PlantRNA_Sniffer: A SVM-Based Workflow to Predict Long Intergenic Non-Coding RNAs in Plants.

Area of Science:

• Plant molecular biology
• Bioinformatics
• Genomics

Background:

• Non-coding RNAs (ncRNAs), including long intergenic non-coding RNAs (lincRNAs), play crucial roles in gene regulation.
• Existing computational methods for lincRNA prediction are often species-specific and lack applicability across different plant species.
• There is a significant knowledge gap regarding lincRNAs in plants, hindering our understanding of their functions.

Purpose of the Study:

• To develop and validate a robust computational workflow for predicting lincRNAs specifically in plants.
• To identify novel lincRNAs in economically important plant species like sugarcane and maize.
• To investigate the differential expression of lincRNAs in response to microbial interactions.

Main Methods:

• Development of a bioinformatics workflow integrating established tools with machine learning techniques.
• Application of a Support Vector Machine (SVM) model for lincRNA prediction.
• Case studies involving sugarcane (Saccharum spp.) and maize (Zea mays) for prediction and expression analysis.

Main Results:

• Successful identification of novel lincRNAs in sugarcane and maize using the proposed workflow.
• Discovery of differentially-expressed lincRNAs in both species upon exposure to pathogenic and beneficial microorganisms.
• Demonstration of the workflow's efficacy and potential for broader application in plant lincRNA research.

Conclusions:

• The developed workflow provides an effective and adaptable approach for lincRNA prediction in plants.
• The findings highlight the potential roles of lincRNAs in plant responses to microbial stimuli.
• This work lays the foundation for further exploration of lincRNA functions in plant biology and agriculture.