CheMixHub: Datasets and Benchmarks for Chemical Mixture Property Prediction

TL;DR

CheMixHub provides a comprehensive benchmark dataset and evaluation framework for predicting properties of chemical mixtures, aiming to advance machine learning models in this underexplored area of chemical research.

Contribution

The paper introduces CheMixHub, a new benchmark dataset with diverse tasks and data splitting techniques, establishing initial deep learning benchmarks for chemical mixture property prediction.

Findings

Established baseline results for multiple chemical mixture prediction tasks.

Demonstrated the effectiveness of different data splitting methods for model evaluation.

Provided a publicly available dataset and code to facilitate future research.

Abstract

Developing improved predictive models for multi-molecular systems is crucial, as nearly every chemical product used results from a mixture of chemicals. While being a vital part of the industry pipeline, the chemical mixture space remains relatively unexplored by the Machine Learning community. In this paper, we introduce CheMixHub, a holistic benchmark for molecular mixtures, covering a corpus of 11 chemical mixtures property prediction tasks, from drug delivery formulations to battery electrolytes, totalling approximately 500k data points gathered and curated from 7 publicly available datasets. CheMixHub introduces various data splitting techniques to assess context-specific generalization and model robustness, providing a foundation for the development of predictive models for chemical mixture properties. Furthermore, we map out the modelling space of deep learning models for chemical mixtures, establishing initial benchmarks for the community. This dataset has the potential to accelerate chemical mixture development, encompassing reformulation, optimization, and discovery. The dataset and code for the benchmarks can be found at: https://github.com/chemcognition-lab/chemixhub