LncPTPred: predicting lncRNA-protein interaction based on crosslinking and immunoprecipitation (CLIP-Seq) data

Area of Science:

• Molecular Biology
• Bioinformatics
• Computational Biology

Background:

• Long noncoding RNA (lncRNA)-protein interactions (LPI) are crucial regulators of cellular processes.
• Experimental identification of LPIs is resource-intensive and time-consuming.
• In silico prediction offers an efficient alternative for identifying LPIs.

Purpose of the Study:

• To develop a state-of-the-art machine learning (ML)-based algorithm for predicting LPI.
• To identify hidden patterns in cross-linking immunoprecipitation sequencing (CLIP-Seq) data for improved prediction accuracy.
• To provide a user-friendly tool for predicting LPIs.

Main Methods:

• Utilized CLIP-Seq data to identify patterns for training an ML model.
• Developed and trained an ML-based prediction algorithm for LPI.
• Compared the performance of the developed model against contemporary prediction tools.

Main Results:

• The developed ML model demonstrated superior performance compared to existing LPI prediction tools.
• The tool successfully identified interaction segments within lncRNA loci.
• The LncPTPred tool is available as a web server and a standalone version.

Conclusions:

• The LncPTPred tool offers an efficient and accurate method for predicting LPIs.
• The identified interaction segments can guide experimental validation of LPIs.
• This computational approach accelerates the study of lncRNA functions in biological systems.