Skip to content

Instantly share code, notes, and snippets.

@ptosco
Created May 28, 2020 13:58
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save ptosco/49bdfc55db7277c7c94aca71b69f64b5 to your computer and use it in GitHub Desktop.
Save ptosco/49bdfc55db7277c7c94aca71b69f64b5 to your computer and use it in GitHub Desktop.
SmilesFromCSV
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import csv\n",
"from rdkit import Chem\n",
"from rdkit.Chem.Draw import rdDepictor"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"csv_data = \"\"\"\\\n",
"\"Parent Molecule ChEMBL ID\";\"Parent Molecule Name\";\"Parent Molecule Type\";\"Max Phase\";\"First Approval\";\"USAN Stem\";\"Smiles\";\"Mechanism of Action\";\"Mechanism Comment\";\"Selectivity Comment\";\"Target ChEMBL ID\";\"Target Name\";\"Action Type\";\"Target Type\";\"Target Organism\";\"Binding Site Name\";\"Binding Site Comment\";\"References\";\"Synonyms\";\"ATC Codes\";\"Level 4 ATC Codes\";\"Level 3 ATC Codes\";\"Level 2 ATC Codes\";\"Level 1 ATC Codes\";\"Parent Molecule ChEMBL ID\"\n",
"\"CHEMBL1201349\";\"HEXAFLUORENIUM\";\"Small molecule\";\"4\";\"1982\";\"'-ium'\";\"C[N+](C)(CCCCCC[N+](C)(C)C1c2ccccc2-c2ccccc21)C1c2ccccc2-c2ccccc21\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: PubMed RefID: 849069 URL: http://europepmc.org/abstract/MED/849069|Type: PubMed RefID: 948350 URL: http://europepmc.org/abstract/MED/948350\";\"Hexafluorenium Bromide (FDA, USAN, USP)|Hexafluronium Bromide (INN)|\";\"M03AC05\";\"M03AC - Other quaternary ammonium compounds\";\"M03A - MUSCLE RELAXANTS, PERIPHERALLY ACTING AGENTS\";\"M03 - MUSCLE RELAXANTS\";\"M - MUSCULO-SKELETAL SYSTEM\";\"CHEMBL1201349\"\n",
"\"CHEMBL1025\";\"ISOFLUROPHATE\";\"Small molecule\";\"4\";\"1957\";\"\";\"CC(C)OP(=O)(F)OC(C)C\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: PubMed RefID: 13016741 URL: http://europepmc.org/abstract/MED/13016741|Type: PubMed RefID: 6007355 URL: http://europepmc.org/abstract/MED/6007355\";\"Dyflos (BAN)|Isoflurophate (FDA, USP)|\";\"S01EB07\";\"S01EB - Parasympathomimetics\";\"S01E - ANTIGLAUCOMA PREPARATIONS AND MIOTICS\";\"S01 - OPHTHALMOLOGICALS\";\"S - SENSORY ORGANS\";\"CHEMBL1025\"\n",
"\"CHEMBL1115\";\"PYRIDOSTIGMINE\";\"Small molecule\";\"4\";\"1955\";\"'-stigmine'\";\"CN(C)C(=O)Oc1ccc[n+](C)c1\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: DailyMed RefID: setid=30cb0b9f-e308-4501-90c2-b17349c048b7 URL: http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=30cb0b9f-e308-4501-90c2-b17349c048b7|Type: Wikipedia RefID: Pyridostigmine#Mode_of_action URL: http://en.wikipedia.org/wiki/Pyridostigmine#Mode_of_action\";\"Pyridostigmine Bromide (BAN, FDA, INN, JAN, MI, USP)|\";\"N07AA02\";\"N07AA - Anticholinesterases\";\"N07A - PARASYMPATHOMIMETICS\";\"N07 - OTHER NERVOUS SYSTEM DRUGS\";\"N - NERVOUS SYSTEM\";\"CHEMBL1115\"\n",
