biotite 1.0.1__cp311-cp311-win_amd64.whl → 1.2.0__cp311-cp311-win_amd64.whl

biotite/sequence/align/pairwise.pyx

@@ -37,11 +37,11 @@ ctypedef fused CodeType2:
 def align_ungapped(seq1, seq2, matrix, score_only=False):
     """
     align_ungapped(seq1, seq2, matrix, score_only=False)
-    
+
     Align two sequences without insertion of gaps.
-    
+
     Both sequences need to have the same length.
-    
+
     Parameters
     ----------
     seq1, seq2 : Sequence
@@ -50,7 +50,7 @@ def align_ungapped(seq1, seq2, matrix, score_only=False):
         The substitution matrix used for scoring.
     score_only : bool, optional
         If true return only the score instead of an alignment.
-    
+
     Returns
     -------
     score : Alignment or int
@@ -105,27 +105,27 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
 
     Perform an optimal alignment of two sequences based on a
     dynamic programming algorithm.
-    
+
     This algorithm yields an optimal alignment, i.e. the sequences
     are aligned in the way that results in the highest similarity
     score. This operation can be very time and space consuming,
     because both scale linearly with each sequence length.
-    
+
     The aligned sequences do not need to be instances from the same
     :class:`Sequence` subclass, since they do not need to have the same
     alphabet. The only requirement is that the
     :class:`SubstitutionMatrix`' alphabets extend the alphabets of the
     two sequences.
-    
+
     This function can either perform a global alignment, based on the
     Needleman-Wunsch algorithm :footcite:`Needleman1970` or a local
     alignment, based on the Smith–Waterman algorithm
     :footcite:`Smith1981`.
-    
+
     Furthermore this function supports affine gap penalties using the
     Gotoh algorithm :footcite:`Gotoh1982`, however, this requires
     approximately 4 times the RAM space and execution time.
-    
+
     Parameters
     ----------
     seq1, seq2 : Sequence
@@ -141,7 +141,7 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
         The values need to be negative. (Default: *-10*)
     terminal_penalty : bool, optional
         If true, gap penalties are applied to terminal gaps.
-        If `local` is true, this parameter has no effect. 
+        If `local` is true, this parameter has no effect.
         (Default: True)
     local : bool, optional
         If false, a global alignment is performed, otherwise a local
@@ -151,26 +151,26 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
         When the number of branches exceeds this value in the traceback
         step, no further branches are created.
         (Default: 1000)
-    
+
     Returns
     -------
     alignments : list, type=Alignment
         A list of alignments.
         Each alignment in the list has the same maximum similarity
         score.
-    
-    See also
+
+    See Also
     --------
     align_banded
-    
+
     References
     ----------
-    
+
     .. footbibliography::
-    
+
     Examples
     --------
-    
+
     >>> seq1 = NucleotideSequence("ATACGCTTGCT")
     >>> seq2 = NucleotideSequence("AGGCGCAGCT")
     >>> matrix = SubstitutionMatrix.std_nucleotide_matrix()
@@ -178,10 +178,10 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
     >>> for a in ali:
     ...     print(a, "\\n")
     ATACGCTTGCT
-    AGGCGCA-GCT 
+    AGGCGCA-GCT
     <BLANKLINE>
     ATACGCTTGCT
-    AGGCGC-AGCT 
+    AGGCGC-AGCT
     <BLANKLINE>
     """
     # Check matrix alphabets
@@ -204,7 +204,7 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
         raise ValueError(
             "Maximum number of returned alignments must be at least 1"
         )
-    
+
 
