Recent advances in machine learning methods for predicting LncRNA and disease associations

Area of Science:

• Genomics
• Molecular Biology
• Computational Biology

Background:

• Long non-coding RNAs (lncRNAs) regulate critical biological processes.
• Dysregulation of lncRNAs is linked to complex human diseases.
• Understanding lncRNA-disease associations (LDAs) is vital for disease mechanisms, diagnosis, and treatment.

Purpose of the Study:

• To review machine learning approaches for predicting lncRNA-disease associations (LDAs).
• To summarize key aspects of LDA prediction models, including diseases studied, features, and evaluation methods.
• To discuss limitations and future directions for machine learning-based LDA prediction.

Main Methods:

• Review of existing literature on machine learning for LDA prediction.
• Analysis of association and similarity features used in LDA models.
• Summary of performance evaluation metrics for LDA prediction models.
• Categorization of advanced machine learning prediction models for LDAs.

Main Results:

• Identified various human diseases studied through LDA prediction.
• Highlighted the importance of association and similarity features in model development.
• Presented an overview of advanced machine learning models and their performance.
• Discussed the limitations inherent in current machine learning-based LDA prediction methods.

Conclusions:

• Machine learning offers a cost-effective and efficient alternative to experimental methods for LDA prediction.
• Further research is needed to overcome limitations and develop more robust prediction models.
• Improved LDA prediction can significantly advance disease diagnosis, treatment, and prevention strategies.