{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "ed0cdaf6-71e1-4ef0-894f-0beabdc392cf",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import re\n",
"from PIL import Image\n",
"import webbrowser\n",
"import json\n",
"import pickle\n",
"import sys \n",
"import joblib\n",
"import sys\n",
"\n",
"from rdkit import Chem\n",
"from rdkit.Chem import Draw\n",
"from rdkit.Chem import rdChemReactions as Reactions\n",
"\n",
"from compound_cacher import CompoundCacher\n",
"from compound import Compound\n",
"from chemaxon import *\n",
"import chemaxon"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "e64deced-2a44-4d8e-ba8f-d9843f11724a",
"metadata": {},
"outputs": [],
"source": [
"def load_smiles():\n",
" db = pd.read_csv('./../data/cache_compounds_20160818.csv',index_col='compound_id')\n",
" db_smiles = db['smiles_pH7'].to_dict()\n",
" return db_smiles\n",
"\n",
"def load_molsig_rad1():\n",
" molecular_signature_r1 = json.load(open('./../data/decompose_vector_ac.json'))\n",
" return molecular_signature_r1\n",
"\n",
"def load_molsig_rad2():\n",
" molecular_signature_r2 = json.load(open('./../data/decompose_vector_ac_r2_py3_indent_modified_manual.json'))\n",
" return molecular_signature_r2\n",
"\n",
"def load_model():\n",
" filename = './../model/M12_model_BR.pkl'\n",
" loaded_model = joblib.load(open(filename, 'rb'))\n",
" return loaded_model"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "71615c14-49c3-45e7-9495-194ef22fb1ee",
"metadata": {},
"outputs": [],
"source": [
"db_smiles = load_smiles()\n",
"molsig_r1 = load_molsig_rad1()\n",
"molsig_r2 = load_molsig_rad2()\n",
"loaded_model = load_model()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "b86b8049-cbf2-473f-8715-5e5f908193a2",
"metadata": {},
"outputs": [],
"source": [
"def parse_reaction_formula_side(s):\n",
" \"\"\"\n",
" Parses the side formula, e.g. '2 C00001 + C00002 + 3 C00003'\n",
" Ignores stoichiometry.\n",
"\n",
" Returns:\n",
" The set of CIDs.\n",
" \"\"\"\n",
" if s.strip() == \"null\":\n",
" return {}\n",
"\n",
" compound_bag = {}\n",
" for member in re.split('\\s+\\+\\s+', s):\n",
" tokens = member.split(None, 1)\n",
" if len(tokens) == 0:\n",
" continue\n",
" if len(tokens) == 1:\n",
" amount = 1\n",
" key = member\n",
" else:\n",
" amount = float(tokens[0])\n",
" key = tokens[1]\n",
"\n",
" compound_bag[key] = compound_bag.get(key, 0) + amount\n",
"\n",
" return compound_bag\n",
"\n",
"def parse_formula(formula, arrow='<=>', rid=None):\n",
" \"\"\"\n",
" Parses a two-sided formula such as: 2 C00001 => C00002 + C00003\n",
"\n",
" Return:\n",
" The set of substrates, products and the direction of the reaction\n",
" \"\"\"\n",
" tokens = formula.split(arrow)\n",
" if len(tokens) < 2:\n",
" print(('Reaction does not contain the arrow sign (%s): %s'\n",
" % (arrow, formula)))\n",
" if len(tokens) > 2:\n",
" print(('Reaction contains more than one arrow sign (%s): %s'\n",
" % (arrow, formula)))\n",
"\n",
" left = tokens[0].strip()\n",
" right = tokens[1].strip()\n",
"\n",
" sparse_reaction = {}\n",
" for cid, count in parse_reaction_formula_side(left).items():\n",
" sparse_reaction[cid] = sparse_reaction.get(cid, 0) - count\n",
"\n",
" for cid, count in parse_reaction_formula_side(right).items():\n",
" sparse_reaction[cid] = sparse_reaction.get(cid, 0) + count \n",
" \n",
" return sparse_reaction"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "7342b178-3472-4734-83e3-3de431abe15e",
"metadata": {},
"outputs": [],
"source": [
"rxn_string = \"C00222 + C00010 + C00006 <=> C00024 + C00011 + C00005\""
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7b4dfe4f-48a8-4011-b201-7fb3a3268cef",
"metadata": {},
"outputs": [],
"source": [
"rxn_dic = parse_formula(rxn_string)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "1f523aa2-b9dc-4153-8c1c-dec58e1ab987",
"metadata": {},
"outputs": [],
"source": [
"def get_ddG0(rxn_dict,pH,I,novel_mets):\n",
" ccache = CompoundCacher()\n",
" # ddG0 = get_transform_ddG0(rxn_dict, ccache, pH, I, T)\n",
" T = 298.15\n",
" ddG0_forward = 0\n",
" for compound_id, coeff in rxn_dict.items():\n",
" if novel_mets != None and compound_id in novel_mets:\n",
" comp = novel_mets[compound_id]\n",
" else:\n",
" comp = ccache.get_compound(compound_id)\n",
" ddG0_forward += coeff * comp.transform_pH7(pH, I, T)\n",
"\n",
" return ddG0_forward"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "33cf30ff-8b2c-4da9-9134-75a60a5c5d66",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"-3.6254822995515497"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"get_ddG0(rxn_dic, 7.0, 0.1, {})"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "9e39855d-eb9e-4ea9-aeb9-8b770cc24c8e",
"metadata": {},
"outputs": [],
"source": [
"def get_rule(rxn_dict, molsig1, molsig2, novel_decomposed1, novel_decomposed2):\n",
" if novel_decomposed1 != None:\n",
" for cid in novel_decomposed1:\n",
" molsig1[cid] = novel_decomposed1[cid]\n",
" if novel_decomposed2 != None:\n",
" for cid in novel_decomposed2:\n",
" molsig2[cid] = novel_decomposed2[cid]\n",
"\n",
" molsigna_df1 = pd.DataFrame.from_dict(molsig1).fillna(0)\n",
" all_mets1 = molsigna_df1.columns.tolist()\n",
" all_mets1.append(\"C00080\")\n",
" all_mets1.append(\"C00282\")\n",
"\n",
" molsigna_df2 = pd.DataFrame.from_dict(molsig2).fillna(0)\n",
" all_mets2 = molsigna_df2.columns.tolist()\n",
" all_mets2.append(\"C00080\")\n",
" all_mets2.append(\"C00282\")\n",
"\n",
" moieties_r1 = open('./data/group_names_r1.txt')\n",
" moieties_r2 = open('./data/group_names_r2_py3_modified_manual.txt')\n",
" moie_r1 = moieties_r1.read().splitlines()\n",
" moie_r2 = moieties_r2.read().splitlines()\n",
"\n",
" molsigna_df1 = molsigna_df1.reindex(moie_r1)\n",
" molsigna_df2 = molsigna_df2.reindex(moie_r2)\n",
"\n",
" rule_df1 = pd.DataFrame(index=molsigna_df1.index)\n",
" rule_df2 = pd.DataFrame(index=molsigna_df2.index)\n",
" # for rid, value in reaction_dict.items():\n",
" # # skip the reactions with missing metabolites\n",
" # mets = value.keys()\n",
" # flag = False\n",
" # for met in mets:\n",
" # if met not in all_mets:\n",
" # flag = True\n",
" # break\n",
" # if flag: continue\n",
"\n",
" rule_df1['change'] = 0\n",
" for met, stoic in rxn_dict.items():\n",
" if met == \"C00080\" or met == \"C00282\":\n",
" continue # hydogen is zero\n",
" rule_df1['change'] += molsigna_df1[met] * stoic\n",
"\n",
" rule_df2['change'] = 0\n",
" for met, stoic in rxn_dict.items():\n",
" if met == \"C00080\" or met == \"C00282\":\n",
" continue # hydogen is zero\n",
" rule_df2['change'] += molsigna_df2[met] * stoic\n",
"\n",
" rule_vec1 = rule_df1.to_numpy().T\n",
" rule_vec2 = rule_df2.to_numpy().T\n",
"\n",
" m1, n1 = rule_vec1.shape\n",
" m2, n2 = rule_vec2.shape\n",
"\n",
" zeros1 = np.zeros((m1, 44))\n",
" zeros2 = np.zeros((m2, 44))\n",
" X1 = np.concatenate((rule_vec1, zeros1), 1)\n",
" X2 = np.concatenate((rule_vec2, zeros2), 1)\n",
"\n",
" rule_comb = np.concatenate((X1, X2), 1)\n",
"\n",
" # rule_df_final = {}\n",
" # rule_df_final['rad1'] = rule_df1\n",
" # rule_df_final['rad2'] = rule_df2\n",
" return rule_comb, rule_df1, rule_df2\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "a93ea75e-9851-45fd-aa58-d7f325b4b5a6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'C00222': -1,\n",
" 'C00010': -1,\n",
" 'C00006': -1,\n",
" 'C00024': 1,\n",
" 'C00011': 1,\n",
" 'C00005': 1}"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rxn_dic"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "981948dd-db2c-4463-b983-1220353d963e",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 23,
"id": "96eb1c38-2ca7-4e38-bcc4-ade1cef73852",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(array([-19.96775194]), array([6.66052556]))"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"loaded_model.predict(X, return_std= True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "81128dd3-5005-40a6-b5fe-8ecacef824bc",
"metadata": {},
"outputs": [],
