GIN-CRC-Pareto: A graph-based pareto-optimized multi-task learning framework to identify miRNA-target interactions in colorectal cancer.

Abstract

Colorectal cancer (CRC) ranks as the third highest incidence among malignancies for human and the second most common cause of cancer-related mortality in the United States. Accumulating evidence has established microRNAs (miRNAs) as critical regulators of cancer development and therapeutic response. Understanding miRNA-mRNA interactions is critical for elucidating the molecular mechanisms driving CRC and other malignancies. However, accurately modeling miRNA-mRNA interactions and their binding patterns remains challenging. In this study, we proposed GIN-CRC-Pareto, a graph-based, Pareto-optimized multi-task learning framework that simultaneously predicts miRNA-mRNA binding pairs, identifies seed match pairings, and classifies seed match subtypes. By leveraging the power of graph neural networks and Pareto-optimized gradient balancing strategy, GIN-CRC-Pareto dynamically adjusted the task weights during training to optimize each task without compromising the others. Experimental results demonstrated that our framework consistently outperforms traditional deep learning models and existing state-of-the-art tools across multiple evaluation metrics, with 0.909 in accuracy, 0.909 in precision and 0.969 in AUC in the miRNA-mRNA binding pairs prediction task. Furthermore, transfer learning experiments on external datasets indicate strong generalizability of the framework for identifying miRNA-target interactions across multiple cancer types. The proposed framework provides an effective and scalable approach for comprehensive identification of miRNA-target interactions in CRC, with the potential to serve as a scalable and generalizable tool across diverse cancer types, ultimately facilitating the development of miRNA-based therapeutics for cancer treatment.