Tutorial on Machine Learning Methods for RNA-RNA Interaction Prediction

RNA-RNA interactions (RRIs) are fundamental to numerous cellular processes, including gene regulation, RNA splicing, and translation. Accurate prediction of RRIs remains a challenging computational problem due to the complex structural and sequence dependencies involved. This tutorial and literature survey provide a comprehensive overview of machine learning (ML) methodologies applied to RRI prediction, focusing on classical models such as Naive Bayes and Bayesian networks, alongside cutting-edge deep learning techniques exemplified by Bidirectional Encoder Representations from Transformers (BERT). We explore the theoretical foundations of these methods, their feature engineering strategies, and their relative strengths and limitations in modeling RNA sequence and structural data. Through critical analysis of recent literature, this survey highlights the evolution of ML-based RRI prediction, emphasizing how probabilistic models and transformer-based architectures have advanced the field. Practical insights and guidelines for applying these methods are discussed, aiming to equip researchers with the knowledge needed to implement and interpret ML models for RNA interaction prediction effectively.