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 96da4d8ed5
commit 2cebd338ba
5 changed files with 373 additions and 382 deletions
Download patch file Download diff file Expand all files Collapse all files

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: