A Comprehensive Review of Machine Learning and Deep Learning Techniques for RRI Prediction

RNA-RNA interactions (RRIs) play a crucial role in regulating diverse biological processes, including gene expression, RNA splicing, and cellular signaling. Accurate prediction of these interactions is essential for understanding RNA function and advancing therapeutic design. In recent years, machine learning (ML) and deep learning (DL) techniques have emerged as powerful tools to model complex RNA interactions from high-dimensional and heterogeneous biological data. This chapter presents a comprehensive review of state-of-the-art ML and DL methods applied to RRI prediction. We review and analyze classical ML algorithms such as support vector machines, random forests, and ensemble approaches, alongside modern DL architectures including convolutional neural networks, recurrent neural networks, and graph neural networks. Key challenges such as feature extraction, model interpretability, and data scarcity are discussed. Furthermore, we evaluate benchmark datasets, performance metrics, and comparative studies to highlight the strengths and limitations of existing approaches. Finally, future research directions are proposed to enhance predictive accuracy and biological relevance, fostering the integration of computational predictions into experimental workflows.