This guide will cover the download, installation, and local use of the DeepLoc 2.1 tool (Ødum et al. 2024) for the prediction of eukayotic 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 DeepLoc 2.1

You will need the compressed ‘.tar.gz’ file for the DeepLoc 2.1 which need to be obtained by DTU by filling out the forms available through the Downloads section: https://services.healthtech.dtu.dk/services/DeepLoc-2.1/

DTU will then email a link to the download for the tool. The easiest way to download this is to move to the directory on your LINUX system where you wish to perform the prediction. E.g. where your amino acid sequence fasta file is.

Then use ‘wget’ to initiate the download.

wget url/of/download/page/sent/to/you/deeploc-2.1.All.tar.gz

Unpack.

tar -xzvf deeploc-2.1.All.tar.gz

This will unpack a number of files into a directory called deeploc2_package.

This contains everything needed for the install.

2 Installing

Firstly, create a conda environment to perform the install.

conda create -n deeploc2 python=3.8 -y
conda activate deeploc2

Then move into the package directory and run the install.

cd deeploc2_package/
pip install .

Now return to the parent directory where your fasta file is.

cd ../

3 Running DeepLoc 2.1

Now we can run DeepLoc 2.1, either in ‘Fast’ or ‘Accurate’ mode.

deeploc2 --fasta example.fasta --output deeploc2_fast_out --model Fast

The first time either of these modes are run, they will download some required files. These downloads will be cached so they won’t need to be downloaded again.

The output is in .csv format with an automatic name, but can be copied to a .txt file with a custom name

cp deeploc2_fast_out/results_*.csv deeploc2_fast_out/results.txt

References

Ødum, Marius Thrane, Felix Teufel, Vineet Thumuluri, José Juan Almagro Armenteros, Alexander Rosenberg Johansen, Ole Winther, and Henrik Nielsen. 2024. “DeepLoc 2.1: Multi-Label Membrane Protein Type Prediction Using Protein Language Models.” Nucleic Acids Research 52 (W1): W215–20. doi:10.1093/nar/gkae237.