lncRNA-disease association prediction based on latent factor model and projection

Area of Science:

• Computational biology
• Genomics
• Bioinformatics

Background:

• Long non-coding RNAs (lncRNAs) play crucial roles in disease development.
• Accurate identification of lncRNA-disease associations is vital for understanding disease mechanisms.
• Computational approaches can enhance the efficiency and accuracy of biological experiments.

Purpose of the Study:

• To develop a novel computational model for predicting lncRNA-disease associations.
• To predict unknown lncRNA-disease associations without requiring direct lncRNA-disease data.
• To improve the accuracy and efficiency of biological experiments in lncRNA research.

Main Methods:

• Proposed a latent factor model and projection-based prediction model (LFMP).
• Utilized lncRNA-miRNA and miRNA-disease association data for prediction.
• Employed a leave-one-out cross-validation (LOOCV) framework for performance evaluation.

Main Results:

• The LFMP model achieved an Area Under the Curve (AUC) of 0.8964 under LOOCV.
• LFMP demonstrated superior performance compared to existing state-of-the-art methods.
• Case studies on lung and colorectal tumors validated LFMP's ability to infer undetected lncRNA-disease associations.

Conclusions:

• LFMP is an effective computational tool for predicting lncRNA-disease associations.
• The model's ability to predict novel associations can guide future experimental validation.
• This approach offers a promising direction for computer-aided disease research.