"source": [
"def get_ddG0(rxn_dict,pH,I,novel_mets):\n",
" ccache = CompoundCacher()\n",
" # ddG0 = get_transform_ddG0(rxn_dict, ccache, pH, I, T)\n",
" T = 298.15\n",
" ddG0_forward = 0\n",
" for compound_id, coeff in rxn_dict.items():\n",
" if novel_mets != None and compound_id in novel_mets:\n",
" comp = novel_mets[compound_id]\n",
" else:\n",
" comp = ccache.get_compound(compound_id)\n",
" ddG0_forward += coeff * comp.transform_pH7(pH, I, T)\n",
"\n",
" return ddG0_forward\n",
"\n",
"\n",
"def get_dG0(rxn_dict,rid,pH,I,loaded_model,molsig_r1, molsig_r2, novel_decomposed_r1, novel_decomposed_r2,novel_mets):\n",
" rule_comb, rule_df1, rule_df2 = get_rule(rxn_dict,molsig_r1,molsig_r2, novel_decomposed_r1, novel_decomposed_r2)\n",
" X = rule_comb\n",
" ymean, ystd = loaded_model.predict(X, return_std=True)\n",
" result = {}\n",
" return ymean[0] + get_ddG0(rxn_dict, pH, I, novel_mets),ystd[0], rule_df1, rule_df2"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "751ec201-f062-4ac0-8d24-fe959636cbdc",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "c6cb1e4d-24be-42a1-b88b-793a62597c92",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "7abe24be-1653-455b-9931-9446480d39bb",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "f13433dc-51a3-41e5-8a0b-b0f21724ef98",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 2,
"id": "db7c764f-d216-44a9-8f88-0e3a7c51377a",
"metadata": {},
"outputs": [],
"source": [
"ccc= CompoundCacher()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "09e6f7f2-5be7-4db3-b55d-756ecb711095",
"metadata": {},
"outputs": [],
"source": [
"a = ccc.get_compound('C00001')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d28e44b7-d942-4739-9d7d-2f4e082ac1b9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"81.4472134155519"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a.transform_pH7(7, 0.25 , 298)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "1ef3fc0d-7d63-42ea-8743-522fe010a95d",
"metadata": {},
"outputs": [],
"source": [
"inchi_k = \"InChI=1S/C14H14O/c15-14-8-4-7-13(11-14)10-9-12-5-2-1-3-6-12/h1-8,11,15H,9-10H2\" ;"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "4e651d1c-2c96-42d1-adab-466dc7518146",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\vuu10\\AppData\\Local\\Continuum\\anaconda3\\envs\\dGPredictor_py3\\lib\\openbabel\\__init__.py:14: UserWarning: \"import openbabel\" is deprecated, instead use \"from openbabel import openbabel\"\n",
" warnings.warn('\"import openbabel\" is deprecated, instead use \"from openbabel import openbabel\"')\n"
]
}
],
"source": [
"c = Compound.from_inchi('Test', 'sajdf', inchi_k )"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "6eb5c2dc-f14c-46de-889b-0e9b7faa9f79",
"metadata": {},
"outputs": [
{
"ename": "AttributeError",
"evalue": "'Compound' object has no attribute 'smiles_ph7'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-18-7a0d06664090>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msmiles_ph7\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m: 'Compound' object has no attribute 'smiles_ph7'"
]
}
],
"source": [
"c.smiles_ph7()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "edd156dc-4355-4c2c-ba4e-6d98e776a96a",
"metadata": {},
"outputs": [],
"source": [
"from chemaxon import *\n",
"import chemaxon"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "880d2ef6-6b03-49d3-8f60-66769c22a84d",
"metadata": {},
"outputs": [],
"source": [
"pKas, major_ms_smiles = chemaxon.GetDissociationConstants(inchi_k)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "7a2391dc-313c-47f2-9f54-823bfdb95fcd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'OC1=CC=CC(CCC2=CC=CC=C2)=C1\\r'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"major_ms_smiles"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "96d90c4a-14a2-45fb-8573-97db84de2dff",
"metadata": {},
"outputs": [],
"source": [
"major_ms_smiles = Compound.smiles2smiles(major_ms_smiles)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "36d46620-b895-4ec8-85d0-7499759812c6",
