biotite 1.1.0__cp312-cp312-win_amd64.whl → 1.2.0__cp312-cp312-win_amd64.whl

biotite/sequence/graphics/logo.py

@@ -9,7 +9,7 @@ __all__ = ["plot_sequence_logo"]
 import numpy as np
 from biotite.sequence.alphabet import LetterAlphabet
 from biotite.sequence.graphics.colorschemes import get_color_scheme
-from biotite.visualize import set_font_size_in_coord
+from biotite.visualize import plot_scaled_text
 
 
 def plot_sequence_logo(axes, profile, scheme=None, **kwargs):
@@ -29,7 +29,7 @@ def plot_sequence_logo(axes, profile, scheme=None, **kwargs):
     ----------
     axes : Axes
         The axes to draw the logo one.
-    profile: SequenceProfile
+    profile : SequenceProfile
         The logo is created based on this profile.
     scheme : str or list of (tuple or str)
         Either a valid color scheme name
@@ -38,7 +38,8 @@ def plot_sequence_logo(axes, profile, scheme=None, **kwargs):
         The list length must be at least as long as the
         length of the alphabet used by the `profile`.
     **kwargs
-        Additional `text parameters <https://matplotlib.org/api/text_api.html#matplotlib.text.Text>`_.
+        Additional parameters for the :class:`matplotlib.font_manager.FontProperties`
+        of the text or the created :class:`matplotlib.patches.PathPatch`.
 
     References
     ----------
@@ -69,23 +70,20 @@ def plot_sequence_logo(axes, profile, scheme=None, **kwargs):
         index_order = np.argsort(symbols_heights)
         start_height = 0
         for j in index_order[i]:
-            # Stack the symbols at position on top of the preceeding one
+            # Stack the symbols at position on top of the preceding one
             height = symbols_heights[i, j]
             if height > 0:
                 symbol = alphabet.decode(j)
-                text = axes.text(
+                plot_scaled_text(
+                    axes,
+                    symbol,
                     i + 0.5,
                     start_height,
-                    symbol,
-                    ha="left",
-                    va="bottom",
+                    width=1,
+                    height=height,
                     color=colors[j],
-                    # Best results are obtained with this font size
-                    size=1,
                     **kwargs,
                 )
-                text.set_clip_on(True)
-                set_font_size_in_coord(text, width=1, height=height)
                 start_height += height
 
     axes.set_xlim(0.5, len(profile.symbols) + 0.5)

biotite/sequence/io/fasta/convert.py

@@ -275,8 +275,7 @@ def _process_nucleotide_sequence(x):
 def _convert_to_string(sequence, as_rna):
     if not isinstance(sequence.get_alphabet(), LetterAlphabet):
         raise ValueError(
-            "Only sequences using single letter alphabets "
-            "can be stored in a FASTA file"
+            "Only sequences using single letter alphabets can be stored in a FASTA file"
         )
     if isinstance(sequence, NucleotideSequence) and as_rna:
         return str(sequence).replace("T", "U")

biotite/sequence/io/fasta/file.py

@@ -102,7 +102,7 @@ class FastaFile(TextFile, MutableMapping):
         if not isinstance(header, str):
             raise IndexError("'FastaFile' only supports header strings as keys")
         if not isinstance(seq_str, str):
-            raise TypeError("'FastaFile' only supports sequence strings " "as values")
+            raise TypeError("'FastaFile' only supports sequence strings as values")
         # Create lines for new header and sequence (with line breaks)
         new_lines = [">" + header.replace("\n", "").strip()] + wrap_string(
             seq_str, width=self._chars_per_line

