total_compare_reject2_unmatched1 = ml.compareTables(unmatched_keeps1, rejects2)
matched_reject2_unmatched1 = total_compare_reject2_unmatched1[1] #1 is the second table
total_compare_reject1_unmatched2 = ml.compareTables(unmatched_keeps2, rejects1)
matched_reject1_unmatched2 = total_compare_reject1_unmatched2[1]
'''
#Debug
ml.outputTable('rejects_NC_TC.txt', rejects1)
ml.outputTable('rejects_NF_TF.txt', rejects2)
ml.outputTable('unmatched_NC_TC.txt', unmatched_keeps1)
ml.outputTable('unmatched_NF_TF.txt', unmatched_keeps2)
'''
#Select only certain categories
keeps1 = ml.saveByCategory(keeps1)
keeps2 = ml.saveByCategory(keeps2)
matched_reject1_unmatched2 = ml.saveByCategory(matched_reject1_unmatched2)
matched_reject2_unmatched1 = ml.saveByCategory(matched_reject2_unmatched1)
#Write tables to text files
'''
ml.outputTable(keeps1, 'NC TC KEEP', 'output_keeps.NC_TC.xls')
ml.outputTable(keeps2, 'NF TF KEEP', 'output_keeps.NF_TF.xls')
ml.outputTable(matched_reject1_unmatched2, 'NC TC Matched REJECTS', 'output_reject of unmatched.NC_TC.xls')
ml.outputTable(matched_reject2_unmatched1, 'NF TF Matched REJECTS','output_reject of unmatched.NF_TF.xls')
'''
book = xlwt.Workbook()
sheet1 = book.add_sheet('NC TC KEEP')
sheet2 = book.add_sheet('NF TF KEEP')
def processMutations(first_file, second_file , input_directory, output_file, output_directory, lines_skip):
from xlsxwriter.workbook import Workbook
import methodslist as ml
import os
# Set directory
old_dir = os.getcwd()
os.chdir(output_directory)
print('\nStarting at %r' % input_directory)
# Import text to tables
table1 = ml.importTable(first_file, input_directory, lines_skip)
table2 = ml.importTable(second_file, input_directory, lines_skip)
# Save rows with detected mutations
keeps1 = ml.saveByValue(table1, 'judgement', 'KEEP')
keeps2 = ml.saveByValue(table2, 'judgement', 'KEEP')
# Find mutated rows with that are matched and unmatched
total_comparison = ml.compareTables(keeps1, keeps2)
'''
Comparision array:
0 is same_first_table
1 is same_second_table
2 is diff_first_table
3 is diff_second_table
'''
matched_keeps1 = total_comparison[0]
matched_keeps2 = total_comparison[1]
unmatched_keeps1 = total_comparison[2]
unmatched_keeps2 = total_comparison[3]
# Save rows with no detected mutations
rejects1 = ml.saveByValue(table1, 'judgement', 'REJECT')
rejects2 = ml.saveByValue(table2, 'judgement', 'REJECT')
# Compare unmatched KEEP rows of one table to REJECT rows of other table
total_compare_reject2_unmatched1 = ml.compareTables(unmatched_keeps1, rejects2)
matched_reject2_unmatched1 = total_compare_reject2_unmatched1[1] # 1 is the second column
total_compare_reject1_unmatched2 = ml.compareTables(unmatched_keeps2, rejects1)
matched_reject1_unmatched2 = total_compare_reject1_unmatched2[1]
# Select only certain categories
keeps1 = ml.saveByCategory(keeps1)
keeps2 = ml.saveByCategory(keeps2)
matched_reject2_unmatched1 = ml.saveByCategory(matched_reject2_unmatched1)
matched_reject1_unmatched2 = ml.saveByCategory(matched_reject1_unmatched2)
# Calculate concordance between NC TC and NF TF
concordance_table = ml.calcCondordance(unmatched_keeps1, unmatched_keeps2, matched_keeps1)
# Write tables to text files
book = Workbook(output_file)
ml.outputTable(book, concordance_table, 'Concordance Summary', output_directory)
ml.outputTable(book, keeps1, 'NC TC KEEP', output_directory)
ml.outputTable(book, keeps2, 'NF TF KEEP', output_directory)
ml.outputTable(book, matched_reject2_unmatched1, 'NF TF Matched REJECTS', output_directory)
ml.outputTable(book, matched_reject1_unmatched2, 'NC TC Matched REJECTS', output_directory)
book.close()
os.chdir(old_dir)
print('Finished')
def processMutations(first_file, second_file , input_directory, output_file, output_directory, lines_skip): import methodslist as ml import xlwt import os # Set directory old_dir = os.getcwd() os.chdir(output_directory) print '\nStarting at %r' % input_directory #Import text to tables table1 = ml.importTable(first_file, input_directory, lines_skip) table2 = ml.importTable(second_file, input_directory, lines_skip) #Save rows with detected mutations keeps1 = ml.saveByValue(table1, 'judgement', 'KEEP') keeps2 = ml.saveByValue(table2, 'judgement', 'KEEP') #Find mutated rows with that are matched and unmatched total_comparison = ml.compareTables(keeps1, keeps2) ''' 0 is same_first_table 1 is same_second_table 2 is diff_first_table 3 is diff_second_table ''' matched_keeps1 = total_comparison[0] matched_keeps2 = total_comparison[1] unmatched_keeps1 = total_comparison[2] unmatched_keeps2 = total_comparison[3] #Save rows with no detected mutations rejects1 = ml.saveByValue(table1, 'judgement', 'REJECT') rejects2 = ml.saveByValue(table2, 'judgement', 'REJECT') #Compare unmatched KEEP rows of one table to REJECT rows of other table total_compare_reject2_unmatched1 = ml.compareTables(unmatched_keeps1, rejects2) matched_reject2_unmatched1 = total_compare_reject2_unmatched1[1] #1 is the second table total_compare_reject1_unmatched2 = ml.compareTables(unmatched_keeps2, rejects1) matched_reject1_unmatched2 = total_compare_reject1_unmatched2[1] #Select only certain categories keeps1 = ml.saveByCategory(keeps1) keeps2 = ml.saveByCategory(keeps2) matched_reject2_unmatched1 = ml.saveByCategory(matched_reject2_unmatched1) matched_reject1_unmatched2 = ml.saveByCategory(matched_reject1_unmatched2) #Calculate concordance between NC TC and NF TF rejects1_unmatched_num = len(unmatched_keeps1)-1.0 rejects2_unmatched_num = len(unmatched_keeps2)-1.0 keeps_num = len(matched_keeps1)-1.0 total_num = rejects1_unmatched_num + rejects2_unmatched_num + keeps_num rejects1_unmatched_percent = rejects1_unmatched_num/total_num * 100 rejects2_unmatched_percent = rejects2_unmatched_num/total_num * 100 keeps_percent = keeps_num/total_num * 100 #Write tables to text files book = xlwt.Workbook() #Output concordance summary_table = [['Concordance', '', '', ''], ['', 'FFPE', 'Both', 'Cryo']] summary_table.append(['', rejects2_unmatched_num, keeps_num, rejects1_unmatched_num]) summary_table.append(['', rejects2_unmatched_percent, keeps_percent, rejects1_unmatched_percent]) #Output tables ml.outputTable(book, summary_table, 'Concordance Summary', output_directory) ml.outputTable(book, keeps1, 'NC TC KEEP', output_directory) ml.outputTable(book, keeps2, 'NF TF KEEP', output_directory) ml.outputTable(book, matched_reject2_unmatched1, 'NF TF Matched REJECTS', output_directory) ml.outputTable(book, matched_reject1_unmatched2, 'NC TC Matched REJECTS', output_directory) book.save(output_file) os.chdir(old_dir) print 'Finished'