72 lack of solvents for packmol tool (#73)

* Improve path_registry init to initialize with files already downloaded in the files/ directory * Fixing packmol: 1. Moving the input validator inside the tool. 2. Packmol needs the pdb files in the same directory. files/pdb doesn't work; Corrected copy and pasting temporarily the pdb files from the path_registry and deleting after termination * Solved unrelated bugs in cleaning tools, mainly from path_registry calls. * Add new tool to make pdb files from small molecules names or smiles. Also include this functionality directly in packmol function with new parameter small_molecules. (#76) --------- Co-authored-by: Sam Cox <[email protected]>
ur-whitelab · Feb 7, 2024 · eaa4f17 · eaa4f17
1 parent a56cfe8
commit eaa4f17
Show file tree

Hide file tree

Showing 10 changed files with 726 additions and 184 deletions.
diff --git a/mdagent/tools/base_tools/__init__.py b/mdagent/tools/base_tools/__init__.py
@@ -13,7 +13,12 @@
     RemoveWaterCleaningTool,
     SpecializedCleanTool,
 )
-from .preprocess_tools.pdb_tools import Name2PDBTool, PackMolTool, get_pdb
+from .preprocess_tools.pdb_tools import (
+    PackMolTool,
+    ProteinName2PDBTool,
+    SmallMolPDB,
+    get_pdb,
+)
 from .simulation_tools.create_simulation import ModifyBaseSimulationScriptTool
 from .simulation_tools.setup_and_run import (
     InstructionSummary,
@@ -32,9 +37,10 @@
     "InstructionSummary",
     "ListRegistryPaths",
     "MapPath2Name",
-    "Name2PDBTool",
+    "ProteinName2PDBTool",
     "PackMolTool",
     "PPIDistance",
+    "SmallMolPDB",
     "VisualizeProtein",
     "RMSDCalculator",
     "RemoveWaterCleaningTool",

diff --git a/mdagent/tools/base_tools/preprocess_tools/__init__.py b/mdagent/tools/base_tools/preprocess_tools/__init__.py
@@ -5,15 +5,16 @@
     RemoveWaterCleaningTool,
     SpecializedCleanTool,
 )
-from .pdb_tools import Name2PDBTool, PackMolTool, get_pdb
+from .pdb_tools import PackMolTool, ProteinName2PDBTool, SmallMolPDB, get_pdb
 
 __all__ = [
     "AddHydrogensCleaningTool",
     "CleaningTools",
-    "Name2PDBTool",
+    "ProteinName2PDBTool",
     "PackMolTool",
     "RemoveWaterCleaningTool",
     "SpecializedCleanTool",
     "get_pdb",
     "CleaningToolFunction",
+    "SmallMolPDB",
 ]
diff --git a/mdagent/tools/base_tools/preprocess_tools/clean_tools.py b/mdagent/tools/base_tools/preprocess_tools/clean_tools.py
@@ -296,17 +296,17 @@ def _run(self, **input_args) -> str:
             file_description = "Cleaned File: "
             CleaningTools()
             try:
-                pdbfile = self.path_registry.get_mapped_path(pdbfile_id)
-                if "/" in pdbfile:
-                    pdbfile = pdbfile.split("/")[-1]
-
-                name = pdbfile.split("_")[0]
-                end = pdbfile.split(".")[1]
+                pdbfile_path = self.path_registry.get_mapped_path(pdbfile_id)
+                if "/" in pdbfile_path:
+                    pdbfile = pdbfile_path.split("/")[-1]
+                else:
+                    pdbfile = pdbfile_path
+                name, end = pdbfile.split(".")
 
             except Exception as e:
                 print(f"error retrieving from path_registry, trying to read file {e}")
                 return "File not found in path registry. "
-            fixer = PDBFixer(filename=pdbfile)
+            fixer = PDBFixer(filename=pdbfile_path)
             try:
                 fixer.findMissingResidues()
             except Exception:
@@ -353,7 +353,7 @@ def _run(self, **input_args) -> str:
             file_mode = "w" if add_hydrogens else "a"
             file_name = self.path_registry.write_file_name(
                 type=FileType.PROTEIN,
-                protein_name=name,
+                protein_name=name.split("_")[0],
                 description="Clean",
                 file_format=end,
             )