biotite/sequence/io/fastq/file.py

@@ -302,10 +302,10 @@ class FastqFile(TextFile, MutableMapping):
                 else:  # score_len > seq_len
                     raise InvalidFileError(
                         f"The amount of scores is not equal to the sequence "
-                        f"length for the sequence in line {seq_start_i+1} "
+                        f"length for the sequence in line {seq_start_i + 1} "
                     )
             else:
-                raise InvalidFileError(f"Line {i+1} in FASTQ file is invalid")
+                raise InvalidFileError(f"Line {i + 1} in FASTQ file is invalid")
         # At the end of the file, the last sequence or score block
         # must have properly ended
         if in_sequence or in_scores:
@@ -392,7 +392,7 @@ class FastqFile(TextFile, MutableMapping):
                     yield identifier, ("".join(seq_str_list), scores)
                 else:  # score_len > seq_len
                     raise InvalidFileError(
-                        "The amount of scores is not equal to the sequence " "length"
+                        "The amount of scores is not equal to the sequence length"
                     )
 
             else:

biotite/sequence/io/genbank/file.py

@@ -80,7 +80,7 @@ class GenBankFile(TextFile):
     >>> print(content)
     ['One line', 'A second line']
     >>> print(subfields)
-    OrderedDict([('SUBFIELD1', ['Single Line']), ('SUBFIELD2', ['Two', 'lines'])])
+    OrderedDict({'SUBFIELD1': ['Single Line'], 'SUBFIELD2': ['Two', 'lines']})
 
     Adding an additional field:
 
@@ -391,7 +391,7 @@ class GenBankFile(TextFile):
             The field name.
         content : list of str
             The content lines.
-        subfield_dict : dict of str -> str, optional
+        subfields : dict of str -> str, optional
             The subfields of the field.
             The dictionary maps subfield names to the content lines of
             the respective subfield.
@@ -432,7 +432,7 @@ class GenBankFile(TextFile):
             The field name.
         content : list of str
             The content lines.
-        subfield_dict : dict of str -> str, optional
+        subfields : dict of str -> str, optional
             The subfields of the field.
             The dictionary maps subfield names to the content lines of
             the respective subfield.

biotite/sequence/io/genbank/sequence.py

@@ -82,6 +82,8 @@ def get_annotated_sequence(gb_file, format="gb", include_only=None):
     ----------
     gb_file : GenBankFile
         The GenBank file to read the fields from.
+    format : {'gb', 'gp'}
+        Whether the file is a *GenBank* or *GenPept* file.
     include_only : iterable object of str, optional
         List of names of feature keys, which should included
         in the annotation. By default all features are included.

biotite/sequence/io/gff/convert.py

@@ -84,7 +84,7 @@ def set_annotation(gff_file, annotation, seqid=None, source=None, is_stranded=Tr
     for feature in sorted(annotation):
         if len(feature.locs) > 1 and "ID" not in feature.qual:
             raise ValueError(
-                "The 'Id' qualifier is required " "for features with multiple locations"
+                "The 'Id' qualifier is required for features with multiple locations"
             )
         ## seqid ##
         if seqid is not None and " " in seqid:

biotite/sequence/io/gff/file.py

@@ -303,8 +303,7 @@ class GFFFile(TextFile):
     def __getitem__(self, index):
         if (index >= 0 and index >= len(self)) or (index < 0 and -index > len(self)):
             raise IndexError(
-                f"Index {index} is out of range for GFFFile with "
-                f"{len(self)} entries"
+                f"Index {index} is out of range for GFFFile with {len(self)} entries"
             )
 
         line_index = self._entries[index]

biotite/sequence/profile.py

@@ -95,7 +95,7 @@ class SequenceProfile(object):
     gaps : ndarray, dtype=int, shape=n
         Array which indicates the number of gaps at each position.
     alphabet : Alphabet, length=k
-        Alphabet of sequences of sequence profile
+        Alphabet of sequences of sequence profile.
 
     Attributes
     ----------
@@ -264,15 +264,14 @@ class SequenceProfile(object):
         alphabet : bool
             This alphabet will be used when creating the SequenceProfile
             object. If no alphabet is selected, the alphabet for this
-            SequenceProfile
+            :class:`SequenceProfile`.
             object will be calculated from the sequences of object
             Alignment.
-            (Default: None).
 
