TWtest/sludge_caculate_PaDEL_descriptor.py
a2d193807e57master

sludge_caculate_PaDEL_descriptor.py
View Options

			from padelpy import from_smiles
			import pandas as pd

			file_location = "C:\\Users\\leetseng\\TWtest"
			input_file_path_all_compounds = file_location+'\\input\\sludgeWithSmiles.tsv' #'input/sludgeWithSmiles.tsv' "Your concatenate the different iterations, so your index is not continuous!!!!"
			output_file_path_padel = file_location+'/output\\descriptors\\sludge_PaDEL_test1.tsv'

			data = pd.read_csv(input_file_path_all_compounds, sep='\t') #pandas Series
			print(data.head(2))

			#create the set of SMILES
			list_of_canonicalize_smiles = data['canonicalize_smiles'].values.tolist()
			set_of_canonicalize_smiles = set(list_of_canonicalize_smiles)
			print(set_of_canonicalize_smiles)

			D = {}
			for index, row in data.iterrows():
			id = row['index']
			print(id)
			try:
			descriptors = from_smiles(row['canonicalize_smiles'], maxruntime=20)
			except RuntimeError:
			print('Warning: No PaDEL descriptor could be calculated for compound {}, smiles = {}'.format(id, row['canonicalize_smiles']))
			else:
			D[id] = descriptors


			df = pd.DataFrame.from_dict(D, orient='index')
			df.to_csv(output_file_path_padel, sep='\t')


			# for index, row in data.iterrows():
			# id = row['index']
			# print(id)
			# smiles_list = []
			# smiles_list.append(row['canonicalize_smiles'])
			# smiles_set = set(smiles_list)
			# print(smiles_set)