Some common tasks you can do with QCrBoxtools¶

This is a short reference of functions that are implemented in the QCrBoxTools library, which is available in the qcrbox conda environment in every QCrBox container. This is not a complete collection but highlights some functions which might be useful for your own development. If these functions work with an iotbx.cif it is assumed that they are in unified cif format.

In this first cell, we create ourselves a content manager for temporary files. Make sure you execute the next cell before all others.

In [1]:

from contextlib import contextmanager
from pathlib import Path
from tempfile import NamedTemporaryFile
from textwrap import dedent


@contextmanager
def temp_file_context(suffix: str, file_text: str) -> str:
    temp_cif = NamedTemporaryFile(suffix=suffix, delete=False)
    temp_cif.write(dedent(file_text).encode("utf-8"))
    temp_cif.close()
    yield Path(temp_cif.name)
    Path(temp_cif.name).unlink()

from contextlib import contextmanager from pathlib import Path from tempfile import NamedTemporaryFile from textwrap import dedent @contextmanager def temp_file_context(suffix: str, file_text: str) -> str: temp_cif = NamedTemporaryFile(suffix=suffix, delete=False) temp_cif.write(dedent(file_text).encode("utf-8")) temp_cif.close() yield Path(temp_cif.name) Path(temp_cif.name).unlink()

Load a cif in unified format¶

We create a small temporary file first and then load it from disk as unified cif. This function makes sure that you do not need to handle aliases yourself.

In [2]:

from qcrboxtools.cif.read import read_cif_as_unified

cif_text = dedent("""
    data_test
    _cell_length_a 10.00(2)
    _cell_length_b 11.01(12)
    _cell_length_c 12.05(5)
""")

with temp_file_context(".cif", cif_text) as cif_path:
    unified_block = read_cif_as_unified(
        cif_path=cif_path,  # path to the CIF file.
        dataset=0,  # use an integer to specify dataset by position, a string to specify by name
    )

# We now use unified keywords. Standard uncertainties are stored in the "<entry>_su" keys.
# We can now be sure which aliases of the entries are used.
print(unified_block["_cell.length_a"], unified_block["_cell.length_a_su"])

from qcrboxtools.cif.read import read_cif_as_unified cif_text = dedent(""" data_test _cell_length_a 10.00(2) _cell_length_b 11.01(12) _cell_length_c 12.05(5) """) with temp_file_context(".cif", cif_text) as cif_path: unified_block = read_cif_as_unified( cif_path=cif_path, # path to the CIF file. dataset=0, # use an integer to specify dataset by position, a string to specify by name ) # We now use unified keywords. Standard uncertainties are stored in the "_su" keys. # We can now be sure which aliases of the entries are used. print(unified_block["_cell.length_a"], unified_block["_cell.length_a_su"])

10.0 0.02

Generating an hkl from a cif.¶

In [4]:

from qcrboxtools.cif.file_converter.hkl import cif2hkl4

cif_text = dedent("""
    data_test

    loop_
      _diffrn_refln.index_h
      _diffrn_refln.index_k
      _diffrn_refln.index_l
      _diffrn_refln.intensity_net
      _diffrn_refln.intensity_net_su
      _diffrn_refln.scale_group_code
      0    0    3   93.4022  38.7231  2
      0    0   -3   192.939   61.994  2
      0    0   -4    144304  1540.24  2
      0    0    4    146626  1495.57  2
      0    0   -5   485.452  123.618  2
      0    0    5   284.703  91.7571  2
""")

with temp_file_context(".cif", cif_text) as cif_path:
    with temp_file_context(".hkl", "") as hkl_path:
        # Generates an HKL file from the CIF file.
        cif2hkl4(cif_path=cif_path, cif_dataset=0, hkl_path=hkl_path)
        print(hkl_path.read_text())  # check the content of the generated HKL file

from qcrboxtools.cif.file_converter.hkl import cif2hkl4 cif_text = dedent(""" data_test loop_ _diffrn_refln.index_h _diffrn_refln.index_k _diffrn_refln.index_l _diffrn_refln.intensity_net _diffrn_refln.intensity_net_su _diffrn_refln.scale_group_code 0 0 3 93.4022 38.7231 2 0 0 -3 192.939 61.994 2 0 0 -4 144304 1540.24 2 0 0 4 146626 1495.57 2 0 0 -5 485.452 123.618 2 0 0 5 284.703 91.7571 2 """) with temp_file_context(".cif", cif_text) as cif_path: with temp_file_context(".hkl", "") as hkl_path: # Generates an HKL file from the CIF file. cif2hkl4(cif_path=cif_path, cif_dataset=0, hkl_path=hkl_path) print(hkl_path.read_text()) # check the content of the generated HKL file

   0   0   3 93.4022 38.7231   2
   0   0  -3 192.939 61.9940   2
   0   0  -4 144304. 1540.24   2
   0   0   4 146626. 1495.57   2
   0   0  -5 485.452 123.618   2
   0   0   5 284.703 91.7571   2

