A Multi-view Divergence-Convergence Feature Augmentation Framework for Drug-related Microbes Prediction

2025-06-23

AI Summary

To address the fragmentation of multi-source views and insufficient feature fusion in drug–microbe association prediction, this paper proposes a multi-view collaborative optimization framework. Methodologically, it integrates the drug–microbe association network with heterogeneous similarity information, incorporates an adversarial learning–driven differential feature optimization module to enhance view discriminability, and designs a bidirectional collaborative attention mechanism for cross-view feature alignment. Furthermore, a Transformer-based graph neural network is employed to model higher-order dependencies among nodes in the heterogeneous graph. Experimental results demonstrate that the proposed method significantly outperforms state-of-the-art models across multiple benchmark datasets. Notably, it maintains high predictive stability and generalization capability in cold-start scenarios—i.e., for novel drugs or novel microbes—thereby providing an interpretable and robust computational tool for precision medicine and drug functional analysis.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In the study of drug function and precision medicine, identifying new drug-microbe associations is crucial. However, current methods isolate association and similarity analysis of drug and microbe, lacking effective inter-view optimization and coordinated multi-view feature fusion. In our study, a multi-view Divergence-Convergence Feature Augmentation framework for Drug-related Microbes Prediction (DCFA_DMP) is proposed, to better learn and integrate association information and similarity information. In the divergence phase, DCFA_DMP strengthens the complementarity and diversity between heterogeneous information and similarity information by performing Adversarial Learning method between the association network view and different similarity views, optimizing the feature space. In the convergence phase, a novel Bidirectional Synergistic Attention Mechanism is proposed to deeply synergize the complementary features between different views, achieving a deep fusion of the feature space. Moreover, Transformer graph learning is alternately applied on the drug-microbe heterogeneous graph, enabling each drug or microbe node to focus on the most relevant nodes. Numerous experiments demonstrate DCFA_DMP's significant performance in predicting drug-microbe associations. It also proves effectiveness in predicting associations for new drugs and microbes in cold start experiments, further confirming its stability and reliability in predicting potential drug-microbe associations.

Problem

• Identifying drug-microbe associations for precision medicine
• Lack of inter-view optimization in current methods
• Need for effective multi-view feature fusion

Innovation

• Adversarial Learning for multi-view feature optimization
• Bidirectional Synergistic Attention Mechanism for feature fusion
• Transformer graph learning for node relevance focus