ALADDIN: Docking Approach Augmented by Machine Learning for Protein Structure Selection Yields Superior Virtual Screening Performance

ALADDIN: Docking Approach Augmented by Machine Learning for Protein Structure Selection Yields Superior Virtual Screening Performance
复制标题

ALADDIN:通过机器学习增强蛋白质结构选择的对接方法可产生卓越的虚拟筛选性能

DOI:
10.1002/minf.201900103
复制
发表时间:
2019
影响因子:
3.6
通讯作者:
Kirchmair
Kirchmair
中科院分区:
医学4区
文献类型:
--
作者:
Bruyn Kops;Kirchmair

文献摘要

参考文献

相似文献

蛋白质的灵活性和溶剂化对对接算法和评分函数提出了重大挑战。解决这些挑战的一种既定策略是使用多种蛋白质构象进行对接(全对全整体对接)。最近的研究表明,通过选择最相关的蛋白质结构进行对接可以提高整体对接的性能。为了寻找一种稳健的蛋白质结构选择方法,我们提出了一种集成的机器学习和对接方法 (ALADDIN)。阿拉丁采用一组随机森林分类器,从蛋白质结构集合中为每种感兴趣的化合物单独选择最适合对接的单一蛋白质结构。 ALADDIN 在四个研究目标中的三个上优于最好的单结构对接运行、整体对接和基于相似性的对接方法,受试者工作特征曲线 (AUC) 值下的面积分别高出 0.15、0.11 和 0.16。仅在细胞色素 P450 3A4 的情况下,ALADDIN 与任何其他测试方法一样,未能获得良好的性能。 ALADDIN 对于可塑性蛋白质(包括激酶、一些病毒酶和抗靶标)的基于结构的虚拟筛选特别有用。
Protein flexibility and solvation pose major challenges to docking algorithms and scoring functions. One established strategy for addressing these challenges is to use multiple protein conformations for docking (all‐against‐all ensemble docking). Recent studies have shown that the performance of ensemble docking can be improved by selecting the most relevant protein structures for docking. In search for a robust approach to protein structure selection, we have come up with an integrated mAchine Learning AnD DockINg approach (ALADDIN). ALADDIN employs a battery of random forest classifiers to select, individually for each compound of interest, from an ensemble of protein structures, the single most suitable protein structure for docking. ALADDIN outperformed the best single‐structure docking runs, ensemble docking and a similarity‐based docking approach on three out of four investigated targets, with up to 0.15, 0.11 and 0.16 higher area under the receiver operating characteristic curve (AUC) values, respectively. Only in the case of cytochrome P450 3A4, ALADDIN, like any of the other tested approaches, failed to obtain decent performance. ALADDIN can be particularly useful for structure‐based virtual screening of malleable proteins, including kinases, some viral enzymes and anti‐targets.
DOI: 10.1021/acs.chemrestox.6b00226
发表时间: 2017-01-17
影响因子: 4.1
作者:
Guengerich FP
通讯作者: Guengerich FP
DOI: 10.1021/acs.jmedchem.5b02008
发表时间: 2016-05-12
影响因子: 7.3
作者:
Irwin JJ;Shoichet BK
通讯作者: Shoichet BK
DOI: 10.2174/156802610790232279
发表时间: 2010
影响因子: 3.4
作者:
Amaro RE;Li WW
通讯作者: Li WW
DOI: 10.1021/jm0306430
发表时间: 2004-03-25
影响因子: 7.3
作者:
Friesner, RA;Banks, JL;Shenkin, PS
通讯作者: Shenkin, PS
通过集成对接提高数据库丰富度
DOI: --
发表时间: 2008
期刊: J. Comput. Aided Mol. Des.
影响因子: --
作者:
Shashidhar N. Rao;P. Sanschagrin;J. Greenwood;Matthew P. Repasky;W. Sherman;R. Farid
通讯作者: R. Farid