Devil in the Tail: A Multi-Modal Framework for Drug-Drug Interaction Prediction in Long Tail Distinction

TL;DR

This paper introduces TFDM, a multi-modal deep learning framework that combines various drug properties and a novel loss function to improve drug-drug interaction prediction, especially for rare, high-risk interactions in long-tailed datasets.

Contribution

The paper presents a novel multi-modal framework with Tailed Focal Loss to address long-tailed distribution challenges in DDI prediction, outperforming existing methods.

Findings

TFDM outperforms recent SOTA methods on long-tailed datasets.

The Tailed Focal Loss improves model performance on rare DDI categories.

Multi-modal feature fusion enhances DDI classification accuracy.

Abstract

Drug-drug interaction (DDI) identification is a crucial aspect of pharmacology research. There are many DDI types (hundreds), and they are not evenly distributed with equal chance to occur. Some of the rarely occurred DDI types are often high risk and could be life-critical if overlooked, exemplifying the long-tailed distribution problem. Existing models falter against this distribution challenge and overlook the multi-faceted nature of drugs in DDI prediction. In this paper, a novel multi-modal deep learning-based framework, namely TFDM, is introduced to leverage multiple properties of a drug to achieve DDI classification. The proposed framework fuses multimodal features of drugs, including graph-based, molecular structure, Target and Enzyme, for DDI identification. To tackle the challenge posed by the distribution skewness across categories, a novel loss function called Tailed Focal Loss is introduced, aimed at further enhancing the model performance and address gradient vanishing problem of focal loss in extremely long-tailed dataset. Intensive experiments over 4 challenging long-tailed dataset demonstrate that the TFMD outperforms the most recent SOTA methods in long-tailed DDI classification tasks. The source code is released to reproduce our experiment results: https://github.com/IcurasLW/TFMD_Longtailed_DDI.git