PRGminer: Deep neural network based Plant Resistance Gene Prediction
PRGminer classify Plant resistance genes in 8 classes: CNL, KIN, LYK, LECRK, RLP, RLK, TIR, TNL.
Input
The PRGminer server requires amino acid sequence(s) in fasta format, and does not support nucleic acid sequences.
Development Environment and Prerequisite
This source code was developed in Linux, and has been tested on Linux and OS X. The only prerequisite is to have Python 3.7 or above installed.
Installation
The installation of PRGminer can be done in two ways:
1. Create a dedicated miniconda3 environment
Download PRGminer from:
https://bioinfo.usu.edu/PRGminer/download/PRGminer.tar.gz
Download the Miniconda installer:
(https://docs.conda.io/en/latest/miniconda.html#linux-installers)
Extract the downloaded file:
tar -xvzf PRGminer.tar.gz
cd PRGminer
Create and activate a conda environment
conda env create -f environment.yml
conda activate PRGminer
pip3 install .
2. Intall using system Python3
Download PRGminer from:
https://bioinfo.usu.edu/PRGminer/download/PRGminer.tar.gz
Extract the downloaded file:
tar -xvzf PRGminer.tar.gz
cd PRGminer
pip3 install .
3. Intall using system Python3
Clone PRGminer from:
git clone https://github.com/usubioinfo/PRGminer.git
cd PRGminer
pip3 install .
Input and Execution
PRGminer will be installed under the name 'PRGminer' with three possible arguments:
-i, --fasta_file. Protein sequence input in FASTA format.
-od, --output_dir. Output directory name.
-l, --level.
Output Files
The output directory will have three files in tab-delimted format:
-
Phase1_dnn_log.txt
- 1st column: Protein ID.
- 2nd column: Prediction.
- 3rd-4th column: Probability for Rgenes and Non-Rgenes.
-
Phase2_dnn.log.txt
- 1st column: Protein ID.
- 2nd column: Prediction.
- 3rd-14th column: Probability for each class.
Queries and Contact
Written by Naveen Duhan (naveen.duhan@usu.edu),
Kaundal Bioinformatics Lab, Utah State University,
Released under the terms of GNU General Public Licence v3
In case of technical problems (bugs etc.) please contact Naveen Duhan naveen.duhan@usu.edu.
For any Questions on the scientific aspects of the PRGminer method please contact:
Rakesh Kaundal, rkaundal@usu.edu
Naveen Duhan, naveen.duhan@usu.edu