"\"CHEMBL1201229\";\"DEMECARIUM\";\"Small molecule\";\"4\";\"1959\";\"'-ium'\";\"CN(CCCCCCCCCCN(C)C(=O)Oc1cccc([N+](C)(C)C)c1)C(=O)Oc1cccc([N+](C)(C)C)c1\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: PubMed RefID: 12641839 URL: http://europepmc.org/abstract/MED/12641839\";\"Demecarium Bromide (BAN, FDA, INN, USP)|\";\"S01EB04\";\"S01EB - Parasympathomimetics\";\"S01E - ANTIGLAUCOMA PREPARATIONS AND MIOTICS\";\"S01 - OPHTHALMOLOGICALS\";\"S - SENSORY ORGANS\";\"CHEMBL1201229\"\n",
"\"CHEMBL1420\";\"PRALIDOXIME\";\"Small molecule\";\"4\";\"1964\";\"'io-'\";\"C[n+]1ccccc1C=NO\";\"Acetylcholinesterase activator\";\"reactivates acetylcholinesterase deactivated by organophosphates\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"ACTIVATOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: DailyMed RefID: setid=a16ac225-bb32-4b27-bb66-9e152cf065eb URL: http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=a16ac225-bb32-4b27-bb66-9e152cf065eb|Type: KEGG RefID: D00469 URL: http://www.kegg.jp/dbget-bin/www_bget?dr:D00469|Type: Wikipedia RefID: Pralidoxime#Mechanism_of_action URL: http://en.wikipedia.org/wiki/Pralidoxime#Mechanism_of_action\";\"Pralidoxime (INN, BAN)|Pralidoxime chloride (FDA, USAN, USP)|Pralidoxime Mesylate (USAN)|Pralidoxime Iodide (INN, JAN, USAN)|\";\"V03AB04\";\"V03AB - Antidotes\";\"V03A - ALL OTHER THERAPEUTIC PRODUCTS\";\"V03 - ALL OTHER THERAPEUTIC PRODUCTS\";\"V - VARIOUS\";\"CHEMBL1420\"\n",
"\"CHEMBL1201341\";\"ECHOTHIOPHATE\";\"Small molecule\";\"4\";\"1960\";\"'io-'\";\"CCOP(=O)(OCC)SCC[N+](C)(C)C\";\"Acetylcholinesterase inhibitor\";\"Irreversible\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: DailyMed RefID: setid=c4adbc81-6681-4e12-f8ab-5d1cb7723aad#nlm34090-1 URL: http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=c4adbc81-6681-4e12-f8ab-5d1cb7723aad#nlm34090-1|Type: Wikipedia RefID: Cholinesterase URL: http://en.wikipedia.org/wiki/Cholinesterase\";\"Echothiophate Iodide (FDA, MI, USP)|Ecothiopate Iodide (BAN, INN, JAN)|\";\"S01EB03\";\"S01EB - Parasympathomimetics\";\"S01E - ANTIGLAUCOMA PREPARATIONS AND MIOTICS\";\"S01 - OPHTHALMOLOGICALS\";\"S - SENSORY ORGANS\";\"CHEMBL1201341\"\n",
"\"CHEMBL278020\";\"NEOSTIGMINE\";\"Small molecule\";\"4\";\"2013\";\"'-stigmine'\";\"CN(C)C(=O)Oc1cccc([N+](C)(C)C)c1\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: DailyMed RefID: setid=79ee2111-d65c-11e1-9b23-0800200c9a66#nlm34090-1 URL: http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=79ee2111-d65c-11e1-9b23-0800200c9a66#nlm34090-1\";\"Neostigmine (BAN, MI, BAN)|Neostigmine methyl sulfate (MI)|Neostigmine Methylsulfate (FDA, JAN, USP)|Neostigmine Bromide (BAN, INN, JAN, USP)|\";\"N07AA01 | S01EB06 | N07AA51\";\"N07AA - Anticholinesterases | S01EB - Parasympathomimetics | N07AA - Anticholinesterases\";\"N07A - PARASYMPATHOMIMETICS | S01E - ANTIGLAUCOMA PREPARATIONS AND MIOTICS | N07A - PARASYMPATHOMIMETICS\";\"N07 - OTHER NERVOUS SYSTEM DRUGS | S01 - OPHTHALMOLOGICALS | N07 - OTHER NERVOUS SYSTEM DRUGS\";\"N - NERVOUS SYSTEM | S - SENSORY ORGANS | N - NERVOUS SYSTEM\";\"CHEMBL278020\"\n",
