{"cells":[{"metadata":{},"cell_type":"markdown","source":"In this kernel, I will explain how to visualize molecules using [RDKit](https://www.rdkit.org/docs/GettingStartedInPython.html) library.\n\nIt provides many kinds of data preprocessing used in chemistry."},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":1,"outputs":[{"output_type":"stream","text":"['test.csv', 'mulliken_charges.csv', 'dipole_moments.csv', 'train.csv', 'structures.csv', 'magnetic_shielding_tensors.csv', 'potential_energy.csv', 'sample_submission.csv', 'scalar_coupling_contributions.csv', 'structures']\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"## Install rdkit\n\n`rdkit` library is not installed in default kaggle kernel.\nBut it can be installed via conda, so let's install it at first."},{"metadata":{"trusted":true},"cell_type":"code","source":"!conda --version","execution_count":2,"outputs":[{"output_type":"stream","text":"conda 4.6.14\r\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"!conda install -y -c rdkit rdkit","execution_count":3,"outputs":[{"output_type":"stream","text":"Collecting package metadata: done\nSolving environment: done\n\n## Package Plan ##\n\n environment location: /opt/conda\n\n added / updated specs:\n - rdkit\n\n\nThe following packages will be downloaded:\n\n package | build\n ---------------------------|-----------------\n ca-certificates-2019.5.15 | 0 133 KB\n openssl-1.0.2s | h7b6447c_0 3.1 MB\n rdkit-2018.09.1.0 | py36h71b666b_1 20.2 MB rdkit\n ------------------------------------------------------------\n Total: 23.5 MB\n\nThe following NEW packages will be INSTALLED:\n\n rdkit rdkit/linux-64::rdkit-2018.09.1.0-py36h71b666b_1\n\nThe following packages will be UPDATED:\n\n ca-certificates 2019.1.23-0 --> 2019.5.15-0\n openssl 1.0.2r-h7b6447c_0 --> 1.0.2s-h7b6447c_0\n\n\n\nDownloading and Extracting Packages\nopenssl-1.0.2s | 3.1 MB | ##################################### | 100% \nrdkit-2018.09.1.0 | 20.2 MB | ##################################### | 100% \nca-certificates-2019 | 133 KB | ##################################### | 100% \nPreparing transaction: done\nVerifying transaction: done\nExecuting transaction: done\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"import rdkit\n\nprint('rdkit version', rdkit.__version__)","execution_count":4,"outputs":[{"output_type":"stream","text":"rdkit version 2018.09.1\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"Installed successfully!"},{"metadata":{},"cell_type":"markdown","source":"## rdkit explanation: visualize via mol instance\n\nWe can visualize molecules via rdkit `Mol` instalce "},{"metadata":{"trusted":true},"cell_type":"code","source":"import rdkit\nfrom rdkit import Chem\n\nfrom rdkit.Chem.Draw import IPythonConsole","execution_count":5,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Below code is referenced from the repository [chainer-chemistry](https://github.com/pfnet-research/chainer-chemistry), [tox21_dataset_exploration notebook](https://github.com/pfnet-research/chainer-chemistry/blob/master/examples/tox21/tox21_dataset_exploration.ipynb)."