     # This implementation uses transposed tables in comparison
     # to the common visualization
@@ -213,7 +213,7 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
     trace_table = np.zeros(( len(seq1)+1, len(seq2)+1 ), dtype=np.uint8)
     code1 = seq1.code
     code2 = seq2.code
-    
+
     # Table filling
     ###############
     if affine_penalty:
@@ -275,8 +275,8 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
             trace_table[0,1:] = TraceDirectionLinear.GAP_LEFT
         _fill_align_table(code1, code2, matrix.score_matrix(), trace_table,
                           score_table, gap_penalty, terminal_penalty, local)
-    
-    
+
+
     # Traceback
     ###########
     # Stores all possible traces (= possible alignments)
@@ -292,7 +292,7 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
     if local:
         # The start point is the maximal score in the table
         # Multiple starting points possible,
-        # when duplicates of maximal score exist 
+        # when duplicates of maximal score exist
         if affine_penalty:
             # The maximum score in the gap score tables do not need to
             # be considered, as these starting positions would indicate
@@ -352,7 +352,7 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
             # Diagonals are only needed for banded alignments
             lower_diag=0, upper_diag=0
         )
-    
+
     # Replace gap entries in trace with -1
     for i, trace in enumerate(trace_list):
         trace = np.flip(trace, axis=0)
@@ -361,7 +361,7 @@ def align_optimal(seq1, seq2, matrix, gap_penalty=-10,
         gap_filter[np.unique(trace[:,1], return_index=True)[1], 1] = True
         trace[~gap_filter] = -1
         trace_list[i] = trace
-    
+
     # Limit the number of generated alignments to `max_number`:
     # In most cases this is achieved by discarding branches in
     # 'follow_trace()', however, if multiple local alignment starts
@@ -406,13 +406,13 @@ def _fill_align_table(CodeType1[:] code1 not None,
     local
         Indicates, whether a local alignment should be performed.
     """
-    
+
     cdef int i, j
     cdef int max_i, max_j
     cdef int32 from_diag, from_left, from_top
     cdef uint8 trace
     cdef int32 score
-    
+
     # For local alignments terminal gaps on the right side are ignored
     # anyway, as the alignment should stop before
     if local:
@@ -439,16 +439,16 @@ def _fill_align_table(CodeType1[:] code1 not None,
                 from_top = score_table[i-1, j]
             else:
                 from_top = score_table[i-1, j] + gap_penalty
-            
+
             trace = get_trace_linear(from_diag, from_left, from_top, &score)
-            
+
             # Local alignment specialty:
             # If score is less than or equal to 0,
             # then the score of the cell remains 0
             # and the trace ends here
             if local == True and score <= 0:
                 continue
-            
+
             score_table[i,j] = score
             trace_table[i,j] = trace
 
@@ -496,7 +496,7 @@ def _fill_align_table_affine(CodeType1[:] code1 not None,
     local
         Indicates, whether a local alignment should be performed.
     """
-    
+
     cdef int i, j
     cdef int max_i, max_j
     cdef int32 mm_score, g1m_score, g2m_score
@@ -505,7 +505,7 @@ def _fill_align_table_affine(CodeType1[:] code1 not None,
     cdef int32 m_score, g1_score, g2_score
     cdef int32 similarity_score
     cdef uint8 trace
-    
+
     # For local alignments terminal gaps on the right and the bottom are
     # ignored anyway, as the alignment should stop before
     if local:
@@ -513,7 +513,7 @@ def _fill_align_table_affine(CodeType1[:] code1 not None,
     # Used in case terminal gaps are not penalized
     i_max = trace_table.shape[0] -1
     j_max = trace_table.shape[1] -1
-    
+
     # Starts at 1 since the first row and column are already filled
     for i in range(1, trace_table.shape[0]):
         for j in range(1, trace_table.shape[1]):
@@ -538,7 +538,7 @@ def _fill_align_table_affine(CodeType1[:] code1 not None,
             else:
                 mg2_score  =  m_table[i-1,j] + gap_open
                 g2g2_score = g2_table[i-1,j] + gap_ext
-            
+
             trace = get_trace_affine(
                 mm_score, g1m_score, g2m_score,
                 mg1_score, g1g1_score,

biotite/sequence/align/selector.pyx

@@ -275,7 +275,7 @@ class SyncmerSelector:
     permutation : Permutation
         The permutation.
 
-    See also
+    See Also
     --------
     CachedSyncmerSelector
         A cached variant with faster syncmer selection at the cost of
@@ -546,7 +546,7 @@ class CachedSyncmerSelector(SyncmerSelector):
     permutation : Permutation
         The permutation.
 
-    See also
+    See Also
     --------
     SyncmerSelector
         A standard variant for syncmer selection.

biotite/sequence/align/statistics.py

@@ -168,7 +168,7 @@ class EValueEstimator:
             raise ValueError("A symmetric substitution matrix is required")
         if not matrix.get_alphabet1().extends(alphabet):
             raise ValueError(
-                "The substitution matrix is not compatible " "with the given alphabet"
+                "The substitution matrix is not compatible with the given alphabet"
             )
         score_matrix = matrix.score_matrix()[: len(alphabet), : len(alphabet)]
         if (

biotite/sequence/alphabet.py

@@ -201,7 +201,7 @@ class Alphabet(object):
         symbols : array-like
             The symbols to encode.
         dtype : dtype, optional
-            The dtype of the output ndarray. (Default: `int64`)
+            The dtype of the output ndarray.
 
         Returns
         -------
@@ -361,7 +361,7 @@ class LetterAlphabet(Alphabet):
             :class:`ndarray`, :class:`str` or :class:`bytes` object
             containing the symbols is provided, instead of e.g. a list.
         dtype : dtype, optional
-            For compatibility with superclass. The value is ignored
+            For compatibility with superclass. The value is ignored.
 
