A Triple-Modal Contrastive Learning Framework with Sequence, Graph, and 3D Features for Drug-Target Interaction Prediction

2026-05-28

AI Summary

Existing methods for drug–target interaction (DTI) prediction are largely confined to unimodal or bimodal representations and often neglect critical three-dimensional structural information, thereby limiting predictive performance. This work proposes the first trimodal contrastive learning framework that integrates one-dimensional sequences, two-dimensional graph structures, and three-dimensional spatial conformations of both drugs and proteins. By explicitly constructing cross-modal positive and negative sample pairs, the framework enables effective alignment and interaction among multimodal features. The proposed method significantly outperforms state-of-the-art models across three benchmark datasets. Ablation studies confirm the contribution of each modality, and case studies further demonstrate its promising applicability in drug discovery.

Abstract

Accurate prediction of drug-target interactions (DTI) is critical for drug discovery. Existing methods often rely on single-modal representations (e.g., sequences or graphs) or combine only two modalities, overlooking 3D structural features. To address this challenge, we propose TriMod-DTI, a triple-modal contrastive learning framework that incorporates 1D sequences, 2D graphs, and 3D structures of drugs and proteins, obtaining the universal and complementary feature representations for DTI prediction. We design a Feature Extractor to capture drug and target features across the three modalities, thereby enriching their representations. We further propose a triple-modal contrastive learning strategy to align different modal representations of the same drug or protein in the latent space. By constructing cross-modal positive and negative sample pairs, this approach enhances the model's discriminative ability. Experiments on three benchmark datasets demonstrate that TriMod-DTI outperforms state-of-the-art methods. The ablation studies validate the contributions of each modality. Moreover, case studies highlight its practical potential for DTI prediction and drug discovery.

Problem

• drug-target interaction
• multi-modal representation
• 3D structure
• sequence
• graph

Innovation

• triple-modal
• contrastive learning
• drug-target interaction
• 3D structure
• multimodal representation