├── misc
└── logo.png
├── CHANGELOG.md
├── descriptors
├── runcrystalnets.jl
└── gen_pers_homology.py
├── duplicates
├── pdd_matrix_compare.py
├── group_by_chemel.sh
├── pdd_matrix_elform.sh
├── README.md
├── multiple_chemform.py
└── analyze_pdd_csv.py
├── zenodo
├── get_subset.py
├── get_unchanged_mofs.py
├── README.md
├── write_pac_cif.py
└── clean_csd_mofs.py
├── FAQ.md
├── structure_validation
├── chk_overlap.py
└── chk_hypervalent.py
├── README.md
└── LICENSE
/misc/logo.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/uowoolab/MOSAEC-DB/HEAD/misc/logo.png
--------------------------------------------------------------------------------
/CHANGELOG.md:
--------------------------------------------------------------------------------
1 | # Current MOSAEC-DB version
2 | ## v1.0.0 Release
3 | Total Structure Count (*including unchanged*): 124.4k
4 |
5 | Latest CSD Data Update processed: v5.4.5 (March 2024)
6 |
7 | # Changelog
8 | -
9 |
--------------------------------------------------------------------------------
/descriptors/runcrystalnets.jl:
--------------------------------------------------------------------------------
1 | using CrystalNets
2 |
3 | function main(args)
4 | show(determine_topology_dataset(args, true, true, true, CrystalNets.Options(export_subnets=false, export_net=false, export_clusters=false, export_input=false, export_trimmed=false, structure=StructureType.MOF, bonding=Bonding.Input, detect_organiccycles=false, clusterings=[Clustering.Auto, Clustering.Standard])))
5 | end
6 |
7 | main(ARGS[1])
8 |
9 |
--------------------------------------------------------------------------------
/duplicates/pdd_matrix_compare.py:
--------------------------------------------------------------------------------
1 | from sys import argv
2 | import amd
3 | import pandas as pd
4 |
5 | structure_list = argv[1]
6 | struc_base = structure_list.split(".cif")[0]
7 |
8 | pdd_df = amd.compare(structure_list, by="PDD", k=100)
9 |
10 | col_list = []
11 | for col in pdd_df.columns:
12 | col_list.append(col)
13 | for idx in pdd_df.index:
14 | if col != idx and idx not in col_list:
15 | print(col, idx, pdd_df.loc[idx, col])
16 |
17 |
18 | pdd_df.to_csv(f"{struc_base}.csv")
19 |
--------------------------------------------------------------------------------
/duplicates/group_by_chemel.sh:
--------------------------------------------------------------------------------
1 | #!/bin/bash
2 |
3 | echo "Extracting empirical formulas ..."
4 |
5 | for i in *.cif
6 | do
7 | cf=$(grep '_chemical_formula_sum' $i | sed 's/_chemical_formula_sum//')
8 | echo "$i $cf" >> all_formulae.txt
9 | done
10 | cut -d ' ' -f2- all_formulae.txt | sort | uniq -c | sort -gr | sed 's/^[ ]*//;s/[ ]*$//' > numX_chemform.txt
11 | cut -d ' ' -f2- numX_chemform.txt | sed 's/ //g' | sed "s/'//g" > unique_empform.txt
12 |
13 |
14 | echo "Making lists of structures with the same chemical formula ..."
15 | n=1
16 | for line in $(awk '{print$1}' numX_chemform.txt)
17 | do
18 | i=$(sed -n "${n}p" numX_chemform.txt | cut -d ' ' -f2- )
19 | ii=$(sed -n "${n}p" unique_empform.txt)
20 | grep "$i" all_formulae.txt | awk '{print$1}' > $ii.lst
21 | ((n++))
22 | done
23 |
24 | echo "Checking for empirical formula multiples ..."
25 |
26 | python multiple_chemform.py unique_empform.txt
27 |
28 | echo "Completed"
29 |
--------------------------------------------------------------------------------
/duplicates/pdd_matrix_elform.sh:
--------------------------------------------------------------------------------
1 | #!/bin/bash
2 |
3 | for i in $(wc -l *.lst | awk '$1 > 1 {print$2}' | grep -v total )
4 | do
5 | echo "running $i comparisons ..."
6 | for ii in $(cat $i)
7 | do
8 | cat $ii >> ${i%.lst}_pdd.cif
9 | done
10 |
11 | cat > pdd_matrix_compare.py << EOF
12 | from sys import argv
13 | import amd
14 | import pandas as pd
15 |
16 | structure_list = argv[1]
17 | struc_base = structure_list.split('.cif')[0]
18 |
19 | pdd_df = amd.compare(structure_list, by='PDD', k=100)
20 |
21 | col_list = []
22 | for col in pdd_df.columns:
23 | col_list.append(col)
24 | for idx in pdd_df.index:
25 | if col != idx and idx not in col_list:
26 | print(col, idx, pdd_df.loc[idx, col])
27 |
28 |
29 | pdd_df.to_csv(f'{struc_base}.csv')
30 |
31 | EOF
32 | ## load necessary environment with amd package installed
33 | . ~/.venvs/XXXX/bin/activate
34 | echo "Running PDD for all ${i%.lst} structures ..."
35 | python pdd_matrix_compare.py ${i%.lst}_pdd.cif > ${i%.lst}_pdd.pyout
36 |
37 | done
38 |
--------------------------------------------------------------------------------
/duplicates/README.md:
--------------------------------------------------------------------------------
1 | # Structure Duplication Analysis using Pointwise Distance Distributions
2 | Identification of duplicated crystal structure based on similarity of their pointwise distance distribution (PDD) scores.
3 |
4 | # Workflow
5 | Warning: Scripts contain relative paths that will require editing to work on each system.
6 |
7 | 1. Normalize the crystal structure file (cif) formats using your preferred method (e.g., pymatgen, critic23, etc.)
8 | 2. Run group_by_chemel.sh to create *.lst files by each empirical formula that contains the filenames possessing the same empirical formula.
9 | 3. Run pdd_matrix_elform.sh to run pairwise PDD comparisons for all *.lst files -- writes separate *_pdd.pyout & *_pdd.csv for each empirical formula.
10 | 4. Combine PDD results from *_pdd.pyout files e.g., `cat *_pdd.pyout | sed 's/ /.cif,/g' | awk '{print$1,$2,$3}' > pdd_scores.txt`
11 | 5. Use analyze_pdd_csv.py on the pdd_scores.txt to identify duplicate crystal structures based on a defined PDD score threshold (default:)
12 |
13 | # Output
14 | A summary of the duplicate structures is stored as a csv file (default: **duplicate_pdd.csv**).
15 |
16 | Description of Columns:
17 | | Column Header | Description |
18 | | -------------- | -------------- |
19 | | `cif` | structure filename |
20 | | `unique` | whether the structure was identified as unique (True/False) |
21 | | `no_duplicates` | number of structure duplicates identified within PDD threshold |
22 | | `duplicate_ids` | structure filenames of those identified as duplicates |
--------------------------------------------------------------------------------
/zenodo/get_subset.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import os
3 | import shutil
4 | import argparse
5 |
6 | CODE_PATH = os.path.dirname(os.path.realpath(__file__))
7 | print(CODE_PATH)
8 | DB_PATH = CODE_PATH.replace("scripts", "")
9 | print(DB_PATH)
10 |
11 |
12 | def subset(txt_file, dest_dir):
13 | # define cif paths
14 | if "-neutral-" in dest_dir:
15 | fpath = os.path.join(DB_PATH, "database/full/neutral")
16 | ppath = os.path.join(DB_PATH, "database/partial/neutral")
17 | else:
18 | fpath = os.path.join(DB_PATH, "database/full/charged")
19 | ppath = os.path.join(DB_PATH, "database/partial/charged")
20 |
21 | with open(txt_file, "r") as rf:
22 | cifs = rf.read().split("\n")
23 |
24 | # separate cifs by origin directory
25 | fcifs = [os.path.join(fpath, x) for x in cifs if "_full" in x]
26 | pcifs = [os.path.join(ppath, x) for x in cifs if "_partial" in x]
27 |
28 | # move files
29 | print(f"Copying {len(fcifs + pcifs)} .cif files ... ")
30 | for cif in fcifs + pcifs:
31 | shutil.copy(cif, dest_dir)
32 | return 0
33 |
34 |
35 | if __name__ == "__main__":
36 | code_desc = "Retrieve MOSAEC-DB cifs from a specific subset (.txt)."
37 | parser = argparse.ArgumentParser(description=code_desc)
38 | parser.add_argument(
39 | "subset",
40 | type=str,
41 | help="path to .txt file with MOSAEC-DB cif names.",
42 | )
43 | args = parser.parse_args()
44 | # create subset dir
45 | subset_dir = os.path.basename(args.subset)[:-4]
46 | print("Making subset directory ... ", subset_dir)
47 | os.makedirs(subset_dir, exist_ok=True)
48 | # find & move files
49 | subset(args.subset, subset_dir)
50 |
--------------------------------------------------------------------------------
/duplicates/multiple_chemform.py:
--------------------------------------------------------------------------------
1 | import re
2 | from sys import argv
3 |
4 |
5 | def parse_formula(formula):
6 | """Parse a chemical formula into its constituent elements and their counts."""
7 | elements = re.findall(r"([A-Z][a-z]*)(\d*)", formula)
8 | return {element: int(count) if count else 1 for element, count in elements}
9 |
10 |
11 | def find_multiples_of_formula(formula, formulas):
12 | """Find multiples of a given chemical formula within a list of formulas."""
13 | parsed_formula = parse_formula(formula)
14 | multiples = []
15 |
16 | for other_formula in formulas:
17 | if formula == other_formula:
18 | continue # Skip the same formula
19 |
20 | parsed_other_formula = parse_formula(other_formula)
21 |
22 | # Check if both formulas contain the same elements
23 | if set(parsed_formula.keys()) != set(parsed_other_formula.keys()):
24 | continue # Skip if the sets of elements are different
25 |
26 | # Check if all elements in the other formula are multiples of the elements in the original formula
27 | is_multiple = True
28 | for element, count in parsed_other_formula.items():
29 | if count % parsed_formula[element] != 0:
30 | is_multiple = False
31 | break # Not a multiple if ratio is not integer
32 | if (
33 | count // parsed_formula[element]
34 | != parsed_other_formula[list(parsed_other_formula.keys())[0]]
35 | // parsed_formula[list(parsed_formula.keys())[0]]
36 | ):
37 | is_multiple = False
38 | break # Not a multiple if ratios between corresponding elements differ
39 |
40 | if is_multiple:
41 | multiples.append(other_formula)
42 |
43 | return multiples
44 |
45 |
46 | # Read chemical formulas from a file
47 | def read_chemical_formulas_from_file(filename):
48 | with open(filename, "r") as file:
49 | chemical_formulas = [line.strip() for line in file if line.strip()]
50 | return chemical_formulas
51 |
52 |
53 | # run
54 | # input file should be tmp.txt from group_by_chemel.sh
55 | filename = argv[1]
56 | chemical_formulas = read_chemical_formulas_from_file(filename)
57 | for formula_to_check in chemical_formulas:
58 | multiples = find_multiples_of_formula(formula_to_check, chemical_formulas)
59 | if multiples:
60 | print(f"Multiples of {formula_to_check}: {multiples}")
61 |
--------------------------------------------------------------------------------
/FAQ.md:
--------------------------------------------------------------------------------
1 | ## Frequently Asked Questions
2 | - [Crystal structure (CIF) count doesn't match the publication?](#crystal-structure-cif-count-doesnt-match-the-publication)
3 | - [Failed to find REFCODEs when retrieving unchanged structure?](#failed-to-find-refcodes-when-retrieving-unchanged-structures)
4 | - [Structure XX missing descriptors?](#structure-xx-missing-descriptors)
5 | - [Found a suspected erroneous crystal structure?](#found-a-suspected-erroneous-crystal-structure)
6 |
7 | ## Crystal structure (CIF) count doesn't match the publication?
