A biologically-inspired multi-modal evaluation of molecular generative machine learning

TL;DR

This paper introduces a biologically-inspired, multi-modal evaluation framework for molecular generative models that incorporates ligand-target interactions, providing more accurate assessments relevant to drug discovery.

Contribution

It proposes a novel benchmark with diverse datasets and metrics, including drug-target affinity and docking, emphasizing multi-modal evaluation for better biological relevance.

Findings

Multi-modal evaluation yields more reliable target binding insights.

Unimodal predictors may lead to misleading conclusions.

The framework enhances drug discovery by integrating physico-chemical knowledge.

Abstract

While generative models have recently become ubiquitous in many scientific areas, less attention has been paid to their evaluation. For molecular generative models, the state-of-the-art examines their output in isolation or in relation to its input. However, their biological and functional properties, such as ligand-target interaction is not being addressed. In this study, a novel biologically-inspired benchmark for the evaluation of molecular generative models is proposed. Specifically, three diverse reference datasets are designed and a set of metrics are introduced which are directly relevant to the drug discovery process. In particular we propose a recreation metric, apply drug-target affinity prediction and molecular docking as complementary techniques for the evaluation of generative outputs. While all three metrics show consistent results across the tested generative models, a more detailed comparison of drug-target affinity binding and molecular docking scores revealed that unimodal predictiors can lead to erroneous conclusions about target binding on a molecular level and a multi-modal approach is thus preferrable. The key advantage of this framework is that it incorporates prior physico-chemical domain knowledge into the benchmarking process by focusing explicitly on ligand-target interactions and thus creating a highly efficient tool not only for evaluating molecular generative outputs in particular, but also for enriching the drug discovery process in general.