AggreProt Predictor

• Web page: https://loschmidt.chemi.muni.cz/aggreprot/
• Paper: https://academic.oup.com/nar/article/52/W1/W159/7683054

Run predictor

Use Python 3.8.

If you don't have Python 3.8, install it with conda (Miniforge):

wget https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh
bash Miniforge3-Linux-x86_64.sh -b -p ~/miniforge3
source ~/miniforge3/bin/activate
conda create -y -n aggreprot python=3.8
conda activate aggreprot

Download the repository:

git clone https://github.com/loschmidt/aggreprot-predictor.git

Extract model files to the cloned repository:

unzip nnap-data.zip -d aggreprot-predictor/

Check that data was properly extracted in correct path:

find aggreprot-predictor/nnap/data -maxdepth 3

It should produce:

aggreprot-predictor/nnap/data
aggreprot-predictor/nnap/data/Atomic.csv
aggreprot-predictor/nnap/data/models
aggreprot-predictor/nnap/data/models/sequential
aggreprot-predictor/nnap/data/models/sequential/saved_model
aggreprot-predictor/nnap/data/models/sequential/hdf5

Then install the predictor:

pip3 install ./aggreprot-predictor/

Run the predictor:

aggreprot-predictor predict-sequential-batch --out-dir out sequences.fa