8 |
9 | Structures which were unchanged during the solvent removal step could not be included publicly due to concerns relating to the Cambridge Structural Database (CSD) licensing agreements.
10 |
11 | **This amounted to an approximate total of 45k files being omitted from the public database provided on zenodo.**
12 |
13 | Scripts to regenerate those structures are available to individuals with an active CSD license.
14 |
15 | ## Failed to find REFCODEs when retrieving unchanged structures?
16 |
17 | The release version of MOSAEC-DB was constructed using several CSD data updates up to the version 5.4.5 (March 2024).
18 |
19 | The crystal structure REFCODEs can change during these CSD data updates, and as a result some REFCODEs reported in MOSAEC-DB may no longer exist in current or future CSD data updates.
20 |
21 | **Mismatch of the CSD database versions is the most likely cause of any mismatch**, though future additions to MOSAEC-DB should capture any new or updated REFCODEs included in the CSD.
22 |
23 | ## Structure XX missing descriptors?
24 |
25 | Any structures missing from the provided descriptors (e.g. RAC, RDF, etc.) csv files **failed during the calculation process**. The same principle applies to any of the data in the primary csv file (i.e. topology, dimensionality, etc.), and the partial atomic charge (REPEAT) structure files.
26 |
27 | Future MOSAEC-DB updates may address these missing values with newer version of the descriptor calculation codes/packages.
28 |
29 | ## Found a suspected erroneous crystal structure?
30 |
31 | Though the MOSAEC-DB construction protocol eliminated a majority of the structure errors, we expect that erroneous structures will remain due to practical limitations in the employed structure validation approach. The MOSAEC algorithm was estimated to be **ca. 95% accurate in flagging erroneous structures and ca. 85% accurate in flagging error-free structures** during manual validation.
32 |
33 | Feel free to contact the [authors](README.md#contact) with any structure error inquiries so that we may address them in future database versions.
34 |
35 | ##
36 |
37 |
--------------------------------------------------------------------------------
/duplicates/analyze_pdd_csv.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import os
3 | import glob
4 | import argparse
5 |
6 | import pandas as pd
7 |
8 |
9 | code_desc = "Analyze csv containing all PDD scores calculated for a given database."
10 | parser = argparse.ArgumentParser(description=code_desc)
11 | parser.add_argument(
12 | "pdd_csv",
13 | type=str,
14 | help="path to csv containing all structure pairs' precomputed pdd scores.",
15 | )
16 | parser.add_argument(
17 | "cif_path",
18 | type=str,
19 | help="path to directory containing all the structures to be considered.",
20 | )
21 | parser.add_argument(
22 | "-output_csv",
23 | type=str,
24 | default="duplicate_pdd.csv",
25 | help="path to csv containing all structure pairs' precomputed pdd scores.",
26 | )
27 | parser.add_argument(
28 | "-pdd_threshold",
29 | type=float,
30 | default=0.15,
31 | help="path to csv containing all structure pairs' precomputed pdd scores.",
32 | )
33 | args = parser.parse_args()
34 |
35 | pdd_threshold = args.pdd_threshold
36 |
37 | cpath = args.cif_path
38 | cifs = glob.glob(f"{cpath}/*.cif", recursive=False)
39 | cifs = [os.path.basename(x) for x in cifs if x[-8:] != "_pdd.cif"]
40 | print(f"Total cifs from db to compare ... {len(cifs)}")
41 | duplicates = {x: [] for x in cifs}
42 |
43 | # read scores
44 | ignore_lines = ["", "s1,s2,pdd_score"]
45 | with open(args.pdd_csv, "r") as rf:
46 | dlines = [x for x in rf.read().split("\n") if x not in ignore_lines]
47 |
48 | # go over files from duplicate analysis
49 | # s1, s2, pdd_score
50 | print("Total no. PDD scores to compare ... ", len(dlines) - 1)
51 | for line in dlines:
52 | spl = line.split(",")
53 | cif1 = spl[0]
54 | cif2 = spl[1]
55 | pdd = float(spl[2])
56 | if pdd < pdd_threshold:
57 | duplicates[cif1].append(cif2)
58 | duplicates[cif2].append(cif1)
59 | else:
60 | continue
61 |
62 |
63 | # get duplicate dictionary
64 | unique = []
65 | dupl = []
66 | rows = []
67 | for cif, dupes in duplicates.items():
68 | dupes = sorted(list(set(dupes)))
69 | if len(dupes) != 0:
70 | intersect = list(set(dupes) & set(unique))
71 | if len(intersect) == 0:
72 | unique.append(cif)
73 | else:
74 | dupl.append(cif)
75 | else:
76 | unique.append(cif)
77 |
78 | rows.append(
79 | {
80 | "cif": cif,
81 | "unique": True if cif in unique else False,
82 | "no_duplicates": len(dupes),
83 | "duplicate_ids": "/".join(dupes),
84 | }
85 | )
86 |
87 |
88 | print(f"Total unique MOFs ... {len(unique)}")
89 | print(f"Total duplicate MOFs ... {len(dupl)}")
90 |
91 | df = pd.DataFrame(rows)
92 | df.to_csv(args.output_csv, index=False)
93 |
--------------------------------------------------------------------------------
/descriptors/gen_pers_homology.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import os
3 | import glob
4 | import time
5 | import argparse
6 |
7 | import numpy as np
8 | import pandas as pd
9 |
10 | from multiprocessing import Pool
11 | from subprocess import PIPE, Popen
12 | from pymatgen.core import Structure
13 | from mofdscribe.featurizers.topology import AtomCenteredPH
14 |
15 |
16 | def run_bash(cmd):
17 | p = Popen([cmd], shell=True, stdout=PIPE, stderr=PIPE)
18 | out, err = p.communicate()
19 | return out.decode("utf-8").strip().split()
20 |
21 |
22 | dest_path = f"{args.search_path}/homology_vectors"
23 | run_bash(f"mkdir -p {dest_path}")
24 |
25 |
26 | def gen_descriptors(file):
27 | stime = time.time()
28 | try:
29 | # read into pymatgen.Structure
30 | struct = Structure.from_file(file)
31 | # select mofdscribe featurizers
32 | new_types = (
33 | "H",
34 | "C",
35 | "N-P",
36 | "O-S-Se",
37 | "F-Cl-Br-I",
38 | "Li-Be-Na-Mg-K-Ca-Rb-Sr-Cs-Ba-Fr-Ra",
39 | "Al-Si-Ga-Ge-As-In-Sn-Sb-Te-Tl-Pb-Bi-Po-At",
40 | "Sc-Ti-V-Cr-Mn-Fe-Co-Ni-Cu-Zn-Y-Zr-Nb-Mo-Tc-Ru-Rh-"
41 | "Pd-Ag-Cd-Hf-Ta-W-Re-Os-Ir-Pt-Au-Hg",
42 | "La-Ce-Pr-Nd-Pm-Sm-Eu-Gd-Tb-Dy-Ho-Er-Tm-Yb-Lu-Ac-"
43 | "Th-Pa-U-Np-Pu-Am-Cm-Bk-Cf-Es-Fm-Md-No-Lr",
44 | )
45 | new_dimens = (0, 1, 2)
46 | featurizer = AtomCenteredPH(atom_types=new_types, dimensions=new_dimens)
47 | # calculate features
48 | feats = featurizer.featurize(struct)
49 | labels = featurizer.feature_labels()
50 | # output features
51 | bname = os.path.basename(file).replace(".cif", "")
52 | np.save(f"{dest_path}/{bname}.npy", feats)
53 | elapsedtime = time.time() - stime
54 | print(file, elapsedtime, "s")
55 | except Exception as e:
56 | print(f"{file} >> FEATURE CALCULATION Failed {e}\n")
57 | return None
58 | else:
59 | row = {"cif": [bname]}
60 | row.update({f"{label}": feats[i] for i, label in enumerate(labels)})
61 | return pd.DataFrame(row)
62 |
63 |
64 | if __name__ == "__main__":
65 | code_desc = "Calculate Atom-specific Persistent Homology features as implemented in mofdscribe."
66 | parser = argparse.ArgumentParser(description=code_desc)
67 | parser.add_argument(
68 | "search_path", help="path where the structure files (cif) are located."
69 | )
70 | parser.add_argument("num_cpus", help="no. cpus available for multiprocessing.")
71 | args = parser.parse_args()
72 | #
73 | files = glob.glob(f"{args.search_path}/*.cif", recursive=False)
74 | pool = Pool(processes=int(args.num_cpus))
75 | df_path = f"{dest_path}/homology.csv"
76 | for results in pool.imap_unordered(gen_descriptors, files):
77 | if results is not None:
78 | if os.path.exists(df_path):
79 | results.to_csv(df_path, mode="a", header=False, index=False)
80 | else:
81 | results.to_csv(df_path, index=False)
82 |
--------------------------------------------------------------------------------
/structure_validation/chk_overlap.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import argparse
3 |
4 | from pymatgen.io.cif import CifParser
5 |
6 | # Covalent radii revisited -- DOI:10.1039/B801115J
7 | COVALENT_RADII = {
8 | "H": 0.31,
9 | "He": 0.28,
10 | "Li": 1.28,
11 | "Be": 0.96,
12 | "B": 0.84,
13 | "C": 0.76, # for sp3; sp2 = 0.73; sp = 0.69
14 | "C_1": 0.69,
15 | "C_2": 0.73,
16 | "C_R": 0.73,
17 | "C_3": 0.76,
18 | "N": 0.71,
19 | "O": 0.66,
20 | "F": 0.57,
21 | "Ne": 0.58,
22 | "Na": 1.66,
23 | "Mg": 1.41,
24 | "Al": 1.21,
25 | "Si": 1.11,
26 | "P": 1.07,
27 | "S": 1.05,
28 | "Cl": 1.02,
29 | "Ar": 1.06,
30 | "K": 2.03,
31 | "Ca": 1.76,
32 | "Sc": 1.7,
33 | "Ti": 1.6,
34 | "V": 1.53,
35 | "Cr": 1.39,
36 | "Mn": 1.61, # low spin = 1.39
37 | "Fe": 1.52, # low spin = 1.32
38 | "Co": 1.5, # low spin = 1.26
39 | "Ni": 1.24,
40 | "Cu": 1.32,
41 | "Zn": 1.22,
42 | "Ga": 1.22,
43 | "Ge": 1.2,
44 | "As": 1.19,
45 | "Se": 1.2,
46 | "Br": 1.2,
47 | "Kr": 1.16,
48 | "Rb": 2.2,
49 | "Sr": 1.95,
50 | "Y": 1.9,
51 | "Zr": 1.75,
52 | "Nb": 1.64,
53 | "Mo": 1.54,
54 | "Tc": 1.47,
55 | "Ru": 1.46,
56 | "Rh": 1.42,
57 | "Pd": 1.39,
58 | "Ag": 1.45,
59 | "Cd": 1.44,
60 | "In": 1.42,
61 | "Sn": 1.39,
62 | "Sb": 1.39,
63 | "Te": 1.38,
64 | "I": 1.39,
65 | "Xe": 1.4,
66 | "Cs": 2.44,
67 | "Ba": 2.15,
68 | "La": 2.07,
69 | "Ce": 2.04,
70 | "Pr": 2.03,
71 | "Nd": 2.01,
72 | "Pm": 1.99,
73 | "Sm": 1.98,
74 | "Eu": 1.98,
75 | "Gd": 1.96,
76 | "Tb": 1.94,
77 | "Dy": 1.92,
78 | "Ho": 1.92,
79 | "Er": 1.89,
80 | "Tm": 1.9,
81 | "Yb": 1.87,
82 | "Lu": 1.87,
83 | "Hf": 1.75,
84 | "Ta": 1.7,
85 | "W": 1.62,
86 | "Re": 1.51,
87 | "Os": 1.44,
88 | "Ir": 1.41,
89 | "Pt": 1.36,
90 | "Au": 1.36,
91 | "Hg": 1.32,
92 | "Tl": 1.45,
93 | "Pb": 1.46,
94 | "Bi": 1.48,
95 | "Po": 1.4,
96 | "At": 1.5,
97 | "Rn": 1.5,
98 | "Fr": 2.6,
99 | "Ra": 2.21,
100 | "Ac": 2.15,
101 | "Th": 2.06,
102 | "Pa": 2,
103 | "U": 1.96,
104 | "Np": 1.9,
105 | "Pu": 1.87,
106 | "Am": 1.8,
107 | "Cm": 1.69,
108 | }
109 |
110 |
111 | if __name__ == "__main__":
112 | code_desc = (
113 | "Check structure for overlapping atomic sites using Cordero Covalent radii."
