def run(filename, query_gene_name):
biogrid_uniprot_conv.run()
id_parsed_df = id_parser.run(filename)
id_converted_df = id_converter.run(df=id_parsed_df)
gene_name_conv_df = uniprot_gene_name_conv.run(
df=id_converted_df, query_gene_name=query_gene_name)
cleaned_file_df = clean_file.run(df=gene_name_conv_df)
return calc_weighted_score.run(df=cleaned_file_df)
df['Interactor name'])
df['Interactor name'] = np.where(
(df['Parsed A gene name'] == query_gene_name) &
(df['Parsed B gene name'] == query_gene_name),
df['Parsed A gene name'], df['Interactor name'])
return df
def run(df, query_gene_name):
'''Calls the find_gene_name function once to create a dataframe column of common gene names of protein A and again
to create a column for the common gene names of protein B. An 'Interactor name' column is then generated for the
dataframe with the interactor_column function. NaN values are dropped from the returned function, which will
mostly be interactors that are not proteins or not human proteins.
'''
print('Generating common gene names...')
gene_name_a_df = find_gene_name(df=df, label='Parsed A')
gene_name_b_df = find_gene_name(df=gene_name_a_df, label='Parsed B')
print('Common gene names generated')
print('Generating Interactor column...')
interactor_column_df = interactor_column(
df=gene_name_b_df,
query_gene_name=query_gene_name).dropna(axis=0).reset_index(drop=True)
print('Interactor column generated')
return interactor_column_df
if __name__ == '__main__':
id_parsed_df = id_parser.run(filename='clusteredQuery_MST1R.txt')
id_converted_df = id_converter.run(df=id_parsed_df)
print(run(df=id_converted_df, query_gene_name='MST1R'))