         Returns
         -------
         profile: SequenceProfile
-            The created SequenceProfile object
+            The created :class:`SequenceProfile` object.
         """
         sequences = get_codes(alignment)
         if alphabet is None:
@@ -306,13 +305,12 @@ class SequenceProfile(object):
             If true, returns consensus sequence as GeneralSequence
             object.
             Otherwise, the consensus sequence object type is chosen
-            based on the alphabet of this SequenceProfile object
-            (Default: False).
+            based on the alphabet of this SequenceProfile object.
 
         Returns
         -------
         consensus: Sequence
-            The calculated consensus sequence
+            The calculated consensus sequence.
         """
         # https://en.wikipedia.org/wiki/International_Union_of_Pure_and_Applied_Chemistry#Amino_acid_and_nucleotide_base_codes
         if as_general:
@@ -420,14 +418,13 @@ class SequenceProfile(object):
 
         Parameters
         ----------
-        pseudocount: int, optional
+        pseudocount : int, optional
             Amount added to the number of observed cases in order to
             change the expected probability of the PPM.
-            (Default: 0)
 
         Returns
         -------
-        ppm: ndarray, dtype=float, shape=(n,k)
+        ppm : ndarray, dtype=float, shape=(n,k)
             The calculated the position probability matrix.
         """
         if pseudocount < 0:
@@ -456,17 +453,16 @@ class SequenceProfile(object):
 
         Parameters
         ----------
-        pseudocount: int, optional
-            Amount added to the number of observed cases in order to change
-            the expected probability of the PPM.
-            (Default: 0)
-        background_frequencies: ndarray, shape=(k,), dtype=float, optional
+        background_frequencies : ndarray, shape=(k,), dtype=float, optional
             The background frequencies for each symbol in the alphabet.
             By default, a uniform distribution is assumed.
+        pseudocount : int, optional
+            Amount added to the number of observed cases in order to change
+            the expected probability of the PPM.
 
         Returns
         -------
-        pwm: ndarray, dtype=float, shape=(n,k)
+        pwm : ndarray, dtype=float, shape=(n,k)
             The calculated the position weight matrix.
         """
         if background_frequencies is None:
@@ -490,14 +486,13 @@ class SequenceProfile(object):
         ----------
         sequence : Sequence
            The input sequence.
-        pseudocount: int, optional
+        pseudocount : int, optional
             Amount added to the number of observed cases in order to change
             the expected probability of the PPM.
-            (Default: 0)
 
         Returns
         -------
-        probability: float
+        probability : float
            The calculated probability for the input sequence based on
            the PPM.
         """
@@ -526,17 +521,16 @@ class SequenceProfile(object):
         ----------
         sequence : Sequence
            The input sequence.
-        pseudocount: int, optional
-            Amount added to the number of observed cases in order to change
-            the expected probability of the PPM.
-            (Default: 0)
-        background_frequencies: ndarray, shape=(k,), dtype=float, optional
+        background_frequencies : ndarray, shape=(k,), dtype=float, optional
             The background frequencies for each symbol in the alphabet.
             By default a uniform distribution is assumed.
+        pseudocount : int, optional
+            Amount added to the number of observed cases in order to change
+            the expected probability of the PPM.
 
         Returns
         -------
-        score: float
+        score : float
            The calculated score for the input sequence based on
            the PWM.
         """

biotite/sequence/search.py

@@ -39,7 +39,6 @@ def find_subsequence(sequence, query):
     >>> sub_seq = NucleotideSequence("TGA")
     >>> print(find_subsequence(main_seq, sub_seq))
     [2 6]
-
     """
     if not sequence.get_alphabet().extends(query.get_alphabet()):
         raise ValueError("The sequences alphabets are not equal")