},{"metadata":{"trusted":true},"cell_type":"code","source":"# This script is referred from http://rdkit.blogspot.jp/2015/02/new-drawing-code.html\n# and http://cheminformist.itmol.com/TEST/wp-content/uploads/2015/07/rdkit_moldraw2d_2.html\nfrom __future__ import print_function\nfrom rdkit import Chem\nfrom rdkit.Chem.Draw import IPythonConsole\nfrom IPython.display import SVG\n\nfrom rdkit.Chem import rdDepictor\nfrom rdkit.Chem.Draw import rdMolDraw2D\ndef moltosvg(mol,molSize=(450,150),kekulize=True):\n mc = Chem.Mol(mol.ToBinary())\n if kekulize:\n try:\n Chem.Kekulize(mc)\n except:\n mc = Chem.Mol(mol.ToBinary())\n if not mc.GetNumConformers():\n rdDepictor.Compute2DCoords(mc)\n drawer = rdMolDraw2D.MolDraw2DSVG(molSize[0],molSize[1])\n drawer.DrawMolecule(mc)\n drawer.FinishDrawing()\n svg = drawer.GetDrawingText()\n return svg\n\ndef render_svg(svg):\n # It seems that the svg renderer used doesn't quite hit the spec.\n # Here are some fixes to make it work in the notebook, although I think\n # the underlying issue needs to be resolved at the generation step\n return SVG(svg.replace('svg:',''))\n","execution_count":6,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"markdown","source":"For example, let's visualize CO2. Molecules can be represented by [SMILES](https://en.wikipedia.org/wiki/Simplified_molecular-input_line-entry_system) string notation."},{"metadata":{"trusted":true},"cell_type":"code","source":"smiles = 'O'\n\nmol = Chem.MolFromSmiles(smiles)\n\nprint('smiles:', smiles)\nrender_svg(moltosvg(mol))","execution_count":9,"outputs":[{"output_type":"stream","text":"smiles: O\n","name":"stdout"},{"output_type":"execute_result","execution_count":9,"data":{"text/plain":"","image/svg+xml":"\n \nH2O\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## visualize from xyz file\n\nNow, we know how to visualize molecule from RDKit `Mol` instance, but how to create mol instance of kaggle data?\n\nI found a nice repository, [xyz2mol](https://github.com/jensengroup/xyz2mol) by jensengroup, which provides a code to convert xyz file to RDKit mol instance under MIT license."},{"metadata":{"trusted":true},"cell_type":"code","source":"\"\"\"\nCopied from\nhttps://github.com/jensengroup/xyz2mol/blob/master/xyz2mol.py\n\"\"\"\n##\n# Written by Jan H. Jensen based on this paper Yeonjoon Kim and Woo Youn Kim\n# \"Universal Structure Conversion Method for Organic Molecules: From Atomic Connectivity\n# to Three-Dimensional Geometry\" Bull. Korean Chem. Soc. 2015, Vol. 36, 1769-1777 DOI: 10.1002/bkcs.10334\n#\nfrom rdkit import Chem\nfrom rdkit.Chem import AllChem\nimport itertools\nfrom rdkit.Chem import rdmolops\nfrom collections import defaultdict\nimport copy\nimport networkx as nx # uncomment if you don't want to use \"quick\"/install networkx\n\nglobal __ATOM_LIST__\n__ATOM_LIST__ = [x.strip() for x in ['h ', 'he', \\\n 'li', 'be', 'b ', 'c ', 'n ', 'o ', 'f ', 'ne', \\\n 'na', 'mg', 'al', 'si', 'p ', 's ', 'cl', 'ar', \\\n 'k ', 'ca', 'sc', 'ti', 'v ', 'cr', 'mn', 'fe', 'co', 'ni', 'cu', \\\n 'zn', 'ga', 'ge', 'as', 'se', 'br', 'kr', \\\n 'rb', 'sr', 'y ', 'zr', 'nb', 'mo', 'tc', 'ru', 'rh', 'pd', 'ag', \\\n 'cd', 'in', 'sn', 'sb', 'te', 'i ', 'xe', \\\n 'cs', 'ba', 'la', 'ce', 'pr', 'nd', 'pm', 'sm', 'eu', 'gd', 'tb', 'dy', \\\n 'ho', 'er', 'tm', 'yb', 'lu', 'hf', 'ta', 'w ', 're', 'os', 'ir', 'pt', \\\n 'au', 'hg', 'tl', 'pb', 'bi', 'po', 'at', 'rn', \\\n 'fr', 'ra', 'ac', 'th', 'pa', 'u ', 'np', 'pu']]\n\n\ndef get_atom(atom):\n global __ATOM_LIST__\n atom = atom.lower()\n return __ATOM_LIST__.index(atom) + 1\n\n\ndef getUA(maxValence_list, valence_list):\n UA = []\n DU = []\n for i, (maxValence, valence) in enumerate(zip(maxValence_list, valence_list)):\n if maxValence - valence > 0:\n UA.append(i)\n DU.append(maxValence - valence)\n return UA, DU\n\n\ndef get_BO(AC, UA, DU, valences, UA_pairs, quick):\n