saving from work

mcsm_analysis/pyrazinamide/scripts/generate_mut_sequences.py

@@ -9,6 +9,7 @@ Created on Tue Jun 25 08:46:36 2019
 # load libraries
 import os
 import pandas as pd
+import numpy as np
 from Bio import SeqIO
 ############################################
 #********************************************************************
@@ -86,7 +87,7 @@ print("new length:", len(my_fasta))
 #############
 # read mutant_info file and extract cols with positions and mutant_info
 # This should be all samples with pncA muts
-#my_data = pd.read_csv('mcsm_complex1_normalised.csv') #335, 15
+#my_data = pd.read_csv('mcsm_complex1_normalised.csv') 
 my_data = pd.read_csv(infile_meta_data)
 list(my_data.columns)
 #my_data['OR'].value_counts()
@@ -95,12 +96,34 @@ list(my_data.columns)
 #FIXME: You need a better way to identify this
 # ideally this file should not contain any non_struc pos
 # remove positions not in the structure
-my_data = my_data[my_data.position != ns_pos_o] #3092, 22
+my_data = my_data[my_data.position != ns_pos_o] 
 
 # if multiple positions, then try the example below;
 # https://stackoverflow.com/questions/29017525/deleting-rows-based-on-multiple-conditions-python-pandas
 #df = df[(df.one > 0) | (df.two > 0) | (df.three > 0) & (df.four < 1)]
 
+# count mutations per sample
+mut_info = my_data[['id', 'Mutationinformation', 'wild_type', 'position', 'mutant_type']]
+
+# test
+foo = mut_info[mut_info.Mutationinformation.str.contains('C72Y')]
+ 
+foo = mut_info.pivot_table(values = ['Mutationinformation']
+                           , index = ['Mutationinformation', 'id']
+#                           , columns = 
+                           , aggfunc = 'count')
+
+# table
+foo_tab = mut_info.pivot_table(values = ['Mutationinformation']
+#                           , index = ['Mutationinformation']
+                           , columns = ['id', 'Mutationinformation']
+                           , aggfunc = 'count'
+#                           , margins = True)
+                           )
+foo_tab.stack('id')
+
+mut_info.to_csv('mutinfo.csv')
+
 mut_info1 = my_data[['position', 'mutant_type']]
 #%%
 ################

meta_data_analysis/pnca_data_extraction.py

@@ -118,14 +118,16 @@ clear variables
 meta_pza = meta_data.loc[meta_data.dr_mutations_pyrazinamide.str.contains('pncA_p.*', na = False)] 
 #2163 {RESULT: samples with dr_muts}
 dr_id = meta_pza['id'].unique()
+dr_id = pd.Series(dr_id)
 
 meta_pza = meta_data.loc[meta_data.other_mutations_pyrazinamide.str.contains('pncA_p.*', na = False)] 
 #526 (RESULT: samples with other_muts)
 other_id = meta_pza['id'].unique()
+other_id = pd.Series(other_id)
 
 # FIXME: See if the sample ids are unique in each
 # find any common IDs
-dr_id.isin(other_id[1,1])
+dr_id.isin(other_id).sum()
 
 del(meta_pza)
 
@@ -159,8 +161,7 @@ del(meta_pnca_other)
 # Now extract "all" mutations
 meta_pnca_all = meta_data_pnca.loc[meta_data_pnca.dr_mutations_pyrazinamide.str.contains('pncA_p.*') | meta_data_pnca.other_mutations_pyrazinamide.str.contains('pncA_p.*') ]
 
-
+meta_pnca_all['id'].nunique() #RESULT: pnca mutations in ALL samples}
-meta_pnca_all['id'].nunique() {#RESULT: pnca mutations in ALL samples}
 pnca_samples = len(meta_pnca_all)
 pnca_na = meta_pnca_all['pyrazinamide'].isna().sum() 
 comp_pnca_samples = pnca_samples - pnca_na 
@@ -170,8 +171,8 @@ comp_pnca_samples = pnca_samples - pnca_na
 #=#=#=#=#=#=#
 
 # sanity checks
-meta_pnca_all.dr_mutations_pyrazinamide.value_counts()
+foo1 = meta_pnca_all.dr_mutations_pyrazinamide.value_counts()
-meta_pnca_all.other_mutations_pyrazinamide.value_counts()
+foo2 = meta_pnca_all.other_mutations_pyrazinamide.value_counts()
 
 # more sanity checks 
 # !CAUTION!: muts will change depending on your gene
@@ -182,7 +183,7 @@ meta_pnca_all.loc[meta_pnca_all.dr_mutations_pyrazinamide.str.contains('pncA_p.P
 meta_pnca_all.loc[meta_pnca_all.dr_mutations_pyrazinamide.str.contains('pncA_p.Val139Leu')]
 
 meta_pnca_all.loc[meta_pnca_all.dr_mutations_pyrazinamide.str.contains('pncA_p.')] # exists #  rows
-m = meta_pnca_all.loc[meta_pnca_all.dr_mutations_pyrazinamide.str.contains('pncA_p.')] # exists #  rows
+meta_pnca_all.loc[meta_pnca_all.dr_mutations_pyrazinamide.str.contains('pncA_p.')] # exists #  rows
 
 # other_muts
 meta_pnca_all.loc[meta_pnca_all.other_mutations_pyrazinamide.str.contains('pncA_p.Gln10Pro*')] # empty