RaSP_postprocess

#!/usr/bin/env python3

#Rapid protein stability prediction, RaSP, Developed by Blaabjerg et al. 2022 doi: 10.1101/2022.07.14.500157 
#Adapted and implemented in 2022, Kristine Degn

import argparse
import pandas as pd

parser = argparse.ArgumentParser(prog = "RaSP_postprocess",
                                 usage = 'RaSP_postprocess [-h] help, [-i] input csv')

parser.add_argument("-i", '--input',
                    metavar = 'input csv',
                    type=str,
                    help='The name and path to of the output csv file, e.g. output/predictions/cavity_pred_P62942_A.csv')

args = parser.parse_args()

#importing file
file = args.input

#reading into dataframe and extracting relevant files.
df = pd.read_csv(file)
df = df[['variant', 'wt_AA', 'pos', 'mt_AA', 'chainid', 'score_ml']]

#assigning Mutatex and Rosetta mutant normenclature
mutatex_normenclature = []
for i,k in enumerate(df.variant):
    mutatex_v = f"{k[0]}{df.chainid[i]}{k[1:-1]}{k[-1]}"
    mutatex_normenclature.append(mutatex_v)
    
rosetta_normenclature = []
for i,k in enumerate(df.variant):
    rosetta_v = f"{df.chainid[i]}.{k[0]}.{k[1:-1]}.{k[-1]}"
    rosetta_normenclature.append(rosetta_v)

df['mutatex_name'] = mutatex_normenclature
df['rosetta_name'] = rosetta_normenclature

#renaming columns
df.rename({'score_ml': 'RaSP_ddG'}, axis=1, inplace=True)
df = df[['variant', 'RaSP_ddG', 'mutatex_name', 'rosetta_name', 'wt_AA', 'pos', 'mt_AA', 'chainid']]

#exporting file.
f = ("/").join(file.split("/")[:-1])
n = file.split("/")[-1].split("cavity_pred_")[-1]
df.to_csv(f"{f}/post_processed_{n}")