Varadharajan Srinidhi, Winiwarter Susanne, Carlsson Lars, Engkvist Ola, Anantha Ajay, Kogej Thierry, Fridén Markus, Stålring Jonna, Chen Hongming
Department of Biology, Lund University, Lund, SE-22100, Sweden; Chemistry Innovation Centre, Discovery Sciences, AstraZeneca R&D Mölndal, Mölndal, SE-43183, Sweden.
J Pharm Sci. 2015 Mar;104(3):1197-206. doi: 10.1002/jps.24301. Epub 2014 Dec 24.
Recently, we built an in silico model to predict the unbound brain-to-plasma concentration ratio (Kp,uu,brain), a measure of the distribution of a compound between the blood plasma and the brain. Here, we validate the previous model with new additional data points expanding the chemical space and use that data also to renew the model. The model building process was similar to our previous approach; however, a new set of descriptors, molecular signatures, was included to facilitate the model interpretation from a structure perspective. The best consensus model shows better predictive power than the previous model (R(2) = 0.6 vs. R(2) = 0.53, when the same 99 compounds were used as test set). The two-class classification accuracy increased from 76% using the previous model to 81%. Furthermore, the atom-summarized gradient based on molecular signature descriptors was proposed as an interesting new approach to interpret the Kp,uu,brain machine learning model and scrutinize structure Kp,uu,brain relationships for investigated compounds.
最近，我们构建了一个计算机模拟模型，用于预测非结合脑血浓度比（Kp,uu,brain），这是衡量化合物在血浆和脑之间分布情况的一个指标。在此，我们用新增加的数据点验证了先前的模型，这些数据点扩展了化学空间，同时还用这些数据更新了模型。模型构建过程与我们之前的方法类似；不过，纳入了一组新的描述符——分子特征，以便从结构角度促进对模型的解释。最佳共识模型比先前的模型显示出更好的预测能力（当使用相同的99种化合物作为测试集时，R(2) = 0.6，而之前为R(2) = 0.53）。两类分类准确率从使用先前模型时的76%提高到了81%。此外，基于分子特征描述符提出了原子汇总梯度，作为解释Kp,uu,brain机器学习模型并仔细研究所研究化合物的结构与Kp,uu,brain关系的一种有趣的新方法。
