Merge pull request #14 from Kolaru/read_geometry

Add example of using the package to read geometry from a CIF file.

examples/parse_geometry/7706719.cif

@@ -0,0 +1,285 @@
+#------------------------------------------------------------------------------
+#$Date: 2021-04-05 17:55:09 +0300 (Mon, 05 Apr 2021) $
+#$Revision: 263781 $
+#$URL: file:///home/coder/svn-repositories/cod/cif/7/70/67/7706719.cif $
+#------------------------------------------------------------------------------
+#
+# This file is available in the Crystallography Open Database (COD),
+# http://www.crystallography.net/
+#
+# All data on this site have been placed in the public domain by the
+# contributors.
+#
+data_7706719
+loop_
+_publ_author_name
+'Awwadi, Firas F.'
+'Alwahsh, Manal I.'
+'Turnbull, Mark M.'
+'Landee, Christopher P.'
+'Twamley, Brendan'
+_publ_section_title
+;
+ Two new canted antiferromagnetic systems: magnetic, theoretical, and
+ crystallographic studies on trans-bis(2-iodopyridine)dihalocopper(ii).
+;
+_journal_issue                   12
+_journal_name_full
+'Dalton transactions (Cambridge, England : 2003)'
+_journal_page_first              4167
+_journal_page_last               4178
+_journal_paper_doi               10.1039/d0dt04071a
+_journal_volume                  50
+_journal_year                    2021
+_chemical_formula_sum            'C10 H8 Br2 Cu I2 N2'
+_chemical_formula_weight         633.34
+_space_group_IT_number           15
+_space_group_name_Hall           '-C 2yc'
+_space_group_name_H-M_alt        'C 1 2/c 1'
+_symmetry_cell_setting           monoclinic
+_symmetry_space_group_name_H-M   'C 1 2/c 1'
+_atom_sites_solution_hydrogens   geom
+_atom_sites_solution_primary     direct
+_atom_sites_solution_secondary   difmap
+_audit_creation_method           'CrysAlisPro 1.171.38.46 (Rigaku OD, 2015)'
+_audit_update_record
+;
+2020-10-10 deposited with the CCDC.	2021-03-01 downloaded from the CCDC.
+;
+_cell_angle_alpha                90.00
+_cell_angle_beta                 108.162(7)
+_cell_angle_gamma                90.00
+_cell_formula_units_Z            4
+_cell_length_a                   15.5605(10)
+_cell_length_b                   7.9626(4)
+_cell_length_c                   12.9489(7)
+_cell_measurement_reflns_used    1246
+_cell_measurement_temperature    293(2)
+_cell_measurement_theta_max      29.0240
+_cell_measurement_theta_min      3.6100
+_cell_volume                     1524.46(16)
+_computing_cell_refinement       'CrysAlisPro 1.171.38.46 (Rigaku OD, 2015)'
+_computing_data_collection       'CrysAlisPro 1.171.38.46 (Rigaku OD, 2015)'
+_computing_data_reduction        'CrysAlisPro 1.171.38.46 (Rigaku OD, 2015)'
+_computing_molecular_graphics    'shelxtl, Bruker,2002'
+_computing_publication_material  'shelxtl, Bruker,2002'
+_computing_structure_refinement  'shelxtl, Bruker,2002'
+_computing_structure_solution    'shelxtl, Bruker,2002'
+_diffrn_ambient_temperature      293(2)
+_diffrn_detector_area_resol_mean 16.0534
+_diffrn_measured_fraction_theta_full 0.998
+_diffrn_measured_fraction_theta_max 0.998
+_diffrn_measurement_device_type  'Xcalibur, Eos'
+_diffrn_measurement_method       '\w scans'
+_diffrn_radiation_monochromator  graphite
+_diffrn_radiation_source         'fine-focus sealed tube'
+_diffrn_radiation_type           MoK\a
+_diffrn_radiation_wavelength     0.71073
+_diffrn_reflns_av_R_equivalents  0.0223
+_diffrn_reflns_av_sigmaI/netI    0.0358
+_diffrn_reflns_limit_h_max       18
+_diffrn_reflns_limit_h_min       -19
