biotite 1.0.1__cp310-cp310-win_amd64.whl → 1.2.0__cp310-cp310-win_amd64.whl

biotite/sequence/graphics/color_schemes/pb_flower.json

@@ -16,7 +16,8 @@
         "m",
         "n",
         "o",
-        "p"
+        "p",
+        "z"
     ],
     "colors": {
         "a": "#31b5fc",

biotite/sequence/graphics/colorschemes.py

@@ -94,27 +94,32 @@ def get_color_scheme(name, alphabet, default="#FFFFFF"):
     >>> print(color_scheme)
     ['#3737f5', '#37f537', '#f5f537', '#f53737']
     """
+    # Try exact alphabet match first
+    for scheme in _color_schemes:
+        if scheme["name"] == name and scheme["alphabet"] == alphabet:
+            return _fit_color_scheme(alphabet, scheme, default)
+    # If no exact match was found, try to find a scheme for an alphabet
+    # that extends the given alphabet
     for scheme in _color_schemes:
         if scheme["name"] == name and scheme["alphabet"].extends(alphabet):
-            colors = scheme["colors"]
-            # Replace None values with default color
-            colors = [color if color is not None else default for color in colors]
-            # Only return colors that are in scope of this alphabet
-            # and not the extended alphabet
-            return colors[: len(alphabet)]
+            return _fit_color_scheme(alphabet, scheme, default)
+
     raise ValueError(f"Unkown scheme '{name}' for given alphabet")
 
 
-def list_color_scheme_names(alphabet):
+def list_color_scheme_names(alphabet, strict=False):
     """
     Get a list of available color scheme names for a given alphabet.
 
     Parameters
     ----------
     alphabet : Alphabet
-        The alphbet to get the color scheme names for.
-        The alphabet of the scheme must equal or extend this parameter,
-        to be included in the list.
+        The alphabet to get the color scheme names for.
+    strict : bool, optional
+        If set to true, only schemes with an exact match to the given
+        alphabet are included in the list.
+        If set to false, schemes with an alphabet that extends the given
+        alphabet are also included.
 
     Returns
     -------
@@ -123,7 +128,9 @@ def list_color_scheme_names(alphabet):
     """
     scheme_list = []
     for scheme in _color_schemes:
-        if scheme["alphabet"].extends(alphabet):
+        if strict and scheme["alphabet"] == alphabet:
+            scheme_list.append(scheme["name"])
+        if not strict and scheme["alphabet"].extends(alphabet):
             scheme_list.append(scheme["name"])
     return scheme_list
 
@@ -135,3 +142,29 @@ _color_schemes = []
 for file_name in glob.glob(_scheme_dir + os.sep + "*.json"):
     scheme = load_color_scheme(file_name)
     _color_schemes.append(scheme)
+
+
+def _fit_color_scheme(alphabet, color_scheme, default_color):
+    """
+    Fit a color scheme to the given alphabet.
+
+    Parameters
+    ----------
+    alphabet : Alphabet
+        The alphabet to get the color scheme for.
+    color_scheme : dict
+        The color scheme.
+    default_color : str or tuple
+        The default color.
+
+    Returns
+    -------
+    scheme : list of str
+        The colors from the scheme.
+    """
+    colors = color_scheme["colors"]
+    # Replace None values with default color
+    colors = [color if color is not None else default_color for color in colors]
+    # Only return colors that are in scope of this alphabet
+    # and not the extended alphabet
+    return colors[: len(alphabet)]

biotite/sequence/graphics/dendrogram.py

@@ -25,8 +25,10 @@ def plot_dendrogram(
 
     Parameters
     ----------
+    axes : Axes
+        A *Matplotlib* axes, that is used as plotting area.
     tree : Tree
-        The tree to be visualized
+        The tree to be visualized.
     orientation : {'left', 'right', 'bottom', 'top'}, optional
         The position of the root node in the plot
     use_distances : bool, optional
@@ -38,7 +40,7 @@ def plot_dendrogram(
         The label of a leaf node is the entry at the position of its
         `index` attribute.
     label_size : float, optional
-        The font size of the labels
+        The font size of the labels.
     color : tuple or str, optional
         A *Matplotlib* compatible color, that is used to draw the lines
         of the dendrogram.

biotite/sequence/graphics/features.py

@@ -71,7 +71,7 @@ def plot_feature_map(
         If true, the sequence position the base/residue of a line is
         shown on the right side of the plot.
     number_size : float, optional
-        The font size of the position numbers
+        The font size of the position numbers.
     line_width : float, optional
         The size of the continuous line as fraction of the height of
         the drawn features.
@@ -416,7 +416,7 @@ class PromoterPlotter(FeaturePlotter):
     line_width : float, optional
         The width of the curved arrow tail.
     head_width : float, optional
-        The width of the arrow head
+        The width of the arrow head.
     head_length : float, optional
         The length of the arrow.
     head_height : float, optional

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

@@ -3,6 +3,7 @@
 # information.
 
 import warnings
+from numbers import Integral
 import numpy as np
 from biotite.sequence.align.alignment import get_codes
 from biotite.sequence.alphabet import LetterAlphabet
@@ -66,6 +67,9 @@ class SequenceProfile(object):
     It also saves the number of gaps at each position in the array
     'gaps'.
 
