CircRNA-DiseaseAnalysis/similarity2.py at master · JesseYule/CircRNA-DiseaseAnalysis · GitHub

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
import math
import numpy as np
import pandas as pd

# disease = ["Meningitis, Pneumococcal", "Meningitis, Pneumococcal", "Mycetoma", "Botulism", "Botulism2", "Botulism3"]
# id = ["C01.252.200.500.600", "C08.345.654.570", "C01.252.410.040.692.606", "C01.252.410.222.151", "C01.252.410.222.151", "C03.252.410.222.151"]

print("开始读取数据")
# 读取数据
meshid = pd.read_csv('data/MeSHID.csv', header=0)
disease = meshid['disease'].tolist()
id = meshid['ID'].tolist()

meshdis = pd.read_csv('data/Mesh_disease.csv', header=0)
unique_disease = meshdis['C1'].tolist()

# 先把各个病的整个家族储存到一个list中，把所有病储存到一个fullID中

disease_list = []
fullID = []

for i in range(len(id)):

    disease_family = [disease[i], id[i]]
    fullID.append(id[i])
    if len(id[i]) > 3:
        id[i] = id[i][:-4]
        disease_family.append(id[i])
        fullID.append(id[i])
        if len(id[i]) > 3:
            id[i] = id[i][:-4]
            disease_family.append(id[i])
            fullID.append(id[i])
            if len(id[i]) > 3:
                id[i] = id[i][:-4]
                disease_family.append(id[i])
                fullID.append(id[i])
                if len(id[i]) > 3:
                    id[i] = id[i][:-4]
                    disease_family.append(id[i])
                    fullID.append(id[i])
                    if len(id[i]) > 3:
                        id[i] = id[i][:-4]
                        disease_family.append(id[i])
                        fullID.append(id[i])
                        if len(id[i]) > 3:
                            id[i] = id[i][:-4]
                            disease_family.append(id[i])
                            fullID.append(id[i])
                            if len(id[i]) > 3:
                                id[i] = id[i][:-4]
                                disease_family.append(id[i])
                                fullID.append(id[i])
                                if len(id[i]) > 3:
                                    id[i] = id[i][:-4]
                                    disease_family.append(id[i])
                                    fullID.append(id[i])

    disease_list.append(disease_family)


id = meshid['ID'].tolist()


# 计算每个病的DV，用字典形式创建list

# 计算每个病在所有病中的出现次数,构建字典

# 方法一:
# 现在有fullID，用fullID和原始ID对比，对fullID中某一个ID，看有多少个原始ID包含它
# countID = []
#
# for i in range(len(fullID)):
#     target = fullID[i]
#     count = 0
#     for j in range(len(id)):
#         if target in id[j]:
#             count += 1
#     countID.append(count)
#
# print(countID)

# 方法二
# 直接统计fullID中每个ID的出现次数，因为每个病的集合中的元素都是唯一的，所以如果一个ID出现了，就证明这个ID在这个病中，所以一个ID出现多少次就证明有多少个病包含这个ID

disease_dv = {}
countdis = len(disease)

for key in fullID:
    disease_dv[key] = round(math.log((disease_dv.get(key, 0) + 1)/countdis, 10)*(-1), 5)

# print(disease_dv)
#
# print(disease_list)
#
# print(fullID)


id = meshid['ID'].tolist()
disease = meshid['disease'].tolist()

# 初始化字典，有重复也没关系
for i in range(len(disease)):
    disease[i] = {}

# 计算每个病的DV，又重复也没关系，之后再合并

for i in range(len(disease)):

    if len(id[i]) > 3:
        disease[i][id[i]] = disease_dv[id[i]]
        id[i] = id[i][:-4]
        # print(disease[i])
        if len(id[i]) > 3:
            disease[i][id[i]] = disease_dv[id[i]]
            id[i] = id[i][:-4]
            # print(disease[i])
            if len(id[i]) > 3:
                disease[i][id[i]] = disease_dv[id[i]]
                id[i] = id[i][:-4]
                # print(disease[i])
                if len(id[i]) > 3:
                    disease[i][id[i]] = disease_dv[id[i]]
                    id[i] = id[i][:-4]
                    # print(disease[i])
                    if len(id[i]) > 3:
                        disease[i][id[i]] = disease_dv[id[i]]
                        id[i] = id[i][:-4]
                        # print(disease[i])
                        if len(id[i]) > 3:
                            disease[i][id[i]] = disease_dv[id[i]]
                            id[i] = id[i][:-4]
                            # print(disease[i])
                            if len(id[i]) > 3:
                                disease[i][id[i]] = disease_dv[id[i]]
                                id[i] = id[i][:-4]
                                # print(disease[i])
                                if len(id[i]) > 3:
                                    disease[i][id[i]] = disease_dv[id[i]]
                                    id[i] = id[i][:-4]
                                    # print(disease[i])
                                else:
                                    disease[i][id[i][:3]] = disease_dv[id[i][:3]]
                                    # print(disease[i])
                            else:
                                disease[i][id[i][:3]] = disease_dv[id[i][:3]]
                                # print(disease[i])
                        else:
                            disease[i][id[i][:3]] = disease_dv[id[i][:3]]
                            # print(disease[i])
                    else:
                        disease[i][id[i][:3]] = disease_dv[id[i][:3]]
                        # print(disease[i])
                else:
                    disease[i][id[i][:3]] = disease_dv[id[i][:3]]
                    # print(disease[i])
            else:
                disease[i][id[i][:3]] = disease_dv[id[i][:3]]
                # print(disease[i])
        else:
            disease[i][id[i][:3]] = disease_dv[id[i][:3]]
            # print(disease[i])
    else:
        disease[i][id[i][:3]] = disease_dv[id[i][:3]]
        # print(disease[i])

# print(disease)


# 合并相同的病不同ID的DV

unique_disease = meshdis['C1'].tolist()

# 这个name用来判断
disease_name = meshid['disease'].tolist()
unique_disease_name = meshdis['C1'].tolist()

for i in range(len(unique_disease)):
    unique_disease[i] = {}
    for j in range(len(disease_name)):
        if unique_disease_name[i] == disease_name[j]:
            unique_disease[i].update(disease[j])

# print(unique_disease)


similarity = np.zeros([len(unique_disease_name), len(unique_disease_name)])


for m in range(len(unique_disease_name)):
    for n in range(len(unique_disease_name)):
        denominator = sum(unique_disease[m].values()) + sum(unique_disease[n].values())
        numerator = 0
        for k, v in unique_disease[m].items():
            if k in unique_disease[n].keys():
                numerator += v + unique_disease[n].get(k)
        similarity[m, n] = round(numerator/denominator, 5)

# print(similarity)

# 保存结果

result = pd.DataFrame(similarity)
result.to_csv('output/similarity2.csv')