Artificial intelligence and machine learning heuristics for discovery of ncRNAs

Artificial intelligence (AI) has emerged as a powerful tool in molecular biology, significantly advancing the study of long non-coding RNAs (lncRNAs). This chapter examines the application of AI techniques, including machine learning (ML) and deep learning (DL), in predicting lncRNA functions, identifying disease associations, and annotating protein interactions. The discussion covers key methodologies such as supervised and unsupervised ML algorithms, recurrent neural networks (RNNs), convolutional neural networks (CNNs), and transformer-based models. A detailed description of a deep learning pipeline for functional annotation of lncRNA-binding proteins (lncRBPs) is provided, highlighting challenges in dataset preparation, model design, and usability. Integrating experimental validation with computational predictions is emphasized as a pathway to bridge AI-driven insights with biological understanding.