FragNet: A Graph Neural Network for Molecular Property Prediction with Four Levels of Interpretability

TL;DR

FragNet is a graph neural network that predicts molecular properties with high accuracy and offers four levels of interpretability, revealing important substructures and connections in molecules.

Contribution

Introduces a GNN model that achieves state-of-the-art accuracy while providing multi-level interpretability of molecular features and connections.

Findings

Matches leading models in prediction accuracy

Provides insights into atom, bond, fragment, and connection importance

Quantifies the impact of fragments on molecular properties

Abstract

Molecular property prediction is essential in a variety of contemporary scientific fields, such as drug development and designing energy storage materials. Although there are many machine learning models available for this purpose, those that achieve high accuracy while also offering interpretability of predictions are uncommon. We present a graph neural network that not only matches the prediction accuracies of leading models but also provides insights on four levels of molecular substructures. This model helps identify which atoms, bonds, molecular fragments, and connections between fragments are significant for predicting a specific molecular property. Understanding the importance of connections between fragments is particularly valuable for molecules with substructures that do not connect through standard bonds. The model additionally can quantify the impact of specific fragments on the prediction, allowing the identification of fragments that may improve or degrade a property value. These interpretable features are essential for deriving scientific insights from the model's learned relationships between molecular structures and properties.