English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Machine learning (ML) is a promising approach for predicting small moleculeproperties in drug discovery. Here, we provide a comprehensive overview ofvarious ML methods introduced for this purpose in recent years. We review awide range of properties, including binding affinities, solubility, and ADMET(Absorption, Distribution, Metabolism, Excretion, and Toxicity). We discussexisting popular datasets and molecular descriptors and embeddings, such aschemical fingerprints and graph-based neural networks. We highlight alsochallenges of predicting and optimizing multiple properties during hit-to-leadand lead optimization stages of drug discovery and explore briefly possiblemulti-objective optimization techniques that can be used to balance diverseproperties while optimizing lead candidates. Finally, techniques to provide anunderstanding of model predictions, especially for critical decision-making indrug discovery are assessed. Overall, this review provides insights into thelandscape of ML models for small molecule property predictions in drugdiscovery. So far, there are multiple diverse approaches, but theirperformances are often comparable. Neural networks, while more flexible, do notalways outperform simpler models. This shows that the availability ofhigh-quality training data remains crucial for training accurate models andthere is a need for standardized benchmarks, additional performance metrics,and best practices to enable richer comparisons between the differenttechniques and models that can shed a better light on the differences betweenthe many techniques.

Machine Learning Small Molecule Properties in Drug Discovery