biotite 0.39.0__cp310-cp310-macosx_10_9_x86_64.whl → 0.41.0__cp310-cp310-macosx_10_9_x86_64.whl

biotite/__init__.py

@@ -9,11 +9,11 @@ it does provide utilities and base classes used by a lot of *Biotite*'s
 modules.
 """
 
-__version__ = "0.39.0"
+__version__ = "0.41.0"
 __name__ = "biotite"
 __author__ = "Patrick Kunzmann"
 
 from .file import *
 from .temp import *
-from .copyable import * 
-from .visualize import * 
+from .copyable import *
+from .visualize import *

biotite/application/dssp/app.py

@@ -9,7 +9,7 @@ __all__ = ["DsspApp"]
 from tempfile import NamedTemporaryFile
 from ..localapp import LocalApp, cleanup_tempfile
 from ..application import AppState, requires_state
-from ...structure.io.pdbx.file import PDBxFile
+from ...structure.io.pdbx.cif import CIFFile
 from ...structure.io.pdbx.convert import set_structure
 import numpy as np
 
@@ -18,13 +18,13 @@ class DsspApp(LocalApp):
     r"""
     Annotate the secondary structure of a protein structure using the
     *DSSP* software.
-    
+
     Internally this creates a :class:`Popen` instance, which handles
     the execution.
-    
+
     DSSP differentiates between 8 different types of secondary
     structure elements:
-    
+
        - C: loop, coil or irregular
        - H: :math:`{\alpha}`-helix
        - B: :math:`{\beta}`-bridge
@@ -32,15 +32,15 @@ class DsspApp(LocalApp):
        - G: 3 :sub:`10`-helix
        - I: :math:`{\pi}`-helix
        - T: hydrogen bonded turn
-       - S: bend 
-    
+       - S: bend
+
     Parameters
     ----------
     atom_array : AtomArray
         The atom array to be annotated.
     bin_path : str, optional
         Path of the *DDSP* binary.
-    
+
     Examples
     --------
 
@@ -51,7 +51,7 @@ class DsspApp(LocalApp):
     ['C' 'H' 'H' 'H' 'H' 'H' 'H' 'H' 'T' 'T' 'G' 'G' 'G' 'G' 'T' 'C' 'C' 'C'
      'C' 'C']
     """
-    
+
     def __init__(self, atom_array, bin_path="mkdssp"):
         super().__init__(bin_path)
 
@@ -77,15 +77,15 @@ class DsspApp(LocalApp):
         self._out_file = NamedTemporaryFile("r", suffix=".dssp", delete=False)
 
     def run(self):
-        in_file = PDBxFile()
-        set_structure(in_file, self._array, data_block="DSSP_INPUT")
+        in_file = CIFFile()
+        set_structure(in_file, self._array)
         in_file.write(self._in_file)
         self._in_file.flush()
         self.set_arguments(
             ["-i", self._in_file.name, "-o", self._out_file.name]
         )
         super().run()
-    
+
     def evaluate(self):
         super().evaluate()
         lines = self._out_file.read().split("\n")
@@ -106,17 +106,17 @@ class DsspApp(LocalApp):
         for i, line in enumerate(lines):
             self._sse[i] = line[16]
         self._sse[self._sse == " "] = "C"
-    
+
     def clean_up(self):
         super().clean_up()
         cleanup_tempfile(self._in_file)
         cleanup_tempfile(self._out_file)
-    
+
     @requires_state(AppState.JOINED)
     def get_sse(self):
         """
         Get the resulting secondary structure assignment.
-        
+
         Returns
         -------
         sse : ndarray, dtype="U1"
@@ -124,22 +124,22 @@ class DsspApp(LocalApp):
             corresponding to the residues in the input atom array.
         """
         return self._sse
-    
+
     @staticmethod
     def annotate_sse(atom_array, bin_path="mkdssp"):
         """
         Perform a secondary structure assignment to an atom array.
-        
+
         This is a convenience function, that wraps the :class:`DsspApp`
         execution.
-        
+
         Parameters
         ----------
         atom_array : AtomArray
             The atom array to be annotated.
         bin_path : str, optional
             Path of the DDSP binary.
-        
+
         Returns
         -------
         sse : ndarray, dtype="U1"

