Sulstice

{
  "metadata": {
    "title": "Cannabis Sativa Volatile Sulfur Compounds Analysis",
    "date": "2025-01-21",
    "source": "Hellma Protein Target Analysis",
    "total_compounds": 7,
    "total_pdb_targets": 195
  },
  "column_definitions": {
    "chemical_name": "IUPAC chemical name",

Sulstice

# Imports
# -------

import time
import requests
import pandas as pd

def cas_to_smiles(cas_number):
  
    url = f"https://cactus.nci.nih.gov/chemical/structure/{cas_number}/smiles"

Sulstice

from transformers import RobertaTokenizer, RobertaModel

benzene = 'C1=CC=CC=C1'

chembert = RobertaModel.from_pretrained("seyonec/ChemBERTa-zinc-base-v1")
chembert_tokenizer = RobertaTokenizer.from_pretrained("seyonec/ChemBERTa-zinc-base-v1")

inputs = chembert_tokenizer(
   benzene, return_tensors="pt", padding=True, truncation=True
)

Sulstice

from global_chem import GlobalChem
from STOUT import translate_forward, translate_reverse

if __name__ == '__main__':

    gc = GlobalChem()
    gc.build_global_chem_network(print_output=False, debugger=False)

    names = gc.get_all_names()
    smiles = gc.get_all_smiles()

Sulstice

def mol2_to_sdf(mol2_file, sdf_file=None):
    """
        Method to convert a multi-mol2 file to sdf format with an extra property that stores the partial charges.
        It invokes PyBel's mol2 file loader because RDKit's mol2 file loader that not read the partial charges.
    """

    if sdf_file == None:
        sdf_file = os.path.splitext(mol2_file)[0] + ".sdf"
    largeSDfile = Outputfile("sdf", sdf_file, overwrite=True)
    for mymol in readfile("mol2", mol2_file):

Sulstice

import cirpy

from global_chem import GlobalChem

gc = GlobalChem()

gc.build_global_chem_network()
smiles_list = gc.get_node_smiles('emerging_perfluoroalkyls')

import time

Sulstice

from global_chem import GlobalChem

gc = GlobalChem()

gc.build_global_chem_network()
smiles_list = list(gc.get_node_smiles('constituents_of_cannabis_sativa').values())

print (f"First SMILES: {smiles_list[0]}")

from rdkit import Chem

Sulstice

from rdkit import Chem
import rdkit.Chem.Descriptors as Descriptors

if __name__ == '__main__':

    molecule = 'O'
    rdkit_molecule = Chem.MolFromSmiles(molecule)

    molecular_weight = Descriptors.ExactMolWt(rdkit_molecule)
    logp = Descriptors.MolLogP(rdkit_molecule)

Sulstice

A chemical dataset spread with filters. 

Sulstice

<?xml version='1.0' encoding='UTF-8'?>
<R_replacements><center SMILES="*O" degree="13627"><first_layer SMILES="*OC" edge_weight="2273"><second_layer SMILES="*Cl" edge_weight="3455" /><second_layer SMILES="*OCC" edge_weight="788" /></first_layer><first_layer SMILES="*N" edge_weight="958"><second_layer SMILES="*NC" edge_weight="305" /><second_layer SMILES="*NC(C)=O" edge_weight="300" /></first_layer><first_layer SMILES="*CO" edge_weight="301"><second_layer SMILES="*C(C)O" edge_weight="75" /><second_layer SMILES="*C(C)(C)O" edge_weight="53" /></first_layer><first_layer SMILES="*OC(C)=O" edge_weight="200" /><first_layer SMILES="*C(=O)NO" edge_weight="89"><second_layer SMILES="*CC(=O)NO" edge_weight="43" /></first_layer></center><center SMILES="*OC" degree="12408"><first_layer SMILES="*Cl" edge_weight="3455"><second_layer SMILES="*F" edge_weight="4152" /><second_layer SMILES="*Br" edge_weight="2208" /></first_layer><first_layer SMILES="*O" edge_weight="2273"><second_layer SMILES="*N" edge_weight="958" /><second_la