molSimplify 1.8.0__tar.gz → 2.0.0__tar.gz

{molsimplify-1.8.0 → molsimplify-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: molSimplify
-Version: 1.8.0
+Version: 2.0.0
 License:                     GNU GENERAL PUBLIC LICENSE
                                Version 3, 29 June 2007
         
@@ -691,6 +691,9 @@ Requires-Dist: keras
 Requires-Dist: tensorflow
 Requires-Dist: pyyaml
 Requires-Dist: importlib-resources
+Requires-Dist: matplotlib
+Requires-Dist: pydentate
+Requires-Dist: setuptools
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-resource-path; extra == "dev"
@@ -825,6 +828,17 @@ url = {https://doi.org/10.1021/acs.iecr.8b04015},
 doi = {10.1021/acs.iecr.8b04015},
 year = {2018},
 }
+
+@Article{molSimplify2.0,
+author = {Terrones, Gianmarco G. and St. Michel, Roland G. and Toney, Jacob W. and Ball, Akash K. and Wang, Yiran and Garrison, Aaron G. and Nandy, Aditya and Meyer, Ralf and Edholm, Freya and Oh, Changhwan and Pujet, Sebastian G. and Chu, Daniel B. K. and Muhammetgulyyev, Davut and Kulik, Heather J.},
+title = {molSimplify 2.0: Improved Structure Generation for Automating Discovery in Inorganic Molecular and Reticular Chemistry},
+volume = {66},
+number = {5},
+pages = {2753-2767},
+url = {https://doi.org/10.1021/acs.jcim.5c02733},
+doi = {10.1021/acs.jcim.5c02733},
+year = {2026},
+}
 ```
 
 If you use any machine learning (ML) models in molSimplify, please cite the corresponding reference in [this ML model reference page](https://github.com/hjkgrp/molSimplify/blob/master/MLmodel-reference.md).

{molsimplify-1.8.0 → molsimplify-2.0.0}/README.md

@@ -121,6 +121,17 @@ url = {https://doi.org/10.1021/acs.iecr.8b04015},
 doi = {10.1021/acs.iecr.8b04015},
 year = {2018},
 }
+
+@Article{molSimplify2.0,
+author = {Terrones, Gianmarco G. and St. Michel, Roland G. and Toney, Jacob W. and Ball, Akash K. and Wang, Yiran and Garrison, Aaron G. and Nandy, Aditya and Meyer, Ralf and Edholm, Freya and Oh, Changhwan and Pujet, Sebastian G. and Chu, Daniel B. K. and Muhammetgulyyev, Davut and Kulik, Heather J.},
+title = {molSimplify 2.0: Improved Structure Generation for Automating Discovery in Inorganic Molecular and Reticular Chemistry},
+volume = {66},
+number = {5},
+pages = {2753-2767},
+url = {https://doi.org/10.1021/acs.jcim.5c02733},
+doi = {10.1021/acs.jcim.5c02733},
+year = {2026},
+}
 ```
 
 If you use any machine learning (ML) models in molSimplify, please cite the corresponding reference in [this ML model reference page](https://github.com/hjkgrp/molSimplify/blob/master/MLmodel-reference.md).

{molsimplify-1.8.0 → molsimplify-2.0.0}/molSimplify/Classes/globalvars.py

@@ -403,7 +403,7 @@ bondsdict = {"H": 1, "Li": 1, "Be": 2, "B": 3, "C": 4, "N": 3, "O": 2, "F": 1,
              "Na": 1, "Mg": 2, "Al": 3, "Si": 4, "P": 3, "S": 2, "Cl": 1,
              "As": 3, "Se": 2, "Br": 1, "I": 1, "He": 2}
 