+_diffrn_reflns_limit_k_max       9
+_diffrn_reflns_limit_k_min       -9
+_diffrn_reflns_limit_l_max       10
+_diffrn_reflns_limit_l_min       -16
+_diffrn_reflns_number            3023
+_diffrn_reflns_theta_full        26.30
+_diffrn_reflns_theta_max         26.30
+_diffrn_reflns_theta_min         3.31
+_exptl_absorpt_coefficient_mu    10.705
+_exptl_absorpt_correction_T_max  1.00000
+_exptl_absorpt_correction_T_min  0.47314
+_exptl_absorpt_correction_type   multi-scan
+_exptl_absorpt_process_details
+;
+CrysAlisPro 1.171.38.46 (Rigaku Oxford Diffraction, 2015)
+Empirical absorption correction using spherical harmonics,
+ implemented in SCALE3 ABSPACK scaling algorithm.
+;
+_exptl_crystal_colour            green
+_exptl_crystal_density_diffrn    2.760
+_exptl_crystal_density_method    'not measured'
+_exptl_crystal_description       parallelepiped
+_exptl_crystal_F_000             1148
+_exptl_crystal_preparation       'Magnetic properties'
+_exptl_crystal_size_max          0.25
+_exptl_crystal_size_mid          0.15
+_exptl_crystal_size_min          0.10
+_refine_diff_density_max         0.559
+_refine_diff_density_min         -0.944
+_refine_diff_density_rms         0.186
+_refine_ls_extinction_method     none
+_refine_ls_goodness_of_fit_ref   1.036
+_refine_ls_hydrogen_treatment    constra
+_refine_ls_matrix_type           full
+_refine_ls_number_parameters     79
+_refine_ls_number_reflns         1538
+_refine_ls_number_restraints     0
+_refine_ls_restrained_S_all      1.036
+_refine_ls_R_factor_all          0.0396
+_refine_ls_R_factor_gt           0.0320
+_refine_ls_shift/su_max          0.000
+_refine_ls_shift/su_mean         0.000
+_refine_ls_structure_factor_coef Fsqd
+_refine_ls_weighting_details
+'calc w=1/[\s^2^(Fo^2^)+(0.0370P)^2^+0.0000P] where P=(Fo^2^+2Fc^2^)/3'
+_refine_ls_weighting_scheme      calc
+_refine_ls_wR_factor_gt          0.0706
+_refine_ls_wR_factor_ref         0.0745
+_reflns_number_gt                1314
+_reflns_number_total             1538
+_reflns_threshold_expression     >2sigma(I)
+_cod_data_source_file            d0dt04071a2.cif
+_cod_data_source_block           exp_2198
+_cod_depositor_comments
+'Adding full bibliography for 7706719--7706724.cif.'
+_cod_original_cell_volume        1524.46(15)
+_cod_database_code               7706719
+loop_
+_symmetry_equiv_pos_as_xyz
+'x, y, z'
+'-x, y, -z+1/2'
+'x+1/2, y+1/2, z'
+'-x+1/2, y+1/2, -z+1/2'
+'-x, -y, -z'
+'x, -y, z-1/2'
+'-x+1/2, -y+1/2, -z'
+'x+1/2, -y+1/2, z-1/2'
+loop_
+_atom_site_label
+_atom_site_type_symbol
+_atom_site_fract_x
+_atom_site_fract_y
+_atom_site_fract_z
+_atom_site_U_iso_or_equiv
+_atom_site_adp_type
+_atom_site_occupancy
+_atom_site_symmetry_multiplicity
+_atom_site_calc_flag
+_atom_site_refinement_flags
+_atom_site_disorder_assembly
+_atom_site_disorder_group
+I1 I 0.14259(3) 0.80733(5) 0.69013(3) 0.04124(15) Uani 1 1 d . . .
+Cu1 Cu 0.2500 0.7500 0.5000 0.0245(2) Uani 1 2 d S . .
+Br1 Br 0.12243(3) 0.85448(7) 0.35677(4) 0.03650(17) Uani 1 1 d . . .
+N1 N 0.1739(2) 0.5694(5) 0.5299(3) 0.0258(9) Uani 1 1 d . . .
+C5 C 0.1653(3) 0.4250(7) 0.4732(4) 0.0348(12) Uani 1 1 d . . .
+H5A H 0.1923 0.4176 0.4187 0.042 Uiso 1 1 calc R . .
+C1 C 0.1332(3) 0.5791(6) 0.6066(4) 0.0285(11) Uani 1 1 d . . .
+C3 C 0.0789(3) 0.2999(6) 0.5723(5) 0.0406(14) Uani 1 1 d . . .
+H3A H 0.0480 0.2081 0.5878 0.049 Uiso 1 1 calc R . .
+C4 C 0.1188(4) 0.2894(7) 0.4918(5) 0.0418(14) Uani 1 1 d . . .
+H4A H 0.1143 0.1919 0.4509 0.050 Uiso 1 1 calc R . .
+C2 C 0.0848(3) 0.4465(7) 0.6299(4) 0.0392(13) Uani 1 1 d . . .
