Computational methods for prediction of in vitro effects of new chemical structures.
Computational methods for prediction of in vitro effects of new chemical structures.
复制标题
DOI：
10.1186/s13321-016-0162-2
复制
发表时间：
2016
影响因子：
8.6
通讯作者：
Preissner R
中科院分区：
文献类型：
--
作者：
Banerjee P;Siramshetty VB;Drwal MN;Preissner R
随着每年合成的新化学品数量的不断增加，采用最可靠、最快速的硅筛选方法来预测它们的安全性和活性特征变得非常重要。近年来，计算机预测方法备受关注，试图减少动物实验，以评估各种毒理学终点，与替代、减少和细化的主题相辅相成。已经提出了各种计算方法来预测化合物毒性，从定量结构活性关系建模到基于分子相似性的方法和机器学习。在“21世纪的毒理学”筛选计划中，建立了一个众包平台，用于开发和验证计算模型，以预测化合物与核受体和应激反应途径的干扰，该模型基于包含10,000多种高通量筛选试验化合物的训练集。在这里，我们展示了各种基于分子相似性和基于机器学习的方法在包含647种化合物的独立评估集上的结果，这些评估集由2014年Tox21数据挑战赛提供。结果表明，基于MACCS分子指纹的随机森林方法和基于统计和文献分析选择的13个分子描述符子集在接收者工作特征曲线值下的面积方面表现最好。此外，我们比较了不同方法的单独和组合性能。回顾过去，我们还讨论了与单个方法相比，将相似搜索方法与随机森林算法相结合的集成方法性能优越的原因，同时解释了后者的内在局限性。我们的研究结果表明，尽管预测方法是针对每个建模目标单独优化的，但相似性和机器学习方法的集合提供了有希望的性能，表明其在毒性预测中的广泛适用性。本文的在线版本（doi:10.1186/s13321-016-0162-2）包含补充材料，可供授权用户使用。
With a constant increase in the number of new chemicals synthesized every year, it becomes important to employ the most reliable and fast in silico screening methods to predict their safety and activity profiles. In recent years, in silico prediction methods received great attention in an attempt to reduce animal experiments for the evaluation of various toxicological endpoints, complementing the theme of replace, reduce and refine. Various computational approaches have been proposed for the prediction of compound toxicity ranging from quantitative structure activity relationship modeling to molecular similarity-based methods and machine learning. Within the “Toxicology in the 21st Century” screening initiative, a crowd-sourcing platform was established for the development and validation of computational models to predict the interference of chemical compounds with nuclear receptor and stress response pathways based on a training set containing more than 10,000 compounds tested in high-throughput screening assays. Here, we present the results of various molecular similarity-based and machine-learning based methods over an independent evaluation set containing 647 compounds as provided by the Tox21 Data Challenge 2014. It was observed that the Random Forest approach based on MACCS molecular fingerprints and a subset of 13 molecular descriptors selected based on statistical and literature analysis performed best in terms of the area under the receiver operating characteristic curve values. Further, we compared the individual and combined performance of different methods. In retrospect, we also discuss the reasons behind the superior performance of an ensemble approach, combining a similarity search method with the Random Forest algorithm, compared to individual methods while explaining the intrinsic limitations of the latter. Our results suggest that, although prediction methods were optimized individually for each modelled target, an ensemble of similarity and machine-learning approaches provides promising performance indicating its broad applicability in toxicity prediction. The online version of this article (doi:10.1186/s13321-016-0162-2) contains supplementary material, which is available to authorized users.
登录
查看更多内容
DOI：
10.1080/10937404.2010.483176
发表时间：
2010-02
期刊：
Journal of toxicology and environmental health. Part B, Critical reviews
影响因子：
--
作者：
Krewski D;Acosta D Jr;Andersen M;Anderson H;Bailar JC 3rd;Boekelheide K;Brent R;Charnley G;Cheung VG;Green S Jr;Kelsey KT;Kerkvliet NI;Li AA;McCray L;Meyer O;Patterson RD;Pennie W;Scala RA;Solomon GM;Stephens M;Yager J;Zeise L
通讯作者：
Zeise L
影响因子：
6
作者：
Berthold, MR;Diamond, J
通讯作者：
Diamond, J
影响因子：
4.6
作者：
Huang, Ruili;Xia, Menghang;Simeonov, Anton
通讯作者：
Simeonov, Anton
影响因子：
4.6
作者：
Drwal, Malgorzata N.;Siramshetty, Vishal B.;Dunkel, Mathias
通讯作者：
Dunkel, Mathias
影响因子：
4.6
作者：
Mayr, Andreas;Klambauer, Gunter;Hochreiter, Sepp
通讯作者：
Hochreiter, Sepp