Skip to content

Add LRGB only valid sequences option #529

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

Merged
j-adamczyk merged 1 commit into from
Mar 16, 2026
Merged

Add LRGB only valid sequences option #529

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 12 additions & 2 deletions skfp/datasets/lrgb/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -203,6 +203,7 @@ def load_lrgb_mol_dataset(
@validate_params(
{
"dataset_name": [StrOptions({"Peptides-func", "Peptides-struct"})],
"valid_sequences_only": ["boolean"],
"data_dir": [None, str, os.PathLike],
"as_frame": ["boolean"],
"verbose": ["boolean"],
Expand All @@ -211,6 +212,7 @@ def load_lrgb_mol_dataset(
)
def load_lrgb_mol_splits(
dataset_name: str,
valid_sequences_only: bool = False,
data_dir: str | os.PathLike | None = None,
as_dict: bool = False,
verbose: bool = False,
Expand All @@ -227,7 +229,12 @@ def load_lrgb_mol_splits(
Parameters
----------
dataset_name : {"Peptides-func", "Peptides-struct"}
Name of the dataset to loads splits for.
Name of the dataset to load splits for.

valid_sequences_only : bool, default=False
Whether to load only rows with valid amino acid sequences, which can be loaded
as RDKit ``Mol`` objects. This removes some sequences with valid SMILES, but custom
notation for chemical modifications.

data_dir : {None, str, path-like}, default=None
Path to the root data directory. If ``None``, currently set scikit-learn directory
Expand Down Expand Up @@ -255,10 +262,13 @@ def load_lrgb_mol_splits(
Advances in Neural Information Processing Systems 35 (2022): 22326-22340
<https://proceedings.neurips.cc/paper_files/paper/2022/hash/8c3c666820ea055a77726d66fc7d447f-Abstract-Datasets_and_Benchmarks.html>`_
"""
file_dataset_name = dataset_name.lower().replace("-", "_")
valid_only = "_valid_seqs" if valid_sequences_only else ""

splits = fetch_splits(
data_dir,
dataset_name=f"LRGB_{dataset_name}",
filename=f"lrgb_splits_{dataset_name.lower().replace('-', '_')}.json",
filename=f"lrgb_splits_{file_dataset_name}{valid_only}.json",
verbose=verbose,
)
if as_dict:
Expand Down
2 changes: 1 addition & 1 deletion skfp/datasets/moleculeace/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -323,7 +323,7 @@ def load_moleculeace_splits(
Parameters
----------
dataset_name : str
Name of the dataset to loads splits for.
Name of the dataset to load splits for.

split_type: {"random", "activity_cliff"}
Type of the split to load.
Expand Down
2 changes: 1 addition & 1 deletion skfp/datasets/moleculenet/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -257,7 +257,7 @@ def load_ogb_splits(
Parameters
----------
dataset_name : {"ESOL", "FreeSolv", "Lipophilicity","BACE", "BBBP", "HIV", "ClinTox", "MUV", "SIDER", "Tox21", "ToxCast", "PCBA"}
Name of the dataset to loads splits for.
Name of the dataset to load splits for.

data_dir : {None, str, path-like}, default=None
Path to the root data directory. If ``None``, currently set scikit-learn directory
Expand Down
2 changes: 1 addition & 1 deletion skfp/datasets/tdc/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -351,7 +351,7 @@ def load_tdc_splits(
Parameters
----------
dataset_name : str
Name of the dataset to loads splits for.
Name of the dataset to load splits for.

data_dir : {None, str, path-like}, default=None
Path to the root data directory. If ``None``, currently set scikit-learn directory
Expand Down
12 changes: 7 additions & 5 deletions tests/datasets/lrgb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,14 +77,16 @@ def test_load_lrgb_splits_as_dict(dataset_name):
only_rerun=["LocalEntryNotFoundError", "FileNotFoundError"],
)
@pytest.mark.parametrize(
"dataset_name, dataset_length",
"dataset_name, valid_sequences_only, dataset_length",
[
("Peptides-func", 15535),
("Peptides-struct", 15535),
("Peptides-func", False, 15535),
("Peptides-struct", False, 15535),
("Peptides-func", True, 15424),
("Peptides-struct", True, 15424),
],
)
def test_load_lrgb_splits_lengths(dataset_name, dataset_length):
train, valid, test = load_lrgb_mol_splits(dataset_name)
def test_load_lrgb_splits_lengths(dataset_name, valid_sequences_only, dataset_length):
train, valid, test = load_lrgb_mol_splits(dataset_name, valid_sequences_only)
loaded_length = len(train) + len(valid) + len(test)
assert_equal(loaded_length, dataset_length)

Expand Down