search

LBM-EPFL / PeSTo

Geometric deep learning method to predict protein binding interfaces from a protein structure.
https://pesto.epfl.ch
Other
108 stars 15 forks source link

interface_ppi_benchmark.ipynb, incorrect paths and missing benchmark data #3

Closed rubenalv closed 1 year ago

rubenalv commented 1 year ago

Hello, I noticed that some module calls do not match the directory structure in the .ipynb file. Eg. from config import config_model, config_data should be (according to the github structure) from model.config import config_model, config_data

Also, the benchmark data is missing in the github. Where could I retrieve it from? dataset = Dataset("datasets/contacts_rr5A_64nn_8192.h5")

Siirui commented 1 year ago

@rubenalv The benchmark data is retrieved through processing/build_dataset.py. You should execute the script data/rsyncPDB.sh first to download the dataset. After processing the scripts above you can fetch the contacts_rr5A_64nn_8192.h5