"metadata": {},
"outputs": [],
"source": [
"MIN_PH = 0.0\n",
"MAX_PH = 14.0\n",
"pKas = sorted([pka for pka in pKas if pka > MIN_PH and pka < MAX_PH], reverse=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "ffccf9d9-5a52-4be6-af4c-f39b3db2a27c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[10.1]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pKas"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "e83721fa-9a42-42ef-9a03-59fc2689c73b",
"metadata": {},
"outputs": [],
"source": [
"atom_bag, major_ms_charge = chemaxon.GetAtomBagAndCharge(major_ms_smiles)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "47a87ed7-968d-44b6-a237-a8469ba3fe3b",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "49cfefde-ee96-4ca8-89af-c50f2f2ca70b",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "9b881c7b-a14a-4561-9c3c-157116efdfd0",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "10c8f915-e61a-4560-b546-fe6ea8bfdde3",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "936fafa5-1bf6-495c-be79-d4cc620f4861",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "285f9370-2fba-44c4-a36b-66c95f9f2eed",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "adbcd78f-869a-4cc9-b727-03c80df31edd",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "17fbfee9-c8b7-4644-814f-0e8aa0ad5ee9",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 21,
"id": "70f90669-ff90-4bc4-955c-63672e42bb3c",
"metadata": {},
"outputs": [],
"source": [
"formula, formal_charge = GetFormulaAndCharge(molstring)\n",
"\n",
"atom_bag = {}"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "e40e4088-c246-4afb-98ae-f92cb738e988",
"metadata": {},
"outputs": [],
"source": [
"for mol_formula_times in formula.split('.'):\n",
" for times, mol_formula in re.findall('^(\\d+)?(\\w+)', mol_formula_times):\n",
" if not times:\n",
" times = 1\n",
" else:\n",
" times = int(times)\n",
" for atom, count in re.findall(\"([A-Z][a-z]*)([0-9]*)\", mol_formula):\n",
" if count == '':\n",
" count = 1\n",
" else:\n",
" count = int(count)\n",
" atom_bag[atom] = atom_bag.get(atom, 0) + count * times"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "391cfbba-2da5-4b60-ba32-217754913b35",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'C': 14, 'H': 14, 'O': 1}"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"atom_bag"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "812f8297-a5cc-4d63-b132-243c278c6b76",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"6\n",
"1\n",
"8\n"
]
}
],
"source": [
"from rdkit.Chem import rdchem\n",
"for (elem, c) in atom_bag.items():\n",
" ll = rdchem.GetPeriodicTable()\n",
" atomic_num = ll.GetAtomicNumber(elem)\n",
" print(atomic_num)"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "463fcb01-2cd0-4aee-990c-946c534dc766",
"metadata": {},
"outputs": [],
"source": [
"\n",
"n_protons = sum([c * ll.GetAtomicNumber(str(elem))\n",
" for (elem, c) in atom_bag.items()])"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "ac1c69f6-54db-41ba-9fdf-e7ab6a2dfcbc",
"metadata": {},
"outputs": [],
"source": [
"atom_bag['e-'] = n_protons - formal_charge"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "61b1931e-dbaf-4e0f-afb2-6595f64d70d6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'C': 14, 'H': 14, 'O': 1, 'e-': 106}"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"atom_bag"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "12bdbf80-7dc5-4d47-a479-703ad5a6aa06",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"formal_charge\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b51f36c0-707a-4856-8c23-9081e2ea2cf7",
"metadata": {},
"outputs": [],
"source": [
"all_pKas, smiles_list = GetDissociationConstants_val(inchi_k)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "6dd79761-760d-4233-b113-a34e6322a0e5",
"metadata": {},
"outputs": [],
"source": [
"MID_PH = 7.0\n",
"N_PKAS = 20\n",
"\n",
