利用化合物名称从PubChempy中批量下载化合物信息

# -*- coding: utf-8 -*-
"""
Created on Tue Nov  8 13:07:40 2022

@author: Administrator
"""

from pubchempy import get_compounds, Compound

for compound in get_compounds('2-(1H-indol-3-yl)acetic acid', 'name'):
    b1 = compound.cid
    c1 = compound.isomeric_smiles
    d1 = compound.molecular_formula
    e1 = compound.molecular_weight
    f1 = compound.iupac_name
    

print(compound.cid)
print(compound.molecular_weight)
print(compound.molecular_formula)
print(compound.isomeric_smiles)
print(compound.iupac_name)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

# -*- coding: utf-8 -*-
"""
Created on Tue Nov  8 13:30:10 2022

@author: Administrator
"""

from pubchempy import get_compounds, Compound

import pandas as pd
a = pd.read_excel("G:\\非靶向代谢组数据库\\wheat\\wheat2.xlsx")
a = a['Metabolites']
for i in a:
    for compound in get_compounds(i, 'name'):
        b1 = compound.cid
        c1 = compound.isomeric_smiles
        d1 = compound.molecular_formula
        e1 = compound.molecular_weight
        f1 = compound.iupac_name
    print(compound.cid)
    print(compound.molecular_weight)
    print(compound.molecular_formula)
    print(compound.isomeric_smiles)
    print(compound.iupac_name)

    
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

# -*- coding: utf-8 -*-
"""
Created on Tue Nov  8 13:30:10 2022

@author: Administrator
"""

from pubchempy import get_compounds, Compound

import pandas as pd
a = pd.read_excel("G:\\非靶向代谢组数据库\\wheat\\wheat2.xlsx")
a = a['Metabolites']
list1 = list()
list2 = list()
list3 = list()
list4 = list()
list5 = list()
for i in range(0, 704):
    for compound in get_compounds(a[i], 'name'):
        b1 = compound.cid
        c1 = compound.isomeric_smiles
        d1 = compound.molecular_formula
        e1 = compound.molecular_weight
        f1 = compound.iupac_name
    print(compound.cid)
    print(compound.molecular_weight)
    print(compound.molecular_formula)
    print(compound.isomeric_smiles)
    print(compound.iupac_name)
    print(i)
    list1.append(b1)
    list2.append(c1)
    list3.append(d1)
    list4.append(e1)
    list5.append(f1)

information = pd.DataFrame(list1,list2,list3,list4,list5)

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

# -*- coding: utf-8 -*-
"""
Created on Tue Nov  8 15:48:20 2022

@author: Administrator
"""

# -*- coding: utf-8 -*-
"""
Created on Tue Nov  8 13:30:10 2022

@author: Administrator
"""

from pubchempy import get_compounds, Compound

import pandas as pd
a = pd.read_excel("G:\\非靶向代谢组数据库\\wheat\\wheat2.xlsx")
a = a['Metabolites']
list1 = list()
list2 = list()
list3 = list()
list4 = list()
list5 = list()
for i in range(110, 704):
    for compound in get_compounds(a[i], 'name'):
        b1 = compound.cid
        c1 = compound.isomeric_smiles
        d1 = compound.molecular_formula
        e1 = compound.molecular_weight
        f1 = compound.iupac_name
    print(compound.cid)
    print(compound.molecular_weight)
    print(compound.molecular_formula)
    print(compound.isomeric_smiles)
    print(compound.iupac_name)
    print(i)
    list1.append(b1)
    list2.append(c1)
    list3.append(d1)
    list4.append(e1)
    list5.append(f1)


import pandas as pd
import numpy as np
information = pd.DataFrame({'PubChem_CID':list1, 'molecular_weight':list2, 
                            'molecular_formula':list3, 'isomeric_smiles':list4,
                            'iupac_name':list5})
information
information.to_excel('e:/count/example2.xlsx')

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