Low cost prediction of probability distributions of molecular properties for early virtual screening

TL;DR

This paper introduces a cost-effective method for predicting probability distributions of molecular properties, enhancing virtual screening by estimating uncertainties and key structural features for drug design.

Contribution

It applies Hierarchical Correlation Reconstruction to predict full distributions of molecular properties, improving upon traditional value prediction methods in drug discovery.

Findings

Effective identification of molecules with desired property ranges

Detection of structural features influencing properties

Facilitation of compound rejection and optimization

Abstract

While there is a general focus on predictions of values, mathematically more appropriate is prediction of probability distributions: with additional possibilities like prediction of uncertainty, higher moments and quantiles. For the purpose of the computer-aided drug design field, this article applies Hierarchical Correlation Reconstruction approach, previously applied in the analysis of demographic, financial and astronomical data. Instead of a single linear regression to predict values, it uses multiple linear regressions to independently predict multiple moments, finally combining them into predicted probability distribution, here of several ADMET properties based on substructural fingerprint developed by Klekota\&Roth. Discussed application example is inexpensive selection of a percentage of molecules with properties nearly certain to be in a predicted or chosen range during virtual screening. Such an approach can facilitate the interpretation of the results as the predictions characterized by high rate of uncertainty are automatically detected. In addition, for each of the investigated predictive problems, we detected crucial structural features, which should be carefully considered when optimizing compounds towards particular property. The whole methodology developed in the study constitutes therefore a great support for medicinal chemists, as it enable fast rejection of compounds with the lowest potential of desired physicochemical/ADMET characteristic and guides the compound optimization process.