Logo Search packages:      
Sourcecode: python-biopython version File versions  Download package

PhyloXML.py

# Copyright (C) 2009 by Eric Talevich (eric.talevich@gmail.com)
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.

"""Classes corresponding to phyloXML elements.

See U{ http://phyloxml.org/ } for the official specification.

See also Han and Zmasek (2009) doi:10.1186/1471-2105-10-356
"""
__docformat__ = "epytext en"

import re
import warnings

from Bio import Alphabet
from Bio.Align import MultipleSeqAlignment
from Bio.Seq import Seq
from Bio.SeqFeature import SeqFeature, FeatureLocation
from Bio.SeqRecord import SeqRecord
import Bio

from Bio.Phylo import BaseTree


00027 class PhyloXMLWarning(Warning):
    """Warning for non-compliance with the phyloXML specification."""
    pass


def _check_str(text, testfunc):
    """Check a string using testfunc, and warn if there's no match."""
    if text is not None and not testfunc(text):
        warnings.warn("String %s doesn't match the given regexp" % text,
                      PhyloXMLWarning, stacklevel=2)


# Core elements

00041 class PhyloElement(BaseTree.TreeElement):
    """Base class for all PhyloXML objects."""


00045 class Phyloxml(PhyloElement):
    """Root node of the PhyloXML document.

    Contains an arbitrary number of Phylogeny elements, possibly followed by
    elements from other namespaces.

    @param attributes: (XML namespace definitions)
    @param phylogenies: list of phylogenetic trees
    @param other: list of arbitrary non-phyloXML elements, if any
    """
    def __init__(self, attributes, phylogenies=None, other=None):
        self.attributes = attributes
        self.phylogenies = phylogenies or []
        self.other = other or []

00060     def __getitem__(self, index):
        """Get a phylogeny by index or name."""
        if isinstance(index, int) or isinstance(index, slice):
            return self.phylogenies[index]
        if not isinstance(index, basestring):
            raise KeyError("can't use %s as an index" % type(index))
        for tree in self.phylogenies:
            if tree.name == index:
                return tree
        else:
            raise KeyError("no phylogeny found with name " + repr(index))

00072     def __iter__(self):
        """Iterate through the phylogenetic trees in this object."""
        return iter(self.phylogenies)

00076     def __len__(self):
        """Number of phylogenetic trees in this object."""
        return len(self.phylogenies)

    def __str__(self):
        return '%s([%s])' % (self.__class__.__name__,
                             ',\n'.join(map(str, self.phylogenies)))


00085 class Other(PhyloElement):
    """Container for non-phyloXML elements in the tree.

    Usually, an Other object will have either a 'value' or a non-empty list
    of 'children', but not both. This is not enforced here, though.

    @param tag: local tag for the XML node
    @param namespace: XML namespace for the node -- should not be the default
        phyloXML namespace.
    @param attributes: string attributes on the XML node
    @param value: text contained directly within this XML node
    @param children: list of child nodes, if any (also Other instances)
    """
    def __init__(self, tag, namespace=None, attributes=None, value=None,
            children=None):
        self.tag = tag
        self.namespace = namespace
        self.attributes = attributes
        self.value = value
        self.children = children or []

00106     def __iter__(self):
        """Iterate through the children of this object (if any)."""
        return iter(self.children)


00111 class Phylogeny(PhyloElement, BaseTree.Tree):
    """A phylogenetic tree.

    @param root: the root node/clade of this tree
    @param rooted: True if this tree is rooted
    @param rerootable: True if this tree is rerootable
    @param branch_length_unit: unit for branch_length values on clades
    @type type: str

    @param name: string identifier for this tree, not required to be unique
    @param id: unique identifier for this tree (type Id)
    @param description: plain-text description
    @param date: date for the root node of this tree (type Date)
    @param confidences: list of Confidence objects for this tree
    @param clade_relations: list of CladeRelation objects
    @param sequence_relations: list of SequenceRelation objects
    @param properties: list of Property objects
    @param other: list of non-phyloXML elements (type Other)
    """
    def __init__(self, root=None, rooted=True,
            rerootable=None, branch_length_unit=None, type=None,
            # Child nodes
            name=None, id=None, description=None, date=None,
            # Collections
            confidences=None, clade_relations=None, sequence_relations=None,
            properties=None, other=None,
            ):
        assert isinstance(rooted, bool)
        self.root = root
        self.rooted = rooted
        self.rerootable = rerootable
        self.branch_length_unit = branch_length_unit
        self.type = type
        self.name = name
        self.id = id
        self.description = description
        self.date = date
        self.confidences = confidences or []
        self.clade_relations = clade_relations or []
        self.sequence_relations = sequence_relations or []
        self.properties = properties or []
        self.other = other or []

    @classmethod
00155     def from_tree(cls, tree, **kwargs):
        """Create a new Phylogeny given a Tree (from Newick/Nexus or BaseTree).

