|
1
|
|
|
#! /usr/bin/env python |
|
2
|
|
|
# |
|
3
|
|
|
# Copyright (C) 2007-2009 Rich Lewis <[email protected]> |
|
4
|
|
|
# License: 3-clause BSD |
|
5
|
|
|
|
|
6
|
|
|
""" |
|
7
|
|
|
skchem.io.smiles |
|
8
|
|
|
|
|
9
|
|
|
Defining input and output operations for smiles files. |
|
10
|
|
|
""" |
|
11
|
|
|
|
|
12
|
|
|
import skchem |
|
13
|
|
|
import pandas as pd |
|
|
|
|
|
|
14
|
|
|
from skchem.utils import Suppressor |
|
15
|
|
|
|
|
16
|
|
|
def read_smiles(smiles_file, smiles_column=0, name_column=None, delimiter='\t', |
|
|
|
|
|
|
17
|
|
|
title_line=False, force=False, *args, **kwargs): |
|
|
|
|
|
|
18
|
|
|
|
|
19
|
|
|
""" |
|
20
|
|
|
Read a smiles file into a pandas dataframe. The class wraps the pandas read_csv function. |
|
21
|
|
|
|
|
22
|
|
|
@param smiles_file A file path provided as a :str:, or a :file-like: object. |
|
23
|
|
|
@param smiles_column The column index as an :int: in which the smiles strings are provided. |
|
24
|
|
|
Defaults to _zero_. |
|
25
|
|
|
@param name_column The column index as an :int: in which compound names are provided, |
|
26
|
|
|
for use as the index in the dataframe. Defaults to _None_. |
|
27
|
|
|
@param delimiter The delimiter used, specified as a :str:. |
|
28
|
|
|
Defaults to _<tab>_. |
|
29
|
|
|
@param title_line A :bool: specifying whether a title line is provided, |
|
30
|
|
|
to use as column titles. |
|
31
|
|
|
@param force A :bool: specifying whether poorly parsed molecules should be skipped, |
|
32
|
|
|
or an error thrown. |
|
33
|
|
|
Additionally, pandas read_csv arguments may be provided. |
|
34
|
|
|
|
|
35
|
|
|
@returns df A dataframe of type :pandas.core.frame.DataFrame:. |
|
36
|
|
|
""" |
|
37
|
|
|
|
|
38
|
|
|
with Suppressor(): |
|
39
|
|
|
|
|
40
|
|
|
# set the header line to pass to the pandas parser |
|
41
|
|
|
# we accept True as being line zero, as is usual for smiles |
|
42
|
|
|
# if user specifies a header already, then do nothing |
|
43
|
|
|
|
|
44
|
|
|
header = kwargs.get('header', None) |
|
45
|
|
|
if title_line is True: |
|
46
|
|
|
header = 0 |
|
47
|
|
|
elif header is not None: |
|
48
|
|
|
kwargs.pop('header') #remove from the kwargs to not pass it twice |
|
49
|
|
|
else: |
|
50
|
|
|
header = None |
|
51
|
|
|
|
|
52
|
|
|
# open file if not already open |
|
53
|
|
|
if isinstance(smiles_file, str): |
|
54
|
|
|
smiles_file = open(smiles_file, 'r') |
|
55
|
|
|
|
|
56
|
|
|
# read the smiles file |
|
57
|
|
|
df = pd.read_csv(smiles_file, delimiter=delimiter, header=header, *args, **kwargs) |
|
|
|
|
|
|
58
|
|
|
|
|
59
|
|
|
# replace the smiles column with the structure column |
|
60
|
|
|
lst = list(df.columns) |
|
61
|
|
|
lst[smiles_column] = 'structure' |
|
62
|
|
|
df.columns = lst |
|
63
|
|
|
|
|
64
|
|
|
# apply the from smiles constructor |
|
65
|
|
|
if force: |
|
66
|
|
|
def parse(smiles): |
|
67
|
|
|
|
|
68
|
|
|
""" |
|
69
|
|
|
Parse a molecule from smiles string and return None if it doesn't load |
|
70
|
|
|
(restoring rdkit functionality) |
|
71
|
|
|
""" |
|
72
|
|
|
|
|
73
|
|
|
try: |
|
74
|
|
|
return skchem.Mol.from_smiles(smiles) |
|
|
|
|
|
|
75
|
|
|
except ValueError: |
|
76
|
|
|
return None |
|
77
|
|
|
else: |
|
78
|
|
|
def parse(smiles): |
|
79
|
|
|
""" |
|
80
|
|
|
Parse a molecule from smiles string |
|
81
|
|
|
""" |
|
82
|
|
|
return skchem.Mol.from_smiles(smiles) |
|
|
|
|
|
|
83
|
|
|
|
|
84
|
|
|
df['structure'] = df['structure'].apply(str).apply(parse) #make sure is a string |
|
85
|
|
|
|
|
86
|
|
|
if force: |
|
87
|
|
|
df = df[df['structure'].notnull()] |
|
|
|
|
|
|
88
|
|
|
|
|
89
|
|
|
# set index if passed |
|
90
|
|
|
if name_column is not None: |
|
91
|
|
|
df = df.set_index(df.columns[name_column]) |
|
|
|
|
|
|
92
|
|
|
|
|
93
|
|
|
return df |
|
94
|
|
|
|
|
95
|
|
|
@classmethod |
|
96
|
|
|
def from_smiles(_, *args, **kwargs): |
|
97
|
|
|
""" Create a DataFrame from a smiles file """ |
|
98
|
|
|
return read_smiles(*args, **kwargs) |
|
99
|
|
|
|
|
100
|
|
|
#set on pandas dataframe |
|
101
|
|
|
pd.DataFrame.from_smiles = from_smiles |
|
102
|
|
|
|
richlewis42 /
scikit-chem
Loading history...
This can be caused by one of the following:
1. Missing Dependencies
This error could indicate a configuration issue of Pylint. Make sure that your libraries are available by adding the necessary commands.
2. Missing __init__.py files
This error could also result from missing
__init__.pyfiles in your module folders. Make sure that you place one file in each sub-folder.