Skip to content

Instantly share code, notes, and snippets.

@dominiquesydow

dominiquesydow/extract_lig_from_pdb.ipynb

Created April 16, 2019 16:33
Show Gist options
  • Save dominiquesydow/1025167190e07229acd157bf6834a1b7 to your computer and use it in GitHub Desktop.
Save dominiquesydow/1025167190e07229acd157bf6834a1b7 to your computer and use it in GitHub Desktop.
Download ZIP
Extract ligand from PDB file
Display the source blob
Display the rendered blob
Raw
extract_lig_from_pdb.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Raw
gistfile1.txt
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Extract ligand coordinates by PDB ID and ligand ID"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"from pypdb import *\n",
"import re\n",
"\n",
"def get_ligand_coord(pdb_id, ligand_id, output_path=\"./\"):\n",
" \"\"\"\n",
" Extract ligand coordinates by PDB ID and ligand ID:\n",
" * Get PDB file from PDB (by PDB ID)\n",
" * Extract ligand entry rows in PDB file (by ligand ID) and save as PDB file\n",
" * Also: Return ligand entry rows\n",
" \"\"\"\n",
" \n",
" full_pdb = None # Full content of PDB file\n",
" lig_pdb = None # Ligand coordinates\n",
" \n",
" \n",
" # Get PDB file\n",
" try:\n",
" full_pdb = get_pdb_file(pdb_id)\n",
" except:\n",
" print(\"PDB ID could not be retrieved from PDB.\")\n",
" \n",
" # Extract ligand coordinates\n",
" try:\n",
" lig_pdb = [i for i in full_pdb.split(\"\\n\") if re.search(\"^HETATM\", i) and ligand_id in i]\n",
" except:\n",
" print(\"Ligand ID not found in PDB file.\")\n",
" \n",
" # Write ligand coordinates to file\n",
" with open(output_path + pdb_id + \"_\" + ligand_id + \".pdb\", \"a\") as f:\n",
" for i in lig_pdb:\n",
" f.write(i + \"\\n\")\n",
" \n",
" return lig_pdb"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"# Test with example\n",
"pdb_id = \"3W32\"\n",
"ligand_id = \"W32\""
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"# Save file to current directory\n",
"ligand_coords = get_ligand_coord(pdb_id, ligand_id)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"['HETATM 2547 C1 W32 A1101 17.523 28.990 5.798 1.00 31.51 C ',\n",
" 'HETATM 2548 C2 W32 A1101 16.291 28.418 6.080 1.00 30.31 C ',\n",
" 'HETATM 2549 C3 W32 A1101 17.399 32.400 11.069 1.00 27.58 C ',\n",
" 'HETATM 2550 C4 W32 A1101 17.766 30.265 6.269 1.00 29.96 C ',\n",
" 'HETATM 2551 C5 W32 A1101 17.620 31.995 9.772 1.00 28.42 C ',\n",
" 'HETATM 2552 C6 W32 A1101 15.605 30.408 7.268 1.00 28.58 C ',\n",
" 'HETATM 2553 C7 W32 A1101 15.786 33.991 10.313 1.00 27.15 C ',\n",
" 'HETATM 2554 C8 W32 A1101 12.748 33.566 13.379 1.00 31.64 C ',\n",
" 'HETATM 2555 C9 W32 A1101 14.942 34.492 14.574 1.00 35.19 C ',\n",
" 'HETATM 2556 C10 W32 A1101 15.370 29.134 6.809 1.00 25.91 C ',\n",
" 'HETATM 2557 C11 W32 A1101 16.480 33.398 11.352 1.00 28.93 C ',\n",
" 'HETATM 2558 C12 W32 A1101 16.830 30.965 6.994 1.00 32.48 C ',\n",
" 'HETATM 2559 C13 W32 A1101 16.923 32.597 8.743 1.00 27.90 C ',\n",
" 'HETATM 2560 C14 W32 A1101 15.995 33.592 9.009 1.00 29.12 C ',\n",
" 'HETATM 2561 C15 W32 A1101 13.699 34.562 15.192 1.00 29.35 C ',\n",
" 'HETATM 2562 C16 W32 A1101 14.989 33.935 13.305 1.00 35.49 C ',\n",
" 'HETATM 2563 C17 W32 A1101 16.163 35.029 15.170 1.00 34.55 C ',\n",
" 'HETATM 2564 C18 W32 A1101 16.443 35.196 16.465 1.00 31.64 C ',\n",
" 'HETATM 2565 C19 W32 A1101 17.734 35.864 16.810 1.00 41.85 C ',\n",
" 'HETATM 2566 C20 W32 A1101 15.566 34.815 17.582 1.00 34.23 C ',\n",
" 'HETATM 2567 C21 W32 A1101 14.310 35.640 17.409 1.00 33.52 C ',\n",
" 'HETATM 2568 C22 W32 A1101 23.039 35.053 18.700 1.00 86.61 C ',\n",
" 'HETATM 2569 C23 W32 A1101 20.048 36.322 16.157 1.00 53.53 C ',\n",
" 'HETATM 2570 C24 W32 A1101 20.735 35.538 17.258 1.00 62.21 C ',\n",
" 'HETATM 2571 C25 W32 A1101 14.038 28.522 7.120 1.00 27.55 C ',\n",
" 'HETATM 2572 N26 W32 A1101 12.598 34.091 14.590 1.00 29.72 N ',\n",
" 'HETATM 2573 N27 W32 A1101 13.891 33.461 12.695 1.00 32.32 N ',\n",
" 'HETATM 2574 N28 W32 A1101 13.391 35.060 16.456 1.00 30.86 N ',\n",
" 'HETATM 2575 N29 W32 A1101 16.248 33.857 12.650 1.00 28.23 N ',\n",
" 'HETATM 2576 N30 W32 A1101 18.733 35.791 15.867 1.00 40.18 N ',\n",
" 'HETATM 2577 O31 W32 A1101 17.835 36.482 17.860 1.00 50.74 O ',\n",
" 'HETATM 2578 O32 W32 A1101 23.066 36.437 16.489 1.00 63.85 O ',\n",
" 'HETATM 2579 O33 W32 A1101 21.997 37.443 18.557 1.00 81.42 O ',\n",
" 'HETATM 2580 O34 W32 A1101 17.118 32.249 7.424 1.00 30.16 O ',\n",
" 'HETATM 2581 F35 W32 A1101 14.097 27.611 8.115 1.00 35.13 F ',\n",
" 'HETATM 2582 F36 W32 A1101 13.166 29.438 7.562 1.00 34.11 F ',\n",
" 'HETATM 2583 F37 W32 A1101 13.559 27.856 6.039 1.00 32.07 F ',\n",
" 'HETATM 2584 S38 W32 A1101 22.276 36.305 17.700 1.00 84.11 S ',\n",
" 'HETATM 2585 CL1 W32 A1101 15.137 34.343 7.702 1.00 34.16 CL ']"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Look at ligand PDB lines (those were written to file)\n",
"ligand_coords"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"# Save file to other directory, e.g.\n",
"ligand_coords = get_ligand_coord(pdb_id, ligand_id, \"/home/dominique/Downloads/\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "teachopencadd",
"language": "python",
"name": "teachopencadd"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment