Machine learning model predicts molecular properties using electron density
Electron-Density-Informed Molecular Property Prediction Using Surrogate Functionals
Machine Learning
Summary
Predicting how molecules behave usually requires heavy calculations that take a lot of time. The authors show that teaching a machine learning model to understand a molecule’s electron cloud helps it make better predictions. They also make sure the model respects certain physics rules, which makes it even more accurate. This approach works well on common chemical datasets and even for bigger molecules that the model hasn’t seen before.
What this means in practice
- •For computational chemists: Predict various extensive molecular properties more accurately and efficiently using machine learning models informed by electron density and surrogate functional constraints.
- •For drug discovery teams: Estimate chemical properties of new, larger molecules more reliably using models that generalize better across molecule sizes.
Authors
Manuel V. Klockow, Simon Wagner, Roman Remme, Dominic Plein, Fred A. Hamprecht
Abstract
Machine learning methods are increasingly used to predict chemical properties directly from the molecular structure to bypass the often prohibitive cost of quantum mechanical calculations. Recent work has shown that including the ground-state electron density as input to the machine learning model can improve accuracy in this setting. This work employs the recent surrogate functional framework originally developed for orbital-free density functional theory and extends it to predicting molecular properties. We show that passing the ground-state density as input to the model, while simultaneously enforcing it to be the minimum of the surrogate functional, surpasses state-of-the-art performance for six out of seven extensive properties of the QM9 dataset. Additionally, the approach shows improved generalization to larger molecules taken from the QM40 dataset. On all extensive properties of both datasets, our approach outperforms models that are informed by the ground-state density but do not enforce the surrogate functional constraints.