-# triple bonds dictionry: Defined as 0.5*(double bond dist + triple bond dist)
+# triple bonds dictionary: Defined as 0.5*(double bond dist + triple bond dist)
 # bond lengths are from http://www.wiredchemist.com/chemistry/data/bond_energies_lengths.html
 tribonddict = {("C", "C"): 1.27, ("C", "N"): 1.235, ("C", "O"): 1.165, ("N", "N"): 1.175,
                ("N", "C"): 1.235, ("O", "C"): 1.165}
@@ -628,31 +628,31 @@ class globalvars(metaclass=Singleton):
     def __init__(self):
         # Program name
         self.PROGRAM = 'molSimplify'
-        program_info = [
-        f'\nmolSimplify v{get_version()}',
-        'Freely distributed under the GNU GPL license.',
-        'Copyright 2017 Kulik Lab @ MIT',
-        'Developed by: Efthymios Ioannidis',
-        'Contributions by:',
-        '\tHeather J. Kulik (corresponding developer; hjkulik@mit.edu)',
-        '\tNaveen Arunachalam',
-        '\tChenru Duan',
-        '\tFreya Edholm',
-        '\tTerry Gani',
-        '\tDaniel Harper',
-        '\tJP Janet',
-        '\tFang Liu',
-        '\tRalf Meyer',
-        '\tAditya Nandy',
-        '\tMichael Taylor',
-        '\tGianmarco Terrones',
-        '\tTzuhsiung (Nick) Yang',
-        'E.I. Ioannidis, T.Z.H. Gani, H.J. Kulik. J. Comput. Chem. 2016, 37, 2106-2117.',
-        'J.P. Janet, Q. Zhao, E.I. Ioannidis, H.J. Kulik. Mol. Simul. 2017, 43(5-6), 327-345.',
-        'J.P. Janet, T.Z.H. Gani, A.H. Steeves, E.I. Ioannidis, H.J. Kulik. Ind. Eng. Chem. Res. 2017, 56(17), 4898-4910.',
-        'For an extended list of references, please see https://molsimplify.readthedocs.io/en/latest/Citation.html'
-        ]
-        s = '\n'.join(program_info)
+        s = f'''
+molSimplify v{get_version()}
+Freely distributed under the GNU GPL license.
+Copyright 2017 Kulik Lab @ MIT
+Developed by: Efthymios Ioannidis
+Contributions by:
+\tHeather J. Kulik (corresponding developer; hjkulik@mit.edu)
+\tNaveen Arunachalam
+\tChenru Duan
+\tFreya Edholm
+\tTerry Gani
+\tDaniel Harper
+\tJP Janet
+\tFang Liu
+\tRalf Meyer
+\tAditya Nandy
+\tMichael Taylor
+\tGianmarco Terrones
+\tTzuhsiung (Nick) Yang
+E.I. Ioannidis, T.Z.H. Gani, H.J. Kulik. J. Comput. Chem. 2016, 37, 2106-2117.
+J.P. Janet, Q. Zhao, E.I. Ioannidis, H.J. Kulik. Mol. Simul. 2017, 43(5-6), 327-345.
+J.P. Janet, T.Z.H. Gani, A.H. Steeves, E.I. Ioannidis, H.J. Kulik. Ind. Eng. Chem. Res. 2017, 56(17), 4898-4910.
+G.G. Terrones, R.G. St. Michel, J.W. Toney, A.K. Ball, Y. Wang, A.G. Garrison, A. Nandy, R. Meyer, F. Edholm, C. Oh, S.G. Pujet, D.B.K. Chu, D. Muhammetgulyyev, H.J. Kulik. J. Chem. Inf. Model. 2026, 66(5), 2753-2767.
+For an extended list of references, please see https://molsimplify.readthedocs.io/en/latest/Citation.html
+'''.rstrip('\n')
 
         # About message
         self.about = s
@@ -690,6 +690,7 @@ class globalvars(metaclass=Singleton):
         self.chemdbdir = ''
         self.multiwfn = ''
         self.custom_path = False
+        self.molsimplify_config_path = homedir + '/.' + self.PROGRAM
         # ##### check for ~/.molSimplify ######
         if glob.glob(homedir + '/.' + self.PROGRAM):
             with open(homedir + '/.' + self.PROGRAM, 'r') as fin:

{molsimplify-1.8.0 → molsimplify-2.0.0}/molSimplify/Classes/ligand.py

@@ -1355,6 +1355,10 @@ def ligand_assign_consistent(mol, liglist, ligdents, ligcons, loud=False,
             eq_con_list = [ligcons[j] for j in eq_lig_list]
             ax_lig_list = list(set(allowed)-set(eq_points_max_mw))
             ax_con_list = [ligcons[j] for j in ax_lig_list]
+        # Canonical equatorial order (formula, then connecting atom index) for reproducibility
+        eq_lig_list = sorted(eq_lig_list, key=lambda i: (
+            built_ligand_list[i].mol.make_formula(latex=False), ligcons[i][0]))
+        eq_con_list = [ligcons[j] for j in eq_lig_list]
         # ###### Find and put trans species in eq plane in order opposite
         # ###### from each other [0,2],[1,3] in indices for monodentates
         eq_con_coords = [flat_coord_list[x] for x in eq_lig_list]
@@ -1366,7 +1370,7 @@ def ligand_assign_consistent(mol, liglist, ligdents, ligcons, loud=False,
                 print(('pair of atoms, angle', pair, angle))
             angle_list_eq.append(angle)
         opposite_lig = combos[np.argmax(angle_list_eq)][1]
-        others = list(set([1, 2, 3])-set([opposite_lig]))
+        others = sorted(set([1, 2, 3]) - set([opposite_lig]))
         eq_order = [0, others[0], opposite_lig, others[1]]
         # Reorder equatorial plane
         eq_con_list = [eq_con_list[x] for x in eq_order]

{molsimplify-1.8.0 → molsimplify-2.0.0}/molSimplify/Classes/mol2D.py

@@ -1,6 +1,7 @@
+from __future__ import annotations
 import networkx as nx
 import numpy as np
-from typing import List, Union
+from typing import Dict, Iterable, List, Optional, Tuple, Union
 from packaging import version
 from molSimplify.Classes.globalvars import globalvars
 from molSimplify.Classes.mol3D import mol3D as Mol3D
@@ -12,6 +13,9 @@ except ImportError:
     import openbabel  # fallback to version 2
 