"\"CHEMBL659\";\"GALANTAMINE\";\"Small molecule\";\"4\";\"2001\";\"\";\"COc1ccc2c3c1O[C@H]1C[C@@H](O)C=C[C@@]31CCN(C)C2\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: DailyMed RefID: setid=bbdaf2f2-14e6-45c4-b807-5b22955444b0 URL: http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=bbdaf2f2-14e6-45c4-b807-5b22955444b0\";\"Galantamine hydrobromide (FDA, USAN)|Galantamine Hydrobromide (JAN, MI, USP)|Galantamine (BAN, INN, MI, USAN)|\";\"N06DA04\";\"N06DA - Anticholinesterases\";\"N06D - ANTI-DEMENTIA DRUGS\";\"N06 - PSYCHOANALEPTICS\";\"N - NERVOUS SYSTEM\";\"CHEMBL659\"\n",
"\"CHEMBL502\";\"DONEPEZIL\";\"Small molecule\";\"4\";\"1996\";\"'-pezil'\";\"COc1cc2c(cc1OC)C(=O)C(CC1CCN(Cc3ccccc3)CC1)C2\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: DailyMed RefID: setid=2b1b7b5f-2f20-418c-b1ac-794c2ef1ce5e URL: http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=2b1b7b5f-2f20-418c-b1ac-794c2ef1ce5e\";\"Donepezil HCl (FDA, JAN, MI, USAN)|Donepezil (BAN, INN, MI)|\";\"N06DA02\";\"N06DA - Anticholinesterases\";\"N06D - ANTI-DEMENTIA DRUGS\";\"N06 - PSYCHOANALEPTICS\";\"N - NERVOUS SYSTEM\";\"CHEMBL502\"\n",
"\"CHEMBL1652\";\"AMBENONIUM\";\"Small molecule\";\"4\";\"1956\";\"'-onium'\";\"CC[N+](CC)(CCNC(=O)C(=O)NCC[N+](CC)(CC)Cc1ccccc1Cl)Cc1ccccc1Cl\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: FDA RefID: label/2014/010155s024lbl.pdf URL: http://www.accessdata.fda.gov/drugsatfda_docs/label/2014/010155s024lbl.pdf\";\"Ambenonium Chloride (BAN, FDA, INN, JAN, MI, USP)|\";\"N07AA30\";\"N07AA - Anticholinesterases\";\"N07A - PARASYMPATHOMIMETICS\";\"N07 - OTHER NERVOUS SYSTEM DRUGS\";\"N - NERVOUS SYSTEM\";\"CHEMBL1652\"\n",
"\"CHEMBL278819\";\"MINAPRINE\";\"Small molecule\";\"4\";\"\";\"\";\"Cc1cc(-c2ccccc2)nnc1NCCN1CCOCC1\";\"Acetylcholinesterase inhibitor\";\"Minaprine binds to serotonin type 2 receptors and to dopamine D1 and D2 type receptors. It also binds to the serotonin reuptake pump. Therefore, minaprine blocks the reuptake of both dopamine and serotonin. It is also, to a slight degree, cholinomimetic. Thus it may exhibit both mood-brightening and nootropic properties. It also acts as a reversible inhibitor of monoamine oxidase. It has also been found to inhibit acetylcholinesterase in a reversible and competitive way.\";\"IC50= 85µM on homogenized rat striatum acetylcholinesterase.