biotite/sequence/seqtypes.py

@@ -200,7 +200,6 @@ class NucleotideSequence(Sequence):
         TGCGAA
         >>> print(dna_seq.reverse().complement())
         AAGCGT
-
         """
         # Interpreting the sequence code of this object in the
         # complementary alphabet gives the complementary symbols
@@ -226,7 +225,7 @@ class NucleotideSequence(Sequence):
         complete : bool, optional
             If true, the complete sequence is translated. In this case
             the sequence length must be a multiple of 3.
-            Otherwise all ORFs are translated. (Default: False)
+            Otherwise all ORFs are translated.
         codon_table : CodonTable, optional
             The codon table to be used. By default the default table
             will be used
@@ -236,7 +235,6 @@ class NucleotideSequence(Sequence):
             even if the start codon codes for another amino acid.
             Otherwise the translation starts with the amino acid
             the codon codes for. Only applies, if `complete` is false.
-            (Default: False)
 
         Returns
         -------
@@ -266,7 +264,6 @@ class NucleotideSequence(Sequence):
         ...    print(seq)
         MML*
         ML*
-
         """
         if self._alphabet != NucleotideSequence.alphabet_unamb:
             raise AlphabetError("Translation requires unambiguous alphabet")
@@ -586,6 +583,11 @@ class ProteinSequence(Sequence):
         in the protein and the average isotopic mass of one water
         molecule.
 
+        Parameters
+        ----------
+        monoisotopic : bool
+            Use the mass of the most common isotope.
+
         Returns
         -------
         weight : float
@@ -599,7 +601,7 @@ class ProteinSequence(Sequence):
 
         if np.isnan(weight):
             raise ValueError(
-                "Sequence contains ambiguous amino acids, " "cannot calculate weight"
+                "Sequence contains ambiguous amino acids, cannot calculate weight"
             )
         return weight
 
@@ -700,6 +702,11 @@ class PurePositionalSequence(Sequence):
     This class is similar to :class:`PositionalSequence`, but the symbols are not
     derived from an original sequence, but are the pure position.
     Hence, there is no meaningful string representation of the sequence and its symbols.
+
+    Parameters
+    ----------
+    length : int
+        The length of the sequence.
     """
 
     def __init__(self, length):

biotite/sequence/sequence.py

@@ -139,7 +139,6 @@ class Sequence(Copyable, metaclass=abc.ABCMeta):
     >>> dna_seq_concat = dna_seq + dna_seq_rev
     >>> print(dna_seq_concat)
     ACGTAATGCA
-
     """
 
     def __init__(self, sequence=()):
@@ -354,7 +353,7 @@ class Sequence(Copyable, metaclass=abc.ABCMeta):
 
         Parameters
         ----------
-        alpahabet_size : int
+        alphabet_size : int
             The size of the alphabet.
 
         Returns

biotite/structure/__init__.py

@@ -125,9 +125,11 @@ from .pseudoknots import *
 from .rdf import *
 from .repair import *
 from .residues import *
+from .rings import *
 from .sasa import *
 from .sequence import *
 from .sse import *
 from .superimpose import *
+from .tm import *
 from .transform import *
 # util and segments are used internally

biotite/structure/alphabet/i3d.py

@@ -31,7 +31,7 @@ class I3DSequence(Sequence):
         May take upper or lower case letters.
         By default the sequence is empty.
 
-    See also
+    See Also
     --------
     to_3di : Create 3Di sequences from a structure.
 
@@ -39,7 +39,6 @@ class I3DSequence(Sequence):
     ----------
 
     .. footbibliography::
-
     """
 
     alphabet = LetterAlphabet("acdefghiklmnpqrstvwy")

biotite/structure/alphabet/pb.py

@@ -52,7 +52,7 @@ class ProteinBlocksSequence(Sequence):
         May take upper or lower case letters.
         By default the sequence is empty.
 
-    See also
+    See Also
     --------
     to_protein_blocks : Create *Protein Blocks* sequences from a structure.
 
