Papers › Learning Graph-Level Representation for Drug Discovery

Learning Graph-Level Representation for Drug Discovery

12 Sep 2017arXiv:1709.03741archive 2025-07-28

Junying Li, Deng Cai, Xiaofei 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. However, graph convolutional networks and other graph neural networks all focus on learning node-level representation rather than graph-level representation. Previous works simply sum all feature vectors for all nodes in the graph to obtain the graph feature vector for drug predication. In this paper, we introduce a dummy super node that is connected with all nodes in the graph by a directed edge as the representation of the graph and modify the graph operation to help the dummy super node learn graph-level feature. Thus, we can handle graph-level classification and regression in the same way as node-level classification and regression. In addition, we apply focal loss to address class imbalance in drug datasets. The experiments on MoleculeNet show that our method can effectively improve the performance of molecular properties predication.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

microljy/graph_level_drug_discovery officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AllDrug DiscoveryGeneral Classificationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Drug Discovery HIV dataset GraphConv + dummy super node + focal loss AUC 0.851 #1 of 5 Archive leaderboard report
Drug Discovery MUV GraphConv + dummy super node AUC 0.845 #2 of 5 Archive leaderboard report
Drug Discovery PCBA GraphConv + dummy super node AUC 0.867 #1 of 2 Archive leaderboard report
Drug Discovery Tox21 GraphConv + dummy super node AUC 0.854 #6 of 11 Archive leaderboard report
Drug Discovery ToxCast GraphConv + dummy super node AUC 0.768 #2 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Focal Loss

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections