The impact of conformer quality on learned representations of molecular conformer ensembles

TL;DR

This paper investigates how the quality of 3D conformers influences the accuracy of machine learning models predicting molecular properties, highlighting the importance of conformer fidelity in 3D representation learning.

Contribution

It provides an analysis of the impact of conformer quality on surrogate model performance for predicting properties of molecular ensembles, offering practical insights for 3D structure-based modeling.

Findings

Lower-quality conformers can still inform property predictions effectively.

Fidelity of geometry optimization affects model accuracy significantly.

Presence of active conformers influences the predictive performance.

Abstract

Training machine learning models to predict properties of molecular conformer ensembles is an increasingly popular strategy to accelerate the conformational analysis of drug-like small molecules, reactive organic substrates, and homogeneous catalysts. For high-throughput analyses especially, trained surrogate models can help circumvent traditional approaches to conformational analysis that rely on expensive conformer searches and geometry optimizations. Here, we question how the performance of surrogate models for predicting 3D conformer-dependent properties (of a single, active conformer) is affected by the quality of the 3D conformers used as their input. How well do lower-quality conformers inform the prediction of properties of higher-quality conformers? Does the fidelity of geometry optimization matter when encoding random conformers? For models that encode sets of conformers, how does the presence of the active conformer that induces the target property affect model accuracy? How do predictions from a surrogate model compare to estimating the properties from cheap ensembles themselves? We explore these questions in the context of predicting Sterimol parameters of conformer ensembles optimized with density functional theory. Although answers will be case-specific, our analyses provide a valuable perspective on 3D representation learning models and raise practical considerations regarding when conformer quality matters.