This guide will cover the download, installation, and local use of the DeepLocPro 1.0 tool (Moreno et al. 2024) for the prediction of prokaryotic protein localisation.

A Linux based system with Miniconda will be required for this guide and some high computing power is suggested, such a system might exist for your institution or can be purchased through an online cloud computing provide. Follow my guide on cloud based VM setup here: https://scottc-bio.github.io/guides/Virtual-machines-for-bioinformatics.html

A basic understanding of LINUX such as creating and moving directories etc. is assumed for this guide.

1 Downloading DeepLocPro 1.0

Firstly, create a conda environment to perform the install.

conda create -n deeplocpro python=3.9 -y
conda activate deeplocpro

Then clone the GitHub repository.

git clone https://github.com/Jaimomar99/deeplocpro.git

This will create the directory “deeplocpro”, so move into it.

cd deeplocpro/

And run the install.

pip install .

2 Running DeepLocPro 1.0

DeepLocPro is now ready to run from any location, so can move to wherever your fasta file is and run the command.

deeplocpro -f example.fasta -o results_out/

This will output a .csv file to the results_out/ directory which can be converted to a .txt file. This is not necessarry, I just prefer working with .txt files.

cp results_out/*.csv results_out/deeplocpro_results.txt

The output is simple, the columns are:

  • Row numbers
  • Sequence ID - the IDs extracted from your fasta sequence headers
  • Prediction - The predicted localisation (Cell wall & surface, Extracellular, Cytoplasmic, Cytoplasmic membrane, Outer membrane and Periplasmic)
  • Location columns - Each location with a score based on its likelihood

References

Moreno, Jaime, Henrik Nielsen, Ole Winther, and Felix Teufel. 2024. “Predicting the Subcellular Location of Prokaryotic Proteins with DeepLocPro.” Bioinformatics 40 (12): btae677. doi:10.1093/bioinformatics/btae677.