biotite/database/pubchem/download.py

@@ -26,9 +26,9 @@ def fetch(cids, format="sdf", target_path=None, as_structural_formula=False,
           throttle_threshold=0.5, return_throttle_status=False):
     """
     Download structure files from *PubChem* in various formats.
-    
+
     This function requires an internet connection.
-    
+
     Parameters
     ----------
     cids : int or iterable object or int
@@ -62,7 +62,7 @@ def fetch(cids, format="sdf", target_path=None, as_structural_formula=False,
     return_throttle_status : float, optional
         If set to true, the :class:`ThrottleStatus` of the final request
         is also returned.
-    
+
     Returns
     -------
     files : str or StringIO or BytesIO or list of (str or StringIO or BytesIO)
@@ -78,10 +78,10 @@ def fetch(cids, format="sdf", target_path=None, as_structural_formula=False,
         of the final response is returned.
         This can be used for custom request throttling, for example.
         Only returned, if `return_throttle_status` is set to true.
-    
+
     Examples
     --------
-    
+
     >>> import os.path
     >>> file = fetch(2244, "sdf", path_to_directory)
     >>> print(os.path.basename(file))
@@ -100,7 +100,7 @@ def fetch(cids, format="sdf", target_path=None, as_structural_formula=False,
     # Create the target folder, if not existing
     if target_path is not None and not isdir(target_path):
         os.makedirs(target_path)
-    
+
     files = []
     for i, cid in enumerate(cids):
         # Prevent IDs as strings, this could be a common error, as other
@@ -111,14 +111,14 @@ def fetch(cids, format="sdf", target_path=None, as_structural_formula=False,
         if verbose:
             print(f"Fetching file {i+1:d} / {len(cids):d} ({cid})...",
                   end="\r")
-        
+
         # Fetch file from database
         if target_path is not None:
             file = join(target_path, str(cid) + "." + format)
         else:
             # 'file = None' -> store content in a file-like object
             file = None
-        
+
         if file is None \
            or not isfile(file) \
            or getsize(file) == 0 \
@@ -130,12 +130,12 @@ def fetch(cids, format="sdf", target_path=None, as_structural_formula=False,
                 )
                 if not r.ok:
                     raise RequestError(parse_error_details(r.text))
-                
+
                 if format.lower() in _binary_formats:
                     content = r.content
                 else:
                     content = r.text
-                
+
                 if file is None:
                     if format in _binary_formats:
                         file = io.BytesIO(content)
@@ -145,11 +145,11 @@ def fetch(cids, format="sdf", target_path=None, as_structural_formula=False,
                     mode = "wb+" if format in _binary_formats else "w+"
                     with open(file, mode) as f:
                         f.write(content)
-                
+
                 throttle_status = ThrottleStatus.from_response(r)
                 if throttle_threshold is not None:
                     throttle_status.wait_if_busy(throttle_threshold)
-        
+
         files.append(file)
     if verbose:
         print("\nDone")
@@ -168,9 +168,9 @@ def fetch_property(cids, name,
                    throttle_threshold=0.5, return_throttle_status=False):
     """
     Download the given property for the given CID(s).
-    
+
     This function requires an internet connection.
-    
+
     Parameters
     ----------
     cids : int or iterable object or int
@@ -189,7 +189,7 @@ def fetch_property(cids, name,
     return_throttle_status : float, optional
         If set to true, the :class:`ThrottleStatus` of the final request
         is also returned.
-    
+
     Returns
     -------
     property : str or list of str
@@ -202,23 +202,23 @@ def fetch_property(cids, name,
         The :class:`ThrottleStatus` obtained from the server response.
         This can be used for custom request throttling, for example.
         Only returned, if `return_throttle_status` is set to true.
-    
+
     Examples
     --------
-    
+
     >>> butane_cids = np.array(search(FormulaQuery("C4H10")))
     >>> # Filter natural isotopes...
     >>> n_iso = np.array(fetch_property(butane_cids, "IsotopeAtomCount"), dtype=int)
     >>> # ...and neutral compounds
     >>> charge = np.array(fetch_property(butane_cids, "Charge"), dtype=int)
     >>> butane_cids = butane_cids[(n_iso == 0) & (charge == 0)]
-    >>> print(butane_cids.tolist())
-    [7843, 6360, 161897780, 161295599, 158934736, 158271732, 157632982, 19048342, 19029854, 18402699]
+    >>> print(sorted(butane_cids.tolist()))
+    [6360, 7843, 18402699, 19029854, 19048342, 157632982, 158271732, 158934736, 161295599, 161897780]
     >>> # Get the IUPAC names for each compound
     >>> iupac_names = fetch_property(butane_cids, "IUPACName")
     >>> # Compounds with multiple molecules use ';' as separator
     >>> print(iupac_names)
-    ['butane', '2-methylpropane', 'methylcyclopropane;molecular hydrogen', 'carbanylium;propane', 'carbanide;propane', 'acetylene;methane', 'cyclobutane;molecular hydrogen', 'cyclopropane;methane', 'ethane;ethene', 'methane;prop-1-ene']
+    ['butane', '2-methylpropane', 'methane;prop-1-ene', 'ethane;ethene', 'cyclopropane;methane', 'cyclobutane;molecular hydrogen', 'acetylene;methane', 'carbanide;propane', 'carbanylium;propane', 'methylcyclopropane;molecular hydrogen']
     """
     # If only a single CID is present,
     # put it into a single element list
@@ -227,13 +227,13 @@ def fetch_property(cids, name,
         single_element = True
     else:
         single_element = False
-    
+
     # Property names may only contain letters and numbers
     if not name.isalnum():
         raise ValueError(
             f"Property '{name}' contains invalid characters"
         )
-    
+
     # Use TXT format instead of CSV to avoid issues with ',' characters
     # within table elements
     r = requests.post(
@@ -245,7 +245,7 @@ def fetch_property(cids, name,
     throttle_status = ThrottleStatus.from_response(r)
     if throttle_threshold is not None:
         throttle_status.wait_if_busy(throttle_threshold)
-    
+
     # Each line contains the property for one CID
     properties = r.text.splitlines()
 

