An interpretable molecular descriptor for machine learning predictions in atmospheric science

TL;DR

This paper introduces ATMOMACCS, an interpretable molecular descriptor tailored for atmospheric compounds, significantly improving machine learning predictions of key properties like vapor pressures and transition temperatures.

Contribution

The paper presents ATMOMACCS, a novel molecular descriptor combining MACCS keys with motifs inspired by SIMPOL, enhancing interpretability and prediction accuracy for atmospheric molecules.

Findings

Improved prediction accuracy for vapor pressures and phase transition properties.

Feature analysis reveals key molecular features governing properties.

Demonstrated generalizability across multiple datasets and properties.

Abstract

The study of aerosol formation and chemistry using machine learning is limited by the lack of molecular descriptors suited to atmospheric compounds. Interpretable models are particularly affected because they often rely on dictionary-based descriptors tied to specific molecular substructures, which currently fail to capture the full range of organic atmospheric compounds, including large, highly oxidized molecules common in the atmosphere. We introduce ATMOMACCS, an interpretable descriptor combining the 166 binary keys of the MACCS fingerprint with motifs inspired by the SIMPOL method for estimating saturation vapor pressures. We show that ATMOMACCS based models improve predictions of saturation vapor pressures (7-8 % error reduction), equilibrium partition coefficients (5 % and 9 % error reduction), glass transition temperatures (22 % error reduction), and enthalpy of vaporization (61 % error reduction) on four datasets with atmospheric compounds. Feature analysis shows that saturation vapor pressure and partition coefficients are governed by carbon number and oxygen-related features, whereas other phase-transition properties (e.g., enthalpy of vaporization, glass transition temperature) depend on carbon-hydrogen bond types and the presence of heteroatoms other than oxygen. This highlights the generalizability of ATMOMACCS across different datasets and properties as an interpretable molecular descriptor.