        Keyword arguments are the usual Phylogeny constructor parameters.
        """
        phy = cls(
                root=Clade.from_clade(tree.root),
                rooted=tree.rooted,
                name=tree.name,
                id=(tree.id is not None) and Id(str(tree.id)) or None)
        phy.__dict__.update(kwargs)
        return phy

    @classmethod
00169     def from_clade(cls, clade, **kwargs):
        """Create a new Phylogeny given a Newick or BaseTree Clade object.

        Keyword arguments are the usual PhyloXML Clade constructor parameters.
        """
        return Clade.from_clade(clade).to_phylogeny(**kwargs)

00176     def as_phyloxml(self):
        """Return this tree, a PhyloXML-compatible Phylogeny object.

        Overrides the BaseTree method.
        """
        return self

00183     def to_phyloxml_container(self, **kwargs):
        """Create a new Phyloxml object containing just this phylogeny."""
        return Phyloxml(kwargs, phylogenies=[self])

00187     def to_alignment(self):
        """Construct an alignment from the aligned sequences in this tree."""
        def is_aligned_seq(elem):
            if isinstance(elem, Sequence) and elem.mol_seq.is_aligned:
                return True
            return False
        seqs = self._filter_search(is_aligned_seq, 'preorder', True)
        try:
            first_seq = seqs.next()
        except StopIteration:
            # No aligned sequences were found --> empty MSA
            return MultipleSeqAlignment([])
        msa = MultipleSeqAlignment([first_seq.to_seqrecord()],
                                   first_seq.get_alphabet())
        msa.extend(seq.to_seqrecord() for seq in seqs)
        return msa

    # Singular property for plural attribute
00205     def _get_confidence(self):
        """Equivalent to self.confidences[0] if there is only 1 value.

        See also: Clade.confidence, Clade.taxonomy
        """
        if len(self.confidences) == 0:
            return None
        if len(self.confidences) > 1:
            raise AttributeError("more than 1 confidence value available; "
                                 "use Phylogeny.confidences")
        return self.confidences[0]

    def _set_confidence(self, value):
        if value is None:
            # Special case: mirror the behavior of _get_confidence
            self.confidences = []
            return
        if isinstance(value, float) or isinstance(value, int):
            value = Confidence(value)
        elif not isinstance(value, Confidence):
            raise ValueError("value must be a number or Confidence instance")
        if len(self.confidences) == 0:
            self.confidences.append(value)
        elif len(self.confidences) == 1:
            self.confidences[0] = value
        else:
            raise ValueError("multiple confidence values already exist; "
                             "use Phylogeny.confidences instead")

    def _del_confidence(self):
        self.confidences = []

    confidence = property(_get_confidence, _set_confidence, _del_confidence)


00240 class Clade(PhyloElement, BaseTree.Clade):
    """Describes a branch of the current phylogenetic tree.

    Used recursively, describes the topology of a phylogenetic tree.

    Both 'color' and 'width' elements should be interpreted by client code as
    applying to the whole clade, including all descendents, unless overwritten
    in-sub clades. This module doesn't automatically assign these attributes to
    sub-clades to achieve this cascade -- and neither should you.

    @param branch_length: parent branch length of this clade
    @param id_source: link other elements to a clade (on the xml-level)

    @param name: short string label for this clade
    @param confidences: list of Confidence objects, used to indicate the
        support for a clade/parent branch.
    @param width: branch width for this clade (including branch from parent)
    @param color: color used for graphical display of this clade
    @param node_id: unique identifier for the root node of this clade
    @param taxonomies: list of Taxonomy objects
    @param sequences: list of Sequence objects
    @param events: describe such events as gene-duplications at the root
        node/parent branch of this clade
    @param binary_characters: a BinaryCharacters object
    @param distributions: list of Distribution objects
    @param date: a date for the root node of this clade (type Date)
    @param references: list of Reference objects
    @param properties: list of Property objects
    @param clades: list of sub-clades (type Clade)
    @param other: list of non-phyloXML objects
    """
    def __init__(self,
            # Attributes
            branch_length=None, id_source=None,
            # Child nodes
            name=None, width=None, color=None, node_id=None, events=None,
            binary_characters=None, date=None,
            # Collections
            confidences=None, taxonomies=None, sequences=None,
            distributions=None, references=None, properties=None, clades=None,
            other=None,
            ):
        self.branch_length = branch_length
        self.id_source = id_source
        self.name = name
        self.width = width
        self.color = color
        self.node_id = node_id
        self.events = events
        self.binary_characters = binary_characters
        self.date = date
        self.confidences = confidences or []
        self.taxonomies = taxonomies or []
        self.sequences = sequences or []
        self.distributions = distributions or []
        self.references = references or []
        self.properties = properties or []
        self.clades = clades or []
        self.other = other or []

    @classmethod
00301     def from_clade(cls, clade, **kwargs):
        """Create a new PhyloXML Clade from a Newick or BaseTree Clade object.
        
