papyrus-scripts 2.1.0__tar.gz → 2.1.1__tar.gz

{papyrus_scripts-2.1.0/src/papyrus_scripts.egg-info → papyrus_scripts-2.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: papyrus_scripts
-Version: 2.1.0
+Version: 2.1.1
 Summary: A collection of scripts to handle the Papyrus bioactivity dataset
 Home-page: https://github.com/OlivierBeq/Papyrus-scripts
 Author: Olivier J. M. Béquignon - Brandon J. Bongers - Willem Jespers

{papyrus_scripts-2.1.0 → papyrus_scripts-2.1.1}/src/papyrus_scripts/__init__.py

@@ -20,4 +20,4 @@ from .utils.IO import PapyrusVersion
 
 from .oop import PapyrusDataset
 
-__version__ = '2.1.0'
+__version__ = '2.1.1'

{papyrus_scripts-2.1.0 → papyrus_scripts-2.1.1}/src/papyrus_scripts/oop.py

@@ -5,6 +5,7 @@
 from __future__ import annotations
 
 import os
+from abc import ABC
 from typing import Any, Dict, Iterator, List, Union, Optional
 
 import pystow
@@ -26,6 +27,15 @@ class PapyrusDataset:
     def __init__(self, version: str | IO.PapyrusVersion = 'latest', is3d: bool = False, plusplus: bool = True,
                  chunksize: Optional[int] = 1_000_000, source_path: Optional[str] = None,
                  download_progress: bool = False):
+        """Read, filter and aggregate data from a release of the Papyrus dataset.
+
+        :param version: version to be used. Either a `PapyrusVersion` or a `str` object to be passed to `PapyrusVersion` (default : 'latest')
+        :param is3d: should the lower-quality data with stereochemistry be read (default: False)
+        :param plusplus: read the Papyrus++ curated subset of even higher quality (defulat: True)
+        :param chunksize: number of lines per chunk. To read without chunks (not recommended) set to None (default: 1_000_000)
+        :param source_path: folder containing the bioactivity dataset (default: pystow's home folder)
+        :param download_progress: if the data not be on disk, should progress of the download be shown
+        """
         version = IO.PapyrusVersion(version=version)
         if not IO.is_local_version_available(version=version.version_old_fmt, root_folder=source_path):
             download.download_papyrus(outdir=source_path, version=version.version_old_fmt, nostereo=True, stereo=True,
@@ -50,6 +60,16 @@ class PapyrusDataset:
                        source_path: Optional[str] = None,
                        download_progress: bool = False
                        ) -> PapyrusDataset:
+        """Create a PapyrusDataset from a pandas DataFrame.
+
+        :param df: pandas DataFrame containing filtered Papyrus data samples (must preserve all default columns)
+        :param is3d: are the samples derived from the lower-quality data with stereochemistry
+        :param version: version of the dataset the samples were obtained from
+        :param plusplus: whether the samples were derived from Papyrus++
+        :param source_path: folder containing the original bioactivity dataset (default: pystow's home folder)
+        :param download_progress: if the data was not on disk, was progress of the download shown
+        :return: the `PapyrusDataset` object corresponding to the given samples
+        """
         dataset = PapyrusDataset.__new__(PapyrusDataset)
         dataset.papyrus_bioactivity_data = df
         dataset.papyrus_protein_data = reader.read_protein_set(source_path=source_path, version=version)
@@ -64,6 +84,14 @@ class PapyrusDataset:
                    papyrus_protein_data: pd.DataFrame,
                    papyrus_params: Dict
                    ) -> PapyrusDataset:
+        """Create a PapyrusDataset from a bioactivities, proteins and initial parameters.
+
+        :param papyrus_bioactivity_data: bioactivity information obtained from a PapyrusDataset object
+        :param papyrus_protein_data: protein information obtained from a PapyrusDataset object
+        :param papyrus_params: parameters of the PapyrusDataset object `papyrus_bioactivity_data` and
+        `papyrus_protein_data` were obtained from
+        :return: the `PapyrusDataset` object corresponding to the given data
+        """
         dataset = PapyrusDataset.__new__(PapyrusDataset)
         dataset.papyrus_bioactivity_data = papyrus_bioactivity_data
         dataset.papyrus_protein_data = papyrus_protein_data
@@ -73,12 +101,14 @@ class PapyrusDataset:
 
     @property
     def _filter(self) -> PapyrusDataFilter:
+        """Create a PapyrusDataFilter object around the current dataset."""
         return PapyrusDataFilter(papyrus_bioactivity_data=self.papyrus_bioactivity_data,
                                  papyrus_protein_data=self.papyrus_protein_data,
                                  papyrus_params=self.papyrus_params)
 
     @property
     def _fpsubsim2(self) -> FPSubSim2Engine:
+        """Obtain the FPSubSim2Engine for substructure and similarity searches."""
         if self._fpsubsim2_ is None:
             self._fpsubsim2_ = FPSubSim2Engine(self.papyrus_params)
         self._fpsubsim2_._set_data(papyrus_bioactivity_data=self.papyrus_bioactivity_data,
@@ -86,56 +116,121 @@ class PapyrusDataset:
         return self._fpsubsim2_
 
     def keep_quality(self, min_quality: str) -> PapyrusDataset:
+        """Keep samples whose quality is at least the one supplied (e.g. 'medium' for both medium and high-quality)."""
         return self._filter.keep_quality(min_quality=min_quality)
 
     def keep_source(self, source: Union[List[str], str]) -> PapyrusDataset:
+        """Keep samples of specific data source(s) (e.g. 'chembl' or ['chembl', 'klaeger'])."""
         return self._filter.keep_source(source=source)
 
     def keep_activity_type(self, activity_types: Union[List[str], str]) -> PapyrusDataset:
+        """Keep samples of specific activity type(s) (e.g. 'ic50' or ['ki', 'ec50'])."""
         return self._filter.keep_activity_type(activity_types=activity_types)
 
     def keep_accession(self, accession: Union[List[str], str] = 'all') -> PapyrusDataset:
+        """Keep samples of specific accession(s) (e.g. 'P00533' or ['P11362', 'P35968'])."""
         return self._filter.keep_accession(accession=accession)
 
