new release v.2.0.0

URV-cheminformatics · Jul 19, 2024 · 0e53ab7 · 0e53ab7
1 parent 0048a41
commit 0e53ab7
Show file tree

Hide file tree

Showing 2 changed files with 228 additions and 223 deletions.
diff --git a/PDB-CAT.ipynb b/PDB-CAT.ipynb
@@ -10,20 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Install libraries\n",
-    "# !pip install --quiet rdkit\n",
-    "# !pip install --quiet pdbecif\n",
-    "# !pip install --quiet biopython\n",
-    "# !pip install --quiet time"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -43,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -69,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -128,15 +115,10 @@
     "        covalent_bond_list = data_from_file[\"Covalent_Bond\"].split('\\n')\n",
     "        ligand_covalents_bond = data_from_file[\"Bond\"].split('\\n')\n",
     "        descarted_ligands = data_from_file[\"Discarted_Ligands\"].split('\\n')\n",
-    "        branched_molecules = data_from_file[\"Branched\"].split('\\n')\n",
-    "        branched_name = data_from_file[\"Branched_name\"].split('\\n')\n",
-    "        branched_type = data_from_file[\"Branched_type\"].split('\\n')\n",
-    "        branched_covalent = data_from_file[\"Branched_Covalent\"].split('\\n')\n",
-    "        branched_bond = data_from_file[\"Branched_Bond\"].split('\\n')\n",
     "\n",
     "\n",
     "        # Find the maximum length among the three lists\n",
-    "        max_length = max(len(ligands), len(ligand_names_list), len(ligand_types_list), len(covalent_bond_list), len(ligand_covalents_bond), len(descarted_ligands), len(branched_molecules))\n",
+    "        max_length = max(len(ligands), len(ligand_names_list), len(ligand_types_list), len(covalent_bond_list), len(ligand_covalents_bond), len(descarted_ligands))\n",
     "        \n",
     "        for i in range(max_length):\n",
     "            ligand_row = {field: data_from_file[field] for field in fields_to_include}\n",
@@ -159,16 +141,7 @@
     "                ligand_row_discarded[\"Covalent_Bond\"] = \"\"\n",
     "                ligand_row_discarded[\"Bond\"] = \"\"\n",
     "                data_ligands.append(ligand_row_discarded)\n",
-    "            \n",
-    "            # Add a column to the ligands DataFrame and fill it with the corresponding information\n",
-    "            if i < len(branched_molecules) and branched_molecules[i].strip():  \n",
-    "                ligand_row_branched = {field: data_from_file[field] for field in fields_to_include}\n",
-    "                ligand_row_branched[\"Ligand\"] = branched_molecules[i].strip() if i < len(branched_molecules) else \"\"\n",
-    "                ligand_row_branched[\"Ligand_names\"] = branched_name[i].strip() if i < len(branched_name) else \"\"\n",
-    "                ligand_row_branched[\"Ligand_types\"] = \"Branched\"\n",
-    "                ligand_row_branched[\"Covalent_Bond\"] = branched_covalent[i].strip() if i < len(branched_covalent) else \"\"\n",
-    "                ligand_row_branched[\"Bond\"] = branched_bond[i].strip() if i < len(branched_bond) else \"\"\n",
-    "                data_ligands.append(ligand_row_branched)\n",
+    "\n",
     "\n",
     "# First csv output. Protein-centered\n",
     "df = pd.DataFrame(data)  # Create a Pandas df\n",
@@ -200,6 +173,13 @@
     "# Classify depend on the bond\n",
     "bond_classification(directory_path, out_file, no_mutated_list, output_path, mutation)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {