KGML-xDTD: A Knowledge Graph-based Machine Learning Framework for Drug Treatment Prediction and Mechanism Description

Abstract

Computational drug repurposing is a cost- and time-efficient method to identify new indications of approved or experimental drugs/compounds. It is especially critical for emerging and/or orphan diseases due to its cheaper investment and shorter research cycle compared with traditional wet-lab drug discovery approaches. However, the underlying mechanisms of action between repurposed drugs and their target diseases remain largely unknown, which is still an unsolved issue in existing repurposing methods. As such, computational drug repurposing has not been widely adopted in clinical settings. In this work, based on a massive biomedical knowledge graph, we propose a computational drug repurposing framework that not only predicts the treatment probabilities between drugs and diseases but also predicts the path-based, testable mechanisms of action (MOAs) as their biomedical explanations. Specifically, we utilize the GraphSAGE model in an unsupervised manner to integrate each entity's neighborhood information and employ a Random Forest model to predict the treatment probabilities between pairs of drugs and diseases. Moreover, we train an adversarial actor-critic reinforcement learning model to predict the potential MOA for explaining drug purposing. To encourage the model to find biologically reasonable paths, we utilize the curated molecular interactions of drugs and a PubMed-publication-based concept distance to extract potential drug MOA paths from the knowledge graph as "demonstration paths" to guide the model during the process of path-finding. Comprehensive experiments and case studies show that the proposed framework outperforms state-of-the-art baselines in both predictive performance of drug repurposing and explanatory performance of recapitulating human-curated DrugMechDB-based paths.

Drug Repurposing Using Knowledge Graph Embeddings with a Focus on Vector-Borne Diseases: A Model Comparison

“…Some of the most popular translation-based embedding models used for drug repurposing include (i)TransE [31], which embeds entities and relations in the same vector space, and variants like (ii)TransH and (iii)TransR [13], designed to differently project entities depending on each relation type, meaning that they assign an entity with different representations when involved in various relation types.…”

Explainable drug repurposing via path-based knowledge graph completion

“…Other researches develop hybrid architectures that make predictions based on embeddings or other non-interpretable methods and apply some technique to provide explanations [17]- [20]. In [11], KGML-xDTD is developed to predict repurposing candidates using embedding methods and random forest. Then, the model includes an actor-critic reinforcement learning approach to find paths between the drugs and the diseases that could explain the predictions.…”