v 2.3.0

CHANGELOG.txt

@@ -1,3 +1,12 @@
+**VERSION 2.3.0 (06/10/2020)**
+
+- Fixes ZINC URL in `lookup_smile_str.py`
+- Adds an optional command line parameter (with arguments `zinc15` or `zinc12`) for `lookup_smile_str.py`
+
+**VERSION 2.2.0**
+
+- Provides an optional command line argument (zinc15) to use ZINC15 as a backend for downloading SMILES
+
 **VERSION 2.1.0**
 
 - Functions and scripts to fetch ZINC IDs corresponding to a SMILE string query

README.md

@@ -291,6 +291,11 @@ An example of the CSV file contents opened in an spreadsheet program is shown in
 
 # Changelog
 
+**VERSION 2.3.0 (06/10/2020)**
+
+- Fixes ZINC URL in `lookup_smile_str.py`
+- Adds an optional command line parameter (with arguments `zinc15` or `zinc12`) for `lookup_smile_str.py`
+
 **VERSION 2.2.0**
 
 * Provides an optional command line argument (zinc15) to use ZINC15 as a backend for downloading SMILES

scripts/cmd_line_online_query_scripts/lookup_smile_str.py

@@ -24,17 +24,27 @@
 
 
 def print_usage():
- print('\nUSAGE: python3 ookup_smile_str.py SMILE_str')
- print('\n\nEXAMPLE (retrieve data from ZINC):\n'
+ print('\nUSAGE: python3 lookup_smile_str.py SMILE_str Backend')
+ print('\n\nUses zinc15 as backend by default'
+ '\n\nEXAMPLE 1 (retrieve data from ZINC12):\n'
  'python3 lookup_smile_str.py'
- ' C[C@H]1CCCC[NH+]1CC#CC(c2ccccc2)(c3ccccc3)O"')
+ ' C[C@H]1CCCC[NH+]1CC#CC(c2ccccc2)(c3ccccc3)O"'
+ '\n\nEXAMPLE 2 (retrieve data from ZINC12):\n'
+ 'python3 lookup_smile_str.py'
+ ' CCOc1ccc(cc1)N([C@@H](C)C(=O)Nc2ccc(cc2C)Cl)S(=O)(=O)C" zinc12')
 
 
 zinc_id = [None]
 
 try:
  smile_str = sys.argv[1]
- zinc_ids = smilite.get_zincid_from_smile(smile_str)
+
+ if len(sys.argv) >= 3:
+ backend = sys.argv[2]
+ else:
+ backend = 'zinc15'
+
+ zinc_ids = smilite.get_zincid_from_smile(smile_str, backend=backend)
  for zid in zinc_ids:
  print(zid)
 

scripts/cmd_line_online_query_scripts/lookup_zincid.py

@@ -28,7 +28,7 @@
 
 
 def print_usage():
- print('\nUSAGE: python3 lookup_zincid.py ZINC_ID [zinc12 (default)/zinc15]')
+ print('\nUSAGE: python3 lookup_zincid.py ZINC_ID [zinc12 (def.) / zinc15]')
  print('\n\nEXAMPLES (retrieve data from ZINC):\n'
  '1) python3 lookup_zincid.py ZINC01234567 zinc12\n'
  '2) python3 lookup_zincid.py ZINC01234567 zinc15')

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup
 
 setup(name='smilite',
- version='2.2.0',
+ version='2.3.0',
  description='smilite is a Python module to download'
  ' and analyze SMILE strings',
  author='Sebastian Raschka',
@@ -18,7 +18,6 @@
  'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
  'Development Status :: 5 - Production/Stable',
  'Programming Language :: Python :: 3',
- 'Programming Language :: Python :: 2.7',
  'Environment :: Console',
  ],
  long_description="""
@@ -28,7 +27,6 @@
 of chemical compounds from ZINC
 (a free database of commercially-available compounds for virtual screening,
 http://zinc.docking.org).
-Now supports both Python 3.x and Python 2.x.
 
