Advancements in RNA Secondary Structure Prediction using Machine Learning Methods

New insights and a greater understanding of role of RNA in diseases, cellular processes and regulation could be achieved by acquiring unmitigated information on RNA secondary structures and their base pairing interactions. In this quest, probabilistic models have proven successful over the past two decades, specifically the machine learning based pipelines. These have improved upon alternative thermodynamic based models, folding algorithms employing stochastic parameters and the comparative sequence analysis techniques. The current study delves into the machine learning techniques which have remarkably augmented RNA secondary structure prediction research. An overview of RNA functions, their types, and the roles they play in diseases, has been supplemented, to equip the reader with the required knowledge for understanding the cruciality of uncovering RNA structural information. Additionally, a revision of previous and alternative models has been included for a cohesive understanding of the history and scope of RNA structure prediction.