114 | )
115 | parser = argparse.ArgumentParser(description=code_desc)
116 | parser.add_argument(
117 | "filename",
118 | type=str,
119 | required=True,
120 | help="path to structure file (cif)",
121 | )
122 | args = parser.parse_args()
123 |
124 | try:
125 | filename = args.filename
126 | parser = CifParser(filename)
127 | structure = parser.get_structures(primitive=False)[0]
128 |
129 | num_atoms = len(structure.frac_coords)
130 |
131 | criteria = 0.7
132 | num_problem = 0
133 | for i in range(num_atoms - 1):
134 | for j in range(i + 1, num_atoms):
135 |
136 | distance = structure.get_distance(i, j)
137 | if distance > 3.65:
138 | continue
139 | else:
140 | sum_radii = (
141 | COVALENT_RADII[str(structure.species[i])]
142 | + COVALENT_RADII[str(structure.species[j])]
143 | )
144 | if distance < criteria * sum_radii:
145 | num_problem += 1
146 | except:
147 | print("CTEST %s Error %i" % (filename, num_atoms))
148 | exit(1)
149 | if num_problem == 0:
150 | print("CTEST %s Good %i" % (filename, num_atoms))
151 | elif num_problem > 0:
152 | print("CTEST %s Bad %i %i" % (filename, num_atoms, num_problem))
153 |
--------------------------------------------------------------------------------
/structure_validation/chk_hypervalent.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import re
3 | import argparse
4 | import warnings
5 |
6 |
7 | from pymatgen.core import Structure
8 |
9 | from pymatgen.analysis.graphs import StructureGraph
10 |
11 | # from pymatgen.analysis.graphs import MoleculeGraph
12 | import pymatgen.analysis.local_env as env
13 |
14 | from pymatgen.io.babel import BabelMolAdaptor
15 |
16 | # from pymatgen.io.cif import CifWriter
17 |
18 | import openbabel
19 | from openbabel import pybel as pb
20 |
21 |
22 | def read_cif(file_path):
23 | return Structure.from_file(file_path, sort=False)
24 |
25 |
26 | def get_metal_indices(struct_):
27 | """This function returns metal site indices from a pymatgen Structure object"""
28 | metal_indices = []
29 |
30 | for i, site in enumerate(struct_.sites):
31 | if site.species.contains_element_type("metal"):
32 | metal_indices.append(i)
33 |
34 | return metal_indices
35 |
36 |
37 | def get_graph(struct_):
38 | return StructureGraph.with_local_env_strategy(struct_, env.IsayevNN())
39 |
40 |
41 | def get_smiles(mol):
42 | """This function returns a SMILES string from a pymatgen molecular graph"""
43 | babel_mol = BabelMolAdaptor(mol)
44 | pybel_mol = pb.Molecule(babel_mol.openbabel_mol)
45 | return pybel_mol.write("can").split()[0]
46 |
47 |
48 | def get_subgraphs(graph_):
49 | smiles_list = []
50 | subgraphs = graph_.get_subgraphs_as_molecules(use_weights=False)
51 | for mol in subgraphs:
52 | if len(mol.sites) > 0:
53 | smiles = get_smiles(mol)
54 | smiles_list.append(smiles)
55 |
56 | return smiles_list
57 |
58 |
59 | def check_atoms(graph_, struct_):
60 | graph_dict = graph_.as_dict()
61 | atom_dict = {}
62 | connection_dict = {}
63 | bad_atom_list = []
64 | counter = 0
65 | counter_2 = 2
66 |
67 | for atom in struct_:
68 |
69 | atom_id = "{}{}".format(atom.specie, 1)
70 |
71 | while atom_id in atom_dict.values():
72 | atom_id = "{}{}".format(atom.specie, counter_2)
73 | counter_2 += 1
74 |
75 | atom_dict["{}".format(counter)] = atom_id
76 |
77 | counter += 1
78 | counter_2 = 2
79 |
80 | for atom, connections in zip(
81 | graph_dict["graphs"]["nodes"], graph_dict["graphs"]["adjacency"]
82 | ):
83 | for connection in connections:
84 | atom1 = atom_dict["{}".format(atom["id"])]
85 | atom2 = atom_dict["{}".format(connection["id"])]
86 | bond_length = round(struct_.get_distance(atom["id"], connection["id"]), 4)
87 | if atom1 not in connection_dict.keys():
88 | connection_dict[atom1] = [atom2]
89 | if atom2 not in connection_dict.keys():
90 | connection_dict[atom2] = [atom1]
91 | else:
92 | connection_dict[atom2].append(atom1)
93 | else:
94 | connection_dict[atom1].append(atom2)
95 | if atom2 not in connection_dict.keys():
96 | connection_dict[atom2] = [atom1]
97 | else:
98 | connection_dict[atom2].append(atom1)
99 | for atom in connection_dict.keys():
100 | if re.sub(r"\d+", "", atom) == "H" and len(connection_dict[atom]) > 1:
101 | print("BAD ATOM: {}".format(atom))
102 | bad_atom_list.append(atom)
103 | elif re.sub(r"\d+", "", atom) == "C" and len(connection_dict[atom]) > 4:
104 | print("BAD ATOM: {}".format(atom))
105 | bad_atom_list.append(atom)
106 | elif re.sub(r"\d+", "", atom) == "O" and len(connection_dict[atom]) > 2:
107 | print("BAD ATOM: {}".format(atom))
108 | bad_atom_list.append(atom)
109 | elif (
110 | re.sub(r"\d+", "", atom) in ["F", "Cl", "Br", "I"]
111 | and len(connection_dict[atom]) > 1
112 | ):
113 | print("BAD ATOM: {}".format(atom))
114 | bad_atom_list.append(atom)
115 | return bad_atom_list
116 |
117 |
118 | def main(filename):
119 |
120 | struct = read_cif(filename)
121 | # atom_dict = struct.as_dict()
122 | metals = get_metal_indices(struct)
123 | graph = get_graph(struct)
124 | graph.remove_nodes(indices=metals)
125 |
126 | bad_atoms = check_atoms(graph, struct)
127 |
128 | if len(bad_atoms) > 0:
129 | print(f" {filename} | BAD STRUCTURE")
130 | elif len(bad_atoms) == 0:
131 | print(f" {filename} | GOOD STRUCTURE")
132 |
133 |
134 | if __name__ == "__main__":
135 | code_desc = "Checks structure for hypervalent H, C, O, and halogens atomic sites."
136 | parser = argparse.ArgumentParser(description=code_desc)
137 | parser.add_argument(
138 | "filename",
139 | type=str,
140 | required=True,
141 | help="path to structure file (cif)",
142 | )
143 | args = parser.parse_args()
144 | with warnings.catch_warnings():
145 | warnings.simplefilter("ignore")
146 | input_cif = args.filename
147 | main(input_cif)
148 |
--------------------------------------------------------------------------------
/zenodo/get_unchanged_mofs.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import os
3 | import shutil
4 | import argparse
5 |
6 | from ccdc import io
7 | from ccdc.io import EntryReader
8 |
9 | from clean_csd_mofs import clean_structure
10 | from write_pac_cif import assign_partial_atomic_charge
11 |
12 | CODE_PATH = os.path.dirname(os.path.realpath(__file__))
13 |
14 |
15 | # text editing to remove disordered/partially occupied sites
16 | def filter_disorder(cif):
17 | filtered_lines = []
18 | if isinstance(cif, str):
19 | lines = cif.split("\n")
20 | else:
21 | with open(cif, "r") as rf:
22 | lines = rf.read().split("\n")
23 |
24 | for line in lines:
25 | try:
26 | spl = line.split()
27 | if (spl[0][-1] != "*") and (spl[0][-1] != "?"):
28 | filtered_lines.append(line)
29 | except IndexError as ie:
30 | filtered_lines.append(line)
31 | continue
32 | except Exception as e:
33 | print(cif, " | error removing disordered sites")
34 | print(e)
35 | else:
36 | continue
37 | return "\n".join(filtered_lines)
38 |
39 |
40 | # get cifs from csd
41 | def print_cifs(gcd_file, write_path, rm_disordered_sites):
42 | with open(gcd_file, "r") as rf:
43 | refcode_list = [_ for _ in rf.read().split("\n") if _ != ""]
44 |
45 | reader = EntryReader("CSD")
46 | for refcode in refcode_list:
47 | try:
48 | entry = reader.entry(refcode)
49 | mol = entry.disordered_molecule
50 | cif_str = mol.to_string("cif")
51 | if rm_disordered_sites:
52 | cif_str = filter_disorder(cif_str)
53 | cif_path = os.path.join(write_path, f"{entry.identifier}.cif")
54 | with open(cif_path, "w") as wf:
55 | wf.write(cif_str)
56 | except Exception as e:
57 | print(refcode, " | failed to print cif")
58 | continue
59 | return refcode_list
60 |
61 |
62 | # convert cifs to P1 symmetry
63 | def convert2P1(refs, out_dir, rename=None):
64 | for ref in refs:
65 | try:
66 | clean_structure(
67 | f"{out_dir}/{ref}_P1.cif",
68 | read_path=f"tmp_cifs/{ref}",
69 | input_is_cif=True,
70 | )
71 | if rename:
72 | p1_name = ref + "_P1.cif"
73 | mdb_name = p1_name.replace("_P1.cif", rename)
74 | shutil.move(f"{out_dir}/{p1_name} ", f"{out_dir}/{mdb_name}")
75 | except Exception as e:
76 | print(ref, " | failed to convert2P1 cif")
77 | print(e)
78 | continue
79 | return 0
80 |
81 |
82 | if __name__ == "__main__":
83 | code_desc = "Retrieve MOSAEC-DB cifs for refcodes which were unchanged."
