Rothfuss Andreas, Steger-Hartmann Thomas, Heinrich Nikolaus, Wichard Jörg
Experimental Toxicology, Schering AG, D-13342 Berlin, Germany.
Chem Res Toxicol. 2006 Oct;19(10):1313-9. doi: 10.1021/tx060136w.
We report on the generation of computer-based models for the prediction of the chromosome-damaging potential of chemicals as assessed in the in vitro chromosome aberration (CA) test. On the basis of publicly available CA-test results of more than 650 chemical substances, half of which are drug-like compounds, we generated two different computational models. The first model was realized using the (Q)SAR tool MCASE. Results obtained with this model indicate a limited performance (53%) for the assessment of a chromosome-damaging potential (sensitivity), whereas CA-test negative compounds were correctly predicted with a specificity of 75%. The low sensitivity of this model might be explained by the fact that the underlying 2D-structural descriptors only describe part of the molecular mechanism leading to the induction of chromosome aberrations, that is, direct drug-DNA interactions. The second model was constructed with a more sophisticated machine learning approach and generated a classification model based on 14 molecular descriptors, which were obtained after feature selection. The performance of this model was superior to the MCASE model, primarily because of an improved sensitivity, suggesting that the more complex molecular descriptors in combination with statistical learning approaches are better suited to model the complex nature of mechanisms leading to a positive effect in the CA-test. An analysis of misclassified pharmaceuticals by this model showed that a large part of the false-negative predicted compounds were uniquely positive in the CA-test but lacked a genotoxic potential in other mutagenicity tests of the regulatory testing battery, suggesting that biologically nonsignificant mechanisms could be responsible for the observed positive CA-test result. Since such mechanisms are not amenable to modeling approaches it is suggested that a positive prediction made by the model reflects a biologically significant genotoxic potential. An integration of the machine-learning model as a screening tool in early discovery phases of drug development is proposed.
我们报告了基于计算机模型的生成情况，该模型用于预测化学物质在体外染色体畸变（CA）试验中评估的染色体损伤潜力。基于650多种化学物质的公开CA试验结果，其中一半是类药物化合物，我们生成了两种不同的计算模型。第一个模型使用（Q）SAR工具MC ASE实现。用该模型获得的结果表明，在评估染色体损伤潜力（敏感性）方面性能有限（53%），而CA试验阴性化合物的预测特异性为75%。该模型敏感性较低可能是因为基础的二维结构描述符仅描述了导致染色体畸变诱导的部分分子机制，即直接的药物 - DNA相互作用。第二个模型采用了更复杂的机器学习方法构建，并基于14个分子描述符生成了一个分类模型，这些描述符是在特征选择后获得的。该模型的性能优于MC ASE模型，主要是因为敏感性提高，这表明更复杂的分子描述符与统计学习方法相结合更适合模拟导致CA试验阳性结果的复杂机制性质。对该模型误分类药物的分析表明，大部分假阴性预测化合物在CA试验中唯一呈阳性，但在监管测试电池的其他致突变性试验中缺乏遗传毒性潜力，这表明生物学上无意义的机制可能是观察到的CA试验阳性结果的原因。由于这种机制不适合建模方法，因此建议该模型的阳性预测反映了生物学上显著的遗传毒性潜力。建议将机器学习模型作为筛选工具整合到药物开发的早期发现阶段。
