| 引用本文: | 胡笑文,赵文慧,张才煜,陈华.基于分子指纹构建细菌回复突变预测模型[J].中国现代应用药学,2024,41(22):61-65. |
| Hu Xiao Wen,Zhao Wen Hui,Zhang Cai Yu,Chen Hua.Construction of A Bacterial Mutagenicity Prediction model based on molecular fingerprints[J].Chin J Mod Appl Pharm(中国现代应用药学),2024,41(22):61-65. |
|
| 摘要: |
| 目的 本研究旨在构建一个精准的致细菌回复突变性预测模型，用于评估药物及其杂质的致突变性。方法 从文献中收集细菌回复突变数据，按4:1随机分割为训练集和测试集。采用扩展连通性指纹作为化合物特征，在训练集上优化指纹和算法参数，建立QSAR模型。根据调参结果，选择最优的参数进行建模，并对测试集数据进行预测。通过比较预测结果与真实值，验证模型的预测能力。结果 从文献中共计收集得到8329条细菌回复突变性数据。对扩展连通性指纹参数优化，得到了较好的指纹参数。采用最佳参数生成特征，继续对支持向量机参数进行优化。当gamma=0.001，C=2.15，模型表现最佳。最佳模型在测试集上的准确率、精确率、召回率和受试者工作曲线的线下面积分别为：0.788、0.783、0.846和0.855。结论 通过优化分子指纹参数和算法参数，成功构建了一套细菌回复突变性预测模型。该方法有望为快速筛选潜在基因毒性杂质提供技术支持。 |
| 关键词: 遗传毒性 杂质 构效关系 分子指纹 评估方法 |
| DOI： |
| 分类号:R917 |
| 基金项目: |
|
| Construction of A Bacterial Mutagenicity Prediction model based on molecular fingerprints |
|
Hu Xiao Wen1, Zhao Wen Hui2, Zhang Cai Yu1, Chen Hua1
|
|
1.National Institutes for Food and Drug Control;2.China Pharmaceutical University
|
| Abstract: |
| OBJECTIVE To develop a model for bacterial mutagenicity prediction, which can be used to assess the genotoxic potential of drugs and their impurities. METHODS Bacterial mutagenicity data were collected from the literature and randomly split into training and testing sets at a ratio of 4:1. Extended connectivity fingerprints were used as compound features, and fingerprint and algorithm parameters were optimized on the training set to establish a QSAR model. Based on the parameter tuning results, the optimal parameters were selected for modeling. Predicted results of the test data were obtained. The predictive ability of the model was validated by comparing the predicted results with the true values. RESULTS A total of 8329 bacterial mutagenicity data were collected from the literature. The parameters of extended connectivity fingerprint were optimized, and a set of superior parameters were obtained. The best parameters were used to generate features, which were employed to construct models by using support vector machine. The model performed best when gamma was 0.001 and C was 2.15. The accuracy, precision, recall, and area under the receiver operating characteristic curve of the optimal model on the test set were 0.788, 0.783, 0.846, and 0.855, respectively. CONCLUSION We have successfully constructed an bacterial mutagenicity prediction model, which holds promise for facilitating the rapid screening of potential genotoxic impurities. |
| Key words: genotoxicity impurities structure activity relationship molecular fingerprints evaluation method |