BO = AC.copy()\n DU_save = []\n\n while DU_save != DU:\n for i, j in UA_pairs:\n BO[i, j] += 1\n BO[j, i] += 1\n\n BO_valence = list(BO.sum(axis=1))\n DU_save = copy.copy(DU)\n UA, DU = getUA(valences, BO_valence)\n UA_pairs = get_UA_pairs(UA, AC, quick)[0]\n\n return BO\n\n\ndef valences_not_too_large(BO, valences):\n number_of_bonds_list = BO.sum(axis=1)\n for valence, number_of_bonds in zip(valences, number_of_bonds_list):\n if number_of_bonds > valence:\n return False\n\n return True\n\n\ndef BO_is_OK(BO, AC, charge, DU, atomic_valence_electrons, atomicNumList, charged_fragments):\n Q = 0 # total charge\n q_list = []\n if charged_fragments:\n BO_valences = list(BO.sum(axis=1))\n for i, atom in enumerate(atomicNumList):\n q = get_atomic_charge(atom, atomic_valence_electrons[atom], BO_valences[i])\n Q += q\n if atom == 6:\n number_of_single_bonds_to_C = list(BO[i, :]).count(1)\n if number_of_single_bonds_to_C == 2 and BO_valences[i] == 2:\n Q += 1\n q = 2\n if number_of_single_bonds_to_C == 3 and Q + 1 < charge:\n Q += 2\n q = 1\n\n if q != 0:\n q_list.append(q)\n\n if (BO - AC).sum() == sum(DU) and charge == Q and len(q_list) <= abs(charge):\n return True\n else:\n return False\n\n\ndef get_atomic_charge(atom, atomic_valence_electrons, BO_valence):\n if atom == 1:\n charge = 1 - BO_valence\n elif atom == 5:\n charge = 3 - BO_valence\n elif atom == 15 and BO_valence == 5:\n charge = 0\n elif atom == 16 and BO_valence == 6:\n charge = 0\n else:\n charge = atomic_valence_electrons - 8 + BO_valence\n\n return charge\n\n\ndef clean_charges(mol):\n # this hack should not be needed any more but is kept just in case\n #\n\n rxn_smarts = ['[N+:1]=[*:2]-[C-:3]>>[N+0:1]-[*:2]=[C-0:3]',\n '[N+:1]=[*:2]-[O-:3]>>[N+0:1]-[*:2]=[O-0:3]',\n '[N+:1]=[*:2]-[*:3]=[*:4]-[O-:5]>>[N+0:1]-[*:2]=[*:3]-[*:4]=[O-0:5]',\n '[#8:1]=[#6:2]([!-:6])[*:3]=[*:4][#6-:5]>>[*-:1][*:2]([*:6])=[*:3][*:4]=[*+0:5]',\n '[O:1]=[c:2][c-:3]>>[*-:1][*:2][*+0:3]',\n '[O:1]=[C:2][C-:3]>>[*-:1][*:2]=[*+0:3]']\n\n fragments = Chem.GetMolFrags(mol, asMols=True, sanitizeFrags=False)\n\n for i, fragment in enumerate(fragments):\n for smarts in rxn_smarts:\n patt = Chem.MolFromSmarts(smarts.split(\">>\")[0])\n while fragment.HasSubstructMatch(patt):\n rxn = AllChem.ReactionFromSmarts(smarts)\n ps = rxn.RunReactants((fragment,))\n fragment = ps[0][0]\n if i == 0:\n mol = fragment\n else:\n mol = Chem.CombineMols(mol, fragment)\n\n return mol\n\n\ndef BO2mol(mol, BO_matrix, atomicNumList, atomic_valence_electrons, mol_charge, charged_fragments):\n # based on code written by Paolo Toscani\n\n l = len(BO_matrix)\n l2 = len(atomicNumList)\n BO_valences = list(BO_matrix.sum(axis=1))\n\n if (l != l2):\n raise RuntimeError('sizes of adjMat ({0:d}) and atomicNumList '\n '{1:d} differ'.format(l, l2))\n\n rwMol = Chem.RWMol(mol)\n\n bondTypeDict = {\n 1: Chem.BondType.SINGLE,\n 2: Chem.BondType.DOUBLE,\n 3: Chem.BondType.TRIPLE\n }\n\n for i in range(l):\n for j in range(i + 1, l):\n bo = int(round(BO_matrix[i, j]))\n if (bo == 0):\n continue\n bt = bondTypeDict.get(bo, Chem.BondType.SINGLE)\n rwMol.AddBond(i, j, bt)\n mol = rwMol.GetMol()\n\n if charged_fragments:\n mol = set_atomic_charges(mol, atomicNumList, atomic_valence_electrons, BO_valences, BO_matrix, mol_charge)\n else:\n mol = set_atomic_radicals(mol, atomicNumList, atomic_valence_electrons, BO_valences)\n\n return mol\n\n\ndef set_atomic_charges(mol, atomicNumList, atomic_valence_electrons, BO_valences, BO_matrix, mol_charge):\n q = 0\n for i, atom in enumerate(atomicNumList):\n a = mol.GetAtomWithIdx(i)\n charge = get_atomic_charge(atom, atomic_valence_electrons[atom], BO_valences[i])\n q += charge\n if atom == 6:\n number_of_single_bonds_to_C = list(BO_matrix[i, :]).count(1)\n if number_of_single_bonds_to_C == 2 and BO_valences[i] == 2:\n q += 1\n charge = 0\n if number_of_single_bonds_to_C == 3 and q + 1 < mol_charge:\n q += 2\n charge = 1\n\n if (abs(charge) > 0):\n a.SetFormalCharge(int(charge))\n\n # shouldn't be needed anymore bit is kept just in case\n # mol = clean_charges(mol)\n\n return mol\n\n\ndef set_atomic_radicals(mol, atomicNumList, atomic_valence_electrons, BO_valences):\n # The number of radical electrons = absolute atomic charge\n for i, atom in enumerate(atomicNumList):\n a = mol.GetAtomWithIdx(i)\n charge = get_atomic_charge(atom, atomic_valence_electrons[atom], BO_valences[i])\n\n if (abs(charge) > 0):\n a.SetNumRadicalElectrons(abs(int(charge)))\n\n return mol\n\n\ndef get_bonds(UA, AC):\n bonds = []\n\n for k, i in enumerate(UA):\n for j in UA[k + 1:]:\n if AC[i, j] == 1:\n bonds.append(tuple(sorted([i, j])))\n\n return bonds\n\n\ndef get_UA_pairs(UA, AC, quick):\n bonds = get_bonds(UA, AC)\n if len(bonds) == 0:\n return [()]\n\n if quick:\n G = nx.Graph()\n G.add_edges_from(bonds)\n UA_pairs = [list(nx.max_weight_matching(G))]\n return UA_pairs\n\n max_atoms_in_combo = 0\n UA_pairs = [()]\n for combo in list(itertools.combinations(bonds, int(len(UA) / 2))):\n flat_list = [item for sublist in combo for item in sublist]\n atoms_in_combo = len(set(flat_list))\n if atoms_in_combo > max_atoms_in_combo:\n max_atoms_in_combo = atoms_in_combo\n UA_pairs = [combo]\n # if quick and max_atoms_in_combo == 2*int(len(UA)/2):\n # return UA_pairs\n elif atoms_in_combo == max_atoms_in_combo:\n UA_pairs.append(combo)\n\n return UA_pairs\n\n\ndef AC2BO(AC, atomicNumList, charge, charged_fragments, quick):\n # TODO\n atomic_valence = defaultdict(list)\n atomic_valence[1] = [1]\n atomic_valence[6] = [4]\n atomic_valence[7] = [4, 3]\n atomic_valence[8] = [2, 1]\n atomic_valence[9] = [1]\n atomic_valence[14] = [4]\n atomic_valence[15] = [5, 4, 3]\n atomic_valence[16] = [6, 4, 2]\n atomic_valence[17] = [1]\n atomic_valence[32] = [4]\n atomic_valence[35] = [1]\n atomic_valence[53] = [1]\n\n atomic_valence_electrons = {}\n atomic_valence_electrons[1] = 1\n atomic_valence_electrons[6] = 4\n atomic_valence_electrons[7] = 5\n atomic_valence_electrons[8] = 6\n atomic_valence_electrons[9] = 7\n atomic_valence_electrons[14] = 4\n atomic_valence_electrons[15] = 5\n atomic_valence_electrons[16] = 6\n atomic_valence_electrons[17] = 7\n atomic_valence_electrons[32] = 4\n atomic_valence_electrons[35] = 7\n atomic_valence_electrons[53] = 7\n\n # make a list of valences, e.g. for CO: [[4],[2,1]]\n valences_list_of_lists = []\n for atomicNum in atomicNumList:\n valences_list_of_lists.append(atomic_valence[atomicNum])\n\n # convert [[4],[2,1]] to [[4,2],[4,1]]\n valences_list = list(itertools.product(*valences_list_of_lists))\n\n best_BO = AC.copy()\n\n # implemenation of algorithm shown in Figure 2\n # UA: unsaturated atoms\n # DU: degree of unsaturation (u matrix in Figure)\n # best_BO: Bcurr in Figure\n #\n\n for valences in valences_list:\n AC_valence = list(AC.sum(axis=1))\n UA, DU_from_AC = getUA(valences, AC_valence)\n\n if len(UA) == 0 and BO_is_OK(AC, AC, charge, DU_from_AC, atomic_valence_electrons, atomicNumList,\n