Relation-weighted Link Prediction for Disease Gene Identification
This work addresses the problem of identifying disease-associated genes for biomedical researchers and clinicians, with incremental improvements in performance.
The paper tackles disease gene identification by proposing a biomedical knowledge graph and a novel machine learning method, achieving a 24.1% improvement over the closest state-of-the-art competitor and higher precision than Open Targets in predicting drug targets for Parkinson's disease.
Identification of disease genes, which are a set of genes associated with a disease, plays an important role in understanding and curing diseases. In this paper, we present a biomedical knowledge graph designed specifically for this problem, propose a novel machine learning method that identifies disease genes on such graphs by leveraging recent advances in network biology and graph representation learning, study the effects of various relation types on prediction performance, and empirically demonstrate that our algorithms outperform its closest state-of-the-art competitor in disease gene identification by 24.1%. We also show that we achieve higher precision than Open Targets, the leading initiative for target identification, with respect to predicting drug targets in clinical trials for Parkinson's disease.