84 | parser = argparse.ArgumentParser(description=code_desc)
85 | # full > os.path.join(CODE_PATH, "../database/full/unchanged_refcodes_full.gcd")
86 | # partial > os.path.join(CODE_PATH, "../database/partial/unchanged_refcodes_partial.gcd")
87 | parser.add_argument(
88 | "--gcd_files",
89 | nargs="+",
90 | default=[
91 | os.path.join(CODE_PATH, "../database/full/unchanged_refcodes_full.gcd"),
92 | os.path.join(
93 | CODE_PATH, "../database/partial/unchanged_refcodes_partial.gcd"
94 | ),
95 | ],
96 | help="path(s) to .gcd file with desired refcodes.",
97 | )
98 | parser.add_argument(
99 | "--remove_disorder",
100 | action="store_true",
101 | help="whether to remove disordered atom sites via simple text editing",
102 | )
103 | parser.add_argument(
104 | "--write_repeat",
105 | action="store_true",
106 | help="whether to also write files containing REPEAT charges.",
107 | )
108 | parser.add_argument(
109 | "--write_mepoml",
110 | action="store_true",
111 | help="whether to also write files containing MEPOML charges.",
112 | )
113 | args = parser.parse_args()
114 |
115 | print("Writing MOSAEC-DB cifs ...\n")
116 | for gcd in args.gcd_files:
117 | # print tmp cifs
118 | cif_dir = "tmp_cifs"
119 | os.makedirs(cif_dir, exist_ok=True)
120 | refs = print_cifs(gcd, cif_dir, args.remove_disorder)
121 |
122 | # convert cifs to P1 & rename
123 | p1_dir = "MOSAEC-DB_unchanged"
124 | os.makedirs(p1_dir, exist_ok=True)
125 | os.makedirs("./tmp", exist_ok=True)
126 | f_end = "_full.cif" if "full" in gcd else "_partial.cif"
127 | convert2P1(refs, p1_dir, rename=f_end)
128 |
129 | shutil.rmtree(cif_dir)
130 | shutil.rmtree("./tmp")
131 |
132 | if args.write_repeat:
133 | print("\nWriting MOSAEC-DB REPEAT cifs ...\n")
134 | repeat_dir = "MOSAEC-DB_unchanged_REPEAT"
135 | os.makedirs(repeat_dir, exist_ok=True)
136 | rpt_json = os.path.join(CODE_PATH, "../misc_data/unchanged_repeat.json")
137 | assign_partial_atomic_charge(p1_dir, rpt_json, repeat_dir, pac_type="REPEAT")
138 |
139 | if args.write_mepoml:
140 | print("\nWriting MOSAEC-DB MEPO-ML cifs ...\n")
141 | mepoml_dir = "MOSAEC-DB_unchanged_MEPOML"
142 | os.makedirs(mepoml_dir, exist_ok=True)
143 | mpml_json = os.path.join(CODE_PATH, "../misc_data/unchanged_mepoml.json")
144 | assign_partial_atomic_charge(p1_dir, mpml_json, mepoml_dir, pac_type="MEPOML")
145 |
146 |
--------------------------------------------------------------------------------
/zenodo/README.md:
--------------------------------------------------------------------------------
1 | # MOSAEC Database (v1.0.0-release)
2 |
3 | > [!WARNING]
4 | > ** The Database Zenodo record(s) will be taken down pending confirmation/amendments to the licensing agreement pertaining to the enclosed crystallographic data**
5 |
6 | [](https://doi.org/10.1039/D4SC07438F)
7 |
8 |
9 | 
10 |
11 |
12 | MOSAEC-DB consists of 124k+ metal-organic framework (MOF) and coordination polymer crystallographic information files (.cif) processed for atomistic simulations. This database contains solely experimental crystal structures derived from the Cambridge Structural Database (CSD) which have been processed by novel solvent removal (SAMOSA) and error analysis (MOSAEC) tools.
13 |
14 | ## Download
15 | The MOSAEC-DB files, including all publicly-available crystal structures, file management scripts, and supplemental data, can be downloaded from the [zenodo](https://doi.org/10.5281/zenodo.14780807) record.
16 |
17 | Additional scripts used in the construction and analysis of MOSAEC-DB, as well as general database use information, are available in a [GitHub](https://github.com/uowoolab/MOSAEC-DB) repository.
18 |
19 | ## Details
20 |
21 | All structures have been converted to 'P1' symmetry, and undergone solvent removal and structure validity verification using in-house codes. Check the [GitHub](https://github.com/uowoolab/MOSAEC-DB) for the links to these codes when they become available.
22 |
23 | Broadly, the solvent removal and structure validity codes employ concept of metal oxidation states and ligand formal charges to establish proper solvent removal decision-making and identify potentially problematic crystal structures.
24 |
25 | ### Directory Structure
26 |
27 | ```
28 | .
29 | ├── database
30 | │ ├── full
31 | │ ├── charged
32 | │ ├── neutral
33 | │ └── unchanged_refcodes_full.gcd
34 | │ └── partial
35 | │ ├── charged
36 | │ ├── neutral
37 | │ └── unchanged_refcodes_partial.gcd
38 | ├── database_MEPOML
39 | ├── database_REPEAT
40 | ├── descriptors
41 | │ ├── APRDF_mosaec-db.csv
42 | │ ├── GEOM_mosaec-db.csv
43 | │ ├── PHOM_mosaec-db.csv
44 | │ └── RAC_mosaec-db.csv
45 | ├── misc_data
46 | | ├── PDD_duplicate_thresh0.15.csv
47 | │ ├── unchanged_mepoml.json
48 | │ └── unchanged_repeat.json
49 | ├── scripts
50 | ├── subsets
51 | │ ├── details_sampling
52 | │ ├── diverse-neutral-*-20k.txt
53 | │ ├── diverse-charged-*-3k.txt
54 | │ ├── uniq-neutral-porous-2.4pld.txt
55 | │ └── uniq-neutral-porous-0.10vf.txt
56 | ├── mosaec-db.xlsx
57 | ├── mosaec-db.csv
58 | └── README.md
59 | ```
60 |
61 | Primary directories containing the crystal structures (.cif) are organized according to activation (i.e. full vs. partial activation) and framework charge (i.e. neutral vs. charged) states.Separate directories are provided for files containing precomputed partial atomic charges, namely those calculated via the DFT-derived REPEAT charges and the ML-predicted MEPO-ML charges.
62 |
63 | Calculated properties and information related to the structure processing can be found in the attached, identical excel worksheet (mosaec-db.xlsx) and csv (mosaec-db.csv). Additional properties will be found in the `misc_data` directory, such as a full record of the structure duplicate data.
64 |
65 | ### Scripts
66 |
67 | Subsets of MOSAEC-DB are arranged according to common conventions of porosity in prior databases, as well as a diverse sampling of several chemical and geometric descriptors (denoted as * in the directory structure). Sampling was achieved using [farthest point sampling](https://github.com/uowoolab/MOF-Diversity-Analysis/blob/main/farthest_point_sampling.py) of the desired descriptor vector. Details regarding the order in which the crystal structures are sampled are provided (subsets/sampling_details) if further sub-sampling is required.
68 |
69 | ```
70 | python get_subset.py ../subsets/______.txt
71 | ```
72 |
73 | Crystal structures that were unchanged by the database construction protocol due to their lack of solvent are outlined in corresponding text files (.gcd). Access to these structures is subject to the users' CSD license status, however the computation ready structure can be regenerated by applying the provided structure processing codes to the relevant CSD REFCODES. This script makes use of a [CSD-Cleaner](https://github.com/uowoolab/CSD-cleaner) code that requires the CSD Python API and pymatgen packages.
74 |
75 | ```
76 | python get_unchanged_mofs.py --remove_disorder
77 | ```
78 |
79 | Additionally, **experimental** functionality to regenerate the structure files containing partial atomic charges (REPEAT/MEPO-ML) is provided in these scripts. Consistency of these functions is subject to change with various versions of pymatgen and the CSD Python API, thus we cannot guarantee accuracy to the original, computed partial atomic charges. Testing was performed using Python 3.9.x, csd-python-api 3.1.0, and pymatgen 2024.5.31. Check the GitHub repository before using these scripts to ensure you are using the most up-to-date versions possible.
80 |
81 | ```
82 | python get_unchanged_mofs.py --remove_disorder --write_repeat --write_mepoml
83 | ```
84 |
85 | ## Updates
86 | Information regarding future updates and additions to the database will be outlined in the [GitHub](https://github.com/uowoolab/MOSAEC-DB/blob/main/CHANGELOG.md) repository established at the time of publication.
87 |
88 | ## Licensing
89 | The [CC BY 4.0 license](https://creativecommons.org/licenses/by/4.0/) applies to the utilization of the MOSAEC database. Follow the license guidelines regarding the use, sharing, adaptation, and attribution of this data.
90 |
91 | ## Citation
92 | Please cite the following [article](https://doi.org/10.1039/D4SC07438F) when using MOSAEC-DB.
93 |
94 | ## Contact
95 | Reach out to any of the following authors with any questions:
96 |
97 | Marco Gibaldi: marco.gibaldi@uottawa.ca
98 |
99 | Tom Woo: tom.woo@uottawa.ca
100 |
101 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # MOSAEC Database (v1.0.0-release)
2 |
3 | > [!WARNING]
4 | > ** The Database Zenodo record(s) will be taken down pending confirmation/amendments to the licensing agreement pertaining to the enclosed crystallographic data**
5 |
6 | [](https://doi.org/10.1039/D4SC07438F)
7 | 
8 | [](https://black.readthedocs.io/en/stable/)
9 |
10 |
11 | 
12 |
13 |
14 | MOSAEC-DB is a database of metal-organic framework (MOF) and coordination polymer crystallographic information files (.cif) processed for atomistic simulations.
15 |
16 | This repository collects the software applied during database construction, validation, and analysis.
17 |
18 | Additionally, this repository will provide further information regarding the use of the database and changes to the database:
19 | - [Frequently Asked Questions](FAQ.md)
20 | - [Updates](CHANGELOG.md)
21 |
22 | # Download
23 | The MOSAEC-DB files, including all publicly-available crystal structures, scripts, and supplemental data, can be downloaded from the [zenodo](https://doi.org/10.5281/zenodo.14780807) repository.
24 |
25 | # Database Construction
26 |
27 | ## Structure Retrieval & Symmetry Conversion
28 |
29 | Initial crystal structures may be retrieved directly from the Cambridge Structural Database (CSD) through the [ConQuest](https://www.ccdc.cam.ac.uk/solutions/software/conquest/) program or their provided [Python API](https://www.ccdc.cam.ac.uk/solutions/csd-core/components/csd-python-api/).
30 |
31 | Retrieved CSD crystal structures were converted to `P1` symmetry using our [CSD-Cleaner](https://github.com/uowoolab/CSD-cleaner) code.
32 |
33 | ## Solvent Removal
34 |
35 | The [SAMOSA](https://github.com/uowoolab/SAMOSA) solvent removal method was utilized in database construction. A [publication](https://doi.org/10.1021/acs.jcim.4c01897) outlining the details of this method is available. All `*_full` MOSAEC-DB structures were generated with default settings, while `*_partial` structures were generated with the `--keep_bound` option.
