Mitigating Molecular Aggregation in Drug Discovery With Predictive Insights From Explainable AI

Abstract Herein, we present the application of multi‐channel graph attention network (MEGAN), our explainable AI (xAI) model, for the identification of small colloidally aggregating molecules (SCAMs). This work offers solutions to the long‐standing problem of false positives caused by SCAMs in high‐throughput screening for drug discovery and demonstrates the power of xAI in the classification of molecular properties that are not chemically intuitive based on our current understanding. We leverage xAI insights and molecular counterfactuals to design alternatives to problematic compounds in drug screening libraries. Additionally, we experimentally validate the MEGAN prediction classification for one of the counterfactuals and demonstrate the utility of counterfactuals for altering the aggregation properties of a compound through minor structural modifications. The integration of this method in high‐throughput screening approaches will help combat and circumvent false positives, providing better lead molecules more rapidly and thus accelerating drug discovery cycles.