DeepPrime

Deep learning-based model that can predict the prime editing efficiency for all possible pegRNAs for a given target sequence

Published Paper Publication
DeepPrime

Installation from source code:

For processing large number of pegRNAs, researchers can download zipped source code, install the necessary python packages, and run DeepPrime on their local systems. We recommend using a Linux-based OS.

View on GitHub

# 1. Install Miniconda
> wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
> bash Miniconda3-latest-Linux-x86_64.sh
# 2. Create and activate virtual environment
> conda create -n dprime python=3.8
> conda activate dprime
# 3. Install Required Python Packages
> pip install tensorflow==2.8.0
> pip install torch==1.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
> pip install biopython==1.78
> pip install pandas regex silence-tensorflow
# 4. Install ViennaRNA
> wget https://www.tbi.univie.ac.at/RNA/download/sourcecode/2_5_x/ViennaRNA-2.5.1.tar.gz
> tar -zxvf ViennaRNA-2.5.1.tar.gz
> cd ViennaRNA-2.5.1
> ./configure --with-python3
> make
> make install
- OR -
> conda install -c bioconda viennarna
- OR -
> pip install ViennaRNA
# 5. Download Source Code
> wget https://github.com/hkimlab/DeepPrime/archive/main.zip
> unzip main.zip

How to use DeepPrime by Source code

Please see Github for more details.

# example_input
> python DeepPrime.py -f ./example_input/dp_core_test.csv