     def keep_protein_class(self, classes: Optional[Union[dict, List[dict]]],
                            generic_regex: bool = False) -> PapyrusDataset:
+        """Keep samples whose protein targets belong to a specific protein class(es).
+
+        :param classes: protein class(es) (e.g. {'l2': 'Kinase'} or [{'l2': 'Kinase'}, {'l1': 'Membrane receptor'}]).
+        :param generic_regex: should the generic pattern 'l?' be considered as a regex, allowing for partial matching.
+        """
         return self._filter.keep_protein_class(classes=classes, generic_regex=generic_regex)
 
     def keep_organism(self, organism: Optional[Union[str, List[str]]],
                       generic_regex: bool = False) -> PapyrusDataset:
+        """Keep samples whose protein targets belong to specific organisms.
+
+        :param organism: organism (e.g. 'Homo sapiens (Human)' or ['Bos taurus (Bovine)', 'Rattus norvegicus (Rat)'])
+        :param generic_regex: should partial matching be considered (e.g. 'human' or 'Pig')
+        """
         return self._filter.keep_organism(organism=organism, generic_regex=generic_regex)
 
     def contains(self, column: str, value: str, case: bool = True, regex: bool = False) -> PapyrusDataset:
+        """Keep samples with the specified field corresponding to the given value.
+
+        :param column: column to be checked for `value` in order for samples to be included
+        :param value: value the column must match
+        :param case: should the value matching be case-sensitive (default: True)
+        :param regex: should the given `value` be interpreted as a regular expression
+        """
         return self._filter.contains(column=column, value=value, case=case, regex=regex)
 
     def not_contains(self, column: str, value: str, case: bool = True, regex: bool = False) -> PapyrusDataset:
+        """Keep samples whose specified field not corresponding to the given value (opposite of the `contains` method).
+
+        :param column: column to be checked for `value` in order for samples to be included
+        :param value: value the column must match
+        :param case: should the value matching be case-sensitive (default: True)
+        :param regex: should the given `value` be interpreted as a regular expression
+        """
         return self._filter.not_contains(column=column, value=value, case=case, regex=regex)
 
     def isin(self, column: str, values: Union[Any, List[Any]]) -> PapyrusDataset:
+        """Keep samples whose value of the specified field is in the given options.
+
+        :param column: column to be checked for `values` in order for samples to be included
+        :param values: values the column must contain
+        """
         return self._filter.isin(column=column, values=values)
 
     def not_isin(self, column: str, values: Union[Any, List[Any]]) -> PapyrusDataset:
+        """Keep samples whose value of the specified field is not in the given options.
+
+        :param column: column to be checked for `values` in order for samples to be included
+        :param values: values the column must not contain
+        """
         return self._filter.not_isin(column=column, values=values)
 
     def keep_similar_molecules(self, smiles: Union[str, List[str]],
                                fingerprint: fingerprint.Fingerprint = fingerprint.MorganFingerprint(),
                                threshold: float = 0.7, cuda: bool = False) -> PapyrusDataset:
+        """Keep samples whose molecular structures are similar to any of the given SMILES.
+
+        :param smiles: SMILES the molecular structures must be similar to
+        :param fingerprint: type of fingerprint (subclass of `papyrus_scripts.fingerprint.Fingerprint`; default: `papyrus_scripts.fingerprint.MorganFingerprint`)
+        :param threshold: threshold of similarity to one of the given SMILES for a molecule to be considered a hit (default: 0.7)
+        :param cuda: should CUDA acceleration be used (default: False)
+        """
         return self._fpsubsim2.keep_similar_molecules(smiles=smiles, fingerprint=fingerprint, threshold=threshold,
                                                       cuda=cuda)
 
     def keep_dissimilar_molecules(self, smiles: Union[str, List[str]],
                                   fingerprint: fingerprint.Fingerprint = fingerprint.MorganFingerprint(),
                                   threshold: float = 0.7, cuda: bool = False) -> PapyrusDataset:
+        """Keep samples whose molecular structures are not similar to any of the given SMILES.
+
+        :param smiles: SMILES the molecular structures must not be similar to
+        :param fingerprint: type of fingerprint (subclass of `papyrus_scripts.fingerprint.Fingerprint`; default: `papyrus_scripts.fingerprint.MorganFingerprint`)
+        :param threshold: threshold of similarity to one of the given SMILES for a molecule to be considered a hit (default: 0.7)
+        :param cuda: should CUDA acceleration be used (default: False)
+        """
         return self._fpsubsim2.keep_dissimilar_molecules(smiles=smiles, fingerprint=fingerprint, threshold=threshold,
                                                          cuda=cuda)
 
     def keep_substructure_molecules(self, smiles: Union[str, List[str]]) -> PapyrusDataset:
+        """Keep samples whose molecular structures are substructures of any of the provided SMILES.
+
+        :param smiles: SMILES the molecular structures must not be substructures of
+        """
         return self._fpsubsim2.keep_substructure_molecules(smiles=smiles)
 
     def keep_not_substructure_molecules(self, smiles: Union[str, List[str]]) -> PapyrusDataset:
+        """Keep samples whose molecular structures are not substructures of any of the provided SMILES.
+
+        :param smiles: SMILES the molecular structures must not be substructures of
+        """
         return self._fpsubsim2.keep_not_substructure_molecules(smiles=smiles)
 
     def aggregate(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusDataset to a pandas DataFrame.
+
+        :param progress: should filtering progress be shown
+        :return: a pandas DataFrame of the filtered data.
+        """
         total = (-(-self.papyrus_params['num_rows'] // self.papyrus_params['chunksize'])
                  if self.papyrus_params['chunksize'] is not None
                  else None)
@@ -145,15 +240,35 @@ class PapyrusDataset:
                                          progress=progress, total=total)
 
     def agg(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusDataset to a pandas DataFrame (synonym of PapyrusDataset.aggregate).
+
+        :param progress: should filtering progress be shown
+        :return: a pandas DataFrame of the filtered data.
+        """
         return self.aggregate(progress=progress)
 
