File size: 6,703 Bytes
70b95b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
#!/usr/bin/python
# coding: utf-8

# Author: LE YUAN
# Date: 2020-07-23  Run in python 3.7
# This script is to combine the Kcat data from BRENDA and Sabio-RK database

import csv
import json


with open('../../Data/database/Kcat_sabio_smiles.json', 'r') as infile:
    sabio_name_smiles = json.load(infile)

with open('../../Data/database/Kcat_brenda_smiles.json', 'r') as infile:
    brenda_name_smiles = json.load(infile)

with open("../../Data/database/Kcat_sabio_clean_unisubstrate_2.tsv", "r", encoding='utf-8') as file1 :
    sabio_lines = file1.readlines()[1:]

with open("../../Data/database/Kcat_brenda_clean.tsv", "r", encoding='utf-8') as file2 :
    brenda_lines = file2.readlines()[1:]

Kcat_data = list()
Kcat_data_include_value = list()
Substrate_name = dict()
Substrate_smiles = dict()
entry_uniprot = dict()

for line in brenda_lines :
    # print(line)
    data = line.strip().split('\t')
    ECNumber = data[1]
    Substrate = data[2]
    EnzymeType = set(data[3].split('/'))
    Organism =data[4]
    Value = data[5]
    Unit = data[6]

    smiles = brenda_name_smiles[Substrate]
    # print(smiles)
    if smiles is not None :
        # print(smiles)
        Substrate_name[Substrate.lower()] = Substrate
        Substrate_smiles[Substrate.lower()+'&smiles'] = smiles

        Kcat_data_include_value.append([ECNumber, Substrate.lower(), EnzymeType, Organism, Value, Unit])
        Kcat_data.append([ECNumber, Substrate.lower(), EnzymeType, Organism])

for line in sabio_lines :
    # print(line)
    data = line.strip().split('\t')
    ECNumber = data[1]
    Substrate = data[2]
    EnzymeType = set(data[3].split('/'))
    Organism =data[5]
    UniprotID = data[6]
    Value = data[7]
    Unit = data[8]

    smiles = sabio_name_smiles[Substrate]
    # print(smiles)
    if smiles is not None :
        # print(smiles)
        Substrate_name[Substrate.lower()] = Substrate
        Substrate_smiles[Substrate.lower()+'&smiles'] = smiles
        entry_uniprot[ECNumber + Substrate.lower() + Organism] = UniprotID

        Kcat_data_include_value.append([ECNumber, Substrate.lower(), EnzymeType, Organism, Value, Unit])
        Kcat_data.append([ECNumber, Substrate.lower(), EnzymeType, Organism])

print(len(Kcat_data))  # 49392


new_lines = list()
for line in Kcat_data :
    if line not in new_lines :
        new_lines.append(line)

print(len(new_lines))  # 48659 included all elements, 46165 included all except for Kcat value and unit,  44166 substrate lower and upper

i = 0
clean_Kcat = list()
for new_line in new_lines :
    # print(new_line)
    i += 1
    print(i)
    value_unit = dict()
    Kcat_values = list()
    for line in Kcat_data_include_value :
        if line[:-2] == new_line :
            value = line[-2]
            value_unit[str(float(value))] = line[-1]
            # print(type(value))  # <class 'str'>
            Kcat_values.append(float(value))
    # print(value_unit)
    # print(Kcat_values)
    max_value = max(Kcat_values) # choose the maximum one for duplication Kcat value under the same entry as the data what we use
    unit = value_unit[str(max_value)]
    # print(max_value)
    # print(unit)
    Substrate = Substrate_name[new_line[1]]
    Smiles = Substrate_smiles[new_line[1]+'&smiles']
    try :
        UniprotID = entry_uniprot[new_line[0]+new_line[1]+new_line[3]]
    except :
        UniprotID = ''
    new_line[1] = Substrate
    new_line[2] = '/'.join(new_line[2])
    new_line = new_line + [Smiles, UniprotID, str(max_value), unit]
    # print(new_line)
    # new_line.append(str(max_value))
    # new_line.append(unit)
    if new_line[-1] == 's^(-1)' :
        clean_Kcat.append(new_line)

# print(clean_Kcat)
print(len(clean_Kcat))  # 44166

with open("../../Data/database/Kcat_combination_0730.tsv", "w") as outfile :
    records = ['ECNumber', 'Substrate', 'EnzymeType', 'Organism', 'Smiles', 'UniprotID', 'Value', 'Unit']
    outfile.write('\t'.join(records) + '\n')
    for line in clean_Kcat :
        outfile.write('\t'.join(line) + '\n')

# The above is to eliminate the dupliaction entries by Substrate name
print('-----------------------------------------------')

# This is to eliminate the duplication entries by Smiles
with open("../../Data/database/Kcat_combination_0730.tsv", "r", encoding='utf-8') as infile :
    Kcat_lines = infile.readlines()[1:]

Kcat_data = list()
Kcat_data_include_value = list()
Substrate_name = dict()
entry_uniprot = dict()

for line in Kcat_lines :
    # print(line)
    data = line.strip().split('\t')
    ECNumber = data[0]
    Substrate = data[1]
    EnzymeType = set(data[2].split('/'))
    Organism =data[3]
    Smiles = data[4]
    UniprotID = data[5]
    Value = data[6]
    Unit = data[7]

    Substrate_name[Smiles] = Substrate
    entry_uniprot[ECNumber + Smiles + Organism] = UniprotID

    Kcat_data_include_value.append([ECNumber, EnzymeType, Organism, Smiles, Value, Unit])
    Kcat_data.append([ECNumber, EnzymeType, Organism, Smiles])

print(len(Kcat_data))  # 44166


new_lines = list()
for line in Kcat_data :
    if line not in new_lines :
        new_lines.append(line)

print(len(new_lines))  # 43495 included all elements, 41558 included all except for Kcat value and unit

i = 0
clean_Kcat = list()
for new_line in new_lines :
    # print(new_line)
    i += 1
    print(i)
    value_unit = dict()
    Kcat_values = list()
    for line in Kcat_data_include_value :
        if line[:-2] == new_line :
            value = line[-2]
            value_unit[str(float(value))] = line[-1]
            # print(type(value))  # <class 'str'>
            Kcat_values.append(float(value))
    # print(value_unit)
    # print(Kcat_values)
    max_value = max(Kcat_values) # choose the maximum one for duplication Kcat value under the same entry as the data what we use
    unit = value_unit[str(max_value)]
    # print(max_value)
    # print(unit)
    Substrate = Substrate_name[new_line[3]]
    try :
        UniprotID = entry_uniprot[new_line[0]+new_line[3]+new_line[2]]
    except :
        UniprotID = ''
    new_line[1] = '/'.join(new_line[1])
    new_line = new_line + [Substrate, UniprotID, str(max_value), unit]
    # print(new_line)
    # new_line.append(str(max_value))
    # new_line.append(unit)
    if new_line[-1] == 's^(-1)' :
        clean_Kcat.append(new_line)

# print(clean_Kcat)
print(len(clean_Kcat))  # 41558, in which 13454 entries have UniprotID

with open("../../Data/database/Kcat_combination_0731.tsv", "w") as outfile :
    records = ['ECNumber', 'EnzymeType', 'Organism', 'Smiles', 'Substrate', 'UniprotID', 'Value', 'Unit']
    outfile.write('\t'.join(records) + '\n')
    for line in clean_Kcat :
        outfile.write('\t'.join(line) + '\n')