Scaffold Network Generator

Contributers

Usage

git clone git@github.com:jach4/scaffold_network_generator.git sng
cd sng

python scaffolds_output.py --out_fmt=protobuf --np=50 --nq=100000 --file_input=data/datasets/input.smi --scaffolds_output=data/datasets/idx_sm.bin --file_output=data/datasets/idx_ls.bin 

python scaffolds_output.py --out_fmt=postgres --np=80 --nq=100000 --file_input=data/datasets/input.smi --sql_dic=./data1.json --db_name=sc1

Read the entire scaffold message from a file

from data import *
from rdkit import Chem
from rdkit.Chem import Draw
from rdkit.Chem.Draw import IPythonConsole

dic_scaffold = DicIdxLs()
with open('data/datasets/idx_ls.bin', 'rb') as f:
    dic_scaffold.ParseFromString(f.read())
dic_idx_sm = DicIdxSm()
with open('data/datasets/idx_sm.bin', 'rb') as f:
    dic_idx_sm.ParseFromString(f.read())

print(len(dic_scaffold.smiles_scaffold))

402344

Get the 1990th scaffold

print(dic_idx_sm.sm_sc[1990])
Chem.MolFromSmiles(dic_idx_sm.sm_sc[1990])

c1n[nH]nc1-c1nnc(-c2cnns2)o1

dic_scaffold.smiles_scaffold[1990]

dic_mol_atoms {
  idx_mol: 111921
  ls_atom {
    idx_atom: 1
    idx_atom: 2
    idx_atom: 3
    idx_atom: 10
    idx_atom: 11
    idx_atom: 12
    idx_atom: 13
    idx_atom: 14
    idx_atom: 15
    idx_atom: 16
    idx_atom: 17
    idx_atom: 18
    idx_atom: 19
    idx_atom: 20
    idx_atom: 22
  }
  ls_nh {
    idx_atom: 3
  }
  ls_np {
  }
}

The 111,921th molecule containing the 1990th scaffold

Chem.MolFromSmiles(smiles_from_line(111921))

Get the scaffold network of The 111,921th molecule

scaffold_list = get_mol_graph(smiles_from_line(111921)).ls_mol_from_sng_u()

Draw.MolsToGridImage(scaffold_list)