@@ -60,7 +60,6 @@ class ProteinBlocksSequence(Sequence):
     ----------
 
     .. footbibliography::
-
     """
 
     alphabet = LetterAlphabet("abcdefghijklmnopz")

biotite/structure/alphabet/unkerasify.py

@@ -41,7 +41,13 @@ class ActivationType(enum.IntEnum):
 
 
 class KerasifyParser:
-    """An incomplete parser for model files serialized with `kerasify`.
+    """
+    An incomplete parser for model files serialized with `kerasify`.
+
+    Parameters
+    ----------
+    file : file-like
+        The ``.kerasify`` file to parse.
 
     Notes
     -----
@@ -65,7 +71,7 @@ class KerasifyParser:
             (w1,) = self._get("I")
             (b0,) = self._get("I")
             weights = (
-                np.frombuffer(self._read(f"={w0*w1}f"), dtype="f4")
+                np.frombuffer(self._read(f"={w0 * w1}f"), dtype="f4")
                 .reshape(w0, w1)
                 .copy()
             )

biotite/structure/atoms.py

@@ -35,6 +35,11 @@ class _AtomArrayBase(Copyable, metaclass=abc.ABCMeta):
     :class:`AtomArrayStack`.
     It implements functionality for annotation arrays and also
     rudimentarily for coordinates.
+
+    Parameters
+    ----------
+    length : int
+        The amount of atoms in the structure.
     """
 
     def __init__(self, length):
@@ -96,11 +101,11 @@ class _AtomArrayBase(Copyable, metaclass=abc.ABCMeta):
             The annotation category to be added.
         dtype : type or str
             A type instance or a valid *NumPy* *dtype* string.
-            Defines the type of the annotation
+            Defines the type of the annotation.
 
         See Also
         --------
-        set_annotation
+        set_annotation : Assign directly a value to an annotation.
 
         Notes
         -----
@@ -171,7 +176,7 @@ class _AtomArrayBase(Copyable, metaclass=abc.ABCMeta):
         array = np.asarray(array)
         if len(array) != self._array_length:
             raise IndexError(
-                f"Expected array length {self._array_length}, " f"but got {len(array)}"
+                f"Expected array length {self._array_length}, but got {len(array)}"
             )
         if category in self._annot:
             # If the annotation already exists, find the compatible dtype
@@ -244,7 +249,7 @@ class _AtomArrayBase(Copyable, metaclass=abc.ABCMeta):
         ----------
         item : AtomArray or AtomArrayStack
             The object to compare the annotation arrays with.
-        equal_nan: bool
+        equal_nan : bool
             Whether to count `nan` values as equal. Default: True.
 
         Returns
@@ -323,17 +328,16 @@ class _AtomArrayBase(Copyable, metaclass=abc.ABCMeta):
             if isinstance(self, AtomArray):
                 if value.ndim != 2:
                     raise ValueError(
-                        "A 2-dimensional ndarray is expected " "for an AtomArray"
+                        "A 2-dimensional ndarray is expected for an AtomArray"
                     )
             elif isinstance(self, AtomArrayStack):
                 if value.ndim != 3:
                     raise ValueError(
-                        "A 3-dimensional ndarray is expected " "for an AtomArrayStack"
+                        "A 3-dimensional ndarray is expected for an AtomArrayStack"
                     )
             if value.shape[-2] != self._array_length:
                 raise ValueError(
-                    f"Expected array length {self._array_length}, "
-                    f"but got {len(value)}"
+                    f"Expected array length {self._array_length}, but got {len(value)}"
                 )
             if value.shape[-1] != 3:
                 raise TypeError("Expected 3 coordinates for each atom")
@@ -358,13 +362,12 @@ class _AtomArrayBase(Copyable, metaclass=abc.ABCMeta):
                 if isinstance(self, AtomArray):
                     if value.ndim != 2:
                         raise ValueError(
-                            "A 2-dimensional ndarray is expected " "for an AtomArray"
+                            "A 2-dimensional ndarray is expected for an AtomArray"
                         )
                 else:  # AtomArrayStack
                     if value.ndim != 3:
                         raise ValueError(
-                            "A 3-dimensional ndarray is expected "
-                            "for an AtomArrayStack"
+                            "A 3-dimensional ndarray is expected for an AtomArrayStack"
                         )
                 if value.shape[-2:] != (3, 3):
                     raise TypeError("Box must be a 3x3 matrix (three vectors)")
@@ -448,9 +451,9 @@ class Atom(Copyable):
 
