Learning Graph-Level Representation for Drug Discovery

12 Sep 2017Junying LiDeng CaiXiaofei He

Predicating macroscopic influences of drugs on human body, like efficacy and toxicity, is a central problem of small-molecule based drug discovery. Molecules can be represented as an undirected graph, and we can utilize graph convolution networks to predication molecular properties... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Drug Discovery HIV dataset GraphConv + dummy super node + focal loss AUC 0.851 # 1
Drug Discovery MUV GraphConv + dummy super node AUC 0.845 # 1
Drug Discovery PCBA GraphConv + dummy super node AUC 0.867 # 1
Drug Discovery Tox21 GraphConv + dummy super node AUC 0.854 # 3
Drug Discovery ToxCast GraphConv + dummy super node AUC 0.768 # 1