     def consume_chunks(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusDataset to a pandas DataFrame (synonym of PapyrusDataset.aggregate).
+
+        :param progress: should filtering progress be shown
+        :return: a pandas DataFrame of the filtered data.
+        """
         return self.aggregate(progress=progress)
 
     def to_dataframe(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusDataset to a pandas DataFrame (synonym of PapyrusDataset.aggregate).
+
+        :param progress: should filtering progress be shown
+        :return: a pandas DataFrame of the filtered data.
+        """
         return self.aggregate(progress=progress)
 
     def molecules(self, chunksize: Optional[int] = 1_000_000, progress: bool = False) -> PapyrusMoleculeSet:
+        """Get the structures of the molecules corresponding to the samples in the current PapyrusDataset.
+
+        :param chunksize: number of molecules to be loaded at once. To read without chunks (not recommended) set to None (default: 1_000_000).
+        :param progress: should progress of molecule aggregation be shown.
+        """
         ids = self.aggregate(progress=progress)['connectivity' if not self.papyrus_params['is3d'] else 'InChIKey'].unique()
         molecules = reader.read_molecular_structures(is3d=self.papyrus_params['is3d'],
                                                      version=self.papyrus_params['version'],
@@ -163,12 +278,24 @@ class PapyrusDataset:
         return PapyrusMoleculeSet(molecules, {**self.papyrus_params, 'chunksize': chunksize})
 
     def proteins(self, progress: bool = False) -> PapyrusProteinSet:
+        """Get the protein targets corresponding to the samples in the current PapyrusDataset.
+
+        :param progress: should progress of molecule aggregation be shown.
+        """
         ids = self.aggregate(progress=progress)['target_id'].unique()
         proteins = self.papyrus_protein_data[self.papyrus_protein_data.target_id.isin(ids)]
         return PapyrusProteinSet(proteins, self.papyrus_params,
                                  len(proteins))
 
     def match_rcsb_pdb(self, update: bool = True, progress: bool = False) -> PapyrusPDBProteinSet:
+        """Get the protein 3D structures from the RCSB Protein Data Bank of both protein targets and molecules
+        corresponding to the samples in the current PapyrusDataset .
+
+
+        :param update: should the local cache of PDB identifiers be updated (default: False).
+        :param progress: should progress of molecule aggregation be shown
+        :return: should progress of 3D structure aggregation be shown.
+        """
         total = (-(-self.papyrus_params['num_rows'] // self.papyrus_params['chunksize'])
                  if self.papyrus_params['chunksize'] is not None
                  else None)
@@ -206,6 +333,23 @@ class PapyrusDataset:
                force: bool = False,
                progress: bool = True,
                source_path: Optional[str] = None) -> None:
+        """Remove the data of the Papyrus dataset with multiple levels of deletion.
+
+        :param version: version to delete
+        :param remove_papyruspp: should Papyrus++ be removed
+        :param remove_bioactivities: should bioactivity data be removed
+        :param remove_proteins: should protein data be removed
+        :param remove_nostereo: should the stereochemistry-agnostic data be removed
+        :param remove_stereo: should the stereochemistry-aware data be removed
+        :param remove_structures: should molecular structures be removed
+        :param remove_descriptors: should molecular descriptors be removed
+        :param remove_other_files: should any additional file be removed
+        :param remove_version_root: should all the data of that version be removed
+        :param remove_papyrus_root: should all data all versions combined be removed
+        :param force: avoid asking for confirmation
+        :param progress: should deletion progress
+        :param source_path: folder containing the bioactivity dataset (default: pystow's home folder)
+        """
         download.remove_papyrus(outdir=source_path, version=version, papyruspp=remove_papyruspp,
                                 bioactivities=remove_bioactivities, proteins=remove_proteins,
                                 nostereo=remove_nostereo, stereo=remove_stereo, structures=remove_structures,
@@ -426,6 +570,11 @@ class PapyrusMoleculeSet:
                                                 root_folder=self.papyrus_params['source_path'])
 
     def to_dataframe(self, progress: bool = False):
+        """Aggregate the data in a PapyrusMoleculeSet to a pandas DataFrame (synonym of `PapyrusMoleculeSet.aggregate`).
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the molecules.
+        """
         if isinstance(self.data, Iterator):
             return self.aggregate(progress=progress)
         return self.data
@@ -436,6 +585,12 @@ class PapyrusMoleculeSet:
         return f'{type(self).__name__}<{len(self.data)} molecules>'
 
     def molecular_descriptors(self, desc_type: str, progress: bool = False) -> pd.DataFrame:
+        """Obtain the molecular descriptors of the molecules in the current PapyrusMoleculeSet.
+
+        :param desc_type: type of descriptor to be obtained. One of {'mold2', 'mordred', 'cddd', 'fingerprint', 'moe', 'all'}
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the molecular descriptors.
+        """
         ids = self.aggregate(progress)['connectivity' if self.papyrus_params['is3d'] else 'InChIKey'].unique()
         # Handle descriptors not yet downloaded
         try:
@@ -456,6 +611,11 @@ class PapyrusMoleculeSet:
             return self.molecular_descriptors(desc_type, progress)
 
     def aggregate(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusMoleculeSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the molecules.
+        """
         total = (-(-self.num_rows // self.papyrus_params['chunksize'])
                  if self.papyrus_params['chunksize'] is not None
                  else None)
@@ -465,12 +625,56 @@ class PapyrusMoleculeSet:
                                          progress=progress, total=total)
 
     def agg(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusMoleculeSet to a pandas DataFrame (synonym of `PapyrusMoleculeSet.aggregate`).
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the molecules.
+        """
         return self.aggregate(progress=progress)
 
     def consume_chunks(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusMoleculeSet to a pandas DataFrame (synonym of `PapyrusMoleculeSet.aggregate`).
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the molecules.
+        """
         return self.aggregate(progress=progress)
 
