ImageDDI: Image-enhanced Molecular Motif Sequence Representation for Drug-Drug Interaction Prediction

2025-08-10

AI Summary

Accurate prediction of drug–drug interactions (DDIs) is critical for ensuring safety in polypharmacy. To address this, we propose ImageDDI—a novel multimodal framework that pioneers the deep integration of visual representations (e.g., texture, spatial layout) from 2D/3D molecular images with functional motif sequence modeling. Specifically, molecular tokenization extracts pharmacophoric groups, which are encoded by a Transformer to capture local structural patterns; concurrently, a CNN processes 2D/3D molecular images to extract global geometric and electronic features. An adaptive multimodal fusion module dynamically weights and integrates sequence- and image-derived features. Evaluated on multiple standard benchmarks, ImageDDI consistently outperforms state-of-the-art methods—achieving robust, high performance under both 2D and 3D molecular representations. Importantly, its design enables enhanced interpretability and synergistic exploitation of heterogeneous data sources, establishing a new paradigm for explainable, multimodal DDI prediction.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

To mitigate the potential adverse health effects of simultaneous multi-drug use, including unexpected side effects and interactions, accurately identifying and predicting drug-drug interactions (DDIs) is considered a crucial task in the field of deep learning. Although existing methods have demonstrated promising performance, they suffer from the bottleneck of limited functional motif-based representation learning, as DDIs are fundamentally caused by motif interactions rather than the overall drug structures. In this paper, we propose an Image-enhanced molecular motif sequence representation framework for extbf{DDI} prediction, called ImageDDI, which represents a pair of drugs from both global and local structures. Specifically, ImageDDI tokenizes molecules into functional motifs. To effectively represent a drug pair, their motifs are combined into a single sequence and embedded using a transformer-based encoder, starting from the local structure representation. By leveraging the associations between drug pairs, ImageDDI further enhances the spatial representation of molecules using global molecular image information (e.g. texture, shadow, color, and planar spatial relationships). To integrate molecular visual information into functional motif sequence, ImageDDI employs Adaptive Feature Fusion, enhancing the generalization of ImageDDI by dynamically adapting the fusion process of feature representations. Experimental results on widely used datasets demonstrate that ImageDDI outperforms state-of-the-art methods. Moreover, extensive experiments show that ImageDDI achieved competitive performance in both 2D and 3D image-enhanced scenarios compared to other models.

Problem

• Predicting drug-drug interactions via motif sequences
• Enhancing molecular representation with image features
• Overcoming limited motif-based DDI prediction methods

Innovation

• Image-enhanced molecular motif sequence representation
• Transformer-based encoder for motif embedding
• Adaptive Feature Fusion for visual integration