Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning

Yaqing Wang, Zaifei Yang, Quanming Yao

TL;DR

The tool, named KnowDDI, can predict which drugs interact with each other and also provide an explanation for why the interaction is likely to take place and it was demonstrated that the tool can identify known drug interactions.

Abstract

Background: Discovering potential drug-drug interactions (DDIs) is a long-standing challenge in clinical treatments and drug developments. Recently, deep learning techniques have been developed for DDI prediction. However, they generally require a huge number of samples, while known DDIs are rare. Methods: In this work, we present KnowDDI, a graph neural network-based method that addresses the above challenge. KnowDDI enhances drug representations by adaptively leveraging rich neighborhood information from large biomedical knowledge graphs. Then, it learns a knowledge subgraph for each drug-pair to interpret the predicted DDI, where each of the edges is associated with a connection strength indicating the importance of a known DDI or resembling strength between a drug-pair whose connection is unknown. Thus, the lack of DDIs is implicitly compensated by the enriched drug representations and propagated drug similarities. Results: We evaluate KnowDDI on two benchmark DDI datasets. Results show that KnowDDI obtains the state-of-the-art prediction performance with better interpretability. We also find that KnowDDI suffers less than existing works given a sparser knowledge graph. This indicates that the propagated drug similarities play a more important role in compensating for the lack of DDIs when the drug representations are less enriched. Conclusions: KnowDDI nicely combines the efficiency of deep learning techniques and the rich prior knowledge in biomedical knowledge graphs. As an original open-source tool, KnowDDI can help detect possible interactions in a broad range of relevant interaction prediction tasks, such as protein-protein interactions, drug-target interactions and disease-gene interactions, eventually promoting the development of biomedicine and healthcare.

Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning

TL;DR

The tool, named KnowDDI, can predict which drugs interact with each other and also provide an explanation for why the interaction is likely to take place and it was demonstrated that the tool can identify known drug interactions.

Abstract

Background: Discovering potential drug-drug interactions (DDIs) is a long-standing challenge in clinical treatments and drug developments. Recently, deep learning techniques have been developed for DDI prediction. However, they generally require a huge number of samples, while known DDIs are rare. Methods: In this work, we present KnowDDI, a graph neural network-based method that addresses the above challenge. KnowDDI enhances drug representations by adaptively leveraging rich neighborhood information from large biomedical knowledge graphs. Then, it learns a knowledge subgraph for each drug-pair to interpret the predicted DDI, where each of the edges is associated with a connection strength indicating the importance of a known DDI or resembling strength between a drug-pair whose connection is unknown. Thus, the lack of DDIs is implicitly compensated by the enriched drug representations and propagated drug similarities. Results: We evaluate KnowDDI on two benchmark DDI datasets. Results show that KnowDDI obtains the state-of-the-art prediction performance with better interpretability. We also find that KnowDDI suffers less than existing works given a sparser knowledge graph. This indicates that the propagated drug similarities play a more important role in compensating for the lack of DDIs when the drug representations are less enriched. Conclusions: KnowDDI nicely combines the efficiency of deep learning techniques and the rich prior knowledge in biomedical knowledge graphs. As an original open-source tool, KnowDDI can help detect possible interactions in a broad range of relevant interaction prediction tasks, such as protein-protein interactions, drug-target interactions and disease-gene interactions, eventually promoting the development of biomedicine and healthcare.
Paper Structure (31 sections, 14 equations, 4 figures, 2 tables)

This paper contains 31 sections, 14 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Results
  4. Discussion
  5. Data availability
  6. Code availability
  7. Acknowledgment
  8. Author contributions
  9. Competing interests
  10. Tables
  11. Figures

Figures (4)

  • Figure 1: Overview of KnowDDI.
  • Figure 2: A closer examination and comparison of KnowDDI with SumGNN, SkipGNN and KnowDDI (w/o resemble).
  • Figure 3: Comparing different subgraphs extraction strategy.
  • Figure 4: T-SNE visualization of drug-pair embeddings, where the four graphs share the same relations (n=10) and drug-pairs (for each relation, n=50).