a School of Materials Science and Engineering , Shanghai University , Shanghai , China.
b School of Mechanical Engineering , Panzhihua University , Panzhihua , China.
Toxicol Mech Methods. 2018 Jul;28(6):440-449. doi: 10.1080/15376516.2018.1449278. Epub 2018 Apr 12.
For safely using the untested metal oxide nanoparticles (MONPs) in industrial and commercial applications, it is important to predict their potential toxicities quickly and efficiently. In this research, the quantitative structure-activity relationship (QSAR) model based on support vector regression (SVR) with a residual bootstrapping technique (BTSVR) was proposed to predict the toxicities of MONPs. It was found that the main features influencing the toxicities of MONPs were RA (atomic ratio of oxygen to metal), ΔH (enthalpy of melting), and E (cohesive energy). The QSPR model constructed was robust and self-explanatory in predicting the toxicities of MONPs with the coefficient of determination (R) of 0.87 and the root mean square error (RMSE) of 0.184 for the training sets, and R of 0.84 and RMSE of 0.217 for the testing sets, respectively. The performance of our model is much better than that published. Moreover, our model was validated by the external testing sets 1000 times. Therefore, it is expected that the method presented here can be used to construct powerful model in predicting the toxicities of MONPs untested or even unavailable.
为了安全地将未经测试的金属氧化物纳米粒子 (MONP) 应用于工业和商业领域，快速有效地预测其潜在毒性非常重要。在这项研究中，提出了一种基于支持向量回归 (SVR) 并带有残差自举技术 (BTSVR) 的定量构效关系 (QSAR) 模型，用于预测 MONP 的毒性。结果表明，影响 MONP 毒性的主要特征是 RA（氧与金属的原子比）、ΔH（熔化焓）和 E（内聚能）。所构建的 QSPR 模型在预测 MONP 的毒性方面具有稳健性和自解释性，其训练集的决定系数 (R) 为 0.87，均方根误差 (RMSE) 为 0.184，测试集的 R 为 0.84，RMSE 为 0.217。与已发表的模型相比，我们的模型性能要好得多。此外，我们的模型还通过了 1000 次外部测试集验证。因此，预计这里提出的方法可用于构建预测未测试甚至不可用的 MONP 毒性的强大模型。
