Recent Advances on the Semi-Supervised Learning for Long Non-Coding RNA-Protein Interactions Prediction: A Review.

Area of Science:

• Molecular Biology
• Genomics
• Bioinformatics

Background:

• Long non-coding RNAs (lncRNAs) are key regulators in cellular processes like chromatin modification and differentiation.
• Dysregulation of lncRNAs is implicated in various human diseases, including cancer.
• Understanding lncRNA functions requires knowledge of their interactions with proteins.

Purpose of the Study:

• To review computational models for predicting lncRNA-protein interactions.
• To highlight models based on semi-supervised learning developed in the last two years.
• To discuss the strengths and weaknesses of these predictive models.

Main Methods:

• Literature review of recent computational prediction models for lncRNA-protein interactions.
• Focus on models employing semi-supervised learning techniques.
• Analysis of model advantages and limitations.

Main Results:

• Several semi-supervised learning-based computational models for lncRNA-protein interaction prediction have emerged.
• These models offer alternatives to time-consuming experimental methods.
• Each model presents unique advantages and limitations in prediction accuracy and applicability.

Conclusions:

• Computational prediction of lncRNA-protein interactions is vital for understanding lncRNA functions and disease mechanisms.
• Semi-supervised learning approaches show promise in this field.
• Further research is needed to refine models and explore future directions in lncRNA-protein interaction prediction.