clean up hybrid top cells

Author: atravitz

cookbook/openfold3_to_openfe.ipynb

@@ -737,7 +737,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Generating charges: 100%|█████████████████████████| 1/1 [00:00<00:00,  1.80it/s]\n"
+      "Generating charges: 100%|█████████████████████████| 1/1 [00:00<00:00,  1.84it/s]\n"
      ]
     }
    ],
@@ -1246,7 +1246,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Generating charges: 100%|███████████████████████| 10/10 [00:05<00:00,  1.78it/s]\n"
+      "Generating charges: 100%|███████████████████████| 10/10 [00:05<00:00,  1.81it/s]\n"
      ]
     }
    ],
@@ -1456,7 +1456,7 @@
     "\n",
     "In addition to aligning the protein structures, we must also align the ligands.\n",
     "\n",
-    "Again, as per the SepTop example above, we will do the transformation between `lig_jmc_27` and `lig_ejm_46`."
+    "We will again use the transformation between `lig_jmc_27` and `lig_ejm_46` as an example."
    ]
   },
   {
@@ -1474,56 +1474,25 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Extracting ligand from lig_ejm_50_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_jmc_23_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_ejm_43_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_ejm_42_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_ejm_31_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_ejm_47_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_jmc_27_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_ejm_46_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_ejm_48_seed_42_sample_1_model.pdb\n",
-      "Extracting ligand from lig_jmc_28_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_ejm_50_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_jmc_23_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_ejm_43_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_ejm_42_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_ejm_31_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_ejm_47_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_jmc_27_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_ejm_46_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_ejm_48_seed_42_sample_1_model.pdb\n",
+      "Calculating volume of lig_jmc_28_seed_42_sample_1_model.pdb\n",
       "\n",
-      "Largest ligand is lig_jmc_27 with volume 0.5209626577896912\n"
+      "Largest ligand_name is lig_jmc_27 with volume 0.521\n"
      ]
     }
    ],
    "source": [
-    "from MDAnalysis.analysis import align\n",
-    "from rdkit.Chem.Descriptors3D import Asphericity\n",
-    "\n",
-    "# gather all the complexes and align to a single structure\n",
-    "# which has the largest ligand by volume \n",
     "of3_results_root = pathlib.Path(\"assets/of3_tyk2_output/\")\n",
-    "tmp_ligand_dir = pathlib.Path(output_root,\"temp_ligands\")\n",
-    "tmp_ligand_dir.mkdir(exist_ok=True,parents=True)\n",
-    "# load all the output pdbs and calculate ligand volumes\n",
-    "ligand_volumes = {}\n",
-    "\n",
-    "for output_file in of3_results_root.glob(\"*/*/*.pdb\"):\n",
-    "    ligand_name = output_file.name.split('_seed')[0]\n",
-    "    print(f\"Extracting ligand from {output_file.name}\")\n",
-    "    with warnings.catch_warnings():   \n",
-    "        warnings.simplefilter(\"ignore\")\n",
-    "        u = mda.Universe(str(output_file))\n",
-    "    ligand = u.select_atoms(\"resname LIG\")\n",
-    "    # write the ligand to a temporary file\n",
-    "    ligand.write(str(tmp_ligand_dir / f\"{ligand_name}.pdb\"))\n",
-    "    # now load back with rdkit\n",
-    "    rdkit_mol = Chem.MolFromPDBFile(str(tmp_ligand_dir / f\"{ligand_name}.pdb\"), removeHs=True)\n",
-    "    # now use a template from the SMILES definitions to make sure the bond orders are correct\n",
-    "    template_mol = Chem.MolFromSmiles(ligand_smiles[ligand_name])\n",
-    "    # don't show rdkit's \"WARNING: More than one matching pattern found - picking one\" for every ligand\n",
-    "    with rdBase.BlockLogs():  \n",
-    "        rdkit_mol = AllChem.AssignBondOrdersFromTemplate(template_mol, rdkit_mol)\n",
-    "    # calculate the volume\n",
-    "    vsa = Asphericity(rdkit_mol)\n",
-    "    ligand_volumes[ligand_name] = vsa\n",
-    "\n",
-    "# find the ligand with the largest volume\n",
-    "largest_ligand = max(ligand_volumes, key=ligand_volumes.get)\n",
-    "print(f\"\\nLargest ligand is {largest_ligand} with volume {ligand_volumes[largest_ligand]}\")"
+    "largest_ligand, largest_vol= find_largest_ligand(of3_results_root.glob(\"*/*/*.pdb\"))\n",
+    "print(f\"\\nLargest ligand_name is {largest_ligand} with volume {largest_vol:.3f}\")\n"
    ]
   },
   {
@@ -1833,6 +1802,14 @@
     "In practice, one would create entire network of Transformations, and then run all the simulations.\n",
     "This notebook will not cover these aspects. To find out more about this, please see the [OpenFE Tutorials](https://docs.openfree.energy/en/latest/tutorials/index.html)."
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fab60c32-e717-43b3-b8e7-81d2e2aaa9c9",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {