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

ran struc param analysis

Browse source
This commit is contained in:
Tanushree Tunstall 2020-06-17 19:36:02 +01:00
parent e21635fe02
commit 8d1daabff4
5 changed files with 373 additions and 382 deletions
Download patch file Download diff file Expand all files Collapse all files

9
scripts/combine_dfs.py
View file

@ -46,10 +46,8 @@ os.getcwd()
#=======================================================================
#%% 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 = 'TESTDRUG')
#arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = 'testGene') # case sensitive
arg_parser.add_argument('-d', '--drug', help='drug name', default = None)
arg_parser.add_argument('-g', '--gene', help='gene name', default = None) # case sensitive
args = arg_parser.parse_args()
#=======================================================================
#%% variable assignment: input and output
@ -288,8 +286,7 @@ def main():
, 'output csv:', out_filename)
combine_dfs(infile1, infile2, infile3, infile4, outfile)
print('Finished Writing file:'
, '\nFilename:', out_filename
, '\nPath:', outdir
, '\nFilename:', outfile
## , '\nNo. of rows:', ''
## , '\nNo. of cols:', ''
, '\n===========================================================')

30
scripts/data_extraction.py
View file

@ -57,8 +57,8 @@ args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
gene_match = gene + '_p.'
# building cols to extract
dr_muts_col = 'dr_mutations_' + drug
other_muts_col = 'other_mutations_' + drug
@ -80,8 +80,8 @@ datadir = homedir + '/' + 'git/Data'
#=======
# input
#=======
#in_filename = 'original_tanushree_data_v2.csv'
in_filename = 'mtb_gwas_v3.csv'
in_filename = 'original_tanushree_data_v2.csv'
#in_filename = 'mtb_gwas_v3.csv'
infile = datadir + '/' + in_filename
print('Input file: ', infile
, '\n============================================================')
@ -1028,25 +1028,25 @@ del(k, v, wt, mut, lookup_dict)
########
# combine the wild_type+poistion+mutant_type columns to generate
# Mutationinformation (matches mCSM output field)
# mutationinformation (matches mCSM output field)
# Remember to use .map(str) for int col types to allow string concatenation
#########
gene_LF1['Mutationinformation'] = gene_LF1['wild_type'] + gene_LF1.position.map(str) + gene_LF1['mutant_type']
print('Created column: Mutationinformation'
gene_LF1['mutationinformation'] = gene_LF1['wild_type'] + gene_LF1.position.map(str) + gene_LF1['mutant_type']
print('Created column: mutationinformation'
, '\n====================================================================='
, gene_LF1.Mutationinformation.head(10))
, gene_LF1.mutationinformation.head(10))
#%% Write file: mCSM muts
snps_only = pd.DataFrame(gene_LF1['Mutationinformation'].unique())
snps_only = pd.DataFrame(gene_LF1['mutationinformation'].unique())
snps_only.head()
# assign column name
snps_only.columns = ['Mutationinformation']
snps_only.columns = ['mutationinformation']
# count how many positions this corresponds to
pos_only = pd.DataFrame(gene_LF1['position'].unique())
print('Checking NA in snps...')# should be 0
if snps_only.Mutationinformation.isna().sum() == 0:
if snps_only.mutationinformation.isna().sum() == 0:
print ('PASS: NO NAs/missing entries for SNPs'
, '\n===============================================================')
else:
@ -1090,27 +1090,27 @@ print('Finished writing:', out_filename3
del(out_filename3)
#%% write file: mCSM style but with repitions for MSA and logo plots
all_muts_msa = pd.DataFrame(gene_LF1['Mutationinformation'])
all_muts_msa = pd.DataFrame(gene_LF1['mutationinformation'])
all_muts_msa.head()
# assign column name
all_muts_msa.columns = ['Mutationinformation']
all_muts_msa.columns = ['mutationinformation']
# make sure it is string
all_muts_msa.columns.dtype
# sort the column
all_muts_msa_sorted = all_muts_msa.sort_values(by = 'Mutationinformation')
all_muts_msa_sorted = all_muts_msa.sort_values(by = 'mutationinformation')
# create an extra column with protein name
all_muts_msa_sorted = all_muts_msa_sorted.assign(fasta_name = '3PL1')
all_muts_msa_sorted.head()
# rearrange columns so the fasta name is the first column (required for mutate.script)
all_muts_msa_sorted = all_muts_msa_sorted[['fasta_name', 'Mutationinformation']]
all_muts_msa_sorted = all_muts_msa_sorted[['fasta_name', 'mutationinformation']]
all_muts_msa_sorted.head()
print('Checking NA in snps...')# should be 0
if all_muts_msa.Mutationinformation.isna().sum() == 0:
if all_muts_msa.mutationinformation.isna().sum() == 0:
print ('PASS: NO NAs/missing entries for SNPs'
, '\n===============================================================')
else:

10
scripts/dssp_df.py
View file

@ -30,10 +30,8 @@ os.getcwd()
#=======================================================================
#%% 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 = 'TESTDRUG')
arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = 'testGene') # case sensitive
arg_parser.add_argument('-d', '--drug', help='drug name', default = None)
arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = None) # case sensitive
args = arg_parser.parse_args()
#=======================================================================
#%% variable assignment: input and output
@ -49,6 +47,8 @@ args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
gene_match = gene + '_p.'
#==========
# data dir
#==========
@ -147,7 +147,7 @@ def extract_chain_dssp(inputpdbfile):
return pdbchainlist
#=======================================================================
#%% write csv of processed dssp output
def dssp_to_csv(inputdsspfile, outfile, pdbchainlist):
def dssp_to_csv(inputdsspfile, outfile, pdbchainlist = ['A']):
"""
Create a df from a dssp file containing ASA, RSA, SS for all chains

11
scripts/kd_df.py
View file

@ -39,10 +39,8 @@ os.getcwd()
#=======================================================================
#%% 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 = 'DRUGNAME')
arg_parser.add_argument('-g', '--gene', help='gene name', default = 'geneName')
arg_parser.add_argument('-d', '--drug', help='drug name', default = None)
arg_parser.add_argument('-g', '--gene', help='gene name', default = None)
#arg_parser.add_argument('-p', '--plot', help='show plot', action='store_true')
args = arg_parser.parse_args()
#=======================================================================
@ -81,7 +79,7 @@ print('Output filename:', out_filename
#%% end of variable assignment for input and output files
#=======================================================================
#%% kd values from fasta file and output csv
def kd_to_csv(inputfasta, outputkdcsv, windowsize):
def kd_to_csv(inputfasta, outputkdcsv, windowsize = 3):
"""
Calculate kd (hydropathy values) from input fasta file
@ -223,8 +221,7 @@ def main():
, '\noutfile:', out_filename)
kd_to_csv(infile, outfile, 3)
print('Finished writing file:'
, '\nFilename:', out_filename
, '\nPath:', outdir
, '\nFilename:', outfile
, '\n=============================================================')
if __name__ == '__main__':

9
scripts/rd_df.py
View file

@ -31,10 +31,8 @@ os.getcwd()
#=======================================================================
#%% 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 = 'TESTDRUG')
arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = 'testGene') # case sensitive
arg_parser.add_argument('-d', '--drug', help='drug name', default = None)
arg_parser.add_argument('-g', '--gene', help='gene name', default = None) # case sensitive
args = arg_parser.parse_args()
#=======================================================================
#%% variable assignment: input and output
@ -165,8 +163,7 @@ def main():
, '\noutfile:', out_filename)
rd_to_csv(infile, outfile)
print('Finished Writing file:'
, '\nFilename:', out_filename
, '\nPath:', outdir
, '\nFilename:', outfile
, '\n=============================================================')
if __name__ == '__main__':