MSc Thesis Defense: Similarity-Based Dual View Heterogenous Graph Neural Network Method for Drug Adverse Side Effect Prediction by Mayank Kumar

Friday, December 8, 2023 - 10:00

The School of Computer Science is pleased to present…

Similarity-Based Dual View Heterogenous Graph Neural Network Method for Drug Adverse Side Effect Prediction

MSc Thesis Defense by: Mayank Kumar


Date: Friday December 8, 2023

Time:  10:00 am – 12:00 pm

Location: Essex Hall, Room 105



Drug adverse side effects (ASEs) have substantial impacts on public health, health[1]care costs, and drug discovery processes. Hospital admissions and emergency department visits are frequently attributed to adverse drug reactions (ADRs), incurring significant expenses. Identification of ASEs during the drug discovery process can slow down and prevent many candidate molecules from being selected as commercial drugs. As medication usage continues to rise, effective management of drug side effects becomes increasingly crucial. Previous works have relied on extracting and utilizing single-perspective drug features such as chemical structure, and topological information, or combining associated information between drugs and other biomarkers using Knowledge Graphs. More recent works jointly learn and fuse drug representation from multiple perspectives – (microscopic) drug molecules feature and (macroscopic) over a heterogeneous network (created using a combination of various biological entity associations).

In this study, we propose a novel Similarity-based Dual View Heterogeneous Graph Neural Network (SDV-HGNN) that simultaneously learns microscopic/intra-view drug substructures features using its molecular graph representation and macroscopic/interview drug and side-effect features over a connectivity-enhanced Drug-Adverse Side Effect Network (DSN). We introduced four additional edges between drugs and three between side effects using multi-context-specific defined similarity metrics. Our ap[1]roach frames the problem as a binary classification task within the context of link prediction on a graph using a novel SDV-HGNN. We performed 10-fold cross-validation to show the superiority of our model and reported an AUC of 0.9173 ±0.0015, AUPR 0.9065 ± 0.0023, and F1 0.8416 ± 0.0028.


Thesis Committee:

Internal Reader: Dr. Jianguo Lu  

External Reader: Dr. Majid Ahmadi          

Advisor: Dr. Alioune Ngom

Chair:    Dr. Robin Gras

MSc Thesis Defense Announcement AI Logo