tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

minor tweaks

Browse source
This commit is contained in:
Tanushree Tunstall 2020-04-08 18:27:09 +01:00
parent fe3d431a3d
commit 7a8bbc6595
4 changed files with 30 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

18
scripts/data_extraction.py
View file

@ -47,8 +47,10 @@ from reference_dict import my_aa_dict # CHECK DIR STRUC THERE!
#=======================================================================
#%% command line args
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help='drug name', default = 'pyrazinamide')
arg_parser.add_argument('-g', '--gene', help='gene name', default = 'pncA') # case sensitive
#arg_parser.add_argument('-d', '--drug', help='drug name', default = 'pyrazinamide')
#arg_parser.add_argument('-g', '--gene', help='gene name', default = 'pncA') # case sensitive
arg_parser.add_argument('-d', '--drug', help='drug name', default = 'TESTDRUG')
arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = 'testGene') # case sensitive
args = arg_parser.parse_args()
#=======================================================================
#%% variable assignment: input and output paths & filenames
@ -346,7 +348,7 @@ print('expected no. of gene samples:', expected_gene_samples)
print('=================================================================')
#%% write file
#print(outdir)
out_filename0 = gene.lower() + '_' + 'common_ids.csv'
out_filename0 = gene.lower() + '_common_ids.csv'
outfile0 = outdir + '/' + out_filename0
#FIXME: CHECK line len(common_ids)
@ -741,7 +743,7 @@ del(c1, c2, col_to_split1, col_to_split2, comp_gene_samples, dr_WF0, dr_df, dr_m
#dr_muts.to_csv('dr_muts.csv', header = True)
#other_muts.to_csv('other_muts.csv', header = True)
out_filename1 = gene.lower() + '_' + 'ambiguous_muts.csv'
out_filename1 = gene.lower() + '_ambiguous_muts.csv'
outfile1 = outdir + '/' + out_filename1
print('Writing file: ambiguous muts',
'\nFilename:', out_filename1,
@ -1053,7 +1055,7 @@ else:
, '\nDebug please!'
, '\n=========================================================')
out_filename2 = gene.lower() + '_' + 'mcsm_snps.csv'
out_filename2 = gene.lower() + '_mcsm_snps.csv'
outfile2 = outdir + '/' + out_filename2
print('Writing file: mCSM style muts'
@ -1074,7 +1076,7 @@ del(out_filename2)
#%% Write file: gene_metadata (i.e gene_LF1)
# where each row has UNIQUE mutations NOT unique sample ids
out_filename3 = gene.lower() + '_' + 'metadata.csv'
out_filename3 = gene.lower() + '_metadata.csv'
outfile3 = outdir + '/' + out_filename3
print('Writing file: LF formatted data'
, '\nFilename:', out_filename3
@ -1117,7 +1119,7 @@ else:
, '\nDebug please!'
, '\n=========================================================')
out_filename4 = gene.lower() + '_' + 'all_muts_msa.csv'
out_filename4 = gene.lower() +'_all_muts_msa.csv'
outfile4 = outdir + '/' + out_filename4
print('Writing file: mCSM style muts for msa',
@ -1149,7 +1151,7 @@ pos_only.position.dtype
# sort by position value
pos_only_sorted = pos_only.sort_values(by = 'position', ascending = True)
out_filename5 = gene.lower() + '_' + 'mutational_positons.csv'
out_filename5 = gene.lower() + '_mutational_positons.csv'
outfile5 = outdir + '/' + out_filename5
print('Writing file: mutational positions'