[ENH] Remove Structure support for packaged pdbs

examples/aptanet_tutorial.ipynb

@@ -981,7 +981,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "pyaptamer-latest",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -995,7 +995,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.11"
+   "version": "3.12.10"
   }
  },
  "nbformat": 4,

pyaptamer/datasets/__init__.py

@@ -1,28 +1,32 @@
 """Contains datasets along with their loaders."""
 
-from pyaptamer.datasets._loaders._aptacom_loader import (
+from pyaptamer.datasets._loaders import (
+    load_1brq,
+    load_1gnh,
+    load_5nu7,
     load_aptacom_full,
     load_aptacom_x_y,
+    load_csv_dataset,
+    load_from_rcsb,
+    load_hf_dataset,
+    load_pfoa,
 )
-from pyaptamer.datasets._loaders._csv_loader import load_csv_dataset
-from pyaptamer.datasets._loaders._hf_loader import load_hf_dataset
 from pyaptamer.datasets._loaders._hf_to_dataset_loader import load_hf_to_dataset
 from pyaptamer.datasets._loaders._li2014 import load_li2014
-from pyaptamer.datasets._loaders._one_gnh import load_1gnh, load_1gnh_structure
-from pyaptamer.datasets._loaders._online_databank import load_from_rcsb
-from pyaptamer.datasets._loaders._pfoa import load_pfoa, load_pfoa_structure
 
 __all__ = [
     "load_aptacom_full",
     "load_aptacom_x_y",
     "load_csv_dataset",
     "load_hf_dataset",
-    "load_pfoa",
-    "load_pfoa_structure",
+    "load_from_rcsb",
+    "mol_loader",
+    "structure_loader",
+    "load_1brq",
+    "load_5nu7",
     "load_1gnh",
-    "load_1gnh_structure",
+    "load_pfoa",
     "load_from_rcsb",
-    "load_csv_dataset",
     "load_li2014",
     "load_hf_to_dataset",
 ]

pyaptamer/datasets/_loaders/_1brq.py

@@ -0,0 +1,19 @@
+__author__ = "satvshr"
+__all__ = ["load_1brq"]
+
+import os
+
+
+def load_1brq():
+    """Load the 1brq molecule as a MoleculeLoader.
+
+    Returns
+    -------
+    loader : MoleculeLoader
+        A MoleculeLoader object representing the 1brq molecule.
+    """
+    from pyaptamer.data.loader import MoleculeLoader
+
+    pdb_path = os.path.join(os.path.dirname(__file__), "..", "data", "1brq.pdb")
+
+    return MoleculeLoader(pdb_path)

pyaptamer/datasets/_loaders/_one_gnh.py → pyaptamer/datasets/_loaders/_1gnh.py

@@ -1,5 +1,5 @@
 __author__ = ["satvshr", "fkiraly"]
-__all__ = ["load_1gnh", "load_1gnh_structure"]
+__all__ = ["load_1gnh"]
 
 import os
 
@@ -19,7 +19,8 @@ def load_1gnh():
     return MoleculeLoader(pdb_path)
 
 
-def load_1gnh_structure(pdb_path=None):
+# This function is provided only to test struct_to_aaseq.
+def _load_1gnh_structure(pdb_path=None):
     """
     Load the 1gnh molecule from a PDB file using Biopython.
 
@@ -32,7 +33,7 @@ def load_1gnh_structure(pdb_path=None):
     Returns
     -------
     structure : Bio.PDB.Structure.Structure
-        A Biopython Structure object representing the PFOA molecule.
+        A Biopython Structure object representing the 1GNH molecule.
     """
     from Bio.PDB import PDBParser
 

pyaptamer/datasets/_loaders/_5nu7.py

@@ -0,0 +1,19 @@
+__author__ = "satvshr"
+__all__ = ["load_5nu7"]
+
+import os
+
+
+def load_5nu7():
+    """Load the 5nu7 molecule as a MoleculeLoader.
+
+    Returns
+    -------
+    loader : MoleculeLoader
+        A MoleculeLoader object representing the 5nu7 molecule.
+    """
+    from pyaptamer.data.loader import MoleculeLoader
+
+    pdb_path = os.path.join(os.path.dirname(__file__), "..", "data", "5nu7.pdb")
+
+    return MoleculeLoader(pdb_path)

pyaptamer/datasets/_loaders/__init__.py

@@ -1,5 +1,8 @@
 """Loaders for different data structures."""
 
+from pyaptamer.datasets._loaders._1brq import load_1brq
+from pyaptamer.datasets._loaders._1gnh import load_1gnh
+from pyaptamer.datasets._loaders._5nu7 import load_5nu7
 from pyaptamer.datasets._loaders._aptacom_loader import (
     load_aptacom_full,
     load_aptacom_x_y,
@@ -8,19 +11,19 @@
 from pyaptamer.datasets._loaders._hf_loader import load_hf_dataset
 from pyaptamer.datasets._loaders._hf_to_dataset_loader import load_hf_to_dataset
 from pyaptamer.datasets._loaders._li2014 import load_li2014
-from pyaptamer.datasets._loaders._one_gnh import load_1gnh_structure
-from pyaptamer.datasets._loaders._pfoa import load_pfoa_structure
+from pyaptamer.datasets._loaders._online_databank import load_from_rcsb
+from pyaptamer.datasets._loaders._pfoa import load_pfoa
 
 __all__ = [
-    "load_pfoa_structure",
-    "load_1gnh_structure",
     "load_aptacom_full",
     "load_aptacom_x_y",
     "load_csv_dataset",
+    "load_from_rcsb",
     "load_hf_dataset",
     "load_hf_to_dataset",
-    "load_pfoa_structure",
     "load_1gnh",
-    "load_1gnh_structure",
     "load_li2014",
+    "load_1brq",
+    "load_5nu7",
+    "load_pfoa",
 ]

pyaptamer/datasets/_loaders/_pfoa.py

@@ -1,5 +1,5 @@
 __author__ = ["satvshr", "fkiraly"]
-__all__ = ["load_pfoa", "load_pfoa_structure"]
+__all__ = ["load_pfoa"]
 
 import os
 
@@ -17,27 +17,3 @@ def load_pfoa():
     pdb_path = os.path.join(os.path.dirname(__file__), "..", "data", "pfoa.pdb")
 
     return MoleculeLoader(pdb_path)
-
-
-def load_pfoa_structure(pdb_path=None):
-    """
-    Load the PFOA molecule from a PDB file using Biopython.
-
-    Parameters
-    ----------
-    pdb_path : str, optional
-        Path to the PDB file. If not provided, the function uses the default path
-        located in the '../data/pfoa.pdb' relative to the current file.
-
-    Returns
-    -------
-    structure : Bio.PDB.Structure.Structure
-        A Biopython Structure object representing the PFOA molecule.
-    """
-    from Bio.PDB import PDBParser
-
-    pdb_path = os.path.join(os.path.dirname(__file__), "..", "data", "pfoa.pdb")
-
-    parser = PDBParser(QUIET=True)
-    structure = parser.get_structure("PFOA", pdb_path)
-    return structure