From 3ac91a30ae9a699600ee8d6808c6c590c7512e63 Mon Sep 17 00:00:00 2001 From: Allen Goodman Date: Fri, 19 Jul 2024 14:57:53 -0400 Subject: [PATCH] datasets --- docs/reference/beignet.datasets.md | 80 +++++++++++++++++++++++++ mkdocs.yml | 26 +------- src/beignet/datasets/__init__.py | 2 - src/beignet/datasets/_pdb_70_dataset.py | 40 ------------- 4 files changed, 81 insertions(+), 67 deletions(-) create mode 100644 docs/reference/beignet.datasets.md delete mode 100644 src/beignet/datasets/_pdb_70_dataset.py diff --git a/docs/reference/beignet.datasets.md b/docs/reference/beignet.datasets.md new file mode 100644 index 0000000000..19ea16585e --- /dev/null +++ b/docs/reference/beignet.datasets.md @@ -0,0 +1,80 @@ +::: beignet.datasets.ATOM3DDataset +::: beignet.datasets.ATOM3DMSPDataset +::: beignet.datasets.ATOM3DPPIDataset +::: beignet.datasets.ATOM3DPSRDataset +::: beignet.datasets.ATOM3DRESDataset +::: beignet.datasets.ATOM3DRSRDataset +::: beignet.datasets.ATOM3DSMPDataset +::: beignet.datasets.AqSolDBSolubilityDataset +::: beignet.datasets.AstraZenecaClearanceDataset +::: beignet.datasets.AstraZenecaLipophilicityDataset +::: beignet.datasets.AstraZenecaPlasmaProteinBindingRateDataset +::: beignet.datasets.BindingDBIC50Dataset +::: beignet.datasets.BindingDBKdDataset +::: beignet.datasets.BindingDBKiDataset +::: beignet.datasets.BroccatelliPGlycoproteinInhibitionDataset +::: beignet.datasets.CarbonMangelsCytochromeP4502C9SubstrateDataset +::: beignet.datasets.CarbonMangelsCytochromeP4502D6SubstrateDataset +::: beignet.datasets.CarbonMangelsCytochromeP4503A4SubstrateDataset +::: beignet.datasets.ChEMBLDataset +::: beignet.datasets.ClinToxDataset +::: beignet.datasets.DAVISDataset +::: beignet.datasets.DataFrameDataset +::: beignet.datasets.DisGeNETDataset +::: beignet.datasets.DrugCombDataset +::: beignet.datasets.FASTADataset +::: beignet.datasets.FreeSolvDataset +::: beignet.datasets.GDSC1Dataset +::: beignet.datasets.GDSC2Dataset +::: beignet.datasets.HDF5TrajectoryDataset +::: beignet.datasets.HouHumanIntestinalAbsorptionDataset +::: beignet.datasets.HuRIDataset +::: beignet.datasets.JespersenIEDBDataset +::: beignet.datasets.JespersenPDBDataset +::: beignet.datasets.KIBADataset +::: beignet.datasets.LMDBDataset +::: beignet.datasets.LombardoVolumeOfDistributionAtSteadyStateDataset +::: beignet.datasets.MOSESDataset +::: beignet.datasets.MaBioavailabilityDataset +::: beignet.datasets.MartinsBloodBrainBarrierDataset +::: beignet.datasets.NCATSPAMPAPermeabilityDataset +::: beignet.datasets.ObachHalfLifeDataset +::: beignet.datasets.PDB70Dataset +::: beignet.datasets.PDBTrajectoryDataset +::: beignet.datasets.PDBbindDataset +::: beignet.datasets.ParquetDataset +::: beignet.datasets.QM7Dataset +::: beignet.datasets.QM7bDataset +::: beignet.datasets.QM8Dataset +::: beignet.datasets.QM9Dataset +::: beignet.datasets.REALDatabaseDataset +::: beignet.datasets.RandomEulerAngleDataset +::: beignet.datasets.RandomQuaternionDataset +::: beignet.datasets.RandomRotationDataset +::: beignet.datasets.RandomRotationMatrixDataset +::: beignet.datasets.RandomRotationVectorDataset +::: beignet.datasets.SAbDabDataset +::: beignet.datasets.SKEMPIDataset +::: beignet.datasets.SequenceDataset +::: beignet.datasets.SizedSequenceDataset +::: beignet.datasets.SwissProtDataset +::: beignet.datasets.TDCDataset +::: beignet.datasets.TherapeuticAntibodyProfilerDataset +::: beignet.datasets.Tox21Dataset +::: beignet.datasets.ToxCastDataset +::: beignet.datasets.TrEMBLDataset +::: beignet.datasets.TrajectoryDataset +::: beignet.datasets.USPTODataset +::: beignet.datasets.USPTOReactionProductDataset +::: beignet.datasets.UniProtDataset +::: beignet.datasets.UniRef100Dataset +::: beignet.datasets.UniRef50Dataset +::: beignet.datasets.UniRef90Dataset +::: beignet.datasets.VeithCytochromeP4501A2InhibitionDataset +::: beignet.datasets.VeithCytochromeP4502C19InhibitionDataset +::: beignet.datasets.VeithCytochromeP4502C9InhibitionDataset +::: beignet.datasets.VeithCytochromeP4502D6InhibitionDataset +::: beignet.datasets.VeithCytochromeP4503A4InhibitionDataset +::: beignet.datasets.WangEffectivePermeabilityDataset +::: beignet.datasets.ZINCDataset +::: beignet.datasets.ZhuAcuteToxicityLD50Dataset diff --git a/mkdocs.yml b/mkdocs.yml index 4c38c36d46..6e0d7a6ae2 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -35,31 +35,7 @@ nav: - "Laguerre polynomial": "reference/operators/special-functions/orthogonal-polynomials/laguerre-polynomial.md" - "Legendre polynomial": "reference/operators/special-functions/orthogonal-polynomials/legendre-polynomial.md" - "Thermodynamics": "reference/operators/thermodynamics.md" - - "beignet.datasets": - - "General-purpose": "reference/datasets/general-purpose.md" - - "Antibody affinity": "reference/datasets/antibody-affinity.md" - - "Catalyst": "reference/datasets/catalyst.md" - - "Drug interaction": "reference/datasets/drug-interaction.md" - - "Drug intolerance": "reference/datasets/drug-intolerance.md" - - "Epitope": "reference/datasets/epitope.md" - - "Geometry": - - "Transformations": "reference/datasets/geometry/transformations.md" - - "Gene-disease association": "reference/datasets/gene-disease-association.md" - - "Molecule": "reference/datasets/molecule.md" - - "Pharmacokinetic property": - - "Absorption": "reference/datasets/pharmacokinetic-property/absorption.md" - - "Distribution": "reference/datasets/pharmacokinetic-property/distribution.md" - - "Excretion": "reference/datasets/pharmacokinetic-property/excretion.md" - - "Metabolism": "reference/datasets/pharmacokinetic-property/metabolism.md" - - "Protein": - - "Protein sequence": "reference/datasets/protein/protein-sequence.md" - - "Protein structure": "reference/datasets/protein/protein-structure.md" - - "Protein–protein interaction": "reference/datasets/protein-protein-interaction.md" - - "Quantum mechanics": "reference/datasets/quantum-mechanics.md" - - "Reaction": "reference/datasets/reaction.md" - - "Retrosynthesis": "reference/datasets/retrosynthesis.md" - - "Toxicity": "reference/datasets/toxicity.md" - - "Sequences": "reference/datasets/sequences.md" + - "beignet.datasets": "reference/beignet.datasets.md" - "beignet.features": - "General-purpose": "reference/features/general-purpose.md" - "Geometry": diff --git a/src/beignet/datasets/__init__.py b/src/beignet/datasets/__init__.py index aa1a082c85..d613dc1b27 100644 --- a/src/beignet/datasets/__init__.py +++ b/src/beignet/datasets/__init__.py @@ -54,7 +54,6 @@ from ._ncats_pampa_permeability_dataset import NCATSPAMPAPermeabilityDataset from ._obach_half_life_dataset import ObachHalfLifeDataset from ._parquet_dataset import ParquetDataset -from ._pdb_70_dataset import PDB70Dataset from ._pdb_trajectory_dataset import PDBTrajectoryDataset from ._pdbbind_dataset import PDBbindDataset from ._qm7_dataset import QM7Dataset @@ -145,7 +144,6 @@ "MartinsBloodBrainBarrierDataset", "NCATSPAMPAPermeabilityDataset", "ObachHalfLifeDataset", - "PDB70Dataset", "PDBTrajectoryDataset", "PDBbindDataset", "ParquetDataset", diff --git a/src/beignet/datasets/_pdb_70_dataset.py b/src/beignet/datasets/_pdb_70_dataset.py deleted file mode 100644 index 5f5880e530..0000000000 --- a/src/beignet/datasets/_pdb_70_dataset.py +++ /dev/null @@ -1,40 +0,0 @@ -from pathlib import Path -from typing import Callable - -from beignet.transforms import Transform - -from ._sequence_dataset import SequenceDataset - - -class PDB70Dataset(SequenceDataset): - def __init__( - self, - root: str | Path, - *, - download: bool = False, - transform: Callable | Transform | None = None, - target_transform: Callable | Transform | None = None, - ): - r""" - Parameters - ---------- - root : str | Path - Root directory of dataset. - - download: bool - If `True`, downloads the dataset to the root directory. If dataset - already exists, it is not redownloaded. Default, `False`. - - transform : Callable | Transform | None - Transforms the input. - - target_transform : Callable | Transform | None - Transforms the target. - """ - super().__init__(root) - - def __getitem__(self, index: int): - raise NotImplementedError - - def __len__(self) -> int: - raise NotImplementedError