Predicting volume of distribution with decision tree-based regression methods using predicted tissue:plasma partition coefficients

Abstract

BackgroundVolume of distribution is an important pharmacokinetic property that indicates the extent of a drug’s distribution in the body tissues. This paper addresses the problem of how to estimate the apparent volume of distribution at steady state (Vss) of chemical compounds in the human body using decision tree-based regression methods from the area of data mining (or machine learning). Hence, the pros and cons of several different types of decision tree-based regression methods have been discussed. The regression methods predict Vss using, as predictive features, both the compounds’ molecular descriptors and the compounds’ tissue:plasma partition coefficients (Kt:p) – often used in physiologically-based pharmacokinetics. Therefore, this work has assessed whether the data mining-based prediction of Vss can be made more accurate by using as input not only the compounds’ molecular descriptors but also (a subset of) their predicted Kt:p values.ResultsComparison of the models that used only molecular descriptors, in particular, the Bagging decision tree (mean fold error of 2.33), with those employing predicted Kt:p values in addition to the molecular descriptors, such as the Bagging decision tree using adipose Kt:p (mean fold error of 2.29), indicated that the use of predicted Kt:p values as descriptors may be beneficial for accurate prediction of Vss using decision trees if prior feature selection is applied.ConclusionsDecision tree based models presented in this work have an accuracy that is reasonable and similar to the accuracy of reported Vss inter-species extrapolations in the literature. The estimation of Vss for new compounds in drug discovery will benefit from methods that are able to integrate large and varied sources of data and flexible non-linear data mining methods such as decision trees, which can produce interpretable models.Graphical AbstractDecision trees for the prediction of tissue partition coefficient and volume of distribution of drugs.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-015-0054-x) contains supplementary material, which is available to authorized users.

Machine learning for predicting lifespan-extending chemical compounds

“…Chemical molecular descriptors are calculated from the chemical structure and are normally used to build predictive models to study the relationship between a compound's chemical structure and its biological and pharmacokinetic properties such as drug distribution and absorption [ 25 , 26 ]. This paper is the first use of chemical molecular descriptors (as well as GO terms) to study the relationship between longevity and the chemical structure of compounds that may affect longevity.…”

Computational Exposure Science: An Emerging Discipline to Support 21st-Century Risk Assessment

“…Innovative modeling approaches are needed to understand relationships among data sources of varying complexity and quality and exposure-related factors, processes, and monitoring data. These approaches include machine-learning classification models, which have already proved to be well-suited for pharmacokinetic and hazard-related contexts ( Freitas et al 2015 ; Liu et al 2015 ; Zang et al 2013 ), and agent-based models, which provide a new opportunity to predict exposure-relevant behavior as a function of characteristics of individuals, their environments, and their interactions ( Luke and Stamatakis 2012 ).…”

Reliability of a decision‐tree model in predicting occupational lead poisoning in a group of highly exposed workers

“…Nevertheless, the DT model confirms the other analyses: that CBLI and AirPb are the most important variables in the prediction of OLP. Tree methods became a valuable tool in clinical and in vitro studies but a direct comparison between the predictive models reported is complicated by the differences in the datasets and types of regression methods used [Freitas et al, ].…”