charged_fragments):\n return AC, atomic_valence_electrons\n\n UA_pairs_list = get_UA_pairs(UA, AC, quick)\n for UA_pairs in UA_pairs_list:\n BO = get_BO(AC, UA, DU_from_AC, valences, UA_pairs, quick)\n if BO_is_OK(BO, AC, charge, DU_from_AC, atomic_valence_electrons, atomicNumList, charged_fragments):\n return BO, atomic_valence_electrons\n\n elif BO.sum() >= best_BO.sum() and valences_not_too_large(BO, valences):\n best_BO = BO.copy()\n\n return best_BO, atomic_valence_electrons\n\n\ndef AC2mol(mol, AC, atomicNumList, charge, charged_fragments, quick):\n # convert AC matrix to bond order (BO) matrix\n BO, atomic_valence_electrons = AC2BO(AC, atomicNumList, charge, charged_fragments, quick)\n\n # add BO connectivity and charge info to mol object\n mol = BO2mol(mol, BO, atomicNumList, atomic_valence_electrons, charge, charged_fragments)\n\n return mol\n\n\ndef get_proto_mol(atomicNumList):\n mol = Chem.MolFromSmarts(\"[#\" + str(atomicNumList[0]) + \"]\")\n rwMol = Chem.RWMol(mol)\n for i in range(1, len(atomicNumList)):\n a = Chem.Atom(atomicNumList[i])\n rwMol.AddAtom(a)\n\n mol = rwMol.GetMol()\n\n return mol\n\n\ndef get_atomicNumList(atomic_symbols):\n atomicNumList = []\n for symbol in atomic_symbols:\n atomicNumList.append(get_atom(symbol))\n return atomicNumList\n\n\ndef read_xyz_file(filename):\n atomic_symbols = []\n xyz_coordinates = []\n\n with open(filename, \"r\") as file:\n for line_number, line in enumerate(file):\n if line_number == 0:\n num_atoms = int(line)\n elif line_number == 1:\n if \"charge=\" in line:\n charge = int(line.split(\"=\")[1])\n else:\n charge = 0\n else:\n atomic_symbol, x, y, z = line.split()\n atomic_symbols.append(atomic_symbol)\n xyz_coordinates.append([float(x), float(y), float(z)])\n\n atomicNumList = get_atomicNumList(atomic_symbols)\n\n return atomicNumList, charge, xyz_coordinates\n\n\ndef xyz2AC(atomicNumList, xyz):\n import numpy as np\n mol = get_proto_mol(atomicNumList)\n\n conf = Chem.Conformer(mol.GetNumAtoms())\n for i in range(mol.GetNumAtoms()):\n conf.SetAtomPosition(i, (xyz[i][0], xyz[i][1], xyz[i][2]))\n mol.AddConformer(conf)\n\n dMat = Chem.Get3DDistanceMatrix(mol)\n pt = Chem.GetPeriodicTable()\n\n num_atoms = len(atomicNumList)\n AC = np.zeros((num_atoms, num_atoms)).astype(int)\n\n for i in range(num_atoms):\n a_i = mol.GetAtomWithIdx(i)\n Rcov_i = pt.GetRcovalent(a_i.GetAtomicNum()) * 1.30\n for j in range(i + 1, num_atoms):\n a_j = mol.GetAtomWithIdx(j)\n Rcov_j = pt.GetRcovalent(a_j.GetAtomicNum()) * 1.30\n if dMat[i, j] <= Rcov_i + Rcov_j:\n AC[i, j] = 1\n AC[j, i] = 1\n\n return AC, mol\n\n\ndef chiral_stereo_check(mol):\n Chem.SanitizeMol(mol)\n Chem.DetectBondStereochemistry(mol, -1)\n Chem.AssignStereochemistry(mol, flagPossibleStereoCenters=True, force=True)\n Chem.AssignAtomChiralTagsFromStructure(mol, -1)\n\n return mol\n\n\ndef xyz2mol(atomicNumList, charge, xyz_coordinates, charged_fragments, quick):\n # Get atom connectivity (AC) matrix, list of atomic numbers, molecular charge,\n # and mol object with no connectivity information\n AC, mol = xyz2AC(atomicNumList, xyz_coordinates)\n\n # Convert AC to bond order matrix and add connectivity and charge info to mol object\n new_mol = AC2mol(mol, AC, atomicNumList, charge, charged_fragments, quick)\n\n # Check for stereocenters and chiral centers\n new_mol = chiral_stereo_check(new_mol)\n\n return new_mol\n\n\n# if __name__ == \"__main__\":\n\n# import argparse\n\n# parser = argparse.ArgumentParser(usage='%(prog)s [options] molecule.xyz')\n# parser.add_argument('structure', metavar='structure', type=str)\n# parser.add_argument('-s', '--sdf', action=\"store_true\", help=\"Dump sdf file\")\n# args = parser.parse_args()\n\n# filename = args.structure\n# charged_fragments = True # alternatively radicals are made\n\n# # quick is faster for large systems but requires networkx\n# # if you don't want to install networkx set quick=False and\n# # uncomment 'import networkx as nx' at the top of the file\n# quick = True\n\n# atomicNumList, charge, xyz_coordinates = read_xyz_file(filename)\n\n# mol = xyz2mol(atomicNumList, charge, xyz_coordinates, charged_fragments, quick)\n\n# if args.sdf:\n# filename = filename.replace(\".xyz\", \"\")\n# filename += \".sdf\"\n# writer = Chem.SDWriter(filename)\n# writer.write(mol)\n\n# # Canonical hack\n# smiles = Chem.MolToSmiles(mol, isomericSmiles=True)\n# m = Chem.MolFromSmiles(smiles)\n# smiles = Chem.MolToSmiles(m, isomericSmiles=True)\n\n# print(smiles)","execution_count":10,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def mol_from_xyz(filepath):\n charged_fragments = True # alternatively radicals are made\n\n # quick is faster for large systems but requires networkx\n # if you don't want to install networkx set quick=False and\n # uncomment 'import networkx as nx' at the top of the file\n quick = True\n\n atomicNumList, charge, xyz_coordinates = read_xyz_file(filepath)\n mol = xyz2mol(atomicNumList, charge, xyz_coordinates, charged_fragments, quick)\n\n # Canonical hack\n smiles = Chem.MolToSmiles(mol, isomericSmiles=True)\n m = Chem.MolFromSmiles(smiles)\n return m","execution_count":27,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from glob import glob\nxyz_filepath_list = list(glob('../input/structures/*.xyz'))\n\nxyz_filepath_list.sort()\nprint('total xyz filepath # ', len(xyz_filepath_list))","execution_count":28,"outputs":[{"output_type":"stream","text":"total xyz filepath # 130775\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Visualize i-th molecules.\nfor i in range(10):\n filepath = xyz_filepath_list[i]\n mol = mol_from_xyz(filepath)\n smiles = Chem.MolToSmiles(mol, isomericSmiles=True)\n print(f'{i}-th file {filepath}: SMILES {smiles}')\n display(render_svg(moltosvg(mol)))\n\n ","execution_count":30,"outputs":[{"output_type":"stream","text":"0-th file ../input/structures/dsgdb9nsd_000001.xyz: SMILES C\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \nCH4\n"},"metadata":{}},{"output_type":"stream","text":"1-th file ../input/structures/dsgdb9nsd_000002.xyz: SMILES N\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \nNH3\n"},"metadata":{}},{"output_type":"stream","text":"2-th file ../input/structures/dsgdb9nsd_000003.xyz: SMILES O\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \nH2O\n"},"metadata":{}},{"output_type":"stream","text":"3-th file ../input/structures/dsgdb9nsd_000004.xyz: SMILES C#C\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \n\n\n\n"},"metadata":{}},{"output_type":"stream","text":"4-th file ../input/structures/dsgdb9nsd_000005.xyz: SMILES C#N\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \n\n\n\n\n\n\nN\n"},"metadata":{}},{"output_type":"stream","text":"5-th file ../input/structures/dsgdb9nsd_000007.xyz: SMILES CC\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \n\n"},"metadata":{}},{"output_type":"stream","text":"6-th file ../input/structures/dsgdb9nsd_000008.xyz: SMILES