Pradeep Prachi, Povinelli Richard J, White Shannon, Merrill Stephen J
National Center for Computational Toxicology (ORISE Fellow), US EPA, Research Triangle Park, NC USA.
Electrical and Computer Engineering Department, Marquette University, Milwaukee, WI USA.
J Cheminform. 2016 Sep 22;8:48. doi: 10.1186/s13321-016-0164-0. eCollection 2016.
Quantitative structure activity relationships (QSARs) are theoretical models that relate a quantitative measure of chemical structure to a physical property or a biological effect. QSAR predictions can be used for chemical risk assessment for protection of human and environmental health, which makes them interesting to regulators, especially in the absence of experimental data. For compatibility with regulatory use, QSAR models should be transparent, reproducible and optimized to minimize the number of false negatives. In silico QSAR tools are gaining wide acceptance as a faster alternative to otherwise time-consuming clinical and animal testing methods. However, different QSAR tools often make conflicting predictions for a given chemical and may also vary in their predictive performance across different chemical datasets. In a regulatory context, conflicting predictions raise interpretation, validation and adequacy concerns. To address these concerns, ensemble learning techniques in the machine learning paradigm can be used to integrate predictions from multiple tools. By leveraging various underlying QSAR algorithms and training datasets, the resulting consensus prediction should yield better overall predictive ability. We present a novel ensemble QSAR model using Bayesian classification. The model allows for varying a cut-off parameter that allows for a selection in the desirable trade-off between model sensitivity and specificity. The predictive performance of the ensemble model is compared with four in silico tools (Toxtree, Lazar, OECD Toolbox, and Danish QSAR) to predict carcinogenicity for a dataset of air toxins (332 chemicals) and a subset of the gold carcinogenic potency database (480 chemicals). Leave-one-out cross validation results show that the ensemble model achieves the best trade-off between sensitivity and specificity (accuracy: 83.8 % and 80.4 %, and balanced accuracy: 80.6 % and 80.8 %) and highest inter-rater agreement [kappa (): 0.63 and 0.62] for both the datasets. The ROC curves demonstrate the utility of the cut-off feature in the predictive ability of the ensemble model. This feature provides an additional control to the regulators in grading a chemical based on the severity of the toxic endpoint under study.
定量构效关系（QSARs）是将化学结构的定量测量与物理性质或生物效应相关联的理论模型。QSAR预测可用于化学风险评估，以保护人类和环境健康，这使得它们对监管机构很有吸引力，尤其是在缺乏实验数据的情况下。为了与监管用途兼容，QSAR模型应具有透明度、可重复性，并进行优化以尽量减少假阴性的数量。计算机模拟QSAR工具作为耗时的临床和动物测试方法的更快替代方案正获得广泛认可。然而，不同的QSAR工具对于给定的化学物质往往会做出相互矛盾的预测，并且在不同化学数据集上的预测性能也可能有所不同。在监管背景下，相互矛盾的预测引发了对解释、验证和充分性的担忧。为了解决这些担忧，可以使用机器学习范式中的集成学习技术来整合来自多个工具的预测。通过利用各种潜在的QSAR算法和训练数据集，所得的共识预测应具有更好的整体预测能力。我们提出了一种使用贝叶斯分类的新型集成QSAR模型。该模型允许改变截止参数，从而可以在模型敏感性和特异性之间进行理想的权衡选择。将集成模型的预测性能与四种计算机模拟工具（Toxtree、Lazar、经合组织工具箱和丹麦QSAR）进行比较，以预测空气毒素数据集（332种化学物质）和黄金致癌潜力数据库子集（480种化学物质）的致癌性。留一法交叉验证结果表明，对于这两个数据集，集成模型在敏感性和特异性之间实现了最佳权衡（准确率：83.8%和80.4%，平衡准确率：80.6%和80.8%），并且具有最高的评分者间一致性[kappa（）：0.63和0.62]。ROC曲线证明了截止特征在集成模型预测能力中的效用。此特征为监管机构根据所研究的毒性终点的严重程度对化学物质进行分级提供了额外的控制。
