Clean Pockets and Examine Ligand Data.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1201ba5f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import random\n",
    "import torch\n",
    "import math\n",
    "from Bio import SeqIO\n",
    "import Bio.PDB\n",
    "import pickle as pickle\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "from Bio import PDB"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "78807be8",
   "metadata": {},
   "source": [
    "**Insert the path to the PDB Refines set from PDBind** "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1256ceb9",
   "metadata": {},
   "outputs": [],
   "source": [
    "class CFG:\n",
    "    pdbfiles: str = \"/home/paul/Desktop/BioHack-Project-Walkthrough/pdbind-refined-set/\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "efef9960",
   "metadata": {},
   "outputs": [],
   "source": [
    "def remove_hetatm(input_pdb_file, output_pdb_file):\n",
    "    \"Removes HETATMS from raw PDB Files and outputs the clean PDB into a new file location\"\n",
    "    # Open the input PDB file for reading and the output PDB file for writing\n",
    "    with open(input_pdb_file, 'r') as infile, open(output_pdb_file, 'w') as outfile:\n",
    "        for line in infile:\n",
    "            # Check if the line starts with 'HETATM' (non-protein atoms)\n",
    "            if line.startswith('HETATM'):\n",
    "                continue  # Skip this line (HETATM record)\n",
    "            # Write all other lines to the output file\n",
    "            outfile.write(line)\n",
    "def remove_missing_alpha_carbons(input_pdb_file, output_pdb_file):\n",
    "    \"Removes all residues from a PDB file if the alpha carbon is missing\"\n",
    "    # Parse the input PDB file\n",
    "    parser = PDB.PDBParser(QUIET=True)\n",
    "    structure = parser.get_structure('structure', input_pdb_file)\n",
    "\n",
    "    # Iterate over residues and identify those missing alpha carbons\n",
    "    residues_to_remove = []\n",
    "    for model in structure:\n",
    "        for chain in model:\n",
    "            for residue in chain:\n",
    "                if 'CA' not in residue:\n",
    "                    residues_to_remove.append(residue)\n",
    "\n",
    "    # Remove identified residues from the structure\n",
    "    for residue in residues_to_remove:\n",
    "        chain = residue.get_parent()\n",
    "        chain.detach_child(residue.id)\n",
    "\n",
    "    # Save the modified structure to the output file\n",
    "    io = PDB.PDBIO()\n",
    "    io.set_structure(structure)\n",
    "    io.save(output_pdb_file)\n",
    "    \n",
    "def get_atom_types_from_mol2_split(mol2_file):\n",
    "    \"Returns a set of the atoms present in a Mol2 File\"\n",
    "    atom_types = set()\n",
    "\n",
    "    with open(mol2_file, 'r') as mol2:\n",
    "        reading_atoms = False\n",
    "        for line in mol2:\n",
    "            if line.strip() == '@<TRIPOS>ATOM':\n",
    "                reading_atoms = True\n",
    "                continue\n",
    "            elif line.strip() == '@<TRIPOS>BOND':\n",
    "                break\n",
    "\n",
    "            if reading_atoms:\n",
    "                parts = line.split()\n",
    "                if len(parts) >= 5:\n",
    "                    atom_type = parts[5]\n",
    "                    atom_types.add(atom_type)\n",
    "    \n",
    "    atom_types_split = set()\n",
    "    for atom in atom_types:\n",
    "        atom_types_split.add(str(atom).split('.')[0])\n",
    "        \n",
    "\n",
    "    return sorted(list(atom_types_split))\n",
    "\n",
    "def get_bond_types_from_mol2(mol2_file):\n",
    "    \"Returns a set of bond types present in a Mol2 File\"\n",
    "    bond_types = set()\n",
    "\n",
    "    with open(mol2_file, 'r') as mol2:\n",
    "        reading_bonds = False\n",
    "        for line in mol2:\n",
    "            if line.strip() == '@<TRIPOS>BOND':\n",
    "                reading_bonds = True\n",
    "                continue\n",
    "            elif reading_bonds and line.strip().startswith('@<TRIPOS>'):\n",
    "                break\n",
    "\n",
    "            if reading_bonds:\n",
    "                parts = line.split()\n",
    "                if len(parts) >= 4:\n",
    "                    bond_type = parts[3]\n",
    "                    bond_types.add(bond_type)\n",
    "\n",
    "    return sorted(list(bond_types))\n",
    "\n",
    "def dict2embeding(dict_):\n",
    "    \"Convert dictionary to a new dictionary containing the OHEings\"\n",
    "    count = 0\n",
    "    out_id = {}\n",
    "    for i in dict_:\n",
    "        x = np.zeros(len(dict_))\n",
    "        x[count] = 1.\n",
    "        count +=1\n",
    "        out_id.update({str(i): x})\n",
    "    return out_id\n",
    "\n",
    "AA_dictionary = {'GLY':torch.Tensor([1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'ALA':torch.Tensor([0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'VAL':torch.Tensor([0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'CYS':torch.Tensor([0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'PRO':torch.Tensor([0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'LEU':torch.Tensor([0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'ILE':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'MET':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'TRP':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'PHE':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'LYS':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'ARG':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'HIS':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'SER':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'THR':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0]),\n",