         Returns
         -------
@@ -410,6 +410,9 @@ class LetterAlphabet(Alphabet):
             symbols = symbols.astype("U1")
         return symbols
 
+    def is_letter_alphabet(self):
+        return True
+
     def __contains__(self, symbol):
         if not isinstance(symbol, (str, bytes)):
             return False

biotite/sequence/annotation.py

@@ -24,7 +24,7 @@ class Location:
 
     Objects of this class are immutable.
 
-    Attributes
+    Parameters
     ----------
     first : int
         Starting base or residue position of the feature.
@@ -35,6 +35,11 @@ class Location:
         Always :attr:`Strand.FORWARD` for peptide features.
     defect : Defect
         A possible defect of the location.
+
+    Attributes
+    ----------
+    first, last, strand, defect
+        Same as the parameters.
     """
 
     class Defect(Flag):
@@ -92,8 +97,8 @@ class Location:
     def __repr__(self):
         """Represent Location as a string for debugging."""
         return (
-            f'Location({self._first}, {self._last}, strand={"Location." + str(self._strand)}, '
-            f'defect={"Location." + str(self._defect)})'
+            f"Location({self._first}, {self._last}, strand={'Location.' + str(self._strand)}, "
+            f"defect={'Location.' + str(self._defect)})"
         )
 
     @property
@@ -356,7 +361,7 @@ class Annotation(Copyable):
     def __repr__(self):
         """Represent Annotation as a string for debugging."""
         return (
-            f'Annotation([{", ".join([feat.__repr__() for feat in self._features])}])'
+            f"Annotation([{', '.join([feat.__repr__() for feat in self._features])}])"
         )
 
     def __copy_create__(self):
@@ -384,8 +389,7 @@ class Annotation(Copyable):
         """
         if not isinstance(feature, Feature):
             raise TypeError(
-                f"Only 'Feature' objects are supported, "
-                f"not {type(feature).__name__}"
+                f"Only 'Feature' objects are supported, not {type(feature).__name__}"
             )
         self._features.add(feature)
 
@@ -498,7 +502,7 @@ class Annotation(Copyable):
     def __delitem__(self, item):
         if not isinstance(item, Feature):
             raise TypeError(
-                f"Only 'Feature' objects are supported, " f"not {type(item).__name__}"
+                f"Only 'Feature' objects are supported, not {type(item).__name__}"
             )
         self.del_feature(item)
 
@@ -550,12 +554,12 @@ class AnnotatedSequence(Copyable):
 
     Parameters
     ----------
+    annotation : Annotation
+        The annotation corresponding to `sequence`.
     sequence : Sequence
         The sequence.
         Usually a :class:`NucleotideSequence` or
         :class:`ProteinSequence`.
-    annotation : Annotation
-        The annotation corresponding to `sequence`.
     sequence_start : int, optional
         By default, the first symbol of the sequence is corresponding
         to location 1 of the features in the annotation. The location
@@ -564,16 +568,17 @@ class AnnotatedSequence(Copyable):
 
     Attributes
     ----------
-    sequence : Sequence
-        The represented sequence.
     annotation : Annotation
         The annotation corresponding to `sequence`.
+    sequence : Sequence
+        The represented sequence.
     sequence_start : int
         The location of the first symbol in the sequence.
 
-    See also
+    See Also
     --------
-    Annotation, Sequence
+    Annotation : An annotation separated from a sequence.
+    Sequence : A sequence separated from an annotation.
 
     Examples
     --------
@@ -666,6 +671,7 @@ class AnnotatedSequence(Copyable):
 
         Returns
         -------
+        rev_sequence : Sequence
             The reverse complement of the annotated sequence.
         """
         rev_seqstart = sequence_start

biotite/sequence/codon.py

@@ -216,7 +216,7 @@ class CodonTable(object):
         code : bool
             If true, the dictionary contains keys and values as code.
             Otherwise, the dictionary contains strings for codons and
-            amino acid. (Default: False)
+            amino acid.
 
         Returns
         -------
@@ -248,7 +248,6 @@ class CodonTable(object):
         ----------
         code : bool
             If true, the code will be returned instead of strings.
-            (Default: False)
 
         Returns
         -------

biotite/sequence/graphics/alignment.py

@@ -54,7 +54,7 @@ class SymbolPlotter(metaclass=abc.ABCMeta):
         Parameters
         ----------
         bbox : Bbox
-            The axes area to plot the symbol in
+            The axes area to plot the symbol in.
         alignment : Alignment
             The respective alignment.
         column_i : int
@@ -148,7 +148,7 @@ class LetterPlotter(SymbolPlotter, metaclass=abc.ABCMeta):
         -------
         color : object
             A *Matplotlib* compatible color used for the background
-            or the symbol itself at the specifed position
+            or the symbol itself at the specifed position.
         """
         pass
 
@@ -321,7 +321,7 @@ class LetterTypePlotter(LetterPlotter):
     axes : Axes
         A *Matplotlib* axes, that is used as plotting area.
     alphabet : Alphabet
-        The alphabet of the alignment(s) to be plotted
+        The alphabet of the alignment(s) to be plotted.
     color_scheme : str or list of (tuple or str), optional
         Either a valid color scheme name
         (e.g. ``"flower"``, ``"clustalx"``, ``blossom``, etc.)
@@ -391,7 +391,6 @@ class ArrayPlotter(LetterPlotter):
     font_param : dict, optional
         Additional parameters that is given to the
         :class:`matplotlib.Text` instance of each symbol.
-
     """
 
     def __init__(
@@ -524,7 +523,7 @@ def plot_alignment(
         but this behavior can be changed using the `number_functions`
         parameter.
     number_size : float, optional
-        The font size of the position numbers
+        The font size of the position numbers.
     number_functions : list of [(None or Callable(int -> int)], optional
         By default the position of the first symbol in a sequence is 1,
         i.e. the sequence position is the sequence index incremented by
@@ -541,7 +540,7 @@ def plot_alignment(
         Must be the same size and order as the sequences in the
         alignment.
     label_size : float, optional
-        Font size of the labels
+        Font size of the labels.
     show_line_position : bool, optional
         If true the position within a line is plotted below the
         alignment.
@@ -549,14 +548,9 @@ def plot_alignment(
         The spacing between the alignment lines. 1.0 means that the size
         is equal to the size of a symbol box.
     symbol_spacing : int, optional
-        А space is placed between each number of elements desired
+        A space is placed between each number of elements desired
         by variable.
 
-    See also
-    --------
-    plot_alignment_similarity_based
-    plot_alignment_type_based
-
     Notes
     -----
     The labels are placed on the Y-axis of the `axes` and the numbers
@@ -722,8 +716,6 @@ def plot_alignment_similarity_based(
     alignment : Alignment
         The pairwise or multiple sequence alignment to be plotted.
         The alphabet of each sequence in the alignment must be the same.
-    symbol_plotter : SymbolPlotter
-        Defines how the symbols in the alignment are drawn.
     symbols_per_line : int, optional
         The amount of alignment columns that are diplayed per line.
     show_numbers : bool, optional
@@ -738,7 +730,7 @@ def plot_alignment_similarity_based(
         but this behavior can be changed using the `number_functions`
         parameter.
     number_size : float, optional
-        The font size of the position numbers
+        The font size of the position numbers.
     number_functions : list of [(None or Callable(int -> int)], optional
         By default the position of the first symbol in a sequence is 1,
         i.e. the sequence position is the sequence index incremented by
@@ -755,7 +747,7 @@ def plot_alignment_similarity_based(
         Must be the same size and order as the sequences in the
         alignment.
     label_size : float, optional
-        Font size of the labels
+        Font size of the labels.
     show_line_position : bool, optional
         If true the position within a line is plotted below the
         alignment.
@@ -782,19 +774,19 @@ def plot_alignment_similarity_based(
         If true, the symbols themselves are colored.
         If false, the symbols are black, and the boxes behind the
         symbols are colored.
+    symbol_spacing : int, optional
+        A space is placed between each number of elements desired
+        by variable.
     symbol_size : float, optional
         Font size of the sequence symbols.
     symbol_param : dict
         Additional parameters that is given to the
         :class:`matplotlib.Text` instance of each symbol.
-    symbol_spacing : int, optional
-        А space is placed between each number of elements desired
-        by variable.
 
-    See also
+    See Also
     --------
-    plot_alignment
-    LetterSimilarityPlotter
+    plot_alignment : Analogous functionality with a customizable :class:`SymbolPlotter`.
+    LetterSimilarityPlotter : The :class:`SymbolPlotter` used in this function.
 
     Notes
     -----
@@ -883,8 +875,6 @@ def plot_alignment_type_based(
     alignment : Alignment
         The pairwise or multiple sequence alignment to be plotted.
         The alphabet of each sequence in the alignment must be the same.
-    symbol_plotter : SymbolPlotter
-        Defines how the symbols in the alignment are drawn.
     symbols_per_line : int, optional
         The amount of alignment columns that are diplayed per line.
     show_numbers : bool, optional
@@ -899,7 +889,7 @@ def plot_alignment_type_based(
         but this behavior can be changed using the `number_functions`
         parameter.
     number_size : float, optional
-        The font size of the position numbers
+        The font size of the position numbers.
     number_functions : list of [(None or Callable(int -> int)], optional
         By default the position of the first symbol in a sequence is 1,
         i.e. the sequence position is the sequence index incremented by
@@ -916,7 +906,7 @@ def plot_alignment_type_based(
         Must be the same size and order as the sequences in the
         alignment.
     label_size : float, optional
-        Font size of the labels
+        Font size of the labels.
     show_line_position : bool, optional
         If true the position within a line is plotted below the
         alignment.
@@ -939,13 +929,13 @@ def plot_alignment_type_based(
         Additional parameters that is given to the
         :class:`matplotlib.Text` instance of each symbol.
     symbol_spacing : int, optional
-        А space is placed between each number of elements desired
+        A space is placed between each number of elements desired
         by variable.
 
-    See also
+    See Also
     --------
-    plot_alignment
-    LetterTypePlotter
+    plot_alignment : Analogous functionality with a customizable :class:`SymbolPlotter`.
+    LetterTypePlotter : The :class:`SymbolPlotter` used in this function.
     """
     alphabet = alignment.sequences[0].get_alphabet()
     symbol_plotter = LetterTypePlotter(
@@ -1007,9 +997,6 @@ def plot_alignment_array(
         The array to map fluorescence values to score residues.
         By default the normalized score is 1 for maximum recognition
         and 0 for non-recognition (no color).
-    symbol_plotter : SymbolPlotter
-        Instance of ArrayPlotter. Defines how the symbols are drawn
-        in the alignment.
     symbols_per_line : int, optional
         The amount of alignment columns that are displayed per line.
     show_numbers : bool, optional
@@ -1024,7 +1011,7 @@ def plot_alignment_array(
         but this behavior can be changed using the `number_functions`
         parameter.
     number_size : float, optional
-        The font size of the position numbers
+        The font size of the position numbers.
     number_functions : list of [(None or Callable(int -> int)], optional
         By default the position of the first symbol in a sequence is 1,
         i.e. the sequence position is the sequence index incremented by
@@ -1041,7 +1028,7 @@ def plot_alignment_array(
         Must be the same size and order as the sequences in the
         alignment.
     label_size : float, optional
-        Font size of the labels
+        Font size of the labels.
     show_line_position : bool, optional
         If true the position within a line is plotted below the
         alignment.
@@ -1054,20 +1041,19 @@ def plot_alignment_array(
         The boxes are
         colored based on the normalized intensity value on the
         given *Matplotlib* Colormap.
+    symbol_spacing : int, optional
+        A space is placed between each number of elements desired
+        by variable.
     symbol_size : float, optional
         Font size of the sequence symbols.
     symbol_param : dict
         Additional parameters that is given to the
         :class:`matplotlib.Text` instance of each symbol.
-    symbol_spacing : int, optional
-        A space is placed between each number of elements desired
-        by variable.
 
     Notes
     -----
     A '*' represents a sequence match on the alignment
     A '-' represents a sequence gap on the alignment
-
     """
     symbol_plotter = ArrayPlotter(
         axes,

biotite/sequence/graphics/color_schemes/3di_flower.json

@@ -0,0 +1,48 @@
+{
+    "comment": "Generated with 'gecos --matrix 3Di --name flower --lmin 60 --lmax 80 -f 3di_flower.json'",
+    "name": "flower",
+    "alphabet": [
+        "a",
+        "c",
+        "d",
+        "e",
+        "f",
+        "g",
+        "h",
+        "i",
+        "k",
+        "l",
+        "m",
+        "n",
+        "p",
+        "q",
+        "r",
+        "s",
+        "t",
+        "v",
+        "w",
+        "y"
+    ],
+    "colors": {
+        "a": "#a189a1",
+        "c": "#ff5806",
+        "d": "#ab9a93",
+        "e": "#e754d5",
+        "f": "#8191b5",
+        "g": "#cbc7ae",
+        "h": "#dac1bc",
+        "i": "#5eaf6e",
+        "k": "#04c1fd",
+        "l": "#ff544b",
+        "m": "#07e560",
+        "n": "#f28d05",
+        "p": "#b68767",
+        "q": "#bc8277",
+        "r": "#eebe86",
+        "s": "#ffa103",
+        "t": "#a4c49a",
+        "v": "#ed6903",
+        "w": "#3a97d8",
+        "y": "#f7adfd"
+    }
+}