        Keyword arguments are the usual PhyloXML Clade constructor parameters.
        """
        new_clade = cls(branch_length=clade.branch_length,
                    name=clade.name)
        new_clade.clades = [cls.from_clade(c) for c in clade]
        new_clade.confidence = clade.confidence
        new_clade.__dict__.update(kwargs)
        return new_clade

00313     def to_phylogeny(self, **kwargs):
        """Create a new phylogeny containing just this clade."""
        phy = Phylogeny(root=self, date=self.date)
        phy.__dict__.update(kwargs)
        return phy

    # Shortcuts for list attributes that are usually only 1 item
    # NB: Duplicated from Phylogeny class
    def _get_confidence(self):
        if len(self.confidences) == 0:
            return None
        if len(self.confidences) > 1:
            raise AttributeError("more than 1 confidence value available; "
                                 "use Clade.confidences")
        return self.confidences[0]

    def _set_confidence(self, value):
        if value is None:
            # Special case: mirror the behavior of _get_confidence
            self.confidences = []
            return
        if isinstance(value, float) or isinstance(value, int):
            value = Confidence(value)
        elif not isinstance(value, Confidence):
            raise ValueError("value must be a number or Confidence instance")
        if len(self.confidences) == 0:
            self.confidences.append(value)
        elif len(self.confidences) == 1:
            self.confidences[0] = value
        else:
            raise ValueError("multiple confidence values already exist; "
                             "use Phylogeny.confidences instead")

    def _del_confidence(self):
        self.confidences = []

    confidence = property(_get_confidence, _set_confidence, _del_confidence)

    def _get_taxonomy(self):
        if len(self.taxonomies) == 0:
            return None
        if len(self.taxonomies) > 1:
            raise AttributeError("more than 1 taxonomy value available; "
                                 "use Clade.taxonomies")
        return self.taxonomies[0]

    def _set_taxonomy(self, value):
        if not isinstance(value, Taxonomy):
            raise ValueError("assigned value must be a Taxonomy instance")
        if len(self.taxonomies) == 0:
            self.taxonomies.append(value)
        elif len(self.taxonomies) == 1:
            self.taxonomies[0] = value
        else:
            raise ValueError("multiple taxonomy values already exist; "
                             "use Phylogeny.taxonomies instead")

    taxonomy = property(_get_taxonomy, _set_taxonomy)

    # Syntax sugar for setting the branch color
    def _get_color(self):
        return self._color

    def _set_color(self, arg):
        if arg is None or isinstance(arg, BranchColor):
            self._color = arg
        elif isinstance(arg, basestring):
            if arg in BranchColor.color_names:
                # Known color name
                self._color = BranchColor.from_name(arg)
            elif arg.startswith('#') and len(arg) == 7:
                # HTML-style hex string
                self._color = BranchColor.from_hex(arg)
            else:
                raise ValueError("invalid color string %s" % arg)
        elif hasattr(arg, '__iter__') and len(arg) == 3:
            # RGB triplet
            self._color = BranchColor(*arg)
        else:
            raise ValueError("invalid color value %s" % arg)

    color = property(_get_color, _set_color, doc="Branch color.")


# PhyloXML-specific complex types

00399 class Accession(PhyloElement):
    """Captures the local part in a sequence identifier.

    Example: In 'UniProtKB:P17304', the Accession instance attribute 'value' is
    'P17304' and the 'source' attribute is 'UniProtKB'.
    """
    def __init__(self, value, source):
        self.value = value
        self.source = source

00409     def __str__(self):
        """Show the class name and an identifying attribute."""
        return '%s:%s' % (self.source, self.value)


00414 class Annotation(PhyloElement):
    """The annotation of a molecular sequence.

    It is recommended to annotate by using the optional 'ref' attribute (some
    examples of acceptable values for the ref attribute: 'GO:0008270',
    'KEGG:Tetrachloroethene degradation', 'EC:1.1.1.1').

    @type ref: str
    @param source: plain-text source for this annotation
    @param evidence: describe evidence as free text (e.g. 'experimental')
    @type type: str

    @param desc: free text description
    @param confidence: state the type and value of support (type Confidence)
    @param properties: list of typed and referenced annotations from external
        resources
    @type uri: Uri
    """
    re_ref = re.compile(r'[a-zA-Z0-9_]+:[a-zA-Z0-9_\.\-\s]+')

    def __init__(self, 
            # Attributes
            ref=None, source=None, evidence=None, type=None,
            # Child nodes
            desc=None, confidence=None, uri=None,
            # Collection
            properties=None):
        _check_str(ref, self.re_ref.match)
        self.ref = ref
        self.source = source
        self.evidence = evidence
        self.type = type
        self.desc = desc
        self.confidence = confidence
        self.uri = uri
        self.properties = properties or []


00452 class BinaryCharacters(PhyloElement):
    """The names and/or counts of binary characters present, gained, and lost
    at the root of a clade. 
    """
    def __init__(self,
            # Attributes
            type=None, gained_count=None, lost_count=None, present_count=None,
            absent_count=None,
            # Child nodes (flattened into collections)
            gained=None, lost=None, present=None, absent=None):
        self.type=type
        self.gained_count=gained_count
        self.lost_count=lost_count
        self.present_count=present_count
        self.absent_count=absent_count
        self.gained=gained or []
        self.lost=lost or []
        self.present=present or []
        self.absent=absent or []


00473 class BranchColor(PhyloElement):
    """Indicates the color of a clade when rendered graphically.

    The color should be interpreted by client code (e.g. visualization
    programs) as applying to the whole clade, unless overwritten by the
    color(s) of sub-clades.

    Color values must be integers from 0 to 255.
    """

    color_names = {
            'red':      (255,   0,   0),
            'r':        (255,   0,   0),
            'yellow':   (255, 255,   0),
            'y':        (255, 255,   0),
            'green':    (  0, 128,   0),
            'g':        (  0, 128,   0),
            'cyan':     (  0, 255, 255),
            'c':        (  0, 255, 255),
            'blue':     (  0,   0, 255),
            'b':        (  0,   0, 255),
            'magenta':  (255,   0, 255),
            'm':        (255,   0, 255),
            'black':    (  0,   0,   0),
            'k':        (  0,   0,   0),
            'white':    (255, 255, 255),
            'w':        (255, 255, 255),
            # Names standardized in HTML/CSS spec
            # http://w3schools.com/html/html_colornames.asp
            'maroon':   (128,   0,   0),
            'olive':    (128, 128,   0),
            'lime':     (  0, 255,   0),
            'aqua':     (  0, 255, 255),
            'teal':     (  0, 128, 128),
            'navy':     (  0,   0, 128),
            'fuchsia':  (255,   0, 255),
            'purple':   (128,   0, 128),
            'silver':   (192, 192, 192),
            'gray':     (128, 128, 128),
            # More definitions from matplotlib/gcolor2
            'grey':     (128, 128, 128),
            'pink':     (255, 192, 203),
            'salmon':   (250, 128, 114),
            'orange':   (255, 165,   0),
            'gold':     (255, 215,   0),
            'tan':      (210, 180, 140),
            'brown':    (165,  42,  42),
            }

    def __init__(self, red, green, blue):
        for color in (red, green, blue):
            assert (isinstance(color, int) and
                    0 <= color <= 255
                    ), "Color values must be integers between 0 and 255."
        self.red = red
        self.green = green
        self.blue = blue

    @classmethod
00532     def from_hex(cls, hexstr):
        """Construct a BranchColor object from a hexadecimal string.

        The string format is the same style used in HTML and CSS, such as
        '#FF8000' for an RGB value of (255, 128, 0).
        """
        assert (isinstance(hexstr, basestring) and
                hexstr.startswith('#') and
                len(hexstr) == 7
                ), "need a 24-bit hexadecimal string, e.g. #000000"
        def unpack(cc):
            return int('0x'+cc, base=16)
        RGB = hexstr[1:3], hexstr[3:5], hexstr[5:]
        return cls(*map(unpack, RGB))

    @classmethod
00548     def from_name(cls, colorname):
        """Construct a BranchColor object by the color's name."""
        return cls(*cls.color_names[colorname])

00552     def to_hex(self):
        """Return a 24-bit hexadecimal RGB representation of this color.

        The returned string is suitable for use in HTML/CSS, as a color
        parameter in matplotlib, and perhaps other situations.

        Example:

            >>> bc = BranchColor(12, 200, 100)
            >>> bc.to_hex()
            '#0cc864'
        """
        return '#' + hex(
                self.red * (16**4)
                + self.green * (16**2)
                + self.blue)[2:].zfill(6)

00569     def to_rgb(self):
        """Return a tuple of RGB values (0 to 255) representing this color.

        Example:

            >>> bc = BranchColor(255, 165, 0)
            >>> bc.to_rgb()
            (255, 165, 0)
        """
        return (self.red, self.green, self.blue)

00580     def __repr__(self):
        """Preserve the standard RGB order when representing this object."""
        return (u'%s(red=%d, green=%d, blue=%d)'
                % (self.__class__.__name__, self.red, self.green, self.blue))

00585     def __str__(self):
        """Show the color's RGB values."""
        return "(%d, %d, %d)" % (self.red, self.green, self.blue)


00590 class CladeRelation(PhyloElement):
    """Expresses a typed relationship between two clades.

    For example, this could be used to describe multiple parents of a clade.

    @type id_ref_0: str
    @type id_ref_1: str
    @type distance: str
    @type type: str

    @type confidence: Confidence
    """
    def __init__(self, type, id_ref_0, id_ref_1,
            distance=None, confidence=None):
        self.distance = distance
        self.type = type
        self.id_ref_0 = id_ref_0
        self.id_ref_1 = id_ref_1
        self.confidence = confidence


00611 class Confidence(PhyloElement):
    """A general purpose confidence element.

    For example, this can be used to express the bootstrap support value of a
    clade (in which case the 'type' attribute is 'bootstrap').

    @type value: float
    @type type: str
    """
    def __init__(self, value, type='unknown'):
        self.value = value
        self.type = type

    def __float__(self):
        return float(self.value)

    def __int__(self):
        return int(self.value)


00631 class Date(PhyloElement):
    """A date associated with a clade/node.

