Convolutional Networks on Graphs for Learning Molecular Fingerprints

TL;DR

This paper presents a convolutional neural network designed to operate directly on molecular graphs, enabling end-to-end learning of molecular features that outperform traditional methods in interpretability and predictive accuracy.

Contribution

The authors introduce a novel graph convolutional network architecture that generalizes circular fingerprint methods for molecular feature extraction.

Findings

Data-driven features are more interpretable.

The method achieves better predictive performance.

It generalizes standard molecular fingerprint techniques.

Abstract

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints. We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.