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

tidy script for linking or_kinship with missense variant info

Browse source
This commit is contained in:
Tanushree Tunstall 2020-08-14 16:41:11 +01:00
parent 805868ce7e
commit 87f5a9ca05
2 changed files with 143 additions and 153 deletions
Download patch file Download diff file Expand all files Collapse all files

40
scripts/find_missense.py
View file

@ -4,15 +4,15 @@ import pandas as pd
DEBUG = False
#%%
#def find_missense(test_df, ref_allele1, alt_allele0):
def find_missense(test_df, ref_allele_column, alt_allele_column, n_diff_colname = 'n_diff', tot_diff_colname = 'tot_diff', ref_a_colname = 'ref_allele', alt_a_colname = 'alt_allele'):
#def find_missense(df, ref_allele1, alt_allele0):
def find_missense(df, ref_allele_column, alt_allele_column, n_diff_colname = 'n_diff', tot_diff_colname = 'tot_diff', ref_a_colname = 'ref_allele', alt_a_colname = 'alt_allele'):
"""Find mismatches in pairwise comparison of strings b/w col_a and col_b
Case insensitive, converts strings to uppercase before comparison
@test_df: df containing columns to compare
@df: df containing columns to compare
@type: pandas df
@ref_allele_column: column containing ref allele str
@ -37,7 +37,7 @@ def find_missense(test_df, ref_allele_column, alt_allele_column, n_diff_colname
name will override original column
@rtype: pandas df
"""
for ind, val in test_df.iterrows():
for ind, val in df.iterrows():
if DEBUG:
print('index:', ind, 'value:', val
, '\n============================================================')
@ -46,9 +46,9 @@ def find_missense(test_df, ref_allele_column, alt_allele_column, n_diff_colname
if DEBUG:
print('ref_allele_string:', ref_a, 'alt_allele_string:', alt_a)
difference = sum(1 for e in zip(ref_a, alt_a) if e[0] != e[1])
test_df.at[ind, n_diff_colname] = difference # adding column
df.at[ind, n_diff_colname] = difference # adding column
tot_difference = difference + abs(len(ref_a) - len(alt_a))
test_df.at[ind, tot_diff_colname] = tot_difference # adding column
df.at[ind, tot_diff_colname] = tot_difference # adding column
if difference != tot_difference:
print('WARNING: lengths of ref_allele and alt_allele differ at index:', ind
, '\nNon-missense muts detected')
@ -57,29 +57,29 @@ def find_missense(test_df, ref_allele_column, alt_allele_column, n_diff_colname
ref_aln = ''
alt_aln = ''
if ref_a == alt_a:
##test_df.at[ind, 'ref_allele'] = 'no_change' # adding column
##test_df.at[ind, 'alt_allele'] = 'no_change' # adding column
test_df.at[ind, ref_a_colname] = 'no_change' # adding column
test_df.at[ind, alt_a_colname] = 'no_change' # adding column
##df.at[ind, 'ref_allele'] = 'no_change' # adding column
##df.at[ind, 'alt_allele'] = 'no_change' # adding column
df.at[ind, ref_a_colname] = 'no_change' # adding column
df.at[ind, alt_a_colname] = 'no_change' # adding column
elif len(ref_a) == len(alt_a) and len(ref_a) > 0:
print('ref:', ref_a, 'alt:', alt_a)
for n in range(len(ref_a)):
if ref_a[n] != alt_a[n]:
ref_aln += ref_a[n]
alt_aln += alt_a[n]
##test_df.at[ind, 'ref_allele'] = ref_aln
##test_df.at[ind, 'alt_allele'] = alt_aln
test_df.at[ind, ref_a_colname] = ref_aln
test_df.at[ind, alt_a_colname] = alt_aln
##df.at[ind, 'ref_allele'] = ref_aln
##df.at[ind, 'alt_allele'] = alt_aln
df.at[ind, ref_a_colname] = ref_aln
df.at[ind, alt_a_colname] = alt_aln
print('ref:', ref_aln)
print('alt:', alt_aln)
else:
##test_df.at[ind, 'ref_allele'] = 'ERROR_Not_nsSNP'
##test_df.at[ind, 'alt_allele'] = 'ERROR_Not_nsSNP'
test_df.at[ind, ref_a_colname] = 'ERROR_Not_nsSNP'
test_df.at[ind, alt_a_colname] = 'ERROR_Not_nsSNP'
##df.at[ind, 'ref_allele'] = 'ERROR_Not_nsSNP'
##df.at[ind, 'alt_allele'] = 'ERROR_Not_nsSNP'
df.at[ind, ref_a_colname] = 'ERROR_Not_nsSNP'
df.at[ind, alt_a_colname] = 'ERROR_Not_nsSNP'
return test_df
return df
#========================================
# a representative example
#eg_df = pd.read_csv('pnca_assoc.txt', sep = '\t', nrows = 10, header = 0, index_col = False)
@ -90,7 +90,7 @@ def find_missense(test_df, ref_allele_column, alt_allele_column, n_diff_colname
#def main():
#find_missense(eg_df, ref_allele1 = 'ref_allele', alt_allele0 = 'alt_allele')
# find_missense(test_df = eg_df, ref_allele_column = 'ref_allele1', alt_allele_column = 'alt_allele0')
# find_missense(df = eg_df, ref_allele_column = 'ref_allele1', alt_allele_column = 'alt_allele0')
# print(eg_df)
#if __name__ == '__main__':