Convolutional Networks on Graphs for Learning Molecular Fingerprints

David Duvenaud, Dougal Maclaurin, Jorge Aguilera-Iparraguirre, Rafael Gómez-Bombarelli, Timothy Hirzel, Alán Aspuru-Guzik, Ryan P. Adams

2015-09-30NeurIPS 2015 12Drug Discovery Graph Regression Node Classification

Paper PDF Code Code Code Code Code Code(official)Code Code

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.

Results

Task	Dataset	Metric	Value	Model
Drug Discovery	Tox21	AUC	0.846	GraphConv
Drug Discovery	HIV dataset	AUC	0.822	GraphConv
Drug Discovery	ToxCast	AUC	0.754	GraphConv
Drug Discovery	MUV	AUC	0.836	GraphConv
Drug Discovery	PCBA	AUC	0.855	GraphConv
Graph Regression	Lipophilicity	RMSE	0.655	GC

Related Papers

Assay2Mol: large language model-based drug design using BioAssay context2025-07-16 A Graph-in-Graph Learning Framework for Drug-Target Interaction Prediction2025-07-15 Graph Learning2025-07-08 Exploring Modularity of Agentic Systems for Drug Discovery2025-06-27 Diverse Mini-Batch Selection in Reinforcement Learning for Efficient Chemical Exploration in de novo Drug Design2025-06-26 Large Language Model Agent for Modular Task Execution in Drug Discovery2025-06-26 Demystifying Distributed Training of Graph Neural Networks for Link Prediction2025-06-25 PocketVina Enables Scalable and Highly Accurate Physically Valid Docking through Multi-Pocket Conditioning2025-06-24