-class PapyrusProteinSet:
+
+class ProteinSet(ABC):
+    """Abstract class."""
+
+    def protein_descriptors(self,
+                            desc_type: Union[str, prodec.Descriptor, prodec.Transform],
+                            progress: bool = False
+                            ) -> pd.DataFrame:
+        """Obtain the protein descriptors of the protein targets in the current PapyrusPDBProteinSet.
+
+        :param desc_type: type of protein descriptor to be obtained. Either 'unirep' or a `ProDEC.Descriptor` or `ProDEC.Transform`.
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the protein descriptors.
+        """
+        self.data = self.aggregate(progress)
+        ids = self.data['target_id'].unique()
+        try:
+            return reader.read_protein_descriptors(desc_type=desc_type,
+                                                   is3d=self.papyrus_params['is3d'],
+                                                   version=self.papyrus_params['version'],
+                                                   chunksize=self.papyrus_params['chunksize'],
+                                                   source_path=self.papyrus_params['source_path'],
+                                                   ids=ids,
+                                                   verbose=progress)
+        except FileNotFoundError:
+            download.download_papyrus(outdir=self.papyrus_params['source_path'],
+                                      version=self.papyrus_params['version'],
+                                      nostereo=not self.papyrus_params['is3d'], stereo=self.papyrus_params['is3d'],
+                                      only_pp=self.papyrus_params['plusplus'], structures=False,
+                                      descriptors=desc_type, progress=self.papyrus_params['download_progress'],
+                                      disk_margin=0.0)
+            return self.protein_descriptors(desc_type, progress)
+
+
+class PapyrusProteinSet(ProteinSet):
     def __init__(self, df: Union[pd.DataFrame, Iterator], papyrus_params: Dict, num_proteins: int):
         self.data = df
         self.papyrus_params = papyrus_params
@@ -482,6 +686,11 @@ class PapyrusProteinSet:
         return f'{type(self).__name__}<{len(self.data)} proteins>'
 
     def to_dataframe(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusProteinSet to a pandas DataFrame (synonym of `PapyrusProteinSet.aggregate`).
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the proteins.
+        """
         if isinstance(self.data, Iterator):
             total = (-(-self.num_rows // self.papyrus_params['chunksize'])
                      if self.papyrus_params['chunksize'] is not None
@@ -490,15 +699,31 @@ class PapyrusProteinSet:
         return self.data
 
     def aggregate(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusProteinSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the proteins.
+        """
         return self.to_dataframe(progress)
 
     def agg(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusProteinSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the proteins.
+        """
         return self.to_dataframe(progress=progress)
 
     def consume_chunks(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusProteinSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the proteins.
+        """
         return self.to_dataframe(progress=progress)
 
-class PapyrusPDBProteinSet:
+
+class PapyrusPDBProteinSet(ProteinSet):
 
     def __init__(self, df: Union[pd.DataFrame, Iterator], papyrus_params: Dict, num_proteins: int):
         self.data = df
@@ -506,6 +731,11 @@ class PapyrusPDBProteinSet:
         self.num_rows = num_proteins
 
     def to_dataframe(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusPDBProteinSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the RCSB Protein Data Bank protein 3D structures.
+        """
         if isinstance(self.data, Iterator):
             total = (-(-self.num_rows // self.papyrus_params['chunksize'])
                      if self.papyrus_params['chunksize'] is not None
@@ -518,33 +748,27 @@ class PapyrusPDBProteinSet:
             return f'{type(self).__name__}<iterator of proteins structures>'
         return f'{type(self).__name__}<{len(self.data)} proteins structures>'
 
-    def protein_descriptors(self,
-                            desc_type: Union[str, prodec.Descriptor, prodec.Transform],
-                            progress: bool = False
-                            ) -> pd.DataFrame:
-        ids = self.aggregate(progress)['target_id'].unique()
-        try:
-            return reader.read_protein_descriptors(desc_type=desc_type,
-                                                   is3d=self.papyrus_params['is3d'],
-                                                   version=self.papyrus_params['version'],
-                                                   chunksize=self.papyrus_params['chunksize'],
-                                                   source_path=self.papyrus_params['source_path'],
-                                                   ids=ids,
-                                                   verbose=progress)
-        except FileNotFoundError:
-            download.download_papyrus(outdir=self.papyrus_params['source_path'],
-                                      version=self.papyrus_params['version'],
-                                      nostereo=not self.papyrus_params['is3d'], stereo=self.papyrus_params['is3d'],
-                                      only_pp=self.papyrus_params['plusplus'], structures=False,
-                                      descriptors=desc_type, progress=self.papyrus_params['download_progress'],
-                                      disk_margin=0.0)
-            return self.protein_descriptors(desc_type, progress)
 
     def aggregate(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusPDBProteinSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the RCSB Protein Data Bank protein 3D structures.
+        """
         return self.to_dataframe(progress)
 
     def agg(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusPDBProteinSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the RCSB Protein Data Bank protein 3D structures.
+        """
         return self.to_dataframe(progress=progress)
 
     def consume_chunks(self, progress: bool = False) -> pd.DataFrame:
+        """Aggregate the data in a PapyrusPDBProteinSet to a pandas DataFrame.
+
+        :param progress: should aggregation progress be shown
+        :return: a pandas DataFrame of the RCSB Protein Data Bank protein 3D structures.
+        """
         return self.to_dataframe(progress=progress)

