Advances in Computational Methodologies for Classification and Sub-Cellular Locality Prediction of Non-Coding RNAs

Area of Science:

• Bioinformatics
• Genomics
• Computational Biology

Background:

• Non-coding RNAs (ncRNAs) play critical roles in cellular processes and disease development, including cancer.
• Understanding ncRNA function requires accurate classification and sub-cellular localization.
• High-throughput sequencing and bioinformatics have accelerated ncRNA research.

Purpose of the Study:

• To review computational methodologies for distinguishing coding RNA from ncRNA.
• To identify various ncRNA subtypes, including microRNA, long ncRNA, and circular RNA.
• To determine the sub-cellular localization of ncRNAs and assess computational approaches for RNA sequence analysis.

Main Methods:

• Literature review of computational approaches developed in the last 10 years.
• Analysis of datasets for ncRNA classification and sub-cellular localization.
• Benchmarking of existing computational methodologies for RNA sequence analysis.

Main Results:

• Identification of diverse ncRNA types and their involvement in cellular regulation and disease.
• Summary of computational tools and techniques for ncRNA identification and localization.
• Evaluation of performance metrics and datasets for computational RNA analysis.

Conclusions:

• Computational approaches are crucial for advancing ncRNA research and understanding disease mechanisms.
• Further development is needed to address research gaps and challenges in RNA sequence analysis.
• This review provides insights for AI researchers on state-of-the-art methods and model selection for ncRNA-related tasks.