36 |
37 | ## Structure Error Analysis
38 |
39 | The results of the [MOSAEC](https://github.com/uowoolab/MOSAEC) error checking algorithm were used to determine whether to include a structure in MOSAEC-DB. A [preprint](https://doi.org/10.26434/chemrxiv-2024-ftsv3) article outlining the details of this method is available, and the GitHub repository will be available to the public shortly (following its publication). Only structures which passed the MOSAEC error flagging routine were included in the final database.
40 |
41 | ## Structure Validation
42 |
43 | Additional tools to check for problematic structures which may not have been caught by the structure error analyses are provided in [structure_validation](structure_validation/). This includes codes to search for overlapping and hypervalent atom sites.
44 |
45 | ## Duplicate Structure Analysis
46 |
47 | Criterion based on pointwise distance distribution (PDD) scores were applied to identify duplicated and/or highly similar crystal structures with shared empirical formulas. The codes used to complete this analysis are provided in [duplicates](duplicates/).
48 |
49 | # Descriptor Calculation
50 |
51 | ## Global Structure Features
52 |
53 | Descriptors characterizing the databases' geometric and chemical environments were generated using a number of standard libraries.
54 |
55 | The codes generating the atomic property-weighted radial distribution function ([AP-RDF](https://github.com/uowoolab/MOF-Descriptor-Codes/tree/main/AP-RDFs)) and revised autocorrelation function ([RAC](https://github.com/uowoolab/MOF-Descriptor-Codes/tree/main/RACs)) are identical to those used in the ARC-MOF database.
56 |
57 | Geometric properties were generated using the [Zeo++](http://www.zeoplusplus.org/) v0.3.0 software with default settings.
58 |
59 | Any code used to generate descriptors which were not previously made available are provided in [descriptors](descriptors/), including the atom-specific persistent homology descriptors included in the zenodo record.
60 |
61 | ## Partial Atomic Charges
62 |
63 | Electrostatic potential-derived partial atomic charges were computed for as many MOSAEC-DB structures as possible using the previously reported [REPEAT](https://doi.org/10.1021/ct9003405) method. The most recent version of this code is available at the following [repository](https://github.com/uowoolab/REPEAT).
64 |
65 | Additionally, a broader set of MOSAEC-DB were assigned ML-predicted partial atomic charges using the [MEPO-ML](https://github.com/uowoolab/MEPO-ML) models that we reported in a recent [publication](https://doi.org/10.1038/s41524-024-01413-4).
66 |
67 | ## Framework Dimensionality
68 |
69 | Each crystal structure's dimensionality was calculated using a previously reported [algorithm](https://github.com/ccdc-opensource/science-paper-mofs-2020/tree/main).
70 |
71 | ## Topology
72 |
73 | The [CrystalNets](https://github.com/coudertlab/CrystalNets.jl) package was applied to compute the net topology. A simple julia [script](descriptors/runcrystalnet.jl) was used to characterize MOSAEC-DB crystal structures.
74 |
75 | # File Management Utilities
76 |
77 | Additional utilities unrelated to the MOSAEC-DB database construction and characterization processes are also provided in the zenodo record to facilitate simple file manipulations. These tools are available in [zenodo](zenodo/) alongside descriptions of their functions below.
78 |
79 | ## Unchanged Crystal Structure Retrieval
80 |
81 | Crystal structures that were unchanged by the database construction protocol due to their lack of solvent are outlined in corresponding text files (.gcd). Access to these structures is subject to the users' CSD license status, however the computation ready structure can be regenerated by applying the provided structure processing codes to the relevant CSD REFCODES. This script makes use of a [CSD-Cleaner](https://github.com/uowoolab/CSD-cleaner) code that depends on the CSD Python API and pymatgen packages.
82 |
83 | ```
84 | python get_unchanged_mofs.py --remove_disorder
85 | ```
86 |
87 | Additionally, **experimental** functionality to regenerate the structure files containing partial atomic charges (REPEAT/MEPO-ML) is provided in these scripts. Consistency of these functions is subject to change with various versions of pymatgen and the CSD Python API, thus we cannot guarantee accuracy to the original, computed partial atomic charges. Testing was performed using Python 3.9.x, csd-python-api 3.1.0, and pymatgen 2024.5.31.
88 |
89 | ```
90 | python get_unchanged_mofs.py --remove_disorder --write_repeat --write_mepoml
91 | ```
92 |
93 | ## Subset Preparation
94 |
95 | Subsets of MOSAEC-DB are arranged according to common conventions of porosity in prior databases, as well as a diverse sampling of several chemical and geometric descriptors. Sampling was achieved using [farthest point sampling](https://github.com/uowoolab/MOF-Diversity-Analysis/blob/main/farthest_point_sampling.py) of the desired descriptor vector.
96 |
97 | ```
98 | python get_subset.py ../subsets/______.txt
99 | ```
100 |
101 | ## Updates
102 | Information regarding future updates and additions to the database will be outlined in the [GitHub](CHANGELOG.md) repository established at the time of publication.
103 |
104 | ## Licensing
105 | The [CC BY 4.0 license](https://creativecommons.org/licenses/by/4.0/) applies to the utilization of the MOSAEC database. Follow the license guidelines regarding the use, sharing, adaptation, and attribution of this data.
106 |
107 | ## Citation
108 | Please cite the following [article](https://doi.org/10.1039/D4SC07438F) when using MOSAEC-DB.
109 |
110 | ## Contact
111 | Reach out to any of the following authors with any questions:
112 |
113 | Marco Gibaldi: marco.gibaldi@uottawa.ca
114 |
115 | Tom Woo: tom.woo@uottawa.ca
116 |
117 |
--------------------------------------------------------------------------------
/zenodo/write_pac_cif.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import os
3 | import glob
4 | import json
5 | import argparse
6 | import warnings
7 |
8 | import numpy as np
9 |
10 | from datetime import date
11 | from pathlib import Path
12 | from collections import defaultdict
13 |
14 | from pymatgen.io.cif import CifParser
15 |
16 |
17 | # compare floats within a certain tolerance
18 | def floats_equal(a, b, tol=0.01):
19 | a = float(a)
20 | b = float(b)
21 | return abs(a - b) <= (min(abs(a), abs(b)) * tol)
22 |
23 |
24 | # read in partial atomic charges stored in JSON file
25 | def read_pac_json(json_name):
26 | with open(json_name, "r") as jsonr:
27 | pac_dict = json.load(jsonr)
28 | return pac_dict
29 |
30 |
31 | # iterate
32 | def assign_partial_atomic_charge(
33 | cifs_path, repeat_json, dst_path=None, pac_type="REPEAT"
34 | ):
35 | # set defaults for arguments
36 | if dst_path is None:
37 | dst_path = cifs_path.parent
38 | else:
39 | dst_path = Path(dst_path)
40 | # get saved json charge dict
41 | charge_dict = read_pac_json(repeat_json)
42 | # find all cifs to be processed
43 | cifs = glob.glob(f"{cifs_path}/*.cif", recursive=False)
44 | #
45 | for cif_path in cifs:
46 | # check if charges available in stored json
47 | if os.path.basename(cif_path) in charge_dict.keys():
48 | charge_dict_i = charge_dict[os.path.basename(cif_path)]
49 | else:
50 | print(f"{cif_path} | ERROR | {pac_type} not stored")
51 | continue
52 | # parse cif using pymatgen
53 | cif_path = Path(cif_path)
54 | with warnings.catch_warnings():
55 | warnings.simplefilter("ignore")
56 | try:
57 | cif_struct = CifParser(cif_path).get_structures(primitive=False).pop()
58 | except ValueError:
59 | print(f"{cif_path} | ERROR | EMPTY cif")
60 | continue
61 |
62 | # compare number of atoms between CIF and saved JSON
63 | # if len(cif_struct) != len(charge_dict_i):
64 | json_num_atoms = sum(
65 | [len(v) for k, v in charge_dict_i.items() if k != "rand_key"]
66 | )
67 | if len(cif_struct) != json_num_atoms:
68 | print(
69 | cif_path,
70 | " | ERROR | Different number of atoms in CIF (",
71 | len(cif_struct),
72 | ") and JSON (",
73 | json_num_atoms,
74 | ").",
75 | )
76 | continue
77 |
78 | # Get atomic symbols and fractional coordinates for all atoms
79 | symbols = [atom.specie.symbol for atom in cif_struct]
80 | frac_xyz = np.around([atom.frac_coords for atom in cif_struct], decimals=6)
81 | frac_xyz[frac_xyz == 0.0] = 0.0
82 |
83 | # Reassign labels for all atoms
84 | labels = []
85 | label_counter = {element: 0 for element in set(symbols)}
86 | for symbol in symbols:
87 | label_counter[symbol] += 1
88 | labels.append(f"{symbol}{label_counter[symbol]}")
89 |
90 | # Create preambles for the new CIF file
91 | if pac_type == "REPEAT":
92 | new_cif = "# Generated by REPEAT Assigner based on pymatgen\n"
93 | else:
94 | new_cif = "# Charges generated by MEPO-ML\n"
95 | #
96 | new_cif += f"data_{cif_path.name.replace('.cif', '')}\n"
97 | new_cif += "_audit_creation_date "
98 | new_cif += date.today().strftime("%Y-%m-%d") + "\n"
99 | #
100 | if pac_type == "REPEAT":
101 | new_cif += "_audit_creation_method REPEAT_Assigner\n"
102 | else:
103 | new_cif += "_audit_creation_method MEPO-ML\n"
104 |
105 | # Create cell info for the new CIF file
106 | new_cif += f"_cell_length_a {cif_struct.lattice.a:.6f}\n"
107 | new_cif += f"_cell_length_b {cif_struct.lattice.b:.6f}\n"
108 | new_cif += f"_cell_length_c {cif_struct.lattice.c:.6f}\n"
109 | new_cif += f"_cell_angle_alpha {cif_struct.lattice.alpha:.6f}\n"
110 | new_cif += f"_cell_angle_beta {cif_struct.lattice.beta:.6f}\n"
111 | new_cif += f"_cell_angle_gamma {cif_struct.lattice.gamma:.6f}\n"
112 | new_cif += (
113 | f"_cell_volume {cif_struct.lattice.volume:.6f}\n"
114 | )
115 |
116 | # [ASSUMED P1] Create symmetry info for the new CIF file
117 | new_cif += "_symmetry_space_group_name_H-M P1\n"
118 | new_cif += "_symmetry_Int_Tables_number 1\n"
119 | new_cif += "loop_\n"
120 | new_cif += " _symmetry_equiv_pos_site_id\n"
121 | new_cif += " _symmetry_equiv_pos_as_xyz\n"
122 | new_cif += " 1 x,y,z\n"
123 |
124 | # Create atom info for the new CIF file
125 | new_cif += "loop_\n"
126 | new_cif += " _atom_site_type_symbol\n"
127 | new_cif += " _atom_site_label\n"
128 | new_cif += " _atom_site_fract_x\n"
129 | new_cif += " _atom_site_fract_y\n"
130 | new_cif += " _atom_site_fract_z\n"
131 | new_cif += " _atom_type_partial_charge\n"
132 |
133 | # Adjust widths for the symbols and labels column
134 | symbol_width = len(max(symbols, key=len))
135 | label_width = len(max(labels, key=len))
136 |
137 | # flags to gauge if cif is consistent with prior entry
138 | # required for changes in atom ordering with different version of
139 | # dependencies e.g., pymatgen
140 |
141 | # block writing if error is encountered
142 | write_cif = True
143 | # whether the ordering of the sites/labels e.g., C1, C2, C3...
