Using machine learning to improve ensemble docking for drug discovery.
Using machine learning to improve ensemble docking for drug discovery.
复制标题
作者：
Chandak T;Mayginnes JP;Mayes H;Wong CF
包封对接提供了一种廉价的方法来考虑受体的灵活性，在分子对接的虚拟筛选。不幸的是，由于没有严格的理论将多个结构的对接分数与测量的活性联系起来，研究人员尚未提出有效的方法来使用这些分数将化合物分类为活性和非活性。当更多的结构被添加到集合中时，这一缺点导致了对化合物的分类性能的降低，而不是增加。以前，我们建议以朴素贝叶斯模型的形式实现的机器学习可以缓解这个问题。然而，朴素贝叶斯模型假设观察到不同结构的对接得分的概率是独立的。这种近似可能会阻止它实现更高的性能。在本文提出的工作中，我们已经放松了这种近似，当使用其他几种机器学习方法-k近邻，逻辑回归，支持向量机和随机森林-以提高集成对接。我们发现了显著的改善。
Ensemble docking has provided an inexpensive method to account for receptor flexibility in molecular docking for virtual screening. Unfortunately, as there is no rigorous theory to connect the docking scores from multiple structures to measured activity, researchers have not yet come up with effective ways to use these scores to classify compounds into actives and inactives. This shortcoming has led to the decrease, rather than an increase in the performance of classifying compounds when more structures are added to the ensemble. Previously, we suggested machine learning, implemented in the form of a naïve Bayesian model could alleviate this problem. However, the naïve Bayesian model assumed that the probabilities of observing the docking scores to different structures to be independent. This approximation might prevent it from achieving even higher performance. In the work presented in this paper, we have relaxed this approximation when using several other machine learning methods—k nearest neighbor, logistic regression, support vector machine, and random forest—to improve ensemble docking. We found significant improvement.
登录
查看更多内容
影响因子：
3.7
作者：
Bottegoni G;Rocchia W;Rueda M;Abagyan R;Cavalli A
通讯作者：
Cavalli A
DOI：
10.3390/molecules20035152
发表时间：
2015-03-19
期刊：
Molecules (Basel, Switzerland)
影响因子：
--
作者：
Awuni Y;Mu Y
通讯作者：
Mu Y
影响因子：
3
作者：
Huang, Zunnan;He, Yantao;Wong, Chung F.
通讯作者：
Wong, Chung F.
影响因子：
7.3
作者：
Triballeau, N;Acher, F;Bertrand, HO
通讯作者：
Bertrand, HO
影响因子：
7.3
作者：
Mysinger, Michael M.;Carchia, Michael;Irwin, John. J.;Shoichet, Brian K.
通讯作者：
Shoichet, Brian K.