by Shaan Sekhon
DeepRNAreg is an exciting new tool for comparative CLIP-Seq analysis. DeepRNAreg leverages recent advances in the field of deep learning to provide a robust method for the elucidation of differential RNA-Binding-protein activity.
Before attempting to execute DeepRNAreg on your processed sequencing data, please first ensure that you have the following three sets of software libraries installed on your device. DeepRNAreg runs best on machines running either linux or MacOS. If you have a Windows PC, virtualization is suggested because this software utilizes multi-core processing that is not yet compatible with windows computers.
First, please ensure that you have samtools installed and executable via the command line. See here: https://www.htslib.org/download/.
Next, please ensure that you have the keras and tensorflow python modules in a python3 environment that are readily imported. DeepRNAreg was tested on keras==2.11.0.
Next, please ensure that you have installed the python modules listed within the requirements.txt file listed within this directory. They may be readily installed using the PyPi installer:
pip install -r requirements.txt
DeepRNAreg was tested on python version 3.9.7.
You may run the DeepRNAreg python file with the --help flag to see all possible input parameters.
. $ python3 DeepRNAreg.py --help
. usage: DeepRNAreg.py [-h] [--bam1 BAM1] [--bam2 BAM2] [--bed BED]
.
. Welcome to DeepRNAreg, a powerful tool for differential CLIP-Seq analysis.
.
. optional arguments:
. -h, --help show this help message and exit
. --bam1 BAM1 This is the absolute path to the first BAM file.
. --bam2 BAM2 This is the absolute path to the second BAM file.
. --bed BED This is the absolute path to a BED format file containing the genomic loci upon which DeepRNAreg should be executed.
The following is a sample execution command for DeepRNAreg:
python3 DeepRNAreg.py --bam1=first.bam --bam2=second.bam --bed=loci.bed
Upon successful completion of the algorithm, the folling message will be displayed:
'DeepRNAreg ran successfully! Output saved to enriched-cond1.csv and enriched-cond2.csv.'
If you run into any issues running DeepRNAreg, please post an 'issue' under the issues tab of github.
- 1.0
- Initial Release
This project is licensed under the MIT License.