# Import necessary libraries
from pathlib import Path
import os

!pip install proteinflow &> /dev/null
!apt-get install -qq -y mmseqs2 &> /dev/null

from google.colab import drive
drive.mount('/content/gdrive', force_remount=True)

path = Path("/content/gdrive/")
path_data = Path("/content/gdrive/MyDrive/data")

import pandas as pd

from slugify import slugify

#!proteinflow generate --help

# Species Homo Sapiens and Resolution 2.5 A
sabdab_summary_url = 'https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab/summary/20240520_0899946/'
sabdab_url = 'https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab/archive/20240520_0899946/'
fname = slugify(sabdab_summary_url.split('/')[-2], lowercase=False)

# Need to generate url fresh everytime
!wget https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab/summary/20240520_0899946/ -O {path_data}/{fname}_summary.tsv

# Need to generate url fresh everytime
!wget https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab/archive/20240520_0899946/ -O {path_data}/{fname}.zip

!ls {path_data}

!proteinflow generate --sabdab \
--sabdab_data_path {path_data}/{fname}.zip --tag {fname} \
--resolution_thr 2.5 --not_remove_redundancies \
--min_seq_id 0.9 \
--local_datasets_folder {path_data} \
--valid_split 0.1 --test_split 0.1 \
--split_tolerance 0.05

!ls /content/gdrive/MyDrive/data/proteinflow_{fname}/

!proteinflow generate --help