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

ran mcsm format for embb

Browse source
This commit is contained in:
Tanushree Tunstall 2021-11-13 09:43:56 +00:00
parent 4eaa0b5d2b
commit cee10cc540
3 changed files with 12 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

2
mcsm/mcsm.py
View file

@ -243,7 +243,7 @@ def format_mcsm_output(mcsm_outputcsv):
mcsm_data = mcsm_data.drop_duplicates(['mutationinformation']) mcsm_data = mcsm_data.drop_duplicates(['mutationinformation'])
print('Dim of data after removing duplicate muts:', mcsm_data.shape print('Dim of data after removing duplicate muts:', mcsm_data.shape
, '\n===========================================================') , '\n===========================================================')
#%%===================================================================== #%%=====================================================================
############# #############
# Create col: duet_outcome # Create col: duet_outcome
############# #############

16
mcsm/run_mcsm.py
View file

@ -79,13 +79,13 @@ gene_match = gene + '_p.'
# directories # directories
#============ #============
if not datadir: if not datadir:
datadir = homedir + '/' + 'git/Data' datadir = homedir + '/git/Data/'
if not indir: if not indir:
indir = datadir + '/' + drug + '/input' indir = datadir + drug + 'input/'
if not outdir: if not outdir:
outdir = datadir + '/' + drug + '/output' outdir = datadir + drug + 'output/'
#======= #=======
# input # input
@ -95,7 +95,7 @@ if pdb_filename:
else: else:
in_filename_pdb = gene.lower() + '_complex.pdb' in_filename_pdb = gene.lower() + '_complex.pdb'
infile_pdb = indir + '/' + in_filename_pdb infile_pdb = indir + in_filename_pdb
#in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile_mcsm_snps, from data_extraction.py) #in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile_mcsm_snps, from data_extraction.py)
#infile_snps = outdir + '/' + in_filename_snps #infile_snps = outdir + '/' + in_filename_snps
@ -105,7 +105,7 @@ if mutation_filename:
else: else:
in_filename_snps = gene.lower() + '_mcsm_formatted_snps.csv' in_filename_snps = gene.lower() + '_mcsm_formatted_snps.csv'
infile_snps = outdir + '/' + in_filename_snps infile_snps = outdir + in_filename_snps
#======= #=======
# output # output
@ -113,13 +113,13 @@ infile_snps = outdir + '/' + in_filename_snps
# mcsm_results globals # mcsm_results globals
if not result_urls: if not result_urls:
result_urls_filename = gene.lower() + '_result_urls.txt' result_urls_filename = gene.lower() + '_result_urls.txt'
result_urls = outdir + '/' + result_urls_filename result_urls = outdir + result_urls_filename
if DEBUG: if DEBUG:
print('DEBUG: Result URLs:', result_urls) print('DEBUG: Result URLs:', result_urls)
if not mcsm_output: if not mcsm_output:
mcsm_output_filename = gene.lower() + '_mcsm_output.csv' mcsm_output_filename = gene.lower() + '_mcsm_output.csv'
mcsm_output = outdir + '/' + mcsm_output_filename mcsm_output = outdir + mcsm_output_filename
if DEBUG: if DEBUG:
print('DEBUG: mCSM output CSV file:', mcsm_output) print('DEBUG: mCSM output CSV file:', mcsm_output)
@ -127,7 +127,7 @@ if not mcsm_output:
#out_filename_format = gene.lower() + '_mcsm_processed.csv' #out_filename_format = gene.lower() + '_mcsm_processed.csv'
if not outfile_format: if not outfile_format:
out_filename_format = gene.lower() + '_complex_mcsm_norm.csv' out_filename_format = gene.lower() + '_complex_mcsm_norm.csv'
outfile_format = outdir + '/' + out_filename_format outfile_format = outdir + out_filename_format
if DEBUG: if DEBUG:
print('DEBUG: formatted CSV output:', outfile_format) print('DEBUG: formatted CSV output:', outfile_format)
#%%===================================================================== #%%=====================================================================

4
scripts/combining_dfs.py
View file

@ -122,7 +122,9 @@ if gene.lower() == "gid":
in_filename_mcsm = gene.lower() + '_complex_mcsm_norm_SRY.csv' # was incorrectly SAM previously in_filename_mcsm = gene.lower() + '_complex_mcsm_norm_SRY.csv' # was incorrectly SAM previously
if gene.lower() == "embb": if gene.lower() == "embb":
print("\nReading mCSM file for gene:", gene) print("\nReading mCSM file for gene:", gene)
in_filename_mcsm = gene.lower() + '_complex_mcsm_norm1.csv' #in_filename_mcsm = gene.lower() + '_complex_mcsm_norm1.csv'
in_filename_mcsm = gene.lower() + '_complex_mcsm_norm2.csv'
if gene.lower() in gene_list_normal: if gene.lower() in gene_list_normal:
print("\nReading mCSM file for gene:", gene) print("\nReading mCSM file for gene:", gene)
in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv' in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv'