Mercurial > repos > rakesh4osdd > asist

comparison clsi_profile_type2.py @ 0:c1a77856070c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/rakesh4osdd/asist/tree/master commit f5b374bef15145c893ffdd3a7d2f2978d8052184-dirty"
author rakesh4osdd
date Sat, 26 Jun 2021 07:27:53 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:c1a77856070c
1 #!/usr/bin/env python
2 # coding: utf-8
3
4 # In[1245]:
5
6
7 # ASIST module2 | map AST result to the CLSI breakporints with combination antibiotics
8 # By rakesh4osdd@gmail.com, 06-Jun-2021
9 import pandas as pd
10 import re
11 import sys
12
13
14 # In[1246]:
15
16
17 # cross check MIC values
18 def sus_res(mic):
19 #print(mic)
20 #print ((mic,pd.isna(mic[1]),pd.isna(mic[0]),'\n')
21 if not (pd.isna(mic[0]) or pd.isna(mic[1]) or pd.isna(mic[2])):#check for NaN value
22 #remove unwanted whitespace
23 o_mic = mic[0].replace(' ', '')
24 s_mic = mic[1].replace(' ', '')
25 r_mic = mic[2].replace(' ', '')
26 #print (o_mic,s_mic,r_mic)
27 #print (type(o_mic),type(s_mic),type(r_mic))
28 if '/' in s_mic: #check for combination antibiotics
29 #print ('combination antibiotics')
30 try:
31 if '/' in o_mic:
32 #print ('input combination')
33 if (float(o_mic.split('/')[0]) <= float(s_mic.split('/')[0]) and float(o_mic.split('/')[1]) <= float(s_mic.split('/')[1])):
34 strain_type='Susceptible'
35 elif (float(o_mic.split('/')[0]) >= float(r_mic.split('/')[0]) and float(o_mic.split('/')[1]) >= float(r_mic.split('/')[1])):
36 strain_type='Resistant'
37 else:
38 strain_type='Intermediate'
39 else:
40 #print ('single')
41 if float(o_mic)==0:
42 strain_type='Strain could not classified'
43 elif (float(o_mic.split('/')[0]) <= float(s_mic.split('/')[0]) and float(1) <= float(s_mic.split('/')[1])):
44 strain_type='Susceptible'
45 elif (float(o_mic.split('/')[0]) >= float(r_mic.split('/')[0]) and float(1) >= float(r_mic.split('/')[1])):
46 strain_type='Resistant'
47 else:
48 strain_type='Intermediate'
49 except ValueError:
50 strain_type='Strain could not classified'
51 else: #single antibiotics
52 #print('single antibiotics')
53 if o_mic:
54 if float(o_mic)==0:
55 strain_type='Strain could not classified'
56 elif (float(o_mic) <= float(s_mic)):
57 strain_type='Susceptible'
58 elif (float(o_mic) >= float(r_mic)):
59 strain_type='Resistant'
60 else:
61 strain_type='Intermediate'
62 else:
63 strain_type='Strain could not classified'
64 else:
65 strain_type='Strain could not classified'
66 return(strain_type)
67
68
69 # In[ ]:
70
71 # for input argument
72 input_user = sys.argv[1]
73 input_clsi = sys.argv[2]
74 output_table = sys.argv[3]
75
76 # In[1247]:
77
78
79 """
80 input_user='input_ast_comb2.csv'
81 input_clsi='clsi_profile_comb.csv'
82 output_profile=input_user+'_profile.csv'
83 output_table=input_user+'_table.csv'
84
85 """
86
87 # In[1248]:
88
89
90 # read user AST data with selected 3 columns
91 strain_mic=pd.read_csv(input_user, sep=',', usecols =['Strain name', 'Antibiotics', 'MIC'],na_filter=False)
92
93
94 # In[1249]:
95
96
97 clsi_bp=pd.read_csv(input_clsi,sep=',')
98
99
100 # In[1290]:
101
102
103 #clsi_bp.head(2)
104 #strain_mic
105
106
107 # In[1251]:
108
109
110 # convert MIC to numbers sMIC, rMIC
111 clsi_bp['s_mic'] =clsi_bp[['Susceptible']].applymap(lambda x: (re.sub(r'[^0-9.\/]', '', x)))