papyrus_scripts-2.1.1/src/papyrus_scripts/utils/links2.json

@@ -0,0 +1,408 @@
+{
+  "05.4": {
+    "readme": {
+      "name": "README.txt",
+      "url": "https://zenodo.org/records/10944245/files/README.txt?download=1",
+      "size": 8743,
+      "sha256": "f552ae0b58121b20c9aefcce0737e5f31240d72676dc9ec559f97585aceb33ad"
+    },
+    "requirements": [
+      {
+        "name": "LICENSE.txt",
+        "url": "https://zenodo.org/records/10944245/files/LICENSE.txt?download=1",
+        "size": 20138,
+        "sha256": "3b2890eacd851373001c4a14623458e3adaf1b1967939aa9c38a318e28d61c00"
+      },
+      {
+        "name": "data_types.json",
+        "url": "https://zenodo.org/records/10944245/files/data_types.json?download=1",
+        "size": 450559,
+        "sha256": "d80a5810d99b62680ee1a214df5d5a30f505ec335a0c221194efb91d1c23913e"
+      },
+      {
+        "name": "data_size.json",
+        "url": "https://zenodo.org/records/10944245/files/data_size.json?download=1",
+        "size": 324,
+        "sha256": "decbe66e14eaeccf5e0f657bb33065600b503e2902503aa59f5ffa81b7126775"
+      }
+    ],
+    "papyrus++": {
+      "name": "05.4++_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4++_combined_set_without_stereochemistry.tsv.xz?download=1",
+      "size": 40278204,
+      "sha256": "42dcbe76b33ad541f6c54673eccffa15af64785cf844938c0f73518dfdf4404b"
+    },
+    "2D_papyrus": {
+      "name": "05.4_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_set_without_stereochemistry.tsv.xz?download=1",
+      "size": 742110788,
+      "sha256": "1a1c946917f77d9a250a181c8ef19bea4d04871915e9e75a615893a2c514684e"
+    },
+    "2D_structures": {
+      "name": "05.4_combined_2D_set_without_stereochemistry.sd.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_2D_set_without_stereochemistry.sd.xz?download=1",
+      "size": 416640448,
+      "sha256": "4595f726daf12a784049f20e9f9464ed0287af3a22a27f2a919399c535f633fc"
+    },
+    "3D_papyrus": {
+      "name": "05.4_combined_set_with_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_set_with_stereochemistry.tsv.xz?download=1",
+      "size": 777395668,
+      "sha256": "56cf389030246d4525bb31cd3dfc9e5ab3afa9613535d1540c71f0f7426c778f"
+    },
+    "3D_structures": {
+      "name": "05.4_combined_3D_set_with_stereochemistry.sd.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_3D_set_with_stereochemistry.sd.xz?download=1",
+      "size": 446702556,
+      "sha256": "b0f04e066b7ac6b1e1f2a868ff0258b13bd8d3433023ff59c3af58317bfeb3e9"
+    },
+    "2D_fingerprint": {
+      "name": "05.4_combined_2D_moldescs_ECFP6.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_2D_moldescs_ECFP6.tsv.xz?download=1",
+      "size": 141318356,
+      "sha256": "4ab781cc238107f7c48f1d866eea0e2114068b6512acf74932a5b21958c9ffe0"
+    },
+    "3D_fingerprint": {
+      "name": "05.4_combined_3D_moldescs_E3FP.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_3D_moldescs_E3FP.tsv.xz?download=1",
+      "size": 146751352,
+      "sha256": "2b89027dad8f4e59f007dd082664a7d2a491f4f79d112fb29f14565acedfe4d0"
+    },
+    "2D_mordred": {
+      "name": "05.4_combined_2D_moldescs_mordred2D.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_2D_moldescs_mordred2D.tsv.xz?download=1",
+      "size": 3085232504,
+      "sha256": "d15bca59f542a6c46528e4f131cb44d8bd6b21440ab139f4175f4327c15c39c6"
+    },
+    "3D_mordred": {
+      "name": "05.4_combined_3D_moldescs_mordred3D.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_3D_moldescs_mordred3D.tsv.xz?download=1",
+      "size": 2996851908,
+      "sha256": "80fc4f9b2d0b89e68c289c44e9f4df78f4c08e5867cd414d6169a4e1344aead8"
+    },
+    "2D_cddd": {
+      "name": "05.4_combined_2D_moldescs_CDDDs.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_2D_moldescs_CDDDs.tsv.xz?download=1",
+      "size": 3770082588,
+      "sha256": "9bb0d9adba1b812aa05b6391ecbc3f0148f6ed37972a004b13772d08790a9bda"
+    },
+    "2D_mold2": {
+      "name": "05.4_combined_2D_moldescs_mold2.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_2D_moldescs_mold2.tsv.xz?download=1",
+      "size": 1552425452,
+      "sha256": "bdfb0cbb6e9a3d1b62065808fa0e6ce238e04760df62e34ce4f15046810efd82"
+    },
+    "proteins": {
+      "name": "05.4_combined_set_protein_targets.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_set_protein_targets.tsv.xz?download=1",
+      "size": 1701316,
+      "sha256": "5f49030509ce188a119910f16054558e1cdd1c70a22d2a1458ec4189f5d1a08e"
+    },
+    "proteins_unirep": {
+      "name": "05.4_combined_prot_embeddings_unirep.tsv.xz",
+      "url": "https://zenodo.org/records/10944245/files/05.4_combined_prot_embeddings_unirep.tsv.xz?download=1",
+      "size": 138392528,
+      "sha256": "19aa0562c3b695883c5aa8c05ad0934c4b9b851a26550345940d92ed17f36b93"
+    }
+  },
+  "05.5": {
+      "readme": {
+      "name": "README.txt",
+      "url": "https://zenodo.org/record/7019874/files/README.txt?download=1",
+      "size": 11092,
+      "sha256": "0af036c1d02b150f6402a53960a6e995611e66ee7724b61a21f58d3366ec8eda"
+  },
+    "requirements": [{
+        "name": "LICENSE.txt",
+        "url": "https://zenodo.org/records/10943207/files/LICENSE.txt?download=1",
+        "size": 20138,
+        "sha256": "3b2890eacd851373001c4a14623458e3adaf1b1967939aa9c38a318e28d61c00"
+    },
+    {
+      "name": "data_types.json",
+      "url": "https://zenodo.org/records/10943207/files/data_types.json?download=1",
+      "size": 450678,
+      "sha256": "d38f0b6b53f0450c5530b5bf44d8a7d0bb85417f22b7c818237e3346fe68149c"
+    },
+    {
+      "name": "data_size.json",
+      "url": "https://zenodo.org/records/10943207/files/data_size.json?download=1",
+      "size": 324,
+      "sha256": "513307863c4acc779789340e900821ff8f38c845865aa078edc649caa1559dcc"
+    }],
+    "papyrus++": {
+      "name": "05.5++_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/records/10943207/files/05.5++_combined_set_without_stereochemistry.tsv.xz?download=1",
+      "size": 41357608,
+      "sha256": "8ecaea9533f3c475dca6d335f30dd1b4abb259fa77b7441548dd15879e1afa58"
+    },
+    "2D_papyrus": {
+      "name": "05.5_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_set_without_stereochemistry.tsv.xz?download=1",
