Comparing Machine Learning Algorithms for Predicting Drug-Induced Liver Injury (DILI).
Comparing Machine Learning Algorithms for Predicting Drug-Induced Liver Injury (DILI).
复制标题
比较机器学习算法预测药物性肝损伤(DILI)
DOI：
10.1021/acs.molpharmaceut.0c00326
复制
发表时间：
2020-07-06
影响因子：
4.9
通讯作者：
Ekins S
中科院分区：
文献类型：
--
作者：
Minerali E;Foil DH;Zorn KM;Lane TR;Ekins S
药物性肝损伤（DILI）是人类对外源性药物最不可预测的不良反应之一，也是已批准药物上市后撤销的主要原因。迄今为止，这些药物已由FDA整理形成DILIRank数据库，该数据库对DILI的严重程度和潜力进行分类。这些分类已被不同的研究小组用于对这种类型的肝损伤进行计算预测。最近，辉瑞（Pfizer）和阿斯利康（AstraZeneca）的研究小组整理了DILI的体外数据和化合物的理化性质，这些数据可以与FDA的数据一起用于构建DILI的机器学习模型。在本研究中，我们使用这些数据集以及生物制药药物处置分类系统数据集，使用我们的内部软件Assay Central™生成贝叶斯机器学习模型。所有机器学习模型的性能通过内部五倍交叉验证指标和具有已知肝毒性的化合物的外部测试集的预测准确性进行评估。表现最好的贝叶斯模型是基于DILIRank数据库中的DILI-concern类别，其ROC为0.814，灵敏度为0.741，特异性为0.755，准确率为0.746。与其他机器学习算法（如k-Nearest Neighbors、支持向量分类、AdaBoosted决策树和深度学习）的比较产生的统计数据与在Assay Central™中使用贝叶斯算法生成的统计数据相似。这项研究展示了在一个名为MegaTox™的工具中分组的机器学习模型，该工具可用于预测早期临床化合物以及最近FDA批准的药物，以识别潜在的DILI。
Drug-Induced Liver Injury (DILI) is one the most unpredictable adverse reactions to xenobiotics in humans and the leading cause of post-marketing withdrawals of approved drugs. To date, these drugs have been collated by the FDA to form the DILIRank database, which classifies DILI severity and potential. These classifications have been used by various research groups in generating computational predictions for this type of liver injury. Recently, groups from Pfizer and AstraZeneca have collated DILI in vitro data and physicochemical properties for compounds that can be used along with data from the FDA to build machine learning models for DILI. In this study, we have used these datasets, as well as the Biopharmaceutics Drug Disposition Classification System dataset, to generate Bayesian machine learning models with our in-house software, Assay Central™. The performance of all machine learning models was assessed through both internal five-fold cross-validation metrics, and prediction accuracy of an external test set of compounds with known hepatotoxicity. The best performing Bayesian model was based on the DILI-concern category from the DILIRank database with an ROC of 0.814, sensitivity of 0.741, specificity of 0.755, and accuracy of 0.746. A comparison of alternative machine learning algorithms, such as k-Nearest Neighbors, support vector classification, AdaBoosted decision trees, and deep learning produced similar statistics to those generated with the Bayesian algorithm in Assay Central™. This study demonstrates machine learning models grouped in a tool called MegaTox™ that can be used to predict early stage clinical compounds, as well as recent FDA approved drugs, to identify potential DILI.
登录
查看更多内容
影响因子：
4.5
作者：
Benet, Leslie Z.;Broccatelli, Fabio;Oprea, Tudor I.
通讯作者：
Oprea, Tudor I.
影响因子：
3
作者：
Kim E;Nam H
通讯作者：
Nam H
影响因子：
4.9
作者：
Lane T;Russo DP;Zorn KM;Clark AM;Korotcov A;Tkachenko V;Reynolds RC;Perryman AL;Freundlich JS;Ekins S
通讯作者：
Ekins S
影响因子：
5.6
作者：
Clark, Alex M.;Ekins, Sean
通讯作者：
Ekins, Sean
影响因子：
5.6
作者：
He, Shuaibing;Ye, Tianyuan;Sun, Xiaobo
通讯作者：
Sun, Xiaobo