Imperial College London
Alternate

DrKirillVeselkov

Faculty of Medicine, Department of Surgery & Cancer

Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 3899kirill.veselkov04

 
 
//

Location

 

Sir Alexander Fleming BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Gonzalez:2020,
author = {Gonzalez, G and Gong, S and Laponogov, I and Veselkov, K and Bronstein, M},
publisher = {arXiv},
title = {Graph attentional autoencoder for anticancer hyperfood prediction},
url = {http://arxiv.org/abs/2001.05724v1},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - Recent research efforts have shown the possibility to discover anticancerdrug-like molecules in food from their effect on protein-protein interactionnetworks, opening a potential pathway to disease-beating diet design. Weformulate this task as a graph classification problem on which graph neuralnetworks (GNNs) have achieved state-of-the-art results. However, GNNs aredifficult to train on sparse low-dimensional features according to ourempirical evidence. Here, we present graph augmented features, integratinggraph structural information and raw node attributes with varying ratios, toease the training of networks. We further introduce a novel neural networkarchitecture on graphs, the Graph Attentional Autoencoder (GAA) to predict foodcompounds with anticancer properties based on perturbed protein networks. Wedemonstrate that the method outperforms the baseline approach andstate-of-the-art graph classification models in this task.
AU  - Gonzalez,G
AU  - Gong,S
AU  - Laponogov,I
AU  - Veselkov,K
AU  - Bronstein,M
PB  - arXiv
PY  - 2020///
TI  - Graph attentional autoencoder for anticancer hyperfood prediction
UR  - http://arxiv.org/abs/2001.05724v1
UR  - http://hdl.handle.net/10044/1/76437
ER  -
Download