biotite/database/pubchem/query.py

@@ -16,7 +16,7 @@ import requests
 from .error import parse_error_details
 from .throttle import ThrottleStatus
 from ..error import RequestError
-from ...structure.io.mol.file import MOLFile
+from ...structure.io.mol.mol import MOLFile
 
 
 _base_url = "https://pubchem.ncbi.nlm.nih.gov/rest/pug/"
@@ -84,7 +84,7 @@ class NameQuery(Query):
     --------
 
     >>> print(search(NameQuery("Alanine")))
-    [5950, ..., ..., ...]
+    [5950, ..., ...]
     """
 
     def __init__(self, name):
@@ -204,10 +204,10 @@ class FormulaQuery(Query):
     --------
 
     >>> print(search(FormulaQuery("C4H10", number=5)))
-    [7843, ..., ..., ..., ...]
+    [..., ..., ..., ..., ...]
     >>> atom_array = residue("ALA")
     >>> print(search(FormulaQuery.from_atoms(atom_array, number=5)))
-    [5950, ..., ..., ..., ...]
+    [..., ..., ..., ..., ...]
     """
 
     def __init__(self, formula, allow_other_elements=False, number=None):
@@ -555,11 +555,11 @@ class SuperstructureQuery(SuperOrSubstructureQuery):
 
     >>> # CID of alanine
     >>> print(search(SuperstructureQuery(cid=5950, number=5)))
-    [1032, ..., ..., ..., ...]
+    [..., ..., ..., ..., ...]
     >>> # AtomArray of alanine
     >>> atom_array = residue("ALA")
     >>> print(search(SuperstructureQuery.from_atoms(atom_array, number=5)))
-    [1032, ..., ..., ..., ...]
+    [..., ..., ..., ..., ...]
     """
 
     def search_type(self):
@@ -801,7 +801,7 @@ def search(query, throttle_threshold=0.5, return_throttle_status=False):
     --------
 
     >>> print(search(NameQuery("Alanine")))
-    [5950, ..., ..., ...]
+    [5950, ..., ...]
     """
     # Use POST to be compatible with the larger payloads
     # of structure searches

biotite/database/rcsb/download.py

@@ -16,24 +16,25 @@ from ..error import RequestError
 
 _standard_url = "https://files.rcsb.org/download/"
 _mmtf_url = "https://mmtf.rcsb.org/v1.0/full/"
+_bcif_url = "https://models.rcsb.org/"
 _fasta_url = "https://www.rcsb.org/fasta/entry/"
 
-_binary_formats = ["mmtf"]
+_binary_formats = ["mmtf", "bcif"]
 