112 clsi_bp['r_mic'] =clsi_bp[['Resistant']].applymap(lambda x: (re.sub(r'[^0-9.\/]', '', x)))
113
114
115 # In[1252]:
116
117
118 # Read only numbers in MIC values
119 #try:
120 strain_mic['o_mic']=strain_mic[['MIC']].applymap(lambda x: (re.sub(r'[^0-9.\/]','', x)))
121 #except TypeError:
122 # print('Waring: Error in MIC value')
123
124
125 # In[1289]:
126
127
128 #strain_mic.head()
129
130
131 # In[1254]:
132
133
134 # capitalize each Antibiotic Name for comparision with removing whitespace
135 strain_mic['Antibiotics']=strain_mic['Antibiotics'].str.capitalize().str.replace(" ","")
136 clsi_bp['Antibiotics']=clsi_bp['Antibiotics'].str.capitalize().str.replace(" ","")
137
138
139 # In[1255]:
140
141
142 #compare CLSI Antibiotics only
143 #result=pd.merge(strain_mic, clsi_bp, on='Antibiotics',how='inner', indicator=True)[['Strain name','Antibiotics', 'MIC', 'o_mic', 's_mic', 'r_mic','_merge']]
144 try:
145 result=pd.merge(strain_mic, clsi_bp, on='Antibiotics',how='inner')[['Strain name','Antibiotics', 'MIC', 'o_mic', 's_mic', 'r_mic']]
146 except KeyError:
147 print('Waring: Error in input Values')
148
149
150 # In[1256]:
151
152
153 #compare MIC values and assign Susceptible and Resistant to Strain
154 #try:
155 result[['CLSI_profile']] = result[['o_mic','s_mic','r_mic']].apply(sus_res,axis = 1)
156 #except ValueError:
157 # print('Waring: Error in input MIC value')
158
159
160 # In[1288]:
161
162
163 #result
164
165
166 # In[1258]:
167
168
169 #result[['Strain name', 'Antibiotics', 'MIC','s_mic','r_mic','CLSI_profile']].to_csv(output_profile,sep=',', index=False, encoding='utf-8-sig')
170
171
172 # In[1259]:
173
174
175 #create a pivot table for ASIST
176 table=result[['Strain name', 'Antibiotics','CLSI_profile']].drop_duplicates()
177 result_table=pd.pivot_table(table, values ='CLSI_profile', index =['Strain name'],columns =['Antibiotics'], aggfunc = lambda x: ' '.join(x))
178
179
180 # In[1261]:
181
182
183 result_table
184
185
186 # In[1264]:
187
188
189 #result_table.to_csv(output_table,na_rep='NA')
190
191
192 # In[1282]:
193
194
195 # reorder the Antibiotics for ASIST
196 clsi_ab=['Amikacin','Tobramycin','Gentamycin','Imipenem','Meropenem','Doripenem','Ciprofloxacin','Levofloxacin',
197 'Piperacillin/tazobactam','Ticarcillin/clavulanicacid','Cefotaxime','Ceftriaxone','Ceftazidime','Cefepime',
198 'Trimethoprim/sulfamethoxazole','Ampicillin/sulbactam','Colistin','Polymyxinb','Tetracycline','Doxicycline ',
199 'Minocycline']
200 result_selected=result_table.filter(clsi_ab)
201
202
203 # In[1283]:
204
205
206 result_selected.shape
207
208
209 # In[1284]:
210
211
212 result_table.shape
213
214
215 # In[1285]:
216
217
218 result_selected.insert(0,'Resistance_phenotype','')
219
220
221 # In[1286]:
222
223
224 result_selected.to_csv(output_table,na_rep='NA')
225
226
227 # In[1287]:
228
229
230 #rename headers
231 result_selected.rename(columns = {'Ticarcillin/clavulanicacid':'Ticarcillin/clavulanic acid','Piperacillin/tazobactam':'Piperacillin/ tazobactam','Trimethoprim/sulfamethoxazole': 'Trimethoprim/ sulfamethoxazole','Ampicillin/sulbactam':'Ampicillin/ sulbactam', 'Polymyxinb': 'Polymyxin B'} )
232
233
234 # In[ ]:
235
236
237
238
239
240 # In[ ]:
241
242
243
244