Skip to content

Allow disabling 3D descriptors while enabling 2D descriptors #62

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Lexachoc wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Allow disabling 3D descriptors while enabling 2D descriptors #62

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bff1846
Allow disabling 3D descriptors while enabling 2D descriptors
Lexachoc Jun 3, 2025
0d39f20
Update functions.py
Lexachoc Jun 3, 2025
3cb44b4
Update README.md
Lexachoc Jun 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,9 @@ descriptors = from_smiles(['CCC', 'CCCC'], threads = 1)

# save descriptors to a CSV file
_ = from_smiles('CCC', output_csv='descriptors.csv')

# only calculate 2-D descriptors (some SMILES strings like 'C' can cause issues with 3-D descriptors)
descriptors = from_smiles('C', descriptors_3d=False)
```

### MDL MolFile to Descriptors/Fingerprints
Expand All @@ -77,6 +80,9 @@ desc_fp = from_mdl('mols.mdl', threads=1)

# save descriptors to a CSV file
_ = from_mdl('mols.mdl', output_csv='descriptors.csv')

# only calculate 2-D descriptors (some SMILES strings like 'C' can cause issues with 3-D descriptors)
descriptors = from_mdl('mols.mdl', descriptors_3d=False)
```

### SDF to Descriptors/Fingerprints
Expand All @@ -102,6 +108,9 @@ desc_fp = from_mdl('mols.sdf', threads=1)

# save descriptors to a CSV file
_ = from_sdf('mols.sdf', output_csv='descriptors.csv')

# only calculate 2-D descriptors (some SMILES strings like 'C' can cause issues with 3-D descriptors)
descriptors = from_sdf('mols.sdf', descriptors_3d=False)
```

### Command Line Wrapper
Expand Down
27 changes: 23 additions & 4 deletions padelpy/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
def from_smiles(smiles,
output_csv: str = None,
descriptors: bool = True,
descriptors_3d: bool = None,
fingerprints: bool = False,
timeout: int = 60,
maxruntime: int = -1,
Expand All @@ -43,6 +44,7 @@ def from_smiles(smiles,
SMILES strings
output_csv (str): if supplied, saves descriptors to this CSV file
descriptors (bool): if `True`, calculates descriptors
descriptors_3d (bool): if `False`, disable 3-D descriptors
fingerprints (bool): if `True`, calculates fingerprints
timeout (int): maximum time, in seconds, for conversion
maxruntime (int): maximum running time per molecule in seconds. default=-1.
Expand Down Expand Up @@ -77,7 +79,12 @@ def from_smiles(smiles,
if output_csv is None:
save_csv = False
output_csv = "{}.csv".format(timestamp)


if descriptors_3d is None:
d_3d = descriptors
else:
d_3d = descriptors_3d

for attempt in range(3):
try:
padeldescriptor(
Expand All @@ -86,7 +93,7 @@ def from_smiles(smiles,
convert3d=True,
retain3d=True,
d_2d=descriptors,
d_3d=descriptors,
d_3d=d_3d,
fingerprints=fingerprints,
sp_timeout=timeout,
retainorder=True,
Expand Down Expand Up @@ -151,6 +158,7 @@ def from_smiles(smiles,
def from_mdl(mdl_file: str,
output_csv: str = None,
descriptors: bool = True,
descriptors_3d: bool = None,
fingerprints: bool = False,
timeout: int = 60,
maxruntime: int = -1,
Expand All @@ -163,6 +171,7 @@ def from_mdl(mdl_file: str,
mdl_file (str): path to MDL file
output_csv (str): if supplied, saves descriptors/fingerprints here
descriptors (bool): if `True`, calculates descriptors
descriptors_3d (bool): if `False`, disable 3-D descriptors
fingerprints (bool): if `True`, calculates fingerprints
timeout (int): maximum time, in seconds, for conversion
maxruntime (int): maximum running time per molecule in seconds. default=-1.
Expand All @@ -181,6 +190,7 @@ def from_mdl(mdl_file: str,
rows = _from_mdl_lower(mol_file=mdl_file,
output_csv=output_csv,
descriptors=descriptors,
descriptors_3d=descriptors_3d,
fingerprints=fingerprints,
timeout=timeout,
maxruntime=maxruntime,
Expand All @@ -192,6 +202,7 @@ def from_mdl(mdl_file: str,
def from_sdf(sdf_file: str,
output_csv: str = None,
descriptors: bool = True,
descriptors_3d: bool = None,
fingerprints: bool = False,
timeout: int = 60,
maxruntime: int = -1,
Expand All @@ -204,6 +215,7 @@ def from_sdf(sdf_file: str,
sdf_file (str): path to sdf file
output_csv (str): if supplied, saves descriptors/fingerprints here
descriptors (bool): if `True`, calculates descriptors
descriptors_3d (bool): if `False`, disable 3-D descriptors
fingerprints (bool): if `True`, calculates fingerprints
timeout (int): maximum time, in seconds, for conversion
maxruntime (int): maximum running time per molecule in seconds. default=-1.
Expand All @@ -223,6 +235,7 @@ def from_sdf(sdf_file: str,
rows = _from_mdl_lower(mol_file=sdf_file,
output_csv=output_csv,
descriptors=descriptors,
descriptors_3d=descriptors_3d,
fingerprints=fingerprints,
timeout=timeout,
maxruntime=maxruntime,
Expand All @@ -234,6 +247,7 @@ def from_sdf(sdf_file: str,
def _from_mdl_lower(mol_file: str,
output_csv: str = None,
descriptors: bool = True,
descriptors_3d: bool = None,
fingerprints: bool = False,
timeout: int = 60,
maxruntime: int = -1,
Expand All @@ -250,7 +264,12 @@ def _from_mdl_lower(mol_file: str,
output_csv = "{}.csv".format(
datetime.now().strftime("%Y%m%d%H%M%S%f")[:-3]
)


if descriptors_3d is None:
d_3d = descriptors
else:
d_3d = descriptors_3d

for attempt in range(3):
try:
padeldescriptor(
Expand All @@ -261,7 +280,7 @@ def _from_mdl_lower(mol_file: str,
retain3d=True,
retainorder=True,
d_2d=descriptors,
d_3d=descriptors,
d_3d=d_3d,
fingerprints=fingerprints,
sp_timeout=timeout,
threads=threads
Expand Down