Helma Christoph, Schöning Verena, Drewe Jürgen, Boss Philipp
In Silico Toxicology Gmbh, Basel, Switzerland.
Clinical Pharmacology and Toxicology, Department of General Internal Medicine, University Hospital Bern, University of Bern, Inselspital, Bern, Switzerland.
Front Pharmacol. 2021 Jul 22;12:708050. doi: 10.3389/fphar.2021.708050. eCollection 2021.
Random forest, support vector machine, logistic regression, neural networks and k-nearest neighbor (lazar) algorithms, were applied to a new mutagenicity dataset with 8,290 unique chemical structures utilizing MolPrint2D and Chemistry Development Kit (CDK) descriptors. Crossvalidation accuracies of all investigated models ranged from 80 to 85% which is comparable with the interlaboratory variability of the mutagenicity assay. Pyrrolizidine alkaloid predictions showed a clear distinction between chemical groups, where otonecines had the highest proportion of positive mutagenicity predictions and monoesters the lowest.
随机森林、支持向量机、逻辑回归、神经网络和k近邻（拉扎尔）算法，被应用于一个新的致突变性数据集，该数据集包含8290个独特的化学结构，利用MolPrint2D和化学开发工具包（CDK）描述符。所有研究模型的交叉验证准确率在80%至85%之间，这与致突变性试验的实验室间变异性相当。吡咯里西啶生物碱预测显示出化学基团之间的明显区别，其中耳毒素的阳性致突变性预测比例最高，单酯的比例最低。
Zotero 插件