    Its value can be numerical by using the 'value' element and/or free text
    with the 'desc' element' (e.g. 'Silurian'). If a numerical value is used, it
    is recommended to employ the 'unit' attribute.

    @param unit: type of numerical value (e.g. 'mya' for 'million years ago')

    @type value: float
    @param desc: plain-text description of the date
    @param minimum: lower bound on the date value
    @param maximum: upper bound on the date value
    """
    def __init__(self, value=None, unit=None, desc=None, 
            minimum=None, maximum=None):
        self.value = value
        self.unit = unit
        self.desc = desc
        self.minimum = minimum
        self.maximum = maximum

00653     def __str__(self):
        """Show the class name and the human-readable date."""
        if self.unit and self.value is not None:
            return '%s %s' % (self.value, self.unit)
        if self.desc is not None:
            return self.desc
        return self.__class__.__name__


00662 class Distribution(PhyloElement):
    """Geographic distribution of the items of a clade (species, sequences).

    Intended for phylogeographic applications.

    The location can be described either by free text in the 'desc' element
    and/or by the coordinates of one or more 'Points' (similar to the 'Point'
    element in Google's KML format) or by 'Polygons'.
    """
    def __init__(self, desc=None, points=None, polygons=None):
        self.desc = desc
        self.points = points or []
        self.polygons = polygons or []


00677 class DomainArchitecture(PhyloElement):
    """Domain architecture of a protein.

    @param length: total length of the protein sequence (type int)
    @param domains: list of ProteinDomain objects
    """
    def __init__(self, length=None, domains=None):
        self.length = length
        self.domains = domains


00688 class Events(PhyloElement):
    """Events at the root node of a clade (e.g. one gene duplication).

    All attributes are set to None by default, but this object can also be
    treated as a dictionary, in which case None values are treated as missing
    keys and deleting a key resets that attribute's value back to None.
    """
    ok_type = set(('transfer', 'fusion', 'speciation_or_duplication', 'other',
                    'mixed', 'unassigned'))

    def __init__(self, type=None, duplications=None, speciations=None,
            losses=None, confidence=None):
        _check_str(type, self.ok_type.__contains__)
        self.type = type
        self.duplications = duplications
        self.speciations = speciations
        self.losses = losses
        self.confidence = confidence

    def items(self):
        return [(k, v) for k, v in self.__dict__.iteritems() if v is not None]

    def keys(self):
        return [k for k, v in self.__dict__.iteritems() if v is not None]

    def values(self):
        return [v for v in self.__dict__.itervalues() if v is not None]

    def __len__(self):
        return len(self.values())

    def __getitem__(self, key):
        if not hasattr(self, key):
            raise KeyError(key)
        val = getattr(self, key)
        if val is None:
            raise KeyError("%s has not been set in this object" % repr(key))
        return val

    def __setitem__(self, key, val):
        setattr(self, key, val)

    def __delitem__(self, key):
        setattr(self, key, None)

    def __iter__(self):
        return iter(self.keys())

    def __contains__(self, key):
        return (hasattr(self, key) and getattr(self, key) is not None)


00740 class Id(PhyloElement):
    """A general-purpose identifier element.

    Allows to indicate the provider (or authority) of an identifier, e.g. NCBI,
    along with the value itself.
    """
    def __init__(self, value, provider=None):
        self.value = value
        self.provider = provider

    def __str__(self):
        if self.provider is not None:
            return '%s:%s' % (self.provider, self.value)
        return self.value


00756 class MolSeq(PhyloElement):
    """Store a molecular sequence.

    @param value: the sequence, as a string
    @param is_aligned: True is mol_seq is aligned (usu. meaning gaps are
        introduced and all aligned seqs are the same length)
    """
    re_value = re.compile(r'[a-zA-Z\.\-\?\*_]+')

    def __init__(self, value, is_aligned=None):
        _check_str(value, self.re_value.match)
        self.value = value
        self.is_aligned = is_aligned

    def __str__(self):
        return self.value


00774 class Point(PhyloElement):
    """Geographic coordinates of a point, with an optional altitude.

    Used by element 'Distribution'.

    @param geodetic_datum: indicate the geodetic datum (also called 'map
        datum'). For example, Google's KML uses 'WGS84'. (required)
    @param lat: latitude
    @param long: longitude
    @param alt: altitude
    @param alt_unit: unit for the altitude (e.g. 'meter')
    """
    def __init__(self, geodetic_datum, lat, long, alt=None, alt_unit=None):
        self.geodetic_datum = geodetic_datum
        self.lat = lat
        self.long = long
        self.alt = alt
        self.alt_unit = alt_unit


00794 class Polygon(PhyloElement):
    """A polygon defined by a list of 'Points' (used by element 'Distribution').

