Machine learning with persistent homology and chemical word embeddings improves prediction accuracy and interpretability in metal-organic frameworks

TL;DR

This paper presents an end-to-end machine learning framework that combines persistent homology and word embeddings to automatically generate interpretable descriptors, significantly improving prediction accuracy and transferability in metal-organic frameworks.

Contribution

It introduces a novel approach that integrates topological data analysis and natural language processing techniques for materials property prediction.

Findings

25-30% reduction in prediction error (RMSE)

40-50% increase in R2 scores

Enhanced interpretability of pore-adsorption relationships

Abstract

Machine learning has emerged as a powerful approach in materials discovery. Its major challenge is selecting features that create interpretable representations of materials, useful across multiple prediction tasks. We introduce an end-to-end machine learning model that automatically generates descriptors that capture a complex representation of a material's structure and chemistry. This approach builds on computational topology techniques (namely, persistent homology) and word embeddings from natural language processing. It automatically encapsulates geometric and chemical information directly from the material system. We demonstrate our approach on multiple nanoporous metal-organic framework datasets by predicting methane and carbon dioxide adsorption across different conditions. Our results show considerable improvement in both accuracy and transferability across targets compared to models constructed from the commonly-used, manually-curated features, consistently achieving an average 25-30% decrease in root-mean-squared-deviation and an average increase of 40-50% in R2 scores. A key advantage of our approach is interpretability: Our model identifies the pores that correlate best to adsorption at different pressures, which contributes to understanding atomic-level structure--property relationships for materials design.