Convolutional Networks on Graphs for Learning Molecular Fingerprints
2015-09-30NeurIPS 2015Code Available0· sign in to hype
David Duvenaud, Dougal Maclaurin, Jorge Aguilera-Iparraguirre, Rafael Gómez-Bombarelli, Timothy Hirzel, Alán Aspuru-Guzik, Ryan P. Adams
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/HIPS/neural-fingerprintOfficialIn papertf★ 0
- github.com/SystemicCypher/Neural-Molecule-Fingerprintstf★ 0
- github.com/kimisyo/simple-GCNpytorch★ 0
- github.com/nrel/m2pnone★ 0
- github.com/pgniewko/solubilitynone★ 0
- github.com/debbiemarkslab/neural-fingerprint-theanonone★ 0
- github.com/onakanob/Peptide_Graph_Autogradnone★ 0
- github.com/Sarikaya-Lab-GEMSEC/Peptide_Graph_Autogradnone★ 0
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| HIV dataset | GraphConv | AUC | 0.82 | — | Unverified |
| MUV | GraphConv | AUC | 0.84 | — | Unverified |
| PCBA | GraphConv | AUC | 0.86 | — | Unverified |
| Tox21 | GraphConv | AUC | 0.85 | — | Unverified |
| ToxCast | GraphConv | AUC | 0.75 | — | Unverified |