+      "size": 718601992,
+      "sha256": "04ecaea97c09d02dbde809ad99ea2127fc3997a4e3b200b56dee85c30801890a"
+    },
+    "2D_structures": {
+      "name": "05.5_combined_2D_set_without_stereochemistry.sd.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_2D_set_without_stereochemistry.sd.xz?download=1",
+      "size": 399767580,
+      "sha256": "2e088ca662c5c33c5fc018c42c9c21e918ec167f1129a0a11fbf9c72888e8be6"
+    },
+    "3D_papyrus": {
+      "name": "05.5_combined_set_with_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_set_with_stereochemistry.tsv.xz?download=1",
+      "size": 690498416,
+      "sha256": "822aca70ccf4c19879ae45dfa16de5fc29c3ee08b25739e7a087899652af7dd9"
+    },
+    "3D_structures": {
+      "name": "05.5_combined_3D_set_with_stereochemistry.sd.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_3D_set_with_stereochemistry.sd.xz?download=1",
+      "size": 492426264,
+      "sha256": "a4a5355ffc56de8d914c2ad281d10c227171c27e4d6c250daad14a16280cf136"
+    },
+    "2D_fingerprint": {
+      "name": "05.5_combined_2D_moldescs_ECFP6.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_2D_moldescs_ECFP6.tsv.xz?download=1",
+      "size": 97818228,
+      "sha256": "3d626b4295cfbe73877157d8eea84b911a3cb60bf9571165d88c00cc0b0880d2"
+    },
+    "3D_fingerprint": {
+      "name": "05.5_combined_3D_moldescs_E3FP.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_3D_moldescs_E3FP.tsv.xz?download=1",
+      "size": 114052016,
+      "sha256": "446fe36d50487f29a2d7402a53cc661097e884dc0df8ffd278646dba6708cb65"
+    },
+    "2D_mordred": {
+      "name": "05.5_combined_2D_moldescs_mordred2D.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_2D_moldescs_mordred2D.tsv.xz?download=1",
+      "size": 2936434876,
+      "sha256": "bcef94b1c04a1e7d8f9da11ad87e598e19932548a8ea4f00029c2f3a89672ff4"
+    },
+    "3D_mordred": {
+      "name": "05.5_combined_3D_moldescs_mordred3D.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_3D_moldescs_mordred3D.tsv.xz?download=1",
+      "size": 3206020732,
+      "sha256": "e6ffd0858f85217b57c4a88619e5f41d7f6bae16a9948612872162e54d3231dc"
+    },
+    "2D_cddd": {
+      "name": "05.5_combined_2D_moldescs_CDDDs.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_2D_moldescs_CDDDs.tsv.xz?download=1",
+      "size": 3775676256,
+      "sha256": "8421d973b4eb119f0739506a0b20ba9508356df97d4673e1c170e871cd134983"
+    },
+    "2D_mold2": {
+      "name": "05.5_combined_2D_moldescs_mold2.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_2D_moldescs_mold2.tsv.xz?download=1",
+      "size": 1553510028,
+      "sha256": "0fd1c2b3869c5fa749c21ddd70c5dff621974eccafb8e04fd6f95f3b37242058"
+    },
+    "proteins": {
+      "name": "05.5_combined_set_protein_targets.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_set_protein_targets.tsv.xz?download=1",
+      "size": 1710756,
+      "sha256": "d8f2cbee8b9849f7c3664fe7e8165c5abf785d374c36a8f151a6ec38fd582d80"
+    },
+    "proteins_unirep": {
+      "name": "05.5_combined_prot_embeddings_unirep.tsv.xz",
+      "url": "https://zenodo.org/record/7019874/files/05.5_combined_prot_embeddings_unirep.tsv.xz?download=1",
+      "size": 128869632,
+      "sha256": "9f1fce00e77563481eafc44405f9dc8188d5669ed93cafaee256c0208ca135b8"
+    }
+  },
+  "05.6": {
+    "readme": {
+      "name": "README.txt",
+      "url": "https://zenodo.org/record/7377161/files/README.txt?download=1",
+      "size": 12170,
+      "sha256": "b6a1977aed99e84c4ab560a04006a86264c9ff83ca67ed14e395e855c2543613"
+    },
+    "requirements": {
+      "name": "05.6_additional_files.zip",
+      "url": "https://zenodo.org/record/7377161/files/05.6_additional_files.zip?download=1",
+      "size": 51310,
+      "sha256": "c1d8df814ba54e17619f3740ff82577898a85a07acd220822403874159e26d8a"
+    },
+    "papyrus++": {
+      "name": "05.6++_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/records/7821775/files/05.6++_combined_set_without_stereochemistry.tsv.xz?download=1",
+      "size": 31085780,
+      "sha256": "7518019c3ba287cd4cd0ff29425fe9da8a4760d891d22ed1abb33da4920cf96a"
+    },
+    "2D_papyrus": {
+      "name": "05.6_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_set_without_stereochemistry.tsv.xz?download=1",
+      "size": 744449364,
+      "sha256": "82a36ed7bb2f80846bb46e4c3e38905895bd1a2cfddd471d32091cb59dcf9437"
+    },
+    "2D_structures": {
+      "name": "05.6_combined_2D_set_without_stereochemistry.sd.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_2D_set_without_stereochemistry.sd.xz?download=1",
+      "size": 439758444,
+      "sha256": "1ec001964aca301494ea05fc24529120f01bc6952dcf4276dcd03625dfec460d"
+    },
+    "3D_papyrus": {
+      "name": "05.6_combined_set_with_stereochemistry.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_set_with_stereochemistry.tsv.xz?download=1",
+      "size": 711529352,
+      "sha256": "62068d500986b78fc90fe82b9e224555f8ca85319cd19f9df8bc73549e8a3e31"
+    },
+    "3D_structures": {
+      "name": "05.6_combined_3D_set_with_stereochemistry.sd.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_3D_set_with_stereochemistry.sd.xz?download=1",
+      "size": 500108592,
+      "sha256": "38e39963cd79845b4adca9dea871ffba18576ea742677471fc46a73a7dabbf38"
+    },
+    "2D_fingerprint": {
+      "name": "05.6_combined_2D_moldescs_ECFP6.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_2D_moldescs_ECFP6.tsv.xz?download=1",
+      "size": 96612972,
+      "sha256": "01c7366ee2ca7353d3a9f76601702b6d2eb312e71f02ea8ef48e2f90870c266c"
+    },
+    "3D_fingerprint": {
+      "name": "05.6_combined_3D_moldescs_E3FP.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_3D_moldescs_E3FP.tsv.xz?download=1",
+      "size": 117065432,
+      "sha256": "0d15baa4a9425daf63a0066511e9e96cbd5d7dab223bdaf48803536ab2484dc2"
+    },
+    "2D_mordred": {
+      "name": "05.6_combined_2D_moldescs_mordred2D.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_2D_moldescs_mordred2D.tsv.xz?download=1",
+      "size": 3055443236,
+      "sha256": "c497db85e97542f59b5252e2b1d3bdd93604e5c4d2ea131088a87d79ea6954c3"
+    },
+    "3D_mordred": {