    @param points: list of 3 or more points representing vertices.
    """
    def __init__(self, points=None):
        self.points = points or []

    def __str__(self):
        return '%s([%s])' % (self.__class__.__name__,
                             ',\n'.join(map(str, self.points)))


00807 class Property(PhyloElement):
    """A typed and referenced property from an external resources.

    Can be attached to 'Phylogeny', 'Clade', and 'Annotation' objects.

    @param ref: reference to an external resource, e.g. "NOAA:depth"

    @param unit: the unit of the property, e.g. "METRIC:m" (optional)

    @param datatype: indicates the type of a property and is limited to
        xsd-datatypes (e.g. 'xsd:string', 'xsd:boolean', 'xsd:integer',
        'xsd:decimal', 'xsd:float', 'xsd:double', 'xsd:date', 'xsd:anyURI').

    @param applies_to: indicates the item to which a property applies to (e.g.
        'node' for the parent node of a clade, 'parent_branch' for the parent
        branch of a clade, or just 'clade').

    @param id_ref: allows to attached a property specifically to one element
        (on the xml-level). (optional)

    @type value: str
    """
    re_ref = re.compile(r'[a-zA-Z0-9_]+:[a-zA-Z0-9_\.\-\s]+')
    ok_applies_to = set(('phylogeny', 'clade', 'node', 'annotation',
                         'parent_branch', 'other'))
    ok_datatype = set(('xsd:string', 'xsd:boolean', 'xsd:decimal', 'xsd:float',
        'xsd:double', 'xsd:duration', 'xsd:dateTime', 'xsd:time', 'xsd:date',
        'xsd:gYearMonth', 'xsd:gYear', 'xsd:gMonthDay', 'xsd:gDay',
        'xsd:gMonth', 'xsd:hexBinary', 'xsd:base64Binary', 'xsd:anyURI',
        'xsd:normalizedString', 'xsd:token', 'xsd:integer',
        'xsd:nonPositiveInteger', 'xsd:negativeInteger', 'xsd:long', 'xsd:int',
        'xsd:short', 'xsd:byte', 'xsd:nonNegativeInteger', 'xsd:unsignedLong',
        'xsd:unsignedInt', 'xsd:unsignedShort', 'xsd:unsignedByte',
        'xsd:positiveInteger'))

    def __init__(self, value, ref, applies_to, datatype,
            unit=None, id_ref=None):
        _check_str(ref, self.re_ref.match)
        _check_str(applies_to, self.ok_applies_to.__contains__)
        _check_str(datatype, self.ok_datatype.__contains__)
        _check_str(unit, self.re_ref.match)
        self.unit = unit
        self.id_ref = id_ref
        self.value = value
        self.ref = ref
        self.applies_to = applies_to
        self.datatype = datatype


00856 class ProteinDomain(PhyloElement):
    """Represents an individual domain in a domain architecture.

    The locations use 0-based indexing, as most Python objects including
    SeqFeature do, rather than the usual biological convention starting at 1.
    This means the start and end attributes can be used directly as slice
    indexes on Seq objects.

    @param start: start of the domain on the sequence, using 0-based indexing
    @type start: non-negative integer
    @param end: end of the domain on the sequence
    @type end: non-negative integer
    @param confidence: can be used to store e.g. E-values. (type float)
    @param id: unique identifier/name
    """
    # TODO: confirm that 'start' counts from 1, not 0
    def __init__(self, value, start, end, confidence=None, id=None):
        self.value = value
        self.start = start
        self.end = end
        self.confidence = confidence
        self.id = id

    @classmethod
    def from_seqfeature(cls, feat):
        return ProteinDomain(feat.id,
                feat.location.nofuzzy_start,
                feat.location.nofuzzy_end,
                confidence=feat.qualifiers.get('confidence'))

    def to_seqfeature(self):
        feat = SeqFeature(location=FeatureLocation(self.start, self.end),
                          id=self.value)
        if hasattr(self, 'confidence'):
            feat.qualifiers['confidence'] = self.confidence
        return feat


00894 class Reference(PhyloElement):
    """Literature reference for a clade.

    It is recommended to use the 'doi' attribute instead of the free text
    'desc' element whenever possible.
    """
    re_doi = re.compile(r'[a-zA-Z0-9_\.]+/[a-zA-Z0-9_\.]+')

    def __init__(self, doi=None, desc=None):
        _check_str(doi, self.re_doi.match)
        self.doi = doi
        self.desc = desc


00908 class Sequence(PhyloElement):
    """A molecular sequence (Protein, DNA, RNA) associated with a node.

    One intended use for 'id_ref' is to link a sequence to a taxonomy (via the
    taxonomy's 'id_source') in case of multiple sequences and taxonomies per
    node. 

