生物信息学
置信区间
缩放比例
预测区间
均方预测误差
计算机科学
统计
数学
生物
几何学
生物化学
基因
作者
Urban Fagerholm,Sven Hellberg,Jonathan Alvarsson,Staffan Arvidsson,Ola Spjuth
出处
期刊:Xenobiotica
[Informa]
日期:2021-12-02
卷期号:51 (12): 1366-1371
被引量:11
标识
DOI:10.1080/00498254.2021.2011471
摘要
Volume of distribution at steady state (Vss) is an important pharmacokinetic endpoint. In this study we apply machine learning and conformal prediction for human Vss prediction, and make a head-to-head comparison with rat-to-man scaling, allometric scaling and the Rodgers-Lukova method on combined in silico and in vitro data, using a test set of 105 compounds with experimentally observed Vss.The mean prediction error and % with <2-fold prediction error for our method were 2.4-fold and 64%, respectively. 69% of test compounds had an observed Vss within the prediction interval at a 70% confidence level. In comparison, 2.2-, 2.9- and 3.1-fold mean errors and 69, 64 and 61% of predictions with <2-fold error was reached with rat-to-man and allometric scaling and Rodgers-Lukova method, respectively.We conclude that our method has theoretically proven validity that was empirically confirmed, and showing predictive accuracy on par with animal models and superior to an alternative widely used in silico-based method. The option for the user to select the level of confidence in predictions offers better guidance on how to optimise Vss in drug discovery applications.
科研通智能强力驱动
Strongly Powered by AbleSci AI