+      "name": "05.6_combined_3D_moldescs_mordred3D.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_3D_moldescs_mordred3D.tsv.xz?download=1",
+      "size": 3324119256,
+      "sha256": "6b022acb6a0bec8bfc1ae7585014ae0b812a12ddcbed7be4ac7ec073c662192f"
+    },
+    "2D_cddd": {
+      "name": "05.6_combined_2D_moldescs_CDDDs.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_2D_moldescs_CDDDs.tsv.xz?download=1",
+      "size": 2103289016,
+      "sha256": "fbb54e5ca9a28ff022dc5baddf87cb6601169a2d86f3b55db4d183fd3885642a"
+    },
+    "2D_mold2": {
+      "name": "05.6_combined_2D_moldescs_mold2.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_2D_moldescs_mold2.tsv.xz?download=1",
+      "size": 1487710808,
+      "sha256": "cd46ce9841a1f956840b4fe7c56310eaa32c5e957a6ffaca62fbc55f820aad99"
+    },
+    "proteins": {
+      "name": "05.6_combined_set_protein_targets.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_set_protein_targets.tsv.xz?download=1",
+      "size": 1850764,
+      "sha256": "f443a2f8c74b8eb3f2c9d1bd7bfbddc86cbcc3fd5e8e505b7057b78a4ad17ee1"
+    },
+    "proteins_unirep": {
+      "name": "05.6_combined_protdescs_unirep.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_protdescs_unirep.tsv.xz?download=1",
+      "size": 207122632,
+      "sha256": "47f37c1f1efcb9d6f002d5a096853975c27ddcc767d7903a8af12bac0439181c"
+    },
+    "proteins_prodec": {
+      "name": "05.6_combined_protdescs_ProDEC.tsv.xz",
+      "url": "https://zenodo.org/record/7377161/files/05.6_combined_protdescs_ProDEC.tsv.xz?download=1",
+      "size": 447818916,
+      "sha256": "3211a62f18ccb7ccc13f885374c1462efeb83ab0e98ed62d2645723f7dc9f1a1"
+    }
+  },
+  "05.7": {
+    "readme": {
+      "name": "README.txt",
+      "url": "https://drive.google.com/uc?id=16ak1O1v70O72_UzFldGzZY_b6Ntd0eZm&confirm=t",
+      "size": 0,
+      "sha256": ""
+    },
+    "requirements": {
+      "name": "05.7_additional_files.zip",
+      "url": "https://drive.google.com/uc?id=18IGeQ4tTW6b7VO8nb7EYJqGSLNdXHEgD&confirm=t",
+      "size": 114037,
+      "sha256": "e8a0b5f65bd79c21b979b69d2b19fe6f51611fbc5a988ff3c0caa738ab0bca73"
+    },
+    "papyrus++": {
+      "name": "05.7++_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1lI_B8MKehKOcstQYpS_IQRTkbsaXovNf&confirm=t",
+      "size": 57295028,
+      "sha256": "a4819cd45f10b973a7bde75e5de58dff47980fc1347f2e552a1ac39f520b780f"
+    },
+    "2D_papyrus": {
+      "name": "05.7_combined_set_without_stereochemistry.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1Jc1Zj43aORhOiLOZX4CE5tYlUPc5zoBK&confirm=t",
+      "size": 749503448,
+      "sha256": "42c1d175e617909701f5baf8175fee18b6be986274c628ef209612a8240368f7"
+    },
+    "2D_structures": {
+      "name": "05.7_combined_2D_set_without_stereochemistry.sd.xz",
+      "url": "https://drive.google.com/uc?id=1yTSKlTyT2rud8_6J0TgiVAnSnswaeL09&confirm=t",
+      "size": 457158128,
+      "sha256": "5ea668a099ff2422accccadb378a50ae570044881d20c017742f53dc8f421680"
+    },
+    "3D_papyrus": {
+      "name": "05.7_combined_set_with_stereochemistry.tsv.xz",
+      "url": "https://drive.google.com/uc?id=14tsxNwjqpKjeJSRyZy5kG_i7Pg0gQPS_&confirm=t",
+      "size": 715818916,
+      "sha256": "0ee09ceace168ec25b0619349b7b41d754a7ad75a4cb82c2d887ab11d7ceb03c"
+    },
+    "3D_structures": {
+      "name": "05.7_combined_3D_set_with_stereochemistry.sd.xz",
+      "url": "https://drive.google.com/uc?id=1rkOz5QxWVMiQUWsNX0fzfb94doGy-FSI&confirm=t",
+      "size": 519810936,
+      "sha256": "fc5a9fd3ca68dba3f1f9b3217d85ecbb31bebb07798ea008d70b5e92caea2c1d"
+    },
+    "2D_fingerprint": {
+      "name": "05.7_combined_2D_moldescs_ECFP6.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1TtJ2iUKVoo-_32cdFbFACSclv6CyeYNI&confirm=t",
+      "size": 100340752,
+      "sha256": "491a8dbc93364718de87b6c1ef3779b9ecdd3ec5af4dadc4dbddaf261a9d254f"
+    },
+    "3D_fingerprint": {
+      "name": "05.7_combined_3D_moldescs_E3FP.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1KKOujpCm31za_i12SKhjxbwg4ywwDbjU&confirm=t",
+      "size": 121328636,
+      "sha256": "4e08240587757adbf6ca481b3998751b09c48fc1cb58068609f54b1a76275c11"
+    },
+    "2D_mordred": {
+      "name": "05.7_combined_2D_moldescs_mordred2D.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1cTJLBz82VShJYrMMcQLOYiCS4IFmiOjk&confirm=t",
+      "size": 3166511800,
+      "sha256": "e9f841c7233f21c7db406f973cb89ec90db9caa7e99a6618dea94ad1fc72cdac"
+    },
+    "3D_mordred": {
+      "name": "05.7_combined_3D_moldescs_mordred3D.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1w-SwQohL60_QsOoqVmlxwz3LLbxC50YX&confirm=t",
+      "size": 3443038656,
+      "sha256": "1e480c48c8eb86c57def26331ea2447e43f60d6fd73a2c33e76a6338abd5d132"
+    },
+    "2D_cddd": {
+      "name": "05.7_combined_2D_moldescs_CDDDs.tsv.xz",
+      "url": "https://drive.google.com/uc?id=18ERbYiqLg7WkXpZ3DyjNCHLr495_stik&confirm=t",
+      "size": 2179141716,
+      "sha256": "c227b3b8e4ea0ff53cb358a765ff89ffdfc7f83b2f3e71142e31fca74be28e3b"
+    },
+    "2D_mold2": {
+      "name": "05.7_combined_2D_moldescs_mold2.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1VJJHcCkfQeRNCL8gYpQ5pToUFfP87ZaA&confirm=t",
+      "size": 1548906976,
+      "sha256": "95be36ae2e883053b8b275f26238fe292c34133e3cb527a40fe9bfaece057d49"
+    },
+    "proteins": {
+      "name": "05.7_combined_set_protein_targets.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1mZYpQm5gMGw1Z8xdq-seqYE4diD81dc-&confirm=t",
+      "size": 1779284,
+      "sha256": "1226453794df7552aa56375d3ec0a045008586f5ab6612cb3a06942dfac4dbac"
+    },
+    "proteins_unirep": {
+      "name": "05.7_combined_protdescs_unirep.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1cFbo402ofPP5YP_JpUKHZle3XjVARc6S&confirm=t",
+      "size": 209760216,
+      "sha256": "cfd8b9e3ea9b95713bd23c69b2db7ae7dfd0c019b5f610912e7d557537c4305c"
+    },
+    "proteins_prodec": {
+      "name": "05.7_combined_protdescs_ProDEC.tsv.xz",
+      "url": "https://drive.google.com/uc?id=1FX7vVUmvtVd4fVk22n4yGRTR0kM_XTQt&confirm=t",
+      "size": 434668804,
+      "sha256": "9011ff21dcb3acb73af40b37d2a587c0aa0060d803b9cee165f8131a2933f80d"
+    }
+  }
+}