    "            'TYR':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0]),\n",
    "            'ASN':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0]),\n",
    "            'GLN':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0]),\n",
    "            'ASP':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0]),\n",
    "            'GLU':torch.Tensor([0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0]),}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7b4103f",
   "metadata": {},
   "source": [
    "Ensure all PDB Files are present (There should be 5316)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d18cbe1b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5316\n",
      "5316\n"
     ]
    }
   ],
   "source": [
    "total_count = 0\n",
    "file_count = 0\n",
    "for filename in os.listdir(CFG.pdbfiles):\n",
    "    num_files = 0\n",
    "    for file in os.listdir(CFG.pdbfiles+filename):\n",
    "        num_files += 1\n",
    "    if num_files > 0:\n",
    "        file_count += 1\n",
    "    total_count += 1\n",
    "\n",
    "print(total_count)\n",
    "print(file_count)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cd9f9c93",
   "metadata": {},
   "source": [
    "Remove all HETATMS from the PDB Files -<br>\n",
    "All Ligands are stored in seperate files as either SDF or Mol2 Files so this command only removes water, ions and crystalographic additives.<br> These HETATMS also need to be removed from the binding pocket PDB files. Some of the binding pockets contain residues with missing backbone atoms. These residues need to be deleted"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "03c48ca0",
   "metadata": {},
   "outputs": [],
   "source": [
    "for filename in os.listdir(CFG.pdbfiles):\n",
    "    input_pdb_filename = CFG.pdbfiles+filename+'/'+filename+'_protein'\n",
    "    output_pdb_filename = input_pdb_filename+'_clean.pdb'\n",
    "    remove_hetatm(input_pdb_filename+'.pdb', output_pdb_filename)\n",
    "\n",
    "for filename in os.listdir(CFG.pdbfiles):\n",
    "    input_pdb_filename = CFG.pdbfiles+filename+'/'+filename+'_pocket'\n",
    "    output_pdb_filename = input_pdb_filename+'_clean.pdb'\n",
    "    remove_hetatm(input_pdb_filename+'.pdb', output_pdb_filename)\n",
    "\n",
    "for filename in os.listdir(CFG.pdbfiles):\n",
    "    input_pdb_filename = CFG.pdbfiles+filename+'/'+filename+'_pocket'\n",
    "    output_pdb_filename = input_pdb_filename+'_clean.pdb'\n",
    "    remove_missing_alpha_carbons(output_pdb_filename, output_pdb_filename)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8fe70e22",
   "metadata": {},
   "source": [
    "Exploring the dataset -<br>Find all elemnts present is the set of ligands and visualize how many of each atom are present across the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "7b110f1c",
   "metadata": {},
   "outputs": [],
   "source": [
    "count = 0\n",
    "Atom_type_count = {}\n",
    "for filename in os.listdir(CFG.pdbfiles):\n",
    "    mol2_file = CFG.pdbfiles+filename+'/'+filename+'_ligand.mol2'\n",
    "    atoms = get_atom_types_from_mol2_split(mol2_file)\n",
    "    for atom in atoms:\n",
    "        if atom in Atom_type_count:\n",
    "            Atom_type_count[atom] += 1\n",
    "        else:\n",
    "            Atom_type_count.update({atom: 1})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "ed586cd1",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = []\n",
    "count = []\n",
    "for atom in Atom_type_count:\n",
    "    x.append(atom)\n",
    "    count.append(Atom_type_count[atom])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "119c409e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.bar(x,count)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "416765fc",
   "metadata": {},
   "source": [
    "Same thing as above except with bond types in the ligand file - Note: Include the \"Not Connected\" type as well, will come up in the future"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3106afcc",
   "metadata": {},
   "outputs": [],
   "source": [
    "count = 0\n",
    "Bond_type_count = {}\n",
    "for filename in os.listdir(CFG.pdbfiles):\n",
    "    mol2_file = CFG.pdbfiles+filename+'/'+filename+'_ligand.mol2'\n",
    "    bonds = get_bond_types_from_mol2(mol2_file)\n",
    "    for bond in bonds:\n",
    "        if bond in Bond_type_count:\n",
    "            Bond_type_count[bond] += 1\n",
    "        else:\n",
    "            Bond_type_count.update({bond: 1})\n",
    "\n",
    "Bond_type_count.update({'nc': 0})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "aa2fa5b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = []\n",
    "bond_count = []\n",
    "for bond in Bond_type_count:\n",
    "    x.append(bond)\n",
    "    bond_count.append(Bond_type_count[bond])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "24f35e56",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.bar(x,bond_count)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "cf00ec38",
   "metadata": {},
   "outputs": [],
   "source": [
    "atom_type_dict = dict2embeding(Atom_type_count)\n",
    "bond_type_dict = dict2embeding(Bond_type_count)\n",
    "AA_dict = dict2embeding(AA_dictionary)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "0ea7d0c2",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('atom_type_dict.pkl', 'wb') as f:\n",
    "    pickle.dump(atom_type_dict, f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "1e48ff94",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('bond_type_dict.pkl', 'wb') as f:\n",
    "    pickle.dump(bond_type_dict, f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "65b5777a",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('AA_dict.pkl', 'wb') as f:\n",
    "    pickle.dump(AA_dict, f)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}