Fixed dictionary key deletion bug

schultzm · Sep 6, 2017 · bc7d1f3 · bc7d1f3
1 parent d0857d9
commit bc7d1f3
Show file tree

Hide file tree

Showing 2 changed files with 73 additions and 66 deletions.
diff --git a/Pandoo/pandoo_tasks.py b/Pandoo/pandoo_tasks.py
@@ -177,30 +177,25 @@ def run_abricate(infile, outfile, outfile_simple, isolate, dbase, coverage,
  ab_results_simplified = defaultdict(list)
  for i in ab_data.index.values:
  gene_name = pregx.sub('', ab_data.loc[i, 'GENE'])
-# print('gene_name', gene_name)
  ab_results_simplified['Abricate_'+dbase[0]+'_all_genes'] \
  .append(gene_name)
  for key, value in genes_dict['GENES'].items():
-# for item in genes_dict['GENES'][key]:
-# print(item)
-# print('key', key)
-# sublist = [j for j in genes_dict['GENES'][key] if gene_name.lower() == j.lower()]
-# print(isolate, 'dbase', dbase[0], 'sublist', sublist, gene_name)
  if gene_name in genes_dict['GENES'][key]:
  ab_results_simplified['Abricate_'+dbase[0]+'_'+key] \
  .append(gene_name)
-
+ # RULES:
+ # CPE_ALERT
+ # ENTEROBACTERIACEAE with CPE_gene
  if key == 'CPE_genes':
- if species.split()[0] in [genus for genus in genes_dict['Enterobacteriaceae']] or species in [genus for genus in genes_dict['Enterobacteriaceae']]:
- if 'CPE_ALERT_'+dbase[0] not in ab_results_simplified:
- ab_results_simplified['CPE_ALERT_'+dbase[0]] = 'CPE_ALERT'
+ if species.split()[0] in [genus for genus in
+ genes_dict['Enterobacteriaceae']] or species in [genus for genus in genes_dict['Enterobacteriaceae']]:
+ ab_results_simplified['CPE_ALERT_'+dbase[0]] = 'CPE_ALERT'
+ # RULES:
+ # CARALERT
+ # Enterobacteriaceae with 16S_Methyltransferase_gene.
  if key == '16S_Methyltransferase_genes':
  if species.split()[0] in [genus for genus in genes_dict['Enterobacteriaceae']] or species in [genus for genus in genes_dict['Enterobacteriaceae']]:
- if 'CARALERT_'+dbase[0] not in ab_results_simplified:
- ab_results_simplified['CARALERT_'+dbase[0]] = 'CARALERT'
-
-
-# print(ab_results_simplified)
+ ab_results_simplified['CARALERT_'+dbase[0]] = 'CARALERT'
  ab_results = {}
  # Generate the simplified dict
  simplifiedtable_key = 'abricate_'+dbase[0] +\
@@ -211,16 +206,17 @@ def run_abricate(infile, outfile, outfile_simple, isolate, dbase, coverage,
  ab_results_simplified[simplifiedtable_key] = 'yes'
  ab_results_simplified['Abricate_'+dbase[0] +
  '_genes_confirmed'] \
- .append(gene_name)
+  .append(gene_name)
  else:
  ab_results_simplified[simplifiedtable_key] = 'maybe'
- del ab_results_simplified['Abricate_'+dbase[0] +
- '_genes_confirmed']
+ if 'Abricate_'+dbase[0]+'_genes_confirmed' in ab_results_simplified:
+ if gene_name in ab_results_simplified['Abricate_'+dbase[0] +
+ '_genes_confirmed']:
+ ab_results_simplified['Abricate_'+dbase[0] +
+ '_genes_confirmed'].remove(gene_name)
  ab_results_simplified['Abricate_'+dbase[0] +
  '_genes_unconfirmed'] \
  .append(gene_name)
-# if ab_data.loc[i, '%COVERAGE'] < coverage or \
-# ab_data.loc[i, '%IDENTITY'] < identity:
  else:
  ab_results_simplified[simplifiedtable_key] = 'maybe'
  ab_results_simplified['Abricate_'+dbase[0] +

diff --git a/Pandoo/resistance_alert.py b/Pandoo/resistance_alert.py
@@ -1,55 +1,77 @@
-#this code is development
 import pandas as pd
 from collections import defaultdict
 
-
-DFRAME = pd.read_table('ftp://ftp.ncbi.nlm.nih.gov/pathogen/betalactamases/Allele.tab', header=0, index_col='#allele name')
-# print(DFRAME)
+FTP_URL = 'ftp://ftp.ncbi.nlm.nih.gov/pathogen/betalactamases/Allele.tab'
+DFRAME = pd.read_table(FTP_URL, header=0, index_col='#allele name')
 
 def gene_list(dframe, k_word, columnname):
  '''
  Parse DFRAME to retrieve gene list matching k_word and columnname criteria.
  '''
- return [dframe.loc[value, 'gene name'] for value in dframe.index.values if k_word in dframe.loc[value, columnname]]
+ return [dframe.loc[value, 'gene name'] for value in dframe.index.values
+ if k_word in dframe.loc[value, columnname]]
 
 
-METALLO_BETALACTAMASES = gene_list(DFRAME, 'metallo-beta-lactamase', 'curated gene product name')
-CARBAPENEMASES = gene_list(DFRAME, 'carbapenem-hydrolyzing', 'curated gene product name')
+METALLO_BETALACTAMASES = gene_list(DFRAME, 'metallo-beta-lactamase',
+ 'curated gene product name')
+CARBAPENEMASES = gene_list(DFRAME, 'carbapenem-hydrolyzing',
+ 'curated gene product name')
 FULL_CPE_GENES = METALLO_BETALACTAMASES + CARBAPENEMASES
-ESBL_GENES = gene_list(DFRAME, 'extended-spectrum beta-lactamase', 'curated gene product name')
+ESBL_GENES = gene_list(DFRAME, 'extended-spectrum beta-lactamase',
+ 'curated gene product name')
 RMTASE_GENES = ['armA',
+ 'npmA',
  'rmtA',
+ 'rmtA_1',
  'rmtB',
+ 'rmtB1',
+ 'rmtB2',
+ 'rmtB2_1',
+ 'rmtB3',
+ 'rmtB4',
+ 'rmtB_1',
  'rmtC',
+ 'rmtC_1',
  'rmtD',
+ 'rmtD1',
+ 'rmtD2',
+ 'rmtD2_1',
+ 'rmtD_1',
  'rmtE',
+ 'rmtE1',
+ 'rmtE2',
+ 'rmtE_1',
  'rmtF',
+ 'rmtF1',
+ 'rmtF2',
  'rmtG',
+ 'rmtG_1',
  'rmtH',
- 'npmA']
-
-COLISTIN_GENES = ['mcr-1']#.1',
-# 'mcr-1.2',
-# 'mcr-1.3',
-# 'mcr-1.4',
-# 'mcr-1.5',
-# 'mcr-1.6',
-# 'mcr-1.7',
-# 'mcr-1.8',
-# 'mcr-2.1',
-# 'mcr-3.1',
-# 'mcr-4.1']
-# print(METALLO_BETALACTAMASES)
-# print(CARBAPENEMASES)
-# print('carbapenemases', FULL_CPE_GENES)
-# print(ESBL_GENES)
+ 'rmtH_1',
+ 'rmtf_1']
 
+COLISTIN_GENES = ['mcr-1',
+ 'mcr-1.1',
+ 'mcr-1.2',
+ 'mcr-1.2_1',
+ 'mcr-1.3',
+ 'mcr-1.3_1',
+ 'mcr-1.4',
+ 'mcr-1.4_1',
+ 'mcr-1.5',
+ 'mcr-1.5_1',
+ 'mcr-1.6',
+ 'mcr-1.6_1',
+ 'mcr-1.7',
+ 'mcr-1.7_1',
+ 'mcr-1.8',
+ 'mcr-1.9_1',
+ 'mcr-1_1',
+ 'mcr-2',
+ 'mcr-2_1',
+ 'mcr-3_1',
+ 'mcr_1.8_1']
 
-#CARALERT NOTIFICATION
-#Enterobacteriaceae with 16S rRNA methylase gene detected.
-
-#CPE alert
-#ENTEROBACTERIACEAE with full_cpe_gene
 ENTEROBACTERIACEAE = ['Cedecea',
  'Citrobacter',
  'Morganella',
@@ -72,25 +94,14 @@ def gene_list(dframe, k_word, columnname):
  'Serratia',
  'Shigella',
  'Yersinia']
+# RULES:
+# CARALERT NOTIFICATION
+# Enterobacteriaceae with 16S_Methyltransferase_gene.
+# CPE alert
+# ENTEROBACTERIACEAE with CPE_gene
 
 GENES_DICT = {'GENES': {'CPE_genes': FULL_CPE_GENES,
  'ESBL_genes': ESBL_GENES,
  '16S_Methyltransferase_genes': RMTASE_GENES,
  'Colistin_genes': COLISTIN_GENES},
  'Enterobacteriaceae': ENTEROBACTERIACEAE}
-# print(GENES_DICT)
-
-# print(genes_dict)
-# class Isolate:
-# def __init__(name, genus_epithet, specific_epithet, amr_profile):
-# '''
-# Isolate name, genus, species, and resistance genes.
-# '''
-# self.name = name
-# self.genus_epithet = genus_epithet
-# self.specific_epithet = specific_epithet
-# self.amr_profile = amr_profile
-# def x():
-# pass
-# 
-