    @param type: type of sequence ('dna', 'rna', or 'protein').
    @type id_ref: str
    @type id_source: str

    @param symbol: short  symbol of the sequence, e.g. 'ACTM' (max. 10 chars)
    @type accession: Accession
    @param name: full name of the sequence, e.g. 'muscle Actin'
    @param location: location of a sequence on a genome/chromosome.
    @type mol_seq: MolSeq
    @type uri: Uri
    @param annotations: list of Annotation objects
    @param domain_architecture: protein domains on this sequence (type
        DomainArchitecture)
    @param other: list of non-phyloXML elements (type Other)
    """
    alphabets = {'dna':     Alphabet.generic_dna,
                 'rna':     Alphabet.generic_rna,
                 'protein': Alphabet.generic_protein}
    re_symbol = re.compile(r'\S{1,10}')

    def __init__(self, 
            # Attributes
            type=None, id_ref=None, id_source=None,
            # Child nodes
            symbol=None, accession=None, name=None, location=None,
            mol_seq=None, uri=None, domain_architecture=None,
            # Collections
            annotations=None, other=None,
            ):
        _check_str(type, self.alphabets.__contains__)
        _check_str(symbol, self.re_symbol.match)
        self.type = type
        self.id_ref = id_ref
        self.id_source = id_source
        self.symbol = symbol
        self.accession = accession
        self.name = name
        self.location = location
        self.mol_seq = mol_seq
        self.uri = uri
        self.domain_architecture = domain_architecture
        self.annotations = annotations or []
        self.other = other or []

    @classmethod
00960     def from_seqrecord(cls, record, is_aligned=None):
        """Create a new PhyloXML Sequence from a SeqRecord object."""
        if is_aligned == None:
            is_aligned = isinstance(record.seq.alphabet, Alphabet.Gapped)
        params = {
                'accession': Accession(record.id, ''),
                'symbol': record.name,
                'name': record.description,
                'mol_seq': MolSeq(str(record.seq), is_aligned),
                }
        if isinstance(record.seq.alphabet, Alphabet.DNAAlphabet):
            params['type'] = 'dna'
        elif isinstance(record.seq.alphabet, Alphabet.RNAAlphabet):
            params['type'] = 'rna'
        elif isinstance(record.seq.alphabet, Alphabet.ProteinAlphabet):
            params['type'] = 'protein'

        # Unpack record.annotations
        for key in ('id_ref', 'id_source', 'location'):
            if key in record.annotations:
                params[key] = record.annotations[key]
        if isinstance(record.annotations.get('uri'), dict):
            params['uri'] = Uri(**record.annotations['uri'])
        # Build a Sequence.annotation object
        if record.annotations.get('annotations'):
            params['annotations'] = []
            for annot in record.annotations['annotations']:
                ann_args = {}
                for key in ('ref', 'source', 'evidence', 'type', 'desc'):
                    if key in annot:
                        ann_args[key] = annot[key]
                if isinstance(annot.get('confidence'), list):
                    ann_args['confidence'] = Confidence(
                                        *annot['confidence'])
                if isinstance(annot.get('properties'), list):
                    ann_args['properties'] = [Property(**prop)
                                        for prop in annot['properties']
                                        if isinstance(prop, dict)]
                params['annotations'].append(Annotation(**ann_args))

        # Unpack record.features
        if record.features:
            params['domain_architecture'] = DomainArchitecture(
                    length=len(record.seq),
                    domains=[ProteinDomain.from_seqfeature(feat)
                             for feat in record.features])

        return Sequence(**params)

01009     def to_seqrecord(self):
        """Create a SeqRecord object from this Sequence instance.
        
        The seqrecord.annotations dictionary is packed like so::

            { # Sequence attributes with no SeqRecord equivalent:
              'id_ref':     self.id_ref,
              'id_source':  self.id_source,
              'location':   self.location,
              'uri':        { 'value': self.uri.value,
                              'desc': self.uri.desc,
                              'type': self.uri.type },
              # Sequence.annotations attribute (list of Annotations)
              'annotations': [{ 'ref':      ann.ref,
                                'source':   ann.source,
                                'evidence': ann.evidence,
                                'type':     ann.type,
                                'confidence': [ ann.confidence.value,
                                                ann.confidence.type ],
                                'properties': [{ 'value': prop.value,
                                                 'ref': prop.ref,
                                                 'applies_to': prop.applies_to,
                                                 'datatype':   prop.datatype,
                                                 'unit':       prop.unit,
                                                 'id_ref':     prop.id_ref }
                                               for prop in ann.properties],
                              } for ann in self.annotations],
            }
        """
        def clean_dict(dct):
            """Remove None-valued items from a dictionary."""
            return dict((key, val) for key, val in dct.iteritems()
                        if val is not None)