{papyrus_scripts-2.1.0 → papyrus_scripts-2.1.1/src/papyrus_scripts.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: papyrus_scripts
-Version: 2.1.0
+Version: 2.1.1
 Summary: A collection of scripts to handle the Papyrus bioactivity dataset
 Home-page: https://github.com/OlivierBeq/Papyrus-scripts
 Author: Olivier J. M. Béquignon - Brandon J. Bongers - Willem Jespers

{papyrus_scripts-2.1.0 → papyrus_scripts-2.1.1}/src/papyrus_scripts.egg-info/SOURCES.txt

@@ -25,5 +25,7 @@ src/papyrus_scripts/utils/UniprotMatch.py
 src/papyrus_scripts/utils/__init__.py
 src/papyrus_scripts/utils/aliases.json
 src/papyrus_scripts/utils/links.json
+src/papyrus_scripts/utils/links2.json
 src/papyrus_scripts/utils/mol_reader.py
+tests/test.py
 tests/test_oop.py

papyrus_scripts-2.1.1/tests/test.py

@@ -0,0 +1,31 @@
+from papyrus_scripts import PapyrusDataset, preprocess, reader
+
+# data2 = (PapyrusDataset(is3d=False, version='latest', plusplus=False, chunksize=int(1e6))
+#                                 .keep_organism('Mus musculus (Mouse)')
+#                                 .keep_source('chembl')
+#                                 .keep_protein_class({'l5': 'CC chemokine receptor'})
+#                                 .not_isin('accession', ['P13500', 'P13501'])
+#                                 .keep_activity_type(['ki', 'kd'])
+#                                 .aggregate(progress=True))
+#
+# #print(data2.organism.value_counts())
+# print(data2.source.value_counts())
+# print(data2.Classification.value_counts())
+# print(data2.accession.value_counts())
+# print(data2[['type_IC50', 'type_EC50', 'type_KD', 'type_Ki', 'type_other']].value_counts())
+
+
+fn_data = reader.read_papyrus(is3d=False, version='latest', plusplus=True, chunksize=int(1e6))
+fn_protein_data = reader.read_protein_set(version='latest')
+fn_filter1 = preprocess.keep_organism(fn_data, fn_protein_data, organism='Homo sapiens (Human)')
+fn_filter2 = preprocess.keep_protein_class(fn_filter1, fn_protein_data, classes={'l5': 'Adenosine receptor'})
+fn_filter3 = preprocess.keep_type(fn_filter2, activity_types='ic50')
+fn_data_agg = preprocess.consume_chunks(fn_filter3, progress=True)
+oop_data_agg = (PapyrusDataset(is3d=False, version='latest', plusplus=True, chunksize=int(1e6))
+                .keep_organism('Homo sapiens (Human)')
+                .keep_protein_class({'l5': 'Adenosine receptor'})
+                .keep_activity_type('ic50')
+                .aggregate(progress=True))
+
+print(fn_data_agg)
+print(oop_data_agg)