Getting a new cif with non-unified cif entries from a unified cif¶

In [9]:

from qcrboxtools.cif.cif2cif import cif_file_to_specific

cif_text = dedent("""
    data_test
    _cell.length_a 10.0002
    _cell.length_a_su 0.02
    _cell.length_b 11.019
    _cell.length_b_su 0.12
    _cell.length_c 12.05
    _cell.length_c_su 0.05
    _cell.volume 1331.0
    _custom_category.entry testme
""")

with temp_file_context(".cif", cif_text) as cif_path:
    with temp_file_context(".cif", "") as new_cif_path:
        # Generates a new CIF file with only the specified entries.
        cif_file_to_specific(
            input_cif_path=cif_path,
            output_cif_path=new_cif_path,
            required_entries=["_cell_length_a", "_cell_length_b", "_custom_category_entry"],
            optional_entries=[
                "_cell_length_c",
                "_cell_angle_alpha",
            ],  # notice that "_cell_angle_alpha" is not present in the input CIF file
            custom_categories=["custom_category"],
            merge_su=True,
        )
        print(new_cif_path.read_text())  # check the content of the generated CIF file

from qcrboxtools.cif.cif2cif import cif_file_to_specific cif_text = dedent(""" data_test _cell.length_a 10.0002 _cell.length_a_su 0.02 _cell.length_b 11.019 _cell.length_b_su 0.12 _cell.length_c 12.05 _cell.length_c_su 0.05 _cell.volume 1331.0 _custom_category.entry testme """) with temp_file_context(".cif", cif_text) as cif_path: with temp_file_context(".cif", "") as new_cif_path: # Generates a new CIF file with only the specified entries. cif_file_to_specific( input_cif_path=cif_path, output_cif_path=new_cif_path, required_entries=["_cell_length_a", "_cell_length_b", "_custom_category_entry"], optional_entries=[ "_cell_length_c", "_cell_angle_alpha", ], # notice that "_cell_angle_alpha" is not present in the input CIF file custom_categories=["custom_category"], merge_su=True, ) print(new_cif_path.read_text()) # check the content of the generated CIF file

data_test
_cell_length_a                    10.00(2)
_cell_length_b                    11.02(12)
_cell_length_c                    12.05(5)
_custom_category_entry            testme

Merge two CIF blocks¶

QCrBox has a helper functions to merge cif blocks, including merging loops on specified entries

In [18]:

from qcrboxtools.cif.merge import merge_cif_blocks
from qcrboxtools.cif.read import read_cif_safe

cif_text1 = dedent("""
    data_test
    _cell.length_a 10.0002
    _cell.length_a_su 0.02
    _cell.length_b 11.019
    _cell.length_b_su 0.12
    _cell.length_c 12.05
    _cell.length_c_su 0.05
    loop_
        _refln.index_h
        _refln.index_k
        _refln.index_l
        _refln.f_squared_meas
        _refln.f_squared_meas_su
        0 0 3 93.4022 38.7231
        0 0 -3 192.939 61.994
        0 0 -4 144304 1540.24
        0 0 4 146626 1495.57
""")

cif_text2 = dedent("""
    data_test
    _cell.length_c 15.05
    _cell.length_c_su 0.05
    loop_
        _refln.index_h
        _refln.index_k
        _refln.index_l
        _refln.f_calc
        _refln.phase_calc
        0 0 3 31.4022 0.5
        0 0 5 192.939 90.5
""")

with temp_file_context(".cif", cif_text1) as cif_path1:
    with temp_file_context(".cif", cif_text2) as cif_path2:
        block1 = read_cif_safe(cif_path1)["test"]  # read_cif_safe also supports pathlib.Path objects
        block2 = read_cif_safe(cif_path2)["test"]
        merged_block = merge_cif_blocks(
            block1=block1,
            block2=block2,  # block2 will overwrite block1
            possible_markers=["_refln.index_.*"],  # markers to merge the loops on h,k,l unique,
            # would also work with default value
        )
        print(merged_block)  # note that missing entries in a loop are filled with ?.
        # Ensure matching index to avoid

from qcrboxtools.cif.merge import merge_cif_blocks from qcrboxtools.cif.read import read_cif_safe cif_text1 = dedent(""" data_test _cell.length_a 10.0002 _cell.length_a_su 0.02 _cell.length_b 11.019 _cell.length_b_su 0.12 _cell.length_c 12.05 _cell.length_c_su 0.05 loop_ _refln.index_h _refln.index_k _refln.index_l _refln.f_squared_meas _refln.f_squared_meas_su 0 0 3 93.4022 38.7231 0 0 -3 192.939 61.994 0 0 -4 144304 1540.24 0 0 4 146626 1495.57 """) cif_text2 = dedent(""" data_test _cell.length_c 15.05 _cell.length_c_su 0.05 loop_ _refln.index_h _refln.index_k _refln.index_l _refln.f_calc _refln.phase_calc 0 0 3 31.4022 0.5 0 0 5 192.939 90.5 """) with temp_file_context(".cif", cif_text1) as cif_path1: with temp_file_context(".cif", cif_text2) as cif_path2: block1 = read_cif_safe(cif_path1)["test"] # read_cif_safe also supports pathlib.Path objects block2 = read_cif_safe(cif_path2)["test"] merged_block = merge_cif_blocks( block1=block1, block2=block2, # block2 will overwrite block1 possible_markers=["_refln.index_.*"], # markers to merge the loops on h,k,l unique, # would also work with default value ) print(merged_block) # note that missing entries in a loop are filled with ?. # Ensure matching index to avoid

_cell.length_a                    10.0002
_cell.length_a_su                 0.02
_cell.length_b                    11.019
_cell.length_b_su                 0.12
_cell.length_c                    15.05
_cell.length_c_su                 0.05
loop_
  _refln.index_h
  _refln.index_k
  _refln.index_l
  _refln.f_squared_meas
  _refln.f_squared_meas_su
  _refln.f_calc
  _refln.phase_calc
  0  0   3  93.4022  38.7231  31.4022   0.5
  0  0  -3  192.939   61.994        ?     ?
  0  0  -4   144304  1540.24        ?     ?
  0  0   4   146626  1495.57        ?     ?
  0  0   5        ?        ?  192.939  90.5

In [ ]: