计算机科学
聚类分析
构象集合
变构调节
药物发现
分子动力学
结构生物信息学
对接(动物)
人工智能
人工神经网络
计算生物学
灵活性(工程)
机器学习
化学
作者
Alessandro Pandini,Domenico Fraccalvieri,Laura Bonati
标识
DOI:10.2174/1568026611313050007
摘要
The biological function of proteins is strictly related to their molecular flexibility and dynamics: enzymatic activity,
protein-protein interactions, ligand binding and allosteric regulation are important mechanisms involving protein
motions. Computational approaches, such as Molecular Dynamics (MD) simulations, are now routinely used to study the
intrinsic dynamics of target proteins as well as to complement molecular docking approaches. These methods have also
successfully supported the process of rational design and discovery of new drugs. Identification of functionally relevant
conformations is a key step in these studies. This is generally done by cluster analysis of the ensemble of structures in the
MD trajectory. Recently Artificial Neural Network (ANN) approaches, in particular methods based on Self-Organising
Maps (SOMs), have been reported performing more accurately and providing more consistent results than traditional clustering
algorithms in various data-mining problems. In the specific case of conformational analysis, SOMs have been successfully
used to compare multiple ensembles of protein conformations demonstrating a potential in efficiently detecting
the dynamic signatures central to biological function. Moreover, examples of the use of SOMs to address problems relevant
to other stages of the drug-design process, including clustering of docking poses, have been reported. In this contribution
we review recent applications of ANN algorithms in analysing conformational and structural ensembles and we
discuss their potential in computer-based approaches for medicinal chemistry.
科研通智能强力驱动
Strongly Powered by AbleSci AI