Make binding site cropping script more generic

Author: amorehead

configs/data/binding_site_crop_preparation.yaml

@@ -1,5 +1,5 @@
 dataset: posebusters_benchmark # the dataset to use - NOTE: must be one of (`posebusters_benchmark`, `astex_diverse`)
 input_data_dir: ${oc.env:PROJECT_ROOT}/data/${dataset}_set # the input protein-ligand complex directory to recursively parse
-input_protein_structure_dir: ${oc.env:PROJECT_ROOT}/data/${dataset}_set/${dataset}_holo_aligned_esmfold_structures # the input protein structure directory to parse
+input_protein_structure_dir: ${oc.env:PROJECT_ROOT}/data/${dataset}_set/${dataset}_holo_aligned_predicted_structures # the input protein structure directory to parse
 protein_ligand_distance_threshold: 4.0 # the heavy-atom distance threshold (in Angstrom) to use for finding protein binding site residues in interaction with ligand heavy atoms
 num_buffer_residues: 7 # the number of sequence-regional buffer residues to include around the native binding site residues

posebench/data/binding_site_crop_preparation.py

@@ -188,7 +188,7 @@ def save_cropped_protein_binding_site(
     for _, pdb_id in tqdm(smiles_and_pdb_id_list, desc="Cropping protein binding sites"):
         pred_protein_filepath = os.path.join(
             input_protein_structure_dir,
-            f"{pdb_id}_holo_aligned_esmfold_protein.pdb",
+            f"{pdb_id}_holo_aligned_predicted_protein.pdb",
         )
         ref_protein_filepath = os.path.join(input_data_dir, pdb_id, f"{pdb_id}_protein.pdb")
         ref_ligand_filepath = os.path.join(input_data_dir, pdb_id, f"{pdb_id}_ligand.sdf")
@@ -214,7 +214,7 @@ def save_cropped_protein_binding_site(
             binding_site_residue_indices,
             output_protein_structure_dir,
             pdb_id,
-            filename_midfix="_holo_aligned_esmfold",
+            filename_midfix="_holo_aligned_predicted",
         )
         crop_protein_binding_site(
             ref_protein_filepath,