+    With :meth:`from_alignment()` a :class:`SequenceProfile` object can
+    be created from an indefinite number of aligned sequences.
+
     With :meth:`probability_matrix()` the position probability matrix
     can be created based on 'symbols' and a pseudocount.
 
@@ -73,9 +77,6 @@ class SequenceProfile(object):
     be created based on the before calculated position probability
     matrix and the background frequencies.
 
-    With :meth:`from_alignment()` a :class:`SequenceProfile` object can
-    be created from an indefinite number of aligned sequences.
-
     With :meth:`sequence_probability_from_matrix()` the probability of a
     sequence can be calculated based on the before calculated position
     probability matrix of this instance of object SequenceProfile.
@@ -94,7 +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
     ----------
@@ -105,6 +106,63 @@ class SequenceProfile(object):
         Array which indicates the number of gaps at each position.
     alphabet : Alphabet, length=k
         Alphabet of sequences of sequence profile
+
+    Examples
+    --------
+
+    Create a profile from a multiple sequence alignment:
+
+    >>> sequences = [
+    ...     NucleotideSequence("CGCTCATTC"),
+    ...     NucleotideSequence("CGCTATTC"),
+    ...     NucleotideSequence("CCCTCAATC"),
+    ... ]
+    >>> msa, _, _, _ = align_multiple(
+    ...     sequences, SubstitutionMatrix.std_nucleotide_matrix(), gap_penalty=-5
+    ... )
+    >>> print(msa)
+    CGCTCATTC
+    CGCT-ATTC
+    CCCTCAATC
+    >>> profile = SequenceProfile.from_alignment(msa)
+    >>> print(profile)
+      A C G T
+    0 0 3 0 0
+    1 0 1 2 0
+    2 0 3 0 0
+    3 0 0 0 3
+    4 0 2 0 0
+    5 3 0 0 0
+    6 1 0 0 2
+    7 0 0 0 3
+    8 0 3 0 0
+    >>> print(profile.gaps)
+    [0 0 0 0 1 0 0 0 0]
+
+    Slice the profile (masks and index arrays are also supported):
+
+    >>> print(profile[2:])
+      A C G T
+    0 0 3 0 0
+    1 0 0 0 3
+    2 0 2 0 0
+    3 3 0 0 0
+    4 1 0 0 2
+    5 0 0 0 3
+    6 0 3 0 0
+
+    Use the profile to compute the position probability matrix:
+
+    >>> print(profile.probability_matrix())
+    [[0.000 1.000 0.000 0.000]
+     [0.000 0.333 0.667 0.000]
+     [0.000 1.000 0.000 0.000]
+     [0.000 0.000 0.000 1.000]
+     [0.000 1.000 0.000 0.000]
+     [1.000 0.000 0.000 0.000]
+     [0.333 0.000 0.000 0.667]
+     [0.000 0.000 0.000 1.000]
+     [0.000 1.000 0.000 0.000]]
     """
 
     def __init__(self, symbols, gaps, alphabet):
@@ -156,8 +214,23 @@ class SequenceProfile(object):
             )
         self._gaps = new_gaps
 
+    def __str__(self):
+        # Add an additional row and column for the position and symbol indicators
+        print_matrix = np.full(
+            (self.symbols.shape[0] + 1, self.symbols.shape[1] + 1), "", dtype=object
+        )
+        print_matrix[1:, 1:] = self.symbols.astype(str)
+        print_matrix[0, 1:] = [str(sym) for sym in self.alphabet]
+        print_matrix[1:, 0] = [str(i) for i in range(self.symbols.shape[0])]
+        max_len = len(max(print_matrix.flatten(), key=len))
+        return "\n".join(
+            [
+                " ".join([str(cell).rjust(max_len) for cell in row])
+                for row in print_matrix
+            ]
+        )
+
     def __repr__(self):
-        """Represent SequenceProfile as a string for debugging."""
         return (
             f"SequenceProfile(np.{np.array_repr(self.symbols)}, "
             f"np.{np.array_repr(self.gaps)}, Alphabet({self.alphabet}))"
@@ -191,15 +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:
@@ -233,13 +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:
@@ -347,14 +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:
@@ -383,17 +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:
@@ -417,14 +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.
         """
@@ -453,17 +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.
         """
@@ -483,3 +550,12 @@ class SequenceProfile(object):
                 f"as 'symbols' {self.symbols.shape}"
             )
         return np.sum(pwm[np.arange(len(sequence)), sequence.code])
+
+    def __getitem__(self, index):
+        if isinstance(index, Integral):
+            # Do not allow to collapse dimensions
+            index = slice(index, index + 1)
+        return SequenceProfile(self.symbols[index], self.gaps[index], self.alphabet)
+
+    def __len__(self):
+        return len(self.symbols)

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")