Understanding active learning of molecular docking and its applications

TL;DR

This paper investigates how active learning models predict molecular docking scores using only 2D structures, assessing their effectiveness and limitations across multiple receptor targets in virtual screening.

Contribution

It provides a critical analysis of surrogate models' ability to predict docking scores without 3D structural features, highlighting their practical utility and memorization tendencies.

Findings

Surrogate models tend to memorize prevalent structural patterns.

Active learning models are useful in virtual screening for identifying actives.

Models perform well in large-scale screening scenarios.

Abstract

With the advancing capabilities of computational methodologies and resources, ultra-large-scale virtual screening via molecular docking has emerged as a prominent strategy for in silico hit discovery. Given the exhaustive nature of ultra-large-scale virtual screening, active learning methodologies have garnered attention as a means to mitigate computational cost through iterative small-scale docking and machine learning model training. While the efficacy of active learning methodologies has been empirically validated in extant literature, a critical investigation remains in how surrogate models can predict docking score without considering three-dimensional structural features, such as receptor conformation and binding poses. In this paper, we thus investigate how active learning methodologies effectively predict docking scores using only 2D structures and under what circumstances they may work particularly well through benchmark studies encompassing six receptor targets. Our findings suggest that surrogate models tend to memorize structural patterns prevalent in high docking scored compounds obtained during acquisition steps. Despite this tendency, surrogate models demonstrate utility in virtual screening, as exemplified in the identification of actives from DUD-E dataset and high docking-scored compounds from EnamineReal library, a significantly larger set than the initial screening pool. Our comprehensive analysis underscores the reliability and potential applicability of active learning methodologies in virtual screening campaigns.