CO\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \n\n\nOH\n"},"metadata":{}},{"output_type":"stream","text":"7-th file ../input/structures/dsgdb9nsd_000009.xyz: SMILES C#CC\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \n\n\n\n\n"},"metadata":{}},{"output_type":"stream","text":"8-th file ../input/structures/dsgdb9nsd_000010.xyz: SMILES CC#N\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \n\n\n\n\n\n\n\nN\n"},"metadata":{}},{"output_type":"stream","text":"9-th file ../input/structures/dsgdb9nsd_000011.xyz: SMILES CC=O\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"","image/svg+xml":"\n \n\n\n\n\n\nO\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_mols = 100\n\nmol_list = []\nfor i in range(num_mols):\n filepath = xyz_filepath_list[i]\n mol = mol_from_xyz(filepath)\n if mol is None:\n print(f'{i}-th file {filepath} failed, skip')\n mol_list.append(mol)","execution_count":48,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from rdkit.Chem import Draw\nimg = Draw.MolsToGridImage(mol_list, molsPerRow=5, subImgSize=(250, 250), maxMols=num_mols,\n legends=None, useSVG=True)","execution_count":49,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img","execution_count":50,"outputs":[{"output_type":"execute_result","execution_count":50,"data":{"text/plain":"","image/svg+xml":"\n \nCH4\nNH3\nH2O\n\n\n\n\n\n\n\n\n\nN\n\n\n\nOH\n\n\n\n\n\n\n\n\n\n\n\nN\n\n\n\n\n\nO\n\n\n\n\n\n\nO\nNH2\n\n\n\n\n\nOH\n\n\n\n\nO\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\nNH2\nO\n\n\n\n\n\n\n\n\nNH2\nO\nH2N\n\n\n\n\n\n\n\nOH\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nN\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\n\n\n\nO\nN\n\n\n\n\n\n\n\n\n\nO\nO\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nN\n\n\n\n\n\n\n\n\n\nH2N\nN\n\n\n\n\n\n\nHO\n\n\n\n\n\n\n\n\n\nHO\nN\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\nO\nNH\n\n\n\n\n\n\n\n\nO\nO\n\n\n\n\n\n\n\nOH\nO\n\n\n\n\n\n\n\nOH\n\n\n\n\n\nO\n\n\n\n\n\nOH\nHO\n\n\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\nN\n\n\n\n\n\nOH\n\n\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\nOH\nN\n\n\n\n\n\n\n\n\n\nNH\n\n\n\n\n\n\n\n\n\n\n\n\nN\nNH\n\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\n\n\n\n\nN\nO\n\n\n\n\n\n\n\n\n\nOH\n\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\n\n\n\n\nO\nN\n\n\n\n\n\n\n\n\n\n\nO\nNH2\n\n\n\n\n\n\n\n\n\n\nO\nO\n\n\n\n\n\n\n\n\n\n\n\nO\nO\nNH2\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nN\n\n\n\n\n\n\n\n\n\n\nNH2\nN\n\n\n\n\n\n\n\nOH\n\n\n\n\n\n\n\n\n\n\nOH\nN\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\nOH\nO\n\n\n\n\n\n\n\n\n\n\nO\nN\n\n\n\n\n\n\n\n\nOH\nO\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\nNH2\nO\n\n\n\n\n\n\n\n\n\nNH\nO\n\n\n\n\n\n\n\n\n\n\nNH2\nO\nNH\n\n\n\n\n\n\n\n\n\n\n\nH\nN\nO\n\n\n\n\n\n\n\n\n\nO\nO\n\n\n\n\n\n\n\n\n\n\nNH2\nO\nO\n\n\n\n\n\n\n\n\n\nHO\nO\nNH2\n\n\n\n\n\nOH\n\n\n\n\n\n\nOH\nOH\n\n\n\n\n\n\n\n\n\nOH\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\nOH\n\n\n\n\n\n\n\n\n\n\n\n\nH\nN\nO\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\n\n\nNH\nO\n\n\n\n\n\n\n\n\n\n\nO\nO\n\n\n\n\n\n\n\n\n\n\nNH\nO\n\n\n\n\n\n\n\n\n\n\nO\nO\n\n\n\n\n\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\nOH\n\n\n\n\n\n\n\n\nOH\nO\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nOH\n\n\n\n\n\n\n\n\nN\n\n\n\n\n\n\n\nO\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nOH\nHO\n\n\n\n\n\n\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}