feat: similar search accross pdb

backend/.gitignore

@@ -3,4 +3,5 @@ __pycache__/
 .foldseek_cache/
 foldseek/bin/foldseek
 foldseek/README.md
-foldseek-linux-sse2.tar.gz
+foldseek-linux-sse2.tar.gz
+pdb*

backend/src/api/similar.py

@@ -4,18 +4,17 @@
  pdb_file_name,
  revert_pdb_filename,
 )
-from ..foldseek import easy_search
+from ..foldseek import easy_search, create_db
 
 router = APIRouter()
 
 
 @router.get("/similar-pdb/{protein_name:str}", response_model=list[SimilarProtein])
 def get_pdb_proteins(protein_name: str):
- # query_name = pdb_file_name(protein_name)
- # target_folder = "src/data/pdbAlphaFold/"
- # similar = easy_search(query_name, target_folder, out_format=["target", "prob"])
- pass
- # return [SimilarProtein(name=revert_pdb_filename(s[0]), prob=s[1]) for s in similar]
+ query_name = pdb_file_name(protein_name)
+ PDB = create_db("PDB", "pdb")
+ similar = easy_search(query_name, PDB, out_format=["target", "prob"])
+ return [SimilarProtein(name=s[0].split(".")[0], prob=s[1]) for s in similar]
 
 
 @router.get("/similar-venome/{protein_name:str}", response_model=list[SimilarProtein])

backend/src/foldseek.py

@@ -80,14 +80,10 @@ def easy_search(
 def create_db(
  dir: str,
  db_name: str,
- foldseek_executable="foldseek",
+ foldseek_executable="foldseek/bin/foldseek",
  print_stdout=False,
  temp_dir=".foldseek_cache",
 ):
- # don't continue unless they actually have foldseek installed
- if bash_cmd(f"which {foldseek_executable}") == "":
- raise Exception("foldseek not found in PATH")
-
  # check that our dir exists
  try:
  bash_cmd(f"ls {dir}")