Machine Learning Small Molecule Properties in Drug Discovery

TL;DR

This paper reviews machine learning methods for predicting small molecule properties in drug discovery, highlighting datasets, models, challenges, and the need for standardized benchmarks to improve model comparison and performance.

Contribution

It provides a comprehensive overview of recent ML approaches, datasets, and challenges in predicting small molecule properties, emphasizing the importance of data quality and benchmarking.

Findings

Multiple ML approaches have similar performance levels.

Neural networks do not always outperform simpler models.

High-quality data is crucial for accurate predictions.

Abstract

Machine learning (ML) is a promising approach for predicting small molecule properties in drug discovery. Here, we provide a comprehensive overview of various ML methods introduced for this purpose in recent years. We review a wide range of properties, including binding affinities, solubility, and ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity). We discuss existing popular datasets and molecular descriptors and embeddings, such as chemical fingerprints and graph-based neural networks. We highlight also challenges of predicting and optimizing multiple properties during hit-to-lead and lead optimization stages of drug discovery and explore briefly possible multi-objective optimization techniques that can be used to balance diverse properties while optimizing lead candidates. Finally, techniques to provide an understanding of model predictions, especially for critical decision-making in drug discovery are assessed. Overall, this review provides insights into the landscape of ML models for small molecule property predictions in drug discovery. So far, there are multiple diverse approaches, but their performances are often comparable. Neural networks, while more flexible, do not always outperform simpler models. This shows that the availability of high-quality training data remains crucial for training accurate models and there is a need for standardized benchmarks, additional performance metrics, and best practices to enable richer comparisons between the different techniques and models that can shed a better light on the differences between the many techniques.