 
+
+
+
 class Mol2D(nx.Graph):
 
     def __repr__(self):
@@ -317,6 +321,8 @@ class Mol2D(nx.Graph):
                 Number of independent coordination paths in graph
             hapticity : list
                 Length of each separate coordination path in graph
+            coordination_paths : list
+                Atom indices corresponding to each coordination path
         """
         # ensure provided coordinating atoms are all within range of atoms in molecule
         if max(catoms) >= self.number_of_nodes():
@@ -344,4 +350,120 @@ class Mol2D(nx.Graph):
         denticity = len(coordination_paths)
         hapticity = [len(path) for path in coordination_paths]
 
-        return denticity, hapticity
+        return denticity, hapticity, coordination_paths
+
+
+def substructure_search(
+    list_of_mol2Ds: List["Mol2D"],
+    r: int,
+    atom_filter: Optional[Union[Iterable[str], set]] = None,
+    wl_iterations: int = 5,
+    include_occurrences: bool = True,
+) -> Dict[str, dict]:
+    """
+    Radius-based motif search over Mol2D graphs using Weisfeiler–Lehman hashing.
+
+    For each molecule and for each allowed starting atom, this builds the induced
+    subgraph containing all atoms within graph distance <= r (number of bonds),
+    computes a node-attributed WL hash, and groups identical hashes as "motifs".
+
+    Parameters
+    ----------
+    list_of_mol2Ds : list[Mol2D]
+        Molecules to search.
+    r : int
+        Radius in number of bonds (graph distance) around each starting atom.
+        r=0 -> single atom motifs; r=1 -> nearest neighbors; r=2 -> next-nearest; etc.
+    atom_filter : iterable[str] | set[str] | None
+        If provided, only atoms whose `symbol` is in this set are used as starting atoms.
+        Example: {"Fe", "Co", "Ni"} or {"C", "N", "O"}.
+    wl_iterations : int
+        Number of WL refinement iterations for hashing (default 5).
+    include_occurrences : bool
+        If True, store where each motif occurs (mol index, center atom, nodes in subgraph).
+
+    Returns
+    -------
+    dict
+        Mapping: motif_hash -> {
+            "count": int,
+            "unique_molecules": int,
+            "occurrences": list[tuple]  # optional
+        }
+
+        Each occurrence tuple is (mol_idx, center_atom_idx, tuple(sorted(nodes_in_subgraph))).
+
+    Notes
+    -----
+    - Motifs are defined purely by graph topology + node symbols within radius r.
+    - If your Mol2D nodes have "symbol" attributes (as in your class), this works out of the box.
+    """
+    if r < 0:
+        raise ValueError("r must be >= 0")
+
+    allowed: Optional[set] = set(atom_filter) if atom_filter is not None else None
+
+    motifs: Dict[str, dict] = {}
+
+    for mol_idx, mol in enumerate(list_of_mol2Ds):
+        # Defensive: ensure it's a graph with nodes
+        if mol is None or mol.number_of_nodes() == 0:
+            continue
+
+        for center in mol.nodes:
+            sym = mol.nodes[center].get("symbol", "X")
+            if allowed is not None and sym not in allowed:
+                continue
+
+            # Nodes within radius r (graph distance <= r)
+            lengths = nx.single_source_shortest_path_length(mol, center, cutoff=r)
+            nodes_in_ball = list(lengths.keys())
+
+            # Induced subgraph (copy so WL hash doesn't see view-only)
+            subG = mol.subgraph(nodes_in_ball).copy()
+
+            # WL hash (node-attributed)
+            h = nx.weisfeiler_lehman_graph_hash(
+                subG, node_attr="symbol", iterations=wl_iterations
+            )
+
+            if h not in motifs:
+                motifs[h] = {
+                    "count": 0,
+                    "molecule_set": set(),  # internal bookkeeping
+                }
+                if include_occurrences:
+                    motifs[h]["occurrences"] = []
+
+            motifs[h]["count"] += 1
+            motifs[h]["molecule_set"].add(mol_idx)
+            if include_occurrences:
+                motifs[h]["occurrences"].append(
+                    (mol_idx, int(center), tuple(sorted(nodes_in_ball)))
+                )
+
+    # finalize: replace molecule_set with unique_molecules
+    for h, d in motifs.items():
+        d["unique_molecules"] = len(d["molecule_set"])
+        del d["molecule_set"]
+
+    return motifs
+
+
+def motif_counts_only(
+    list_of_mol2Ds: List["Mol2D"],
+    r: int,
+    atom_filter: Optional[Union[Iterable[str], set]] = None,
+    wl_iterations: int = 5,
+) -> Dict[str, int]:
+    """
+    Convenience wrapper: returns only hash -> count.
+    """
+    motifs = substructure_search(
+        list_of_mol2Ds,
+        r,
+        atom_filter=atom_filter,
+        wl_iterations=wl_iterations,
+        include_occurrences=False,
+    )
+    return {h: d["count"] for h, d in motifs.items()}