144 | # equals past ordering (potential for different CifParsing behaviour)
145 | label_order_issue = False
146 | # dict mapping the current:past cif atom labels
147 | label_mismatch = defaultdict(str)
148 | # Loop over all atoms and create info line for each of
149 | rand_num = np.array(charge_dict_i["rand_key"])
150 | # track number of matches
151 | try:
152 | match_count = 0
153 | for j, (symbol, label, frac) in enumerate(zip(symbols, labels, frac_xyz)):
154 | # prev_line = charge_dict_i[str(j)]
155 | pac_list_Z = charge_dict_i[symbol]
156 | # iterate over all sites with shared atomic symbol to find match
157 | # match_ind = None
158 | # frac_sum = sum(frac)
159 | frac_sum = sum(frac * rand_num)
160 | for k, site_dict in enumerate(pac_list_Z):
161 | # check X
162 | if not floats_equal(frac[0], site_dict["x"]):
163 | continue
164 | # check sum
165 | # if not floats_equal(frac_sum, site_dict["sum"]):
166 | if not floats_equal(frac_sum, site_dict["sum_rand"]):
167 | continue
168 | # check label
169 | if label != site_dict["label"]:
170 | label_mismatch[label] = site_dict["label"]
171 | label_order_issue = True
172 | # select index that passes all checks
173 | match_ind = k
174 | break
175 | # cleanup
176 | if match_ind != None:
177 | match_count += 1
178 | charge = pac_list_Z[match_ind]["charge"]
179 | # write line
180 | new_cif += f" {symbol:{symbol_width}} {label:{label_width}} "
181 | new_cif += "{:.6f} {:.6f} {:.6f} ".format(*frac) + f"{charge}\n"
182 | else:
183 | print(
184 | f"{cif_path} | ERROR | Did not find a matching atom site ... \n",
185 | label,
186 | )
187 | print(symbol, label, frac, frac_sum)
188 | print(pac_list_Z)
189 | write_cif = False
190 | break
191 | except Exception as e:
192 | print(f"{cif_path} | ERROR | Issue assigning Charge", e)
193 | continue
194 |
195 | if label_order_issue:
196 | print(
197 | f"{cif_path} | WARNING | Label mismatch ... \n",
198 | dict(label_mismatch),
199 | )
200 | if write_cif & (match_count == len(cif_struct)):
201 | # Write the new CIF
202 | dst_path.joinpath(
203 | cif_path.name.replace(".cif", f"_{pac_type}.cif")
204 | ).write_text(new_cif)
205 |
206 |
207 | if __name__ == "__main__":
208 | code_desc = "Assigning partial atomic charges (PAC e.g., REPEAT, MEPO-ML) to a MOSAEC-DB CIF."
209 | ap = argparse.ArgumentParser(description=code_desc)
210 | ap.add_argument("cif_path", type=str, help="path to the structure files (cif).")
211 | ap.add_argument(
212 | "-o",
213 | "--outdir",
214 | type=str,
215 | metavar="OUTPUT_DIR",
216 | help="output directory for structure files with PACs included.",
217 | )
218 | ap.add_argument(
219 | "-r",
220 | "--repeat_json",
221 | type=str,
222 | metavar="REPEAT_JSON",
223 | help="Explicitly provide the name of the REPEAT output file.",
224 | )
225 | ap.add_argument(
226 | "--pac_type",
227 | type=str,
228 | default="REPEAT",
229 | metavar="PAC_TYPE",
230 | choices=["REPEAT", "MEPOML"],
231 | )
232 | args = ap.parse_args()
233 | assign_partial_atomic_charge(args.cif, args.repeat_json, args.outdir, args.pac_type)
234 |
235 |
--------------------------------------------------------------------------------
/zenodo/clean_csd_mofs.py:
--------------------------------------------------------------------------------
1 | from ccdc import io
2 | from ccdc.io import CrystalWriter
3 | from pymatgen.symmetry.groups import sg_symbol_from_int_number, SpaceGroup
4 | from pymatgen.core import Structure, Lattice
5 | from pymatgen.core.operations import SymmOp
6 | from pymatgen.io.cif import CifWriter
7 | import argparse
8 | import os
9 | import uuid
10 | import numpy as np
11 | import shutil
12 |
13 | script_path, script_name = os.path.split(os.path.realpath(__file__))
14 | temp_cif_path = "/tmp/temp-{}.cif".format(uuid.uuid4().hex)
15 |
16 |
17 | def get_block(cif_lines, keyword, start):
18 | """
19 | Separate a cif into blocks based on "loop_" sections.
20 |
21 | Parameters:
22 | cif_lines (list of str): list of lines in cif file
23 | keyword (str): keyword identifying block (e.g., "atom" for atoms
24 | "symmetry" for symmetry operations, "geom" for geometry
25 | (bonding) information, etc.)
26 | start (int): the line number of beginning of block (line after "loop_")
27 |
28 | Returns:
29 | block (list of str): list of lines in the "block" from the cif
30 | """
31 |
32 | for num, line in enumerate(cif_lines[start:]):
33 | if (
34 | line[0] == "_"
35 | and not line.strip("\n").split("_", maxsplit=1)[1].startswith(keyword)
36 | or "loop_" in line
37 | ):
38 | end = num + start
39 | break
40 | try:
41 | block = cif_lines[start:end]
42 | except UnboundLocalError:
43 | block = cif_lines[start:]
44 | # Remove any "loop_" lines
45 | block = [val for val in block if val != "loop_\n"]
46 |
47 | return block
48 |
49 |
50 | def get_dict(lst, good_atoms, label_key):
51 | """
52 | Get a dictionary of structural attributes of a cif containing only certain
53 | atoms. For example, to get a dictionary of atoms and their coordinates for only
54 | a certain list of atoms. This works given a list of lines from a "block" in a cif
55 | (identified by the "loop_" sections)
56 |
57 | Parameters:
58 | lst (list of str): List of lines to consider for dictionary
59 | good_atoms (list of str): Atom labels to consider for dictionary
60 | label_key (str): the header which will be used as the keys of the dict
61 | (e.g., for atom labels use _atom_site_label)
62 |
63 | Returns:
64 | dict (dict): Dictionary of specified keys and attributes (properties)
65 | (properties are the remaining headers in the "loop_" section)
66 | """
67 |
68 | dict = {}
69 | for num, line in enumerate(lst):
70 | if line[0] == "_":
71 | dict[line.strip().strip("\n")] = []
72 | for num, line in enumerate(lst):
73 | if line[0] != "_":
74 | line = line.strip().replace("(", "").replace(")", "").split()
75 | if line[list(dict.keys()).index(label_key)] in good_atoms:
76 | for n, prop in enumerate(dict.keys()):
77 | dict[prop].append(line[n])
78 |
79 | return dict
80 |
81 |
82 | def get_asymmetric_unit(ref, is_cif=False):
83 | """
84 | Retrieve a cif from the CSD and return the
85 | asymmetric unit molecule atoms. Also, write the crystal to a
86 | temporary cif to get atomic coordinates of the crystal
87 | (no way to do this with CSD). If is_cif is True, do not
88 | retrieve the structure from CSD, just read the specified cif.
89 |
90 | Parameters:
91 | ref (str): the CSD refcode for the structure (or cif filename if
92 | is_cif is equal to True)
93 | Returns:
94 | atoms (list of str): the atom labels of the asymmetric unit molecule
95 |
96 | """
97 | if is_cif:
98 | cryst = io.CrystalReader(ref)[0]
99 | else:
100 | csd_reader = io.EntryReader("CSD")
101 | cryst = csd_reader.entry(ref).crystal
102 | cryst.centre_molecule()
103 | mol = cryst.asymmetric_unit_molecule
104 | atoms = [str(atom).replace("Atom(", "").strip(")") for atom in mol.atoms]
105 | with CrystalWriter(temp_cif_path) as mol_writer:
106 | mol_writer.write(cryst)
107 |
108 | return atoms
109 |
110 |
111 | def convert_to_p1(ops, asym_unit_atoms, asym_unit_coords):
112 | """
113 | From a list of symmetry operations in string format and a list of atoms and
114 | their coordinates, generate a full unit cell in P1 symmetry.
115 |
116 | Parameters:
117 | ops (list of str): list
118 | asym_unit_atoms (list of str): list of elements in asymmetric unit
119 | asym_unit_coords (list of float): list of fractional coordinates of
120 | atoms in asymmetric unit
121 |
122 | Returns:
123 | new_species (list of str): species in the full unit cell
124 | new_coords (numpy array): array of fractional coordinates
125 | of atoms in full unit cell
126 |
127 | """
128 |
129 | op_matrices = []
130 | unit_cell_atoms = []
131 | unit_cell_coords = []
132 | # Need to apply symmetry operations specified in cif manually,
133 | # space group isn't good enough
134 | a = np.zeros((4, 4), dtype=np.float32)
135 | # Need to instantiate SymmOp class with some 4x4 affine matrix to
136 | # use from_xyz_string function
137 | sym_op_obj = SymmOp(a)
138 | for op in ops:
139 | op_matrices.append(sym_op_obj.from_xyz_string(op).affine_matrix)
140 |
141 | for num, atom in enumerate(asym_unit_atoms):
142 | for op in op_matrices:
143 | unit_cell_coords.append(op @ asym_unit_coords[num])
144 | unit_cell_atoms.append(atom)
145 |
146 | unit_cell_coords = np.asarray(unit_cell_coords)
147 | unit_cell_coords = unit_cell_coords[:, :-1]
148 |
149 | return unit_cell_atoms, unit_cell_coords
150 |
151 |
152 | def remove_duplicate_atoms(pm_struct):
153 | """
154 | Remove atoms which have identical fractional coordinates.
155 |
156 | Parameters:
157 | pm_struct (Pymatgen Structure object): structure from which
158 | to remove duplicates
159 | Returns:
160 | pm_struct (Pymatgen Structure object): structure with duplicates
161 | removed
162 | """
163 |
164 | coords_check = []
165 | bad_indices = []
166 |
167 | for atom in pm_struct:
168 | if any(np.round(atom.frac_coords, 2) == 1):
169 | for x in range(3):
170 | if round(atom.frac_coords[x], 2) == 1:
171 | atom.frac_coords[x] = 0
172 |
173 | for num, atom in enumerate(pm_struct):
174 | for coord in coords_check:
175 | if all(np.round(coord, 2) == np.round(atom.frac_coords, 2)):
176 | bad_indices.append(num)
177 | else:
178 | coords_check.append(atom.frac_coords)
179 |
180 | pm_struct.remove_sites(bad_indices)
181 |
182 | return pm_struct
183 |
184 |
185 | def csd_to_pymatgen(path, atoms):
186 | """
187 | Manually parse a CSD cif to generate a pymatgen structure which contains
188 | only a list of atoms specified (in this case, the asymmetric unit). This
189 | function returns a Pymatgen structure which is in P1 symmetry by applying
190 | the symmetry operations found in the cif.
191 |
192 | Parameters:
193 | path (str): path to the cif file
194 | atoms (list): list of the atoms in the asymmetric unit
195 |
196 | Returns:
197 | struct (Pymatgen Structure object): Structure in P1 symmetry
198 | """
199 | with open(path) as f:
200 | cif = f.readlines()
201 | f.close()
202 |
203 | blocks = {"symmetry": None, "atom_site": None, "geom": None}
204 |
205 | for num, line in enumerate(cif):
206 | if "loop_" in line:
207 | for block in blocks.keys():
208 | test_header = cif[num + 1].strip().split("_", maxsplit=1)[1]
209 | # Found some cases with anisotropic info with same prefix
210 | # ignore these for now...
211 | if test_header.startswith(block):
212 | if block == "atom_site" and test_header.startswith(
213 | "atom_site_aniso"
214 | ):
215 | pass
216 | else:
217 | blocks[block] = get_block(cif, block, num + 1)
218 | elif "_symmetry_space_group_name_H-M" in line:
219 | space_group_name_HM = line.strip().split()[-1]
220 | elif "_symmetry_Int_Tables_number" in line:
221 | int_tables_num = line.strip().split()[-1]
222 | elif "_space_group_name_Hall" in line:
223 | space_group_name_hall = line.strip().split()[-1]
224 | elif "cell_length_a" in line:
225 | cell_length_a = float(
226 | line.strip().replace("(", "").replace(")", "").split()[-1]
227 | )
228 | elif "cell_length_b" in line:
229 | cell_length_b = float(
230 | line.strip().replace("(", "").replace(")", "").split()[-1]
231 | )
232 | elif "cell_length_c" in line:
233 | cell_length_c = float(
234 | line.strip().replace("(", "").replace(")", "").split()[-1]
235 | )
236 | elif "cell_angle_alpha" in line:
237 | cell_angle_alpha = float(
238 | line.strip().replace("(", "").replace(")", "").split()[-1]
239 | )
240 | elif "cell_angle_beta" in line:
241 | cell_angle_beta = float(
242 | line.strip().replace("(", "").replace(")", "").split()[-1]
243 | )
244 | elif "cell_angle_gamma" in line:
245 | cell_angle_gamma = float(
246 | line.strip().replace("(", "").replace(")", "").split()[-1]
247 | )
248 | num_cols = 0
249 | atom_dict = {}
250 | coords = []
251 |
252 | atom_dict = get_dict(blocks["atom_site"], atoms, "_atom_site_label")
253 | # Need to have 4th dimension (value of 1) for matrix multiplication
254 | # when applying the symmetry operations. The extra dimension
255 | # is removed later by the covert_to_p1 function
256 | for x, y, z in zip(
257 | atom_dict["_atom_site_fract_x"],
258 | atom_dict["_atom_site_fract_y"],
259 | atom_dict["_atom_site_fract_z"],
260 | ):
261 | coords.append([float(x), float(y), float(z), 1])
262 |
263 | species = atom_dict["_atom_site_type_symbol"]
264 | sg = SpaceGroup.from_int_number(int(int_tables_num))
265 | # Get only the operations (not headers) from the Symmetry block
266 | sym_ops = [val for val in blocks["symmetry"] if val[0] != "_"]
267 | # Get rid of any numbering "e.g., 1 x,y,z" from the symmetry operations
268 | for i in range(len(sym_ops)):
269 | sym_ops[i] = ",".join(
270 | [val.split()[-1] for val in sym_ops[i].strip().split(",")]
271 | )
272 |
273 | species, coords = convert_to_p1(sym_ops, species, coords)
274 |
275 | lattice = Lattice.from_parameters(
276 | a=cell_length_a,
277 | b=cell_length_b,
278 | c=cell_length_c,
279 | alpha=cell_angle_alpha,
280 | beta=cell_angle_beta,
281 | gamma=cell_angle_gamma,
282 | )
283 | struct = Structure(
284 | lattice=lattice, species=species, coords=coords, to_unit_cell=True
285 | )
286 | # Need to remove duplicates since some atoms lie on
287 | # boundaries when converted to P1
288 | struct = remove_duplicate_atoms(struct)
289 |
290 | return struct
291 |
292 |
293 | def main(write_path, read_path=None, tmp_path=None, input_is_cif=False):
294 | """
295 | Get the asymmetric unit of a CSD structure and convert it to a Pymatgen
296 | Structure object in P1 symmetry. Then, write the cif to a specified path.
297 |
298 | Parameters:
299 | read_path (str): Path to read the cif from (used if inp_is_cif)
300 | write_path (str): Path to write the cif
301 | tmp_path (str): Path to write the temporary cif for debugging
302 |
303 | Returns:
304 | mof_p1 (Pymatgen Structure object): MOF in P1 symmetry
305 | """
306 |
307 | if input_is_cif:
308 | ref = read_path.rsplit("_P1.cif", 1)[0]
309 | ref = f"{ref}.cif"
310 | else:
311 | ref = write_path.split("/")[-1].rsplit("_P1.cif", 1)[0]
312 | asymmetric_unit_atoms = get_asymmetric_unit(ref, input_is_cif)
313 | if tmp_path is not None:
314 | shutil.copyfile(temp_cif_path, tmp_path)
315 | mof_p1 = csd_to_pymatgen(temp_cif_path, asymmetric_unit_atoms)
316 | os.remove(temp_cif_path)
317 | CifWriter(mof_p1).write_file(write_path)
318 |
319 | return mof_p1
320 |
321 |
322 | if __name__ == "__main__":
323 | parser = argparse.ArgumentParser(
324 | description="Retrieve crystal structure from the CSD,"
325 | + "and convert it to P1 symmetry."
326 | )
327 | parser.add_argument("refcode", metavar="r", type=str, help="CSD Refcode of the MOF")
328 | parser.add_argument(
329 | "--write_dir",
330 | type=str,
331 | default=os.getcwd(),
332 | help="Directory to write the cif." + " Defaults to current working directory.",
333 | )
334 | parser.add_argument(
335 | "--read_dir",
336 | type=str,
337 | default=os.getcwd(),
338 | help="Directory of where the cif is located",
339 | )
340 | parser.add_argument(
341 | "-d",
342 | action="store_true",
343 | help="If this flag is present, " + " keep the temporary CSD cif.",
344 | )
345 | parser.add_argument(
346 | "-inp_is_cif",
347 | action="store_true",
348 | help="If this flag is present, " + " the input is a cif file.",
349 | )
350 |
351 | args = parser.parse_args()
352 | refcode = args.refcode
353 | write_dir = args.write_dir
354 | inp_is_cif = args.inp_is_cif
355 | if inp_is_cif:
356 | refcode = refcode.split(".cif")[0]
357 | read_path = "{}/{}".format(args.read_dir, refcode)
358 | final_cif_path = "{}/{}_P1.cif".format(write_dir, refcode)
359 | if args.d:
360 | main(
361 | final_cif_path,
362 | tmp_path="{}/{}_original.cif".format(write_dir, refcode),
363 | input_is_cif=inp_is_cif,
364 | )
365 | else:
366 | if inp_is_cif:
367 | main(final_cif_path, read_path=read_path, input_is_cif=inp_is_cif)
368 | else:
369 | main(final_cif_path, input_is_cif=inp_is_cif)
370 |
371 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Attribution 4.0 International
2 |
3 | =======================================================================
4 |
5 | Creative Commons Corporation ("Creative Commons") is not a law firm and
6 | does not provide legal services or legal advice. Distribution of
7 | Creative Commons public licenses does not create a lawyer-client or
8 | other relationship. Creative Commons makes its licenses and related
9 | information available on an "as-is" basis. Creative Commons gives no
10 | warranties regarding its licenses, any material licensed under their
11 | terms and conditions, or any related information. Creative Commons
12 | disclaims all liability for damages resulting from their use to the
13 | fullest extent possible.
14 |
15 | Using Creative Commons Public Licenses
16 |
17 | Creative Commons public licenses provide a standard set of terms and
18 | conditions that creators and other rights holders may use to share
19 | original works of authorship and other material subject to copyright
20 | and certain other rights specified in the public license below. The
21 | following considerations are for informational purposes only, are not
22 | exhaustive, and do not form part of our licenses.
23 |
24 | Considerations for licensors: Our public licenses are
25 | intended for use by those authorized to give the public
26 | permission to use material in ways otherwise restricted by
27 | copyright and certain other rights. Our licenses are
28 | irrevocable. Licensors should read and understand the terms
29 | and conditions of the license they choose before applying it.
30 | Licensors should also secure all rights necessary before
31 | applying our licenses so that the public can reuse the
32 | material as expected. Licensors should clearly mark any
33 | material not subject to the license. This includes other CC-
34 | licensed material, or material used under an exception or
35 | limitation to copyright. More considerations for licensors:
36 | wiki.creativecommons.org/Considerations_for_licensors
37 |
38 | Considerations for the public: By using one of our public
39 | licenses, a licensor grants the public permission to use the
40 | licensed material under specified terms and conditions. If
41 | the licensor's permission is not necessary for any reason--for
42 | example, because of any applicable exception or limitation to
43 | copyright--then that use is not regulated by the license. Our
44 | licenses grant only permissions under copyright and certain
45 | other rights that a licensor has authority to grant. Use of
46 | the licensed material may still be restricted for other
47 | reasons, including because others have copyright or other
48 | rights in the material. A licensor may make special requests,
49 | such as asking that all changes be marked or described.
50 | Although not required by our licenses, you are encouraged to
51 | respect those requests where reasonable. More considerations
52 | for the public:
53 | wiki.creativecommons.org/Considerations_for_licensees
54 |
55 | =======================================================================
56 |
57 | Creative Commons Attribution 4.0 International Public License
58 |
59 | By exercising the Licensed Rights (defined below), You accept and agree
60 | to be bound by the terms and conditions of this Creative Commons
61 | Attribution 4.0 International Public License ("Public License"). To the
62 | extent this Public License may be interpreted as a contract, You are
63 | granted the Licensed Rights in consideration of Your acceptance of
64 | these terms and conditions, and the Licensor grants You such rights in
65 | consideration of benefits the Licensor receives from making the
66 | Licensed Material available under these terms and conditions.
67 |
68 |
69 | Section 1 -- Definitions.
70 |
71 | a. Adapted Material means material subject to Copyright and Similar
72 | Rights that is derived from or based upon the Licensed Material
73 | and in which the Licensed Material is translated, altered,
74 | arranged, transformed, or otherwise modified in a manner requiring
75 | permission under the Copyright and Similar Rights held by the
76 | Licensor. For purposes of this Public License, where the Licensed
77 | Material is a musical work, performance, or sound recording,
78 | Adapted Material is always produced where the Licensed Material is
79 | synched in timed relation with a moving image.
80 |
81 | b. Adapter's License means the license You apply to Your Copyright
82 | and Similar Rights in Your contributions to Adapted Material in
83 | accordance with the terms and conditions of this Public License.
84 |
85 | c. Copyright and Similar Rights means copyright and/or similar rights
86 | closely related to copyright including, without limitation,
87 | performance, broadcast, sound recording, and Sui Generis Database
88 | Rights, without regard to how the rights are labeled or
89 | categorized. For purposes of this Public License, the rights
90 | specified in Section 2(b)(1)-(2) are not Copyright and Similar
91 | Rights.
92 |
93 | d. Effective Technological Measures means those measures that, in the
94 | absence of proper authority, may not be circumvented under laws
95 | fulfilling obligations under Article 11 of the WIPO Copyright
96 | Treaty adopted on December 20, 1996, and/or similar international
97 | agreements.
98 |
99 | e. Exceptions and Limitations means fair use, fair dealing, and/or
100 | any other exception or limitation to Copyright and Similar Rights
101 | that applies to Your use of the Licensed Material.
102 |
103 | f. Licensed Material means the artistic or literary work, database,
104 | or other material to which the Licensor applied this Public
105 | License.
106 |
107 | g. Licensed Rights means the rights granted to You subject to the
108 | terms and conditions of this Public License, which are limited to
109 | all Copyright and Similar Rights that apply to Your use of the
110 | Licensed Material and that the Licensor has authority to license.
111 |
112 | h. Licensor means the individual(s) or entity(ies) granting rights
113 | under this Public License.
114 |
115 | i. Share means to provide material to the public by any means or
116 | process that requires permission under the Licensed Rights, such
117 | as reproduction, public display, public performance, distribution,
118 | dissemination, communication, or importation, and to make material
119 | available to the public including in ways that members of the
120 | public may access the material from a place and at a time
121 | individually chosen by them.
122 |
123 | j. Sui Generis Database Rights means rights other than copyright
124 | resulting from Directive 96/9/EC of the European Parliament and of
125 | the Council of 11 March 1996 on the legal protection of databases,
126 | as amended and/or succeeded, as well as other essentially
127 | equivalent rights anywhere in the world.
128 |
129 | k. You means the individual or entity exercising the Licensed Rights
130 | under this Public License. Your has a corresponding meaning.
131 |
132 |
133 | Section 2 -- Scope.
134 |
135 | a. License grant.
136 |
137 | 1. Subject to the terms and conditions of this Public License,
138 | the Licensor hereby grants You a worldwide, royalty-free,
139 | non-sublicensable, non-exclusive, irrevocable license to
140 | exercise the Licensed Rights in the Licensed Material to:
141 |
142 | a. reproduce and Share the Licensed Material, in whole or
143 | in part; and
144 |
145 | b. produce, reproduce, and Share Adapted Material.
146 |
147 | 2. Exceptions and Limitations. For the avoidance of doubt, where
148 | Exceptions and Limitations apply to Your use, this Public
149 | License does not apply, and You do not need to comply with
150 | its terms and conditions.
151 |
152 | 3. Term. The term of this Public License is specified in Section
153 | 6(a).
154 |
155 | 4. Media and formats; technical modifications allowed. The
156 | Licensor authorizes You to exercise the Licensed Rights in
157 | all media and formats whether now known or hereafter created,
158 | and to make technical modifications necessary to do so. The
159 | Licensor waives and/or agrees not to assert any right or
160 | authority to forbid You from making technical modifications
161 | necessary to exercise the Licensed Rights, including
162 | technical modifications necessary to circumvent Effective
163 | Technological Measures. For purposes of this Public License,
164 | simply making modifications authorized by this Section 2(a)
165 | (4) never produces Adapted Material.
166 |
167 | 5. Downstream recipients.
168 |
169 | a. Offer from the Licensor -- Licensed Material. Every
170 | recipient of the Licensed Material automatically
171 | receives an offer from the Licensor to exercise the
172 | Licensed Rights under the terms and conditions of this
173 | Public License.
174 |
175 | b. No downstream restrictions. You may not offer or impose
176 | any additional or different terms or conditions on, or
177 | apply any Effective Technological Measures to, the
178 | Licensed Material if doing so restricts exercise of the
179 | Licensed Rights by any recipient of the Licensed
180 | Material.
181 |
182 | 6. No endorsement. Nothing in this Public License constitutes or
183 | may be construed as permission to assert or imply that You
184 | are, or that Your use of the Licensed Material is, connected
185 | with, or sponsored, endorsed, or granted official status by,
186 | the Licensor or others designated to receive attribution as
187 | provided in Section 3(a)(1)(A)(i).
188 |
189 | b. Other rights.
190 |
191 | 1. Moral rights, such as the right of integrity, are not
192 | licensed under this Public License, nor are publicity,
193 | privacy, and/or other similar personality rights; however, to
194 | the extent possible, the Licensor waives and/or agrees not to
195 | assert any such rights held by the Licensor to the limited
196 | extent necessary to allow You to exercise the Licensed
197 | Rights, but not otherwise.
198 |
199 | 2. Patent and trademark rights are not licensed under this
200 | Public License.
201 |
202 | 3. To the extent possible, the Licensor waives any right to
203 | collect royalties from You for the exercise of the Licensed
204 | Rights, whether directly or through a collecting society
205 | under any voluntary or waivable statutory or compulsory
206 | licensing scheme. In all other cases the Licensor expressly
207 | reserves any right to collect such royalties.
208 |
209 |
210 | Section 3 -- License Conditions.
211 |
212 | Your exercise of the Licensed Rights is expressly made subject to the
213 | following conditions.
214 |
215 | a. Attribution.
216 |
217 | 1. If You Share the Licensed Material (including in modified
218 | form), You must:
219 |
220 | a. retain the following if it is supplied by the Licensor
221 | with the Licensed Material:
222 |
223 | i. identification of the creator(s) of the Licensed
224 | Material and any others designated to receive
225 | attribution, in any reasonable manner requested by
226 | the Licensor (including by pseudonym if
227 | designated);
228 |
229 | ii. a copyright notice;
230 |
231 | iii. a notice that refers to this Public License;
232 |
233 | iv. a notice that refers to the disclaimer of
234 | warranties;
235 |
236 | v. a URI or hyperlink to the Licensed Material to the
237 | extent reasonably practicable;
238 |
239 | b. indicate if You modified the Licensed Material and
240 | retain an indication of any previous modifications; and
241 |
242 | c. indicate the Licensed Material is licensed under this
243 | Public License, and include the text of, or the URI or
244 | hyperlink to, this Public License.
245 |
246 | 2. You may satisfy the conditions in Section 3(a)(1) in any
247 | reasonable manner based on the medium, means, and context in
248 | which You Share the Licensed Material. For example, it may be
249 | reasonable to satisfy the conditions by providing a URI or
250 | hyperlink to a resource that includes the required
251 | information.
252 |
253 | 3. If requested by the Licensor, You must remove any of the
254 | information required by Section 3(a)(1)(A) to the extent
255 | reasonably practicable.
256 |
257 | 4. If You Share Adapted Material You produce, the Adapter's
258 | License You apply must not prevent recipients of the Adapted
259 | Material from complying with this Public License.
260 |
261 |
262 | Section 4 -- Sui Generis Database Rights.
263 |
264 | Where the Licensed Rights include Sui Generis Database Rights that
265 | apply to Your use of the Licensed Material:
266 |
267 | a. for the avoidance of doubt, Section 2(a)(1) grants You the right
268 | to extract, reuse, reproduce, and Share all or a substantial
269 | portion of the contents of the database;
270 |
271 | b. if You include all or a substantial portion of the database
272 | contents in a database in which You have Sui Generis Database
273 | Rights, then the database in which You have Sui Generis Database
274 | Rights (but not its individual contents) is Adapted Material; and
275 |
276 | c. You must comply with the conditions in Section 3(a) if You Share
277 | all or a substantial portion of the contents of the database.
278 |
279 | For the avoidance of doubt, this Section 4 supplements and does not
280 | replace Your obligations under this Public License where the Licensed
281 | Rights include other Copyright and Similar Rights.
282 |
283 |
284 | Section 5 -- Disclaimer of Warranties and Limitation of Liability.
285 |
286 | a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
287 | EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
288 | AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
289 | ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
290 | IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
291 | WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
292 | PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
293 | ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
294 | KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
295 | ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
296 |
297 | b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
298 | TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
299 | NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
300 | INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
301 | COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
302 | USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
303 | ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
304 | DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
305 | IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
306 |
307 | c. The disclaimer of warranties and limitation of liability provided
308 | above shall be interpreted in a manner that, to the extent
309 | possible, most closely approximates an absolute disclaimer and
310 | waiver of all liability.
311 |
312 |
313 | Section 6 -- Term and Termination.
314 |
315 | a. This Public License applies for the term of the Copyright and
316 | Similar Rights licensed here. However, if You fail to comply with
317 | this Public License, then Your rights under this Public License
318 | terminate automatically.
319 |
320 | b. Where Your right to use the Licensed Material has terminated under
321 | Section 6(a), it reinstates:
322 |
323 | 1. automatically as of the date the violation is cured, provided
324 | it is cured within 30 days of Your discovery of the
325 | violation; or
326 |
327 | 2. upon express reinstatement by the Licensor.
328 |
329 | For the avoidance of doubt, this Section 6(b) does not affect any
330 | right the Licensor may have to seek remedies for Your violations
331 | of this Public License.
332 |
333 | c. For the avoidance of doubt, the Licensor may also offer the
334 | Licensed Material under separate terms or conditions or stop
335 | distributing the Licensed Material at any time; however, doing so
336 | will not terminate this Public License.
337 |
338 | d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
339 | License.
340 |
341 |
342 | Section 7 -- Other Terms and Conditions.
343 |
344 | a. The Licensor shall not be bound by any additional or different
345 | terms or conditions communicated by You unless expressly agreed.
346 |
347 | b. Any arrangements, understandings, or agreements regarding the
348 | Licensed Material not stated herein are separate from and
349 | independent of the terms and conditions of this Public License.
350 |
351 |
352 | Section 8 -- Interpretation.
353 |
354 | a. For the avoidance of doubt, this Public License does not, and
355 | shall not be interpreted to, reduce, limit, restrict, or impose
356 | conditions on any use of the Licensed Material that could lawfully
357 | be made without permission under this Public License.
358 |
359 | b. To the extent possible, if any provision of this Public License is
360 | deemed unenforceable, it shall be automatically reformed to the
361 | minimum extent necessary to make it enforceable. If the provision
362 | cannot be reformed, it shall be severed from this Public License
363 | without affecting the enforceability of the remaining terms and
364 | conditions.
365 |
366 | c. No term or condition of this Public License will be waived and no
367 | failure to comply consented to unless expressly agreed to by the
368 | Licensor.
369 |
370 | d. Nothing in this Public License constitutes or may be interpreted
371 | as a limitation upon, or waiver of, any privileges and immunities
372 | that apply to the Licensor or You, including from the legal
373 | processes of any jurisdiction or authority.
374 |
375 |
376 | =======================================================================
377 |
378 | Creative Commons is not a party to its public
379 | licenses. Notwithstanding, Creative Commons may elect to apply one of
380 | its public licenses to material it publishes and in those instances
381 | will be considered the “Licensor.” The text of the Creative Commons
382 | public licenses is dedicated to the public domain under the CC0 Public
383 | Domain Dedication. Except for the limited purpose of indicating that
384 | material is shared under a Creative Commons public license or as
385 | otherwise permitted by the Creative Commons policies published at
386 | creativecommons.org/policies, Creative Commons does not authorize the
387 | use of the trademark "Creative Commons" or any other trademark or logo
388 | of Creative Commons without its prior written consent including,
389 | without limitation, in connection with any unauthorized modifications
390 | to any of its public licenses or any other arrangements,
391 | understandings, or agreements concerning use of licensed material. For
392 | the avoidance of doubt, this paragraph does not form part of the
393 | public licenses.
394 |
395 | Creative Commons may be contacted at creativecommons.org.
396 |
397 |
--------------------------------------------------------------------------------