        seqrec = SeqRecord(Seq(self.mol_seq.value, self.get_alphabet()),
                           **clean_dict({
                               'id':    str(self.accession),
                               'name':  self.symbol,
                               'description': self.name,
                               # 'dbxrefs': None,
                               }))
        if self.domain_architecture:
            seqrec.features = [dom.to_seqfeature()
                               for dom in self.domain_architecture.domains]
        # Sequence attributes with no SeqRecord equivalent
        seqrec.annotations = clean_dict({
                'id_ref':       self.id_ref,
                'id_source':    self.id_source,
                'location':     self.location,
                'uri':          self.uri and clean_dict({
                                    'value': self.uri.value,
                                    'desc': self.uri.desc,
                                    'type': self.uri.type,
                                    }),
                'annotations':  self.annotations and [
                    clean_dict({
                        'ref':          ann.ref,
                        'source':       ann.source,
                        'evidence':     ann.evidence,
                        'type':         ann.type,
                        'confidence':   ann.confidence and [
                                            ann.confidence.value,
                                            ann.confidence.type],
                        'properties':   [clean_dict({
                                            'value':      prop.value,
                                            'ref':        prop.ref,
                                            'applies_to': prop.applies_to,
                                            'datatype':   prop.datatype,
                                            'unit':       prop.unit,
                                            'id_ref':     prop.id_ref })
                                         for prop in ann.properties],
                        }) for ann in self.annotations],
                })
        return seqrec

    def get_alphabet(self):
        alph = self.alphabets.get(self.type, Alphabet.generic_alphabet)
        if self.mol_seq and self.mol_seq.is_aligned:
            return Alphabet.Gapped(alph)
        return alph


01091 class SequenceRelation(PhyloElement):
    """Express a typed relationship between two sequences.

    For example, this could be used to describe an orthology (in which case
    attribute 'type' is 'orthology'). 

    @param id_ref_0: first sequence reference identifier
    @param id_ref_1: second sequence reference identifier
    @param distance: distance between the two sequences (type float)
    @param type: describe the type of relationship

    @type confidence: Confidence
    """
    ok_type = set(('orthology', 'one_to_one_orthology', 'super_orthology',
        'paralogy', 'ultra_paralogy', 'xenology', 'unknown', 'other'))

    def __init__(self, type, id_ref_0, id_ref_1,
            distance=None, confidence=None):
        _check_str(type, self.ok_type.__contains__)
        self.distance = distance
        self.type = type
        self.id_ref_0 = id_ref_0
        self.id_ref_1 = id_ref_1
        self.confidence = confidence


01117 class Taxonomy(PhyloElement):
    """Describe taxonomic information for a clade.

    @param id_source: link other elements to a taxonomy (on the XML level)

    @param id: unique identifier of a taxon, e.g. Id('6500',
        provider='ncbi_taxonomy') for the California sea hare
    @param code: store UniProt/Swiss-Prot style organism codes, e.g. 'APLCA'
        for the California sea hare 'Aplysia californica' (restricted string)
    @param scientific_name: the standard scientific name for this organism,
        e.g. 'Aplysia californica' for the California sea hare
    @param authority: keep the authority, such as 'J. G. Cooper, 1863',
        associated with the 'scientific_name'
    @param common_names: list of common names for this organism
    @param synonyms: ???
    @param rank: taxonomic rank (restricted string)
    @type uri: Uri
    @param other: list of non-phyloXML elements (type Other)
    """
    re_code = re.compile(r'[a-zA-Z0-9_]{2,10}')
    ok_rank = set(('domain', 'kingdom', 'subkingdom', 'branch', 'infrakingdom',
        'superphylum', 'phylum', 'subphylum', 'infraphylum', 'microphylum',
        'superdivision', 'division', 'subdivision', 'infradivision',
        'superclass', 'class', 'subclass', 'infraclass', 'superlegion',
        'legion', 'sublegion', 'infralegion', 'supercohort', 'cohort',
        'subcohort', 'infracohort', 'superorder', 'order', 'suborder',
        'superfamily', 'family', 'subfamily', 'supertribe', 'tribe', 'subtribe',
        'infratribe', 'genus', 'subgenus', 'superspecies', 'species',
        'subspecies', 'variety', 'subvariety', 'form', 'subform', 'cultivar',
        'unknown', 'other'))

    def __init__(self, 
            # Attributes
            id_source=None,
            # Child nodes
            id=None, code=None, scientific_name=None, authority=None,
            rank=None, uri=None,
            # Collections
            common_names=None, synonyms=None, other=None,
            ):
        _check_str(code, self.re_code.match)
        _check_str(rank, self.ok_rank.__contains__)
        self.id_source = id_source
        self.id = id
        self.code = code
        self.scientific_name = scientific_name
        self.authority = authority
        self.rank = rank
        self.uri = uri
        self.common_names = common_names or []
        self.synonyms = synonyms or []
        self.other = other or []

01170     def __str__(self):
        """Show the class name and an identifying attribute."""
        if self.code is not None:
            return self.code
        if self.scientific_name is not None:
            return self.scientific_name
        if self.rank is not None:
            return self.rank
        if self.id is not None:
            return str(self.id)
        return self.__class__.__name__


01183 class Uri(PhyloElement):
    """A uniform resource identifier.

    In general, this is expected to be an URL (for example, to link to an image
    on a website, in which case the 'type' attribute might be 'image' and 'desc'
    might be 'image of a California sea hare').
    """
    def __init__(self, value, desc=None, type=None):
        self.value = value
        self.desc = desc
        self.type = type

    def __str__(self):
        if self.value:
            return self.value
        return repr(self)

Generated by  Doxygen 1.6.0   Back to index