SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations

TL;DR

SafeDrug is a novel drug recommendation model that explicitly incorporates drug molecular structures and controls drug-drug interactions, leading to safer and more effective medication suggestions with improved accuracy and efficiency.

Contribution

The paper introduces SafeDrug, a dual-encoder model utilizing molecular graph encoders and a controllable loss to explicitly model DDIs and improve drug recommendation quality.

Findings

Reduces DDI by 19.43% compared to previous methods.

Improves recommendation accuracy with a 2.88% increase in Jaccard similarity.

Requires fewer parameters, speeding up training and inference.

Abstract

Medication recommendation is an essential task of AI for healthcare. Existing works focused on recommending drug combinations for patients with complex health conditions solely based on their electronic health records. Thus, they have the following limitations: (1) some important data such as drug molecule structures have not been utilized in the recommendation process. (2) drug-drug interactions (DDI) are modeled implicitly, which can lead to sub-optimal results. To address these limitations, we propose a DDI-controllable drug recommendation model named SafeDrug to leverage drugs' molecule structures and model DDIs explicitly. SafeDrug is equipped with a global message passing neural network (MPNN) module and a local bipartite learning module to fully encode the connectivity and functionality of drug molecules. SafeDrug also has a controllable loss function to control DDI levels in the recommended drug combinations effectively. On a benchmark dataset, our SafeDrug is relatively shown to reduce DDI by 19.43% and improves 2.88% on Jaccard similarity between recommended and actually prescribed drug combinations over previous approaches. Moreover, SafeDrug also requires much fewer parameters than previous deep learning-based approaches, leading to faster training by about 14% and around 2x speed-up in inference.