Cross-domain contrastive graph neural network for lncRNA-protein interaction prediction

Identifying lncRNA-protein interactions (LPIs) is an important biomedical task, facilitating the comprehension of the biological functions and mechanisms of lncRNAs. Many computational methods have been developed for this task, especially graph neural network (GNN)-based methods have attracted increasing attention. Typically, the LPI network involves two types of interaction domains: the interactive domain capturing the direct interaction information between lncRNAs and proteins, and the collaborative domain reflecting the collaboration information among lncRNAs or proteins. However, existing GNN-based methods only leverage one of them to obtain topological information, which cannot fully characterize lncRNAs and proteins, resulting in suboptimal node representations. Moreover, each domain contains task -irrelevant redundant information, posing a challenge in effectively integrating information from different domains. To address these issues, we propose a novel Cross -domain Contrastive Graph Neural Network (CCGNN) for predicting potential LPIs. CCGNN employs a multi -domain encoder that consists of an interactive domain encoder and two collaborative domain encoders to capture valuable information from each interaction domain. Subsequently, domainadaptive fusion is designed to integrate information from different domains to acquire comprehensive node representations. Furthermore, cross -domain contrastive learning is devised to enrich the node representations, drawing inspiration from the information bottleneck principle by retaining as much task -relevant information as possible within each domain and minimizing mutual information between representations across different domains. Extensive experiments on four real -world datasets demonstrate the superiority of CCGNN over stateof-the-art methods, and a further case study and generalization analysis illustrate the effectiveness of CCGNN in the biomedical link prediction tasks.