 
 def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
     """
     Download structure files (or sequence files) from the RCSB PDB in
     various formats.
-    
+
     This function requires an internet connection.
-    
+
     Parameters
     ----------
     pdb_ids : str or iterable object of str
         A single PDB ID or a list of PDB IDs of the structure(s)
         to be downloaded.
-    format : {'pdb', 'pdbx', 'cif', 'mmcif', 'mmtf', 'fasta'}
+    format : {'pdb', 'pdbx', 'cif', 'mmcif', 'bcif', 'mmtf', 'fasta'}
         The format of the files to be downloaded.
         ``'pdbx'``, ``'cif'`` and ``'mmcif'`` are synonyms for
         the same format.
@@ -48,7 +49,7 @@ def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
         the file is empty.
     verbose: bool, optional
         If set to true, the function will output the download progress.
-    
+
     Returns
     -------
     files : str or StringIO or BytesIO or list of (str or StringIO or BytesIO)
@@ -58,7 +59,7 @@ def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
         object) was given, a list of strings is returned.
         If no `target_path` was given, the file contents are stored in
         either :class:`StringIO` or :class:`BytesIO` objects.
-    
+
     Warnings
     --------
     Even if you give valid input to this function, in rare cases the
@@ -66,10 +67,10 @@ def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
     In these cases the request should be retried.
     When the issue occurs repeatedly, the error is probably in your
     input.
-    
+
     Examples
     --------
-    
+
     >>> import os.path
     >>> file = fetch("1l2y", "cif", path_to_directory)
     >>> print(os.path.basename(file))
@@ -88,21 +89,21 @@ def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
     # Create the target folder, if not existing
     if target_path is not None and not os.path.isdir(target_path):
         os.makedirs(target_path)
-    
+
     files = []
     for i, id in enumerate(pdb_ids):
         # Verbose output
         if verbose:
             print(f"Fetching file {i+1:d} / {len(pdb_ids):d} ({id})...",
                   end="\r")
-        
+
         # Fetch file from database
         if target_path is not None:
             file = join(target_path, id + "." + format)
         else:
             # 'file = None' -> store content in a file-like object
             file = None
-        
+
         if file is None \
            or not isfile(file) \
            or getsize(file) == 0 \
@@ -115,6 +116,10 @@ def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
                     r = requests.get(_standard_url + id + ".cif")
                     content = r.text
                     _assert_valid_file(content, id)
+                elif format in ["bcif"]:
+                    r = requests.get(_bcif_url + id + ".bcif")
+                    content = r.content
+                    _assert_valid_file(r.text, id)
                 elif format == "mmtf":
                     r = requests.get(_mmtf_url + id)
                     content = r.content
@@ -125,7 +130,7 @@ def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
                     _assert_valid_file(content, id)
                 else:
                     raise ValueError(f"Format '{format}' is not supported")
-                
+
                 if file is None:
                     if format in _binary_formats:
                         file = io.BytesIO(content)
@@ -135,7 +140,7 @@ def fetch(pdb_ids, format, target_path=None, overwrite=False, verbose=False):
                     mode = "wb+" if format in _binary_formats else "w+"
                     with open(file, mode) as f:
                         f.write(content)
-        
+
         files.append(file)
     if verbose:
         print("\nDone")
@@ -153,7 +158,7 @@ def _assert_valid_file(response_text, pdb_id):
     """
     # Structure file and FASTA file retrieval
     # have different error messages
-    if any(err_msg in response_text for err_msg in [
+    if len(response_text) == 0 or any(err_msg in response_text for err_msg in [
         "404 Not Found",
         "<title>RCSB Protein Data Bank Error Page</title>",
         "No fasta files were found.",

biotite/file.py

@@ -4,7 +4,8 @@
 
 __name__ = "biotite"
 __author__ = "Patrick Kunzmann"
-__all__ = ["File", "TextFile", "InvalidFileError"]
+__all__ = ["File", "TextFile", "InvalidFileError",
+           "SerializationError", "DeserializationError"]
 
 import abc
 import io
@@ -38,13 +39,13 @@ class File(Copyable, metaclass=abc.ABCMeta):
     def read(cls, file):
         """
         Parse a file (or file-like object).
-        
+
         Parameters
         ----------
         file : file-like object or str
             The file to be read.
             Alternatively a file path can be supplied.
-        
+
         Returns
         -------
         file_object : File
@@ -74,7 +75,7 @@ class File(Copyable, metaclass=abc.ABCMeta):
     def write(self, file):
         """
         Write the contents of this :class:`File` object into a file.
-        
+
         Parameters
         ----------
         file_name : file-like object or str
@@ -90,7 +91,7 @@ class TextFile(File, metaclass=abc.ABCMeta):
     When reading a file, the text content is saved as list of strings,
     one for each line.
     When writing a file, this list is written into the file.
-    
+
     Attributes
     ----------
     lines : list
@@ -121,13 +122,13 @@ class TextFile(File, metaclass=abc.ABCMeta):
     def read_iter(file):
         """
         Create an iterator over each line of the given text file.
-        
+
         Parameters
         ----------
         file : file-like object or str
             The file to be read.
             Alternatively a file path can be supplied.
-        
+
         Yields
         ------
         line : str
@@ -147,7 +148,7 @@ class TextFile(File, metaclass=abc.ABCMeta):
         """
         Write the contents of this object into a file
         (or file-like object).
-        
+
         Parameters
         ----------
         file : file-like object or str
@@ -174,7 +175,7 @@ class TextFile(File, metaclass=abc.ABCMeta):
         Hence, this static method may save a large amount of memory if
         a large file should be written, especially if the `lines`
         are provided as generator.
-        
+
         Parameters
         ----------
         file : file-like object or str
@@ -211,6 +212,13 @@ class InvalidFileError(Exception):
     pass
 
 
+class SerializationError(Exception):
+    pass
+
+class DeserializationError(Exception):
+    pass
+
+
 def wrap_string(text, width):
     """
     A much simpler and hence much more efficient version of