+H2A H 0.0568 0.4566 0.6834 0.047 Uiso 1 1 calc R . .
+loop_
+_atom_site_aniso_label
+_atom_site_aniso_U_11
+_atom_site_aniso_U_22
+_atom_site_aniso_U_33
+_atom_site_aniso_U_23
+_atom_site_aniso_U_13
+_atom_site_aniso_U_12
+I1 0.0547(3) 0.0377(2) 0.0355(2) -0.00672(17) 0.02011(19) 0.00020(16)
+Cu1 0.0290(4) 0.0223(4) 0.0244(4) -0.0004(4) 0.0114(3) -0.0059(3)
+Br1 0.0352(3) 0.0372(3) 0.0336(3) 0.0069(2) 0.0056(2) -0.0030(2)
+N1 0.028(2) 0.026(2) 0.024(2) 0.0038(18) 0.0090(17) -0.0047(17)
+C5 0.041(3) 0.032(3) 0.035(3) -0.004(3) 0.017(2) -0.003(2)
+C1 0.032(3) 0.028(3) 0.025(2) 0.001(2) 0.008(2) -0.002(2)
+C3 0.034(3) 0.026(3) 0.060(4) 0.014(3) 0.012(3) -0.007(2)
+C4 0.040(3) 0.027(3) 0.055(4) -0.007(3) 0.010(3) -0.008(2)
+C2 0.039(3) 0.042(3) 0.042(3) 0.010(3) 0.020(2) -0.001(3)
+loop_
+_atom_type_symbol
+_atom_type_description
+_atom_type_scat_dispersion_real
+_atom_type_scat_dispersion_imag
+_atom_type_scat_source
+C C 0.0033 0.0016 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+H H 0.0000 0.0000 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+N N 0.0061 0.0033 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+Cu Cu 0.3201 1.2651 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+Br Br -0.2901 2.4595 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+I I -0.4742 1.8119 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+loop_
+_geom_angle_atom_site_label_1
+_geom_angle_atom_site_label_2
+_geom_angle_atom_site_label_3
+_geom_angle
+_geom_angle_site_symmetry_1
+_geom_angle_site_symmetry_3
+_geom_angle_publ_flag
+N1 Cu1 N1 180.0 7_566 . ?
+N1 Cu1 Br1 90.10(11) 7_566 7_566 ?
+N1 Cu1 Br1 89.91(11) . 7_566 ?
+N1 Cu1 Br1 89.90(11) 7_566 . ?
+N1 Cu1 Br1 90.09(11) . . ?
+Br1 Cu1 Br1 180.0 7_566 . ?
+C1 N1 C5 117.7(4) . . ?
+C1 N1 Cu1 123.7(3) . . ?
+C5 N1 Cu1 118.5(3) . . ?
+N1 C5 C4 123.2(5) . . ?
+N1 C5 H5A 118.4 . . ?
+C4 C5 H5A 118.4 . . ?
+N1 C1 C2 122.3(5) . . ?
+N1 C1 I1 117.4(3) . . ?
+C2 C1 I1 120.2(4) . . ?
+C2 C3 C4 119.6(5) . . ?
+C2 C3 H3A 120.2 . . ?
+C4 C3 H3A 120.2 . . ?
+C5 C4 C3 118.5(5) . . ?
+C5 C4 H4A 120.8 . . ?
+C3 C4 H4A 120.8 . . ?
+C3 C2 C1 118.6(5) . . ?
+C3 C2 H2A 120.7 . . ?
+C1 C2 H2A 120.7 . . ?
+loop_
+_geom_bond_atom_site_label_1
+_geom_bond_atom_site_label_2
+_geom_bond_distance
+_geom_bond_site_symmetry_2
+_geom_bond_publ_flag
+I1 C1 2.097(5) . ?
+Cu1 N1 1.976(4) 7_566 ?
+Cu1 N1 1.976(4) . ?
+Cu1 Br1 2.4036(5) 7_566 ?
+Cu1 Br1 2.4036(5) . ?
+N1 C1 1.336(5) . ?
+N1 C5 1.349(6) . ?
+C5 C4 1.361(7) . ?
+C5 H5A 0.9300 . ?
+C1 C2 1.384(7) . ?
+C3 C2 1.373(8) . ?
+C3 C4 1.374(7) . ?
+C3 H3A 0.9300 . ?
+C4 H4A 0.9300 . ?
+C2 H2A 0.9300 . ?
+loop_
+_geom_torsion_atom_site_label_1
+_geom_torsion_atom_site_label_2
+_geom_torsion_atom_site_label_3
+_geom_torsion_atom_site_label_4
+_geom_torsion
+_geom_torsion_site_symmetry_1
+_geom_torsion_site_symmetry_2
+_geom_torsion_site_symmetry_3
+_geom_torsion_site_symmetry_4
+_geom_torsion_publ_flag
+N1 Cu1 N1 C1 -112(100) 7_566 . . . ?
+Br1 Cu1 N1 C1 84.2(4) 7_566 . . . ?
+Br1 Cu1 N1 C1 -95.8(4) . . . . ?
+N1 Cu1 N1 C5 71(100) 7_566 . . . ?
+Br1 Cu1 N1 C5 -92.9(3) 7_566 . . . ?
+Br1 Cu1 N1 C5 87.1(3) . . . . ?
+C1 N1 C5 C4 -1.2(7) . . . . ?
+Cu1 N1 C5 C4 176.1(4) . . . . ?
+C5 N1 C1 C2 1.0(7) . . . . ?
+Cu1 N1 C1 C2 -176.1(4) . . . . ?
+C5 N1 C1 I1 -177.6(3) . . . . ?
+Cu1 N1 C1 I1 5.3(5) . . . . ?
+N1 C5 C4 C3 -0.1(8) . . . . ?
+C2 C3 C4 C5 1.5(8) . . . . ?
+C4 C3 C2 C1 -1.7(8) . . . . ?
+N1 C1 C2 C3 0.4(8) . . . . ?
+I1 C1 C2 C3 179.0(4) . . . . ?

examples/parse_geometry/Project.toml

@@ -0,0 +1,4 @@
+[deps]
+CrystalInfoFramework = "6007d9b0-c6b2-11e8-0510-1d10e825f3f1"
+Measurements = "eff96d63-e80a-5855-80a2-b1b0885c5ab7"
+Unitful = "1986cc42-f94f-5a68-af5c-568840ba703d"

examples/parse_geometry/README.md

@@ -0,0 +1,33 @@
+# Parsing CIF geometry
+
+The file `parse_geometry.jl` defines the function `cif_geometry(path)` that
+reads a geometry from a CIF file and returns
+
+- A list of element symbol, e.g. `:C` for a carbon atom, in
+  a format that is compatible with the `PeriodicTable.jl` and `Mendeleeiev.jl` packages to look up properties of the elements.
+- A `3 x n_atoms` array of the position.
+  The array elements are `Measurement`s of `Unitful` quantities,
+  therefore both the uncertainty given in the CIF file
+  and the units are carried with the geometry.
+  The uncertainties and units can be dropped using, respectively,
+  `Measurements.value.(geometry)` and `ustrip.(geometry)`.
+
+To use the file directly,
+make the `examples/parse_geometry/` folder the working
+directory (usually using the `cd` terminal command).
+
+The example requires the `Measurements`, `Unitful` and `CrystalInfoFramework`
+packages.
+You can either install them manually
+(by typing `] add Measurements Unitful CrystalInforFramework` in julia REPL)
+or use the example environment
+(by starting julia as `julia --project`
+while being in the `examples/parse_geometry/` folder
+and then typing `] instantiate` in julia REPL).
+
+To run as a command line program from the folder, type `julia --project parse_geometry.jl <filename>`,
+where `<filename>` is a CIF file. If `<filename>` is missing, the supplied example
+file from the COD is used.
+
+To run interactively from the folder, type `julia --project`, then at the prompt `include("parse_geometry.jl")`,
+then `cif_geometry(<path>)`.

examples/parse_geometry/parse_geometry.jl

@@ -0,0 +1,52 @@
+using CrystalInfoFramework
+using Measurements
+using Unitful
+
+parse_cif_value(x) = measurement(x)
+
+function cif_geometry(file)
+    cif = only(Cif(file))[2]
+
+    atoms = Symbol.(cif["_atom_site_type_symbol"])
+    fract_x = parse_cif_value.(cif["_atom_site_fract_x"])
+    fract_y = parse_cif_value.(cif["_atom_site_fract_y"])
+    fract_z = parse_cif_value.(cif["_atom_site_fract_z"])
+    fract = permutedims(hcat(fract_x, fract_y, fract_z))
+
+    a, b, c = map(["a", "b", "c"]) do dim
+        return parse_cif_value(only(cif["_cell_length_$dim"])) * u"Å"
+    end
+
+    α, β, γ = map(["alpha", "beta", "gamma"]) do angle
+        return parse_cif_value(only(cif["_cell_angle_$angle"])) * u"°"
+    end
+
+    # Transformation matrix according to
+    # https://chemistry.stackexchange.com/questions/136836/converting-fractional-coordinates-into-cartesian-coordinates-for-crystallography
+    n2 = (cos(α) - cos(γ)*cos(β)) / sin(γ)
+
+    M = [
+        a 0u"Å" 0u"Å" ;
+        b*cos(γ) b*sin(γ) 0u"Å" ;
+        c*cos(β) c*n2 c*sqrt(sin(β)^2 - n2^2)
+    ]
+
+    return atoms, M' * fract
+end
+
+
+if abspath(PROGRAM_FILE) == @__FILE__
+    if length(ARGS) == 0
+
+        # Some data from the Crystallography Open Database (COD), ID 7706719
+	file = "7706719.cif"
+    else	
+        file = first(a)
+    end
+
+    atoms, geometry = cif_geometry(file)
+    println("Atoms from $file")
+    println(atoms)
+    println("\n Geometry:")
+    println(geometry)
+end