"n_acidic = N_PKAS\n",
"n_basic = N_PKAS\n",
"pH = MID_PH"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "6167191a-b361-4ae0-a78a-927490c72f87",
"metadata": {},
"outputs": [],
"source": [
"args = []\n",
"if n_acidic + n_basic > 0:\n",
" args += ['pka', '-a', str(n_acidic), '-b', str(n_basic),\n",
" 'majorms', '-M', 'true', '--pH', str(pH)]\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "dd4275ec-c71e-4b5b-bb35-de8b3c7c4883",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['pka', '-a', '20', '-b', '20', 'majorms', '-M', 'true', '--pH', '7.0']"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"args"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "79d07dc5-963a-4373-9d72-1eb6de48ede9",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 16,
"id": "712a71fb-e3e3-4b01-828d-5a3862aa1b30",
"metadata": {},
"outputs": [],
"source": [
"logging.debug(\"INPUT: echo %s | %s\" % (inchi_k, ' '.join([CXCALC_BIN] + args)))"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "287bf822-23b8-42de-85ca-e52678875cfa",
"metadata": {},
"outputs": [],
"source": [
"molstring= inchi_k"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "4d2ff427-237c-4d63-a718-f29f12884d96",
"metadata": {},
"outputs": [],
"source": [
"p1 = Popen([\"echo\", molstring], stdout=PIPE, shell=use_shell_for_echo)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "923a09f2-b959-4837-ab1a-a858d91de0b4",
"metadata": {},
"outputs": [],
"source": [
"p2 = Popen([CXCALC_BIN] + args, stdin=p1.stdout,\n",
" executable=CXCALC_BIN, stdout=PIPE, shell=False)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "a6b30545-c65a-4c56-9985-71a103b9da00",
"metadata": {},
"outputs": [],
"source": [
"res = p2.communicate()[0]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "ac059602-027f-4a1a-932f-c1339c38c7d7",
"metadata": {},
"outputs": [],
"source": [
"if p2.returncode != 0:\n",
" raise ChemAxonError(str(args))\n",
"logging.debug(\"OUTPUT: %s\" % res)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "671642a5-3877-44e3-b935-f987fd601444",
"metadata": {},
"outputs": [],
"source": [
"output = res"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "a9f4bb4a-af86-4e97-bf1d-40c58013f90e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"b'id\\tapKa1\\tapKa2\\tapKa3\\tapKa4\\tapKa5\\tapKa6\\tapKa7\\tapKa8\\tapKa9\\tapKa10\\tapKa11\\tapKa12\\tapKa13\\tapKa14\\tapKa15\\tapKa16\\tapKa17\\tapKa18\\tapKa19\\tapKa20\\tbpKa1\\tbpKa2\\tbpKa3\\tbpKa4\\tbpKa5\\tbpKa6\\tbpKa7\\tbpKa8\\tbpKa9\\tbpKa10\\tbpKa11\\tbpKa12\\tbpKa13\\tbpKa14\\tbpKa15\\tbpKa16\\tbpKa17\\tbpKa18\\tbpKa19\\tbpKa20\\tatoms\\tmajor-ms\\r\\n1\\t10.10\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t-5.48\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t\\t15,15\\tOC1=CC=CC(CCC2=CC=CC=C2)=C1\\r\\n'"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"output"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "215ffc9b-35a8-4f45-8f39-9c99deae6335",
"metadata": {},
"outputs": [],
"source": [
"atom2pKa, smiles_list = ParsePkaOutput(output, n_acidic, n_basic)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "21c380d3-5410-4c55-b6d7-cb0588f373ca",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['OC1=CC=CC(CCC2=CC=CC=C2)=C1\\r']"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"smiles_list"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "1437693a-0923-4df1-837d-acb2b524fcae",
"metadata": {},
"outputs": [],
"source": [
"all_pKas = []\n",
"for pKa_list in list(atom2pKa.values()):\n",
" all_pKas += [pKa for pKa, _ in pKa_list]"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "8e77324c-ed61-4615-a7c7-4f5ca781dc90",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[10.1, -5.48]"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"all_pKas"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8616be46-1814-4755-b919-4b7790569890",
"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": "3.8.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}