     Parameters
     ----------
-    coord: list or ndarray
+    coord : list or ndarray
         The x, y and z coordinates.
-    kwargs
+    **kwargs
         Atom annotations as key value pair.
 
     Attributes
@@ -472,7 +475,6 @@ class Atom(Copyable):
     CA
     >>> print(atom.coord)
     [1. 2. 3.]
-
     """
 
     def __init__(self, coord, **kwargs):
@@ -632,6 +634,10 @@ class AtomArray(_AtomArrayBase):
         The single value in the tuple is
         the length of the atom array.
 
+    See Also
+    --------
+    AtomArrayStack : Representation of multiple structure models.
+
     Examples
     --------
     Creating an atom array from atoms:
@@ -700,10 +706,6 @@ class AtomArray(_AtomArrayBase):
             Shape of the array.
             The single value in the tuple is
             the :func:`array_length()`.
-
-        See Also
-        --------
-        array_length
         """
         return (self.array_length(),)
 
@@ -895,9 +897,9 @@ class AtomArrayStack(_AtomArrayBase):
         The numbers correspond to the stack depth
         and array length, respectively.
 
-    See also
+    See Also
     --------
-    AtomArray
+    AtomArray : Representation of a single structure model.
 
     Examples
     --------
@@ -1195,9 +1197,18 @@ def array(atoms):
                 f"annotation categories as the atom at index 0"
             )
     array = AtomArray(len(atoms))
+
     # Add all (also optional) annotation categories
     for name in names:
-        array.add_annotation(name, dtype=type(atoms[0]._annot[name]))
+        value = atoms[0]._annot[name]
+        if isinstance(value, str):
+            # Find maximum string length across all atoms for this annotation
+            max_len = max(len(str(atom._annot[name])) for atom in atoms)
+            dtype = f"<U{max_len}"
+        else:
+            dtype = type(value)
+        array.add_annotation(name, dtype=dtype)
+
     # Add all atoms to AtomArray
     for i in range(len(atoms)):
         for name in names:
@@ -1443,8 +1454,7 @@ def repeat(atoms, coord):
     if isinstance(atoms, AtomArray):
         if coord.ndim != 3:
             raise ValueError(
-                f"Expected 3 dimensions for the coordinate array, "
-                f"but got {coord.ndim}"
+                f"Expected 3 dimensions for the coordinate array, but got {coord.ndim}"
             )
         repeated = AtomArray(new_length)
         repeated.coord = coord.reshape((new_length, 3))
@@ -1452,16 +1462,14 @@ def repeat(atoms, coord):
     elif isinstance(atoms, AtomArrayStack):
         if coord.ndim != 4:
             raise ValueError(
-                f"Expected 4 dimensions for the coordinate array, "
-                f"but got {coord.ndim}"
+                f"Expected 4 dimensions for the coordinate array, but got {coord.ndim}"
             )
         repeated = AtomArrayStack(atoms.stack_depth(), new_length)
         repeated.coord = coord.reshape((atoms.stack_depth(), new_length, 3))
 
     else:
         raise TypeError(
-            f"Expected 'AtomArray' or 'AtomArrayStack', "
-            f"but got {type(atoms).__name__}"
+            f"Expected 'AtomArray' or 'AtomArrayStack', but got {type(atoms).__name__}"
         )
 
     for category in atoms.get_annotation_categories():