Merge pull request #14 from cimranm/protein_searching

Protein searching
kamurani · Aug 4, 2022 · eea2250 · eea2250
2 parents f5076ae + 99ab21e
commit eea2250
Show file tree

Hide file tree

Showing 12 changed files with 20,840 additions and 17,461 deletions.
diff --git a/examples/pdbs/10gs.pdb b/examples/pdbs/10gs.pdb
diff --git a/examples/pdbs/134l.pdb b/examples/pdbs/134l.pdb
diff --git a/examples/pdbs/16gs.pdb b/examples/pdbs/16gs.pdb
diff --git a/examples/pdbs/1u2z.pdb b/examples/pdbs/1u2z.pdb
diff --git a/examples/pdbs/3eiy.pdb b/examples/pdbs/3eiy.pdb
diff --git a/examples/pdbs/3opt.pdb b/examples/pdbs/3opt.pdb
diff --git a/examples/pdbs/4hhb.pdb b/examples/pdbs/4hhb.pdb
diff --git a/examples/pdbs/A0A0C5B5G6.pdb b/examples/pdbs/A0A0C5B5G6.pdb
diff --git a/examples/pdbs/P50549.pdb b/examples/pdbs/P50549.pdb
diff --git a/examples/pdbs/Q5VSL9.pdb b/examples/pdbs/Q5VSL9.pdb
@@ -1,4 +1,4 @@
-HEADER                                            01-JUL-21                     
+HEADER                                            01-JUN-22                     
 TITLE     ALPHAFOLD MONOMER V2.0 PREDICTION FOR STRIATIN-INTERACTING PROTEIN 1  
 TITLE    2 (Q5VSL9)                                                             
 COMPND    MOL_ID: 1;                                                            

diff --git a/pomegranate/definitions.py b/pomegranate/definitions.py
@@ -22,5 +22,6 @@
 EMBEDDINGS_FILENAME = f"ALL_CURRENT.csv"
 EMBEDDINGS_PATH = os.path.join(os.path.join(ROOT_DIR, 'embeddings'), EMBEDDINGS_FILENAME)
 
+AF_VERSION = 3
 
 
diff --git a/pomegranate/protein/phosphosite.py b/pomegranate/protein/phosphosite.py
@@ -8,7 +8,7 @@
 
 
 ### DEFINITIONS
-from definitions import ROOT_DIR, STRUCTURE_PATH, SAVED_PDB_DIR, SAVED_GRAPHS_DIR
+from definitions import ROOT_DIR, STRUCTURE_PATH, SAVED_PDB_DIR, SAVED_GRAPHS_DIR, AF_VERSION
 
 ### External libraries
 import os
@@ -91,7 +91,7 @@ def get_protein_graph(id=None, config=None, database='PDB'):
         print("AF or SP")
         # NOTE: DEBUGGING: construct graph is always looking at examples/pdbs. Just put everything in examples/pdbs
         # protein_path = download_alphafold_structure(id, aligned_score=False, out_dir=STRUCTURE_PATH)
-        protein_path = download_alphafold_structure(id, aligned_score=False, out_dir=SAVED_PDB_DIR)
+        protein_path = download_alphafold_structure(id, AF_VERSION, aligned_score=False, out_dir=SAVED_PDB_DIR)
         #protein_path = STRUCTURE_PATH + id + '.pdb'
         print("After")
 
@@ -118,15 +118,15 @@ def get_protein_graph(id=None, config=None, database='PDB'):
             if database == 'PDB':
                 g = construct_graph(config=config, pdb_path=protein_path)
             else:
-                g = construct_graph(pdb_path=protein_path)
+                g = construct_graph(config=config, pdb_path=protein_path)
         else:
             print(f"Retrieving {id}...")
             if database == 'PDB':
                 #g = construct_graph(config=config, pdb_code=id)
                 g = construct_graph(config=config, pdb_code=id)
             else: # NOTE: FIX THIS. BAD STYLE. Same line as 119
                 #g = construct_graph(config=config, pdb_path=protein_path)
-                g = construct_graph(pdb_path=protein_path)
+                g = construct_graph(config=config, pdb_path=protein_path)
 
     # TODO: check if file exists and download if not.
Original file line number	Diff line number	Diff line change
Expand Up		@@ -22,5 +22,6 @@
		EMBEDDINGS_FILENAME = f"ALL_CURRENT.csv"
		EMBEDDINGS_PATH = os.path.join(os.path.join(ROOT_DIR, 'embeddings'), EMBEDDINGS_FILENAME)

		AF_VERSION = 3