Related Experiment Video
Updated: Jun 29, 2025
06:34
A Bioinformatics Pipeline to Accurately and Efficiently Analyze the MicroRNA Transcriptomes in Plants
Published on: January 21, 2020
8.3K
Identification of plant microRNAs using convolutional neural network.
Yun Zhang1, Jianghua Huang1, Feixiang Xie1
1College of Information Engineering, Guizhou University of Traditional Chinese Medicine, Guiyang, Guizhou, China.
Frontiers in Plant Science
|April 3, 2024
Summary
We developed a new AI tool, SRICATs, to accurately identify plant microRNAs (miRNAs) from sequencing data. This user-friendly software outperforms existing methods for plant miRNA analysis.
Area of Science:
- Plant molecular biology
- Bioinformatics
- Genomics
Background:
- MicroRNAs (miRNAs) are crucial regulators of gene expression in plants.
- Identifying plant miRNAs from next-generation sequencing (NGS) data is complex.
- Existing analysis tools have limitations in accuracy and user-friendliness.
Purpose of the Study:
- To develop an accurate and user-friendly computational tool for plant miRNA identification.
- To leverage machine learning for improved miRNA detection from NGS data.
- To provide a comprehensive software package for plant small RNA analysis.
Main Methods:
- Training a convolutional neural network (CNN) for plant miRNA identification.
- Developing a Java-based software package named SRICATs.
- Validating the tool's performance on NGS data from five diverse plant species.
Main Results:
- The CNN model achieved high accuracy in identifying plant miRNAs.
- SRICATs successfully integrated all essential plant miRNA analysis steps.
- SRICATs demonstrated superior performance compared to popular existing software.
Conclusions:
- SRICATs offers a powerful and efficient solution for plant miRNA discovery.
- The developed AI approach enhances the accuracy of miRNA identification from NGS data.
- SRICATs is freely available for non-commercial use, facilitating plant research.