 Source repository: https://github.com/rasbt/smilite
 

smilite/__init__.py

@@ -1,4 +1,4 @@
-# Copyright 2014 Sebastian Raschka
+# Copyright 2014-2020 Sebastian Raschka
 #
 # A small module to retrieve SMILE strings 
 # (Simplified molecular-input line-entry system) from the ZINC online
@@ -18,5 +18,5 @@
 from .smilite import sqlite_to_csv
 from .smilite import get_zincid_from_smile
 
-__version__ = '2.1.1'
+__version__ = '2.3.0'
 

smilite/smilite.py

@@ -1,4 +1,4 @@
-# Copyright 2014 Sebastian Raschka
+# Copyright 2014-2020 Sebastian Raschka
 #
 # smilite is a Python module to download and analyze SMILE strings
 # (Simplified Molecular-Input Line-entry System) of chemical compounds
@@ -82,50 +82,75 @@ def get_zinc_smile(zinc_id, backend='zinc12'):
  return smile_str
 
 
-def get_zincid_from_smile(smile_str):
+def get_zincid_from_smile(smile_str, backend='zinc15'):
  """
  Gets the corresponding ZINC ID(s) for a SMILE string query from
  the ZINC online database. Requires an internet connection.
 
  Keyword arguments:
  smile_str (str): A valid SMILE string, e.g.,
  C[C@H]1CCCC[NH+]1CC#CC(c2ccccc2)(c3ccccc3)O'
+ backend (str): Specifies the database backend, "zinc12" or "zinc15"
 
  Returns the SMILE string for the corresponding ZINC ID(s) in a list.
  E.g., ['ZINC01234567', 'ZINC01234568', 'ZINC01242053', 'ZINC01242055']
 
  """
+
+ if backend not in {'zinc12', 'zinc15'}:
+ raise ValueError("backend must be 'zinc12' or 'zinc15'")
+
  stripped_smile = smile_str.strip()
+ encoded_smile = urllib.parse.quote(stripped_smile)
+
+ if backend == 'zinc12':
+ url_part1 = 'http://zinc12.docking.org/results?structure.smiles='
+ url_part3 = '&structure.similarity=1.0'
+ elif backend == 'zinc15':
+ url_part1 = 'http://zinc.docking.org/substances/search/?q='
+ url_part3 = ''
+ else:
+ raise ValueError("Backend must be 'zinc12' or 'zinc15'. "
+ "Got %s" % (backend))
 
  zinc_ids = []
- url_part1 = 'http://zinc.docking.org/results?structure.smiles='
- url_part3 = '&structure.similarity=1.0'
+
  try:
  if sys.version_info[0] == 3:
- smile_url = urllib.request.pathname2url(stripped_smile)
+ #smile_url = urllib.request.pathname2url(encoded_smile)
  response = urllib.request.urlopen('{}{}{}'
  .format(url_part1,
- smile_url,
+ encoded_smile,
  url_part3))
  else:
- smile_url = urllib.pathname2url(stripped_smile)
+ #smile_url = urllib.pathname2url(encoded_smile)
  response = urllib.urlopen('{}{}{}'
  .format(url_part1,
- smile_url,
+ encoded_smile,
  url_part3))
  except urllib.error.HTTPError:
  print('Invalid SMILE string {}'.format(smile_str))
  response = []
  for line in response:
  line = line.decode(encoding='UTF-8').strip()
- if line.startswith('<a href="//zinc.docking.org/substance/'):
- line = line.split('</a>')[-2].split('>')[-1]
- if sys.version_info[0] == 3:
- zinc_id = urllib.parse.unquote(line)
- else:
- zinc_id = urllib.unquote(line)
- zinc_id = 'ZINC' + (8-len(zinc_id)) * '0' + zinc_id
- zinc_ids.append(str(zinc_id))
+
+ if backend == 'zinc15':
+ if line.startswith('<a href="/substances/ZINC'):
+ line = line.split('/')[-2]
+ if sys.version_info[0] == 3:
+ zinc_id = urllib.parse.unquote(line)
+ else:
+ zinc_id = urllib.unquote(line)
+ zinc_ids.append(str(zinc_id))
+ else:
+ if line.startswith('<a href="//zinc.docking.org/substance/'):
+ line = line.split('</a>')[-2].split('>')[-1]
+ if sys.version_info[0] == 3:
+ zinc_id = urllib.parse.unquote(line)
+ else:
+ zinc_id = urllib.unquote(line)
+ zinc_id = 'ZINC' + (8-len(zinc_id)) * '0' + zinc_id
+ zinc_ids.append(str(zinc_id))
  return zinc_ids