Predicting drug properties with parameter-free machine learning: Pareto-Optimal Embedded Modeling (POEM)
This addresses the need for a generally applicable method in medicinal chemistry to reduce trial-and-error in model selection, though it appears incremental as it builds on similarity-based approaches.
The paper tackles the problem of predicting ADMET properties of small molecules in drug discovery by introducing POEM, a parameter-free similarity-based method that combines multiple molecular representations to achieve reliable performance across 17 classification tasks without tuning.
The prediction of absorption, distribution, metabolism, excretion, and toxicity (ADMET) of small molecules from their molecular structure is a central problem in medicinal chemistry with great practical importance in drug discovery. Creating predictive models conventionally requires substantial trial-and-error for the selection of molecular representations, machine learning (ML) algorithms, and hyperparameter tuning. A generally applicable method that performs well on all datasets without tuning would be of great value but is currently lacking. Here, we describe Pareto-Optimal Embedded Modeling (POEM), a similarity-based method for predicting molecular properties. POEM is a non-parametric, supervised ML algorithm developed to generate reliable predictive models without need for optimization. POEMs predictive strength is obtained by combining multiple different representations of molecular structures in a context-specific manner, while maintaining low dimensionality. We benchmark POEM relative to industry-standard ML algorithms and published results across 17 classifications tasks. POEM performs well in all cases and reduces the risk of overfitting.