure prediction. The novelty of the framework lies in its approach to conformation space search. Conformation space search is considered to be the primary bottleneck towards consistent, high-resolution prediction. The proposed approach to conformation space search represents a major conceptual shift in protein structure prediction, made possible by combining insights and algorithms from robotics and machine learning with techniques from molecular biology in an innovative manner. The key innovation comes from the insight that target-specific information can effectively guide conformation space search towards biologically relevant regions. We propose to develop a framework for protein structure prediction that achieves biological accuracy and computational efficiency by guiding conformation space search using target-specific information. The proposed framework exploits two sources of target-specific information: 1) information about the characteristics of the target's energy landscape acquired continuously during search, and 2) spatial restraints about the target's structure obtained from NMR experiments. As search progresses, the continuous integration of these sources of information will tailor conformation space search to the particular characteristics of the target. This tailored conformation space exploration can overcome the current bottleneck, yielding highly accurate and efficient structure prediction. The ability to determine the three-dimensional structures of proteins, which represent the molecular machinery inside every cell, would greatly facilitate finding cures or treatments for many diseases. This research effort will develop of a novel, efficient, and biologically accurate computational approach to determine the three-dimensional structure of proteins.