\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: PubMed RefID: 10052979 URL: http://europepmc.org/abstract/MED/10052979|Type: PubMed RefID: 1361012 URL: http://europepmc.org/abstract/MED/1361012|Type: PubMed RefID: 2586634 URL: http://europepmc.org/abstract/MED/2586634|Type: PubMed RefID: 2975224 URL: http://europepmc.org/abstract/MED/2975224|Type: PubMed RefID: 3836113 URL: http://europepmc.org/abstract/MED/3836113|Type: PubMed RefID: 3954800 URL: http://europepmc.org/abstract/MED/3954800|Type: PubMed RefID: 6425901 URL: http://europepmc.org/abstract/MED/6425901|Type: PubMed RefID: 6890359 URL: http://europepmc.org/abstract/MED/6890359|Type: PubMed RefID: 8494598 URL: http://europepmc.org/abstract/MED/8494598|Type: PubMed RefID: 8904622 URL: http://europepmc.org/abstract/MED/8904622\";\"Minaprine HCl (USAN)|Minaprine (BAN, INN, USAN)|\";\"N06AX07\";\"N06AX - Other antidepressants\";\"N06A - ANTIDEPRESSANTS\";\"N06 - PSYCHOANALEPTICS\";\"N - NERVOUS SYSTEM\";\"CHEMBL278819\"\n",
"\"CHEMBL2105345\";\"PROPANIDID\";\"Small molecule\";\"4\";\"\";\"\";\"CCCOC(=O)Cc1ccc(OCC(=O)N(CC)CC)c(OC)c1\";\"Acetylcholinesterase inhibitor\";\"Propanidid is a competitive inhibitor of serum cholinesterase, and neuromuscular plaque and brain acetylcholinesterase. It is an intravenous anesthetic that has been used for rapid induction of anesthesia and for maintenance of anesthesia of short duration.\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: PubMed RefID: 7465080 URL: http://europepmc.org/abstract/MED/7465080|Type: PubMed RefID: 7573906 URL: http://europepmc.org/abstract/MED/7573906\";\"Propanidid (BAN, INN, USAN)|\";\"N01AX04\";\"N01AX - Other general anesthetics\";\"N01A - ANESTHETICS, GENERAL\";\"N01 - ANESTHETICS\";\"N - NERVOUS SYSTEM\";\"CHEMBL2105345\"\n",
"\"CHEMBL1104\";\"EDROPHONIUM\";\"Small molecule\";\"4\";\"1951\";\"'-onium'\";\"CC[N+](C)(C)c1cccc(O)c1\";\"Acetylcholinesterase inhibitor\";\"\";\"\";\"CHEMBL220\";\"Acetylcholinesterase\";\"INHIBITOR\";\"SINGLE PROTEIN\";\"Homo sapiens\";\"\";\"\";\"Type: DailyMed RefID: setid=98a5a2f6-3194-4202-963f-0fcd28ecadbc URL: http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=98a5a2f6-3194-4202-963f-0fcd28ecadbc\";\"Edrophonium Chloride (BAN, FDA, INN, JAN, USP)|\";\"\";\"\";\"\";\"\";\"\";\"CHEMBL1104\"\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"smiles_data = \"\"\n",
"for i, row in enumerate(csv.reader(csv_data.split(\"\\n\"), delimiter=\";\")):\n",
" if (i == 0):\n",
" chembl_id_idx = row.index(\"Parent Molecule ChEMBL ID\")\n",
" smiles_idx = row.index(\"Smiles\")\n",
" elif row:\n",
" smiles_data += \"{0:s} {1:s}\\n\".format(row[smiles_idx], row[chembl_id_idx])"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"suppl = Chem.SmilesMolSupplierFromText(smiles_data)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"w = Chem.SDWriter(\"chembl_mols.sdf\")\n",
"for mol in suppl:\n",
" rdDepictor.Compute2DCoords(mol)\n",
" w.write(mol)\n",
"w.close()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.6.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment