<!-- Last modified: 2016.07.06 by Christian Zmasek -->
<!-- -->
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:phy="http://www.phyloxml.org"
- targetNamespace="http://www.phyloxml.org" elementFormDefault="qualified" attributeFormDefault="unqualified">
+ targetNamespace="http://www.phyloxml.org" elementFormDefault="qualified"
+ attributeFormDefault="unqualified">
<xs:annotation>
- <xs:documentation> phyloXML is an XML language to describe evolutionary trees and associated data. Version: 1.10.
- License: dual-licensed under the LGPL or Ruby's License. Copyright (c) 2008-2011 Christian M Zmasek.</xs:documentation>
+ <xs:documentation>phyloXML is an XML language to describe evolutionary trees and associated
+ data. Version: 1.20. License: dual-licensed under the LGPL or Ruby's License. Copyright (c)
+ 2008-2016 Christian M Zmasek.</xs:documentation>
</xs:annotation>
<!-- phyloxml is the root element:-->
<xs:element name="phyloxml" type="phy:Phyloxml"/>
<!-- phyloXML definition:-->
<xs:complexType name="Phyloxml">
<xs:annotation>
- <xs:documentation> 'phyloxml' is the name of the root element. Phyloxml contains an arbitrary number of
- 'phylogeny' elements (each representing one phylogeny) possibly followed by elements from other namespaces.
- </xs:documentation>
+ <xs:documentation> 'phyloxml' is the name of the root element. Phyloxml contains an
+ arbitrary number of 'phylogeny' elements (each representing one phylogeny) possibly
+ followed by elements from other namespaces. </xs:documentation>
</xs:annotation>
<xs:sequence maxOccurs="unbounded">
<xs:element name="phylogeny" type="phy:Phylogeny" minOccurs="0" maxOccurs="unbounded"/>
<!-- Phylogeny:-->
<xs:complexType name="Phylogeny">
<xs:annotation>
- <xs:documentation> Element Phylogeny is used to represent a phylogeny. The required attribute 'rooted' is used
- to indicate whether the phylogeny is rooted or not. The attribute 'rerootable' can be used to indicate that
- the phylogeny is not allowed to be rooted differently (i.e. because it is associated with root dependent
- data, such as gene duplications). The attribute 'type' can be used to indicate the type of phylogeny (i.e.
- 'gene tree'). It is recommended to use the attribute 'branch_length_unit' if the phylogeny has branch
- lengths. Element clade is used in a recursive manner to describe the topology of a phylogenetic
- tree.</xs:documentation>
+ <xs:documentation> Element Phylogeny is used to represent a phylogeny. The required
+ attribute 'rooted' is used to indicate whether the phylogeny is rooted or not. The
+ attribute 'rerootable' can be used to indicate that the phylogeny is not allowed to be
+ rooted differently (i.e. because it is associated with root dependent data, such as gene
+ duplications). The attribute 'type' can be used to indicate the type of phylogeny (i.e.
+ 'gene tree'). It is recommended to use the attribute 'branch_length_unit' if the
+ phylogeny has branch lengths. Element clade is used in a recursive manner to describe
+ the topology of a phylogenetic tree.</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="name" type="xs:token" minOccurs="0"/>
<xs:element name="date" type="xs:dateTime" minOccurs="0"/>
<xs:element name="confidence" type="phy:Confidence" minOccurs="0" maxOccurs="unbounded"/>
<xs:element name="clade" type="phy:Clade" minOccurs="0"/>
- <xs:element name="clade_relation" type="phy:CladeRelation" minOccurs="0" maxOccurs="unbounded"/>
- <xs:element name="sequence_relation" type="phy:SequenceRelation" minOccurs="0" maxOccurs="unbounded"/>
+ <xs:element name="clade_relation" type="phy:CladeRelation" minOccurs="0"
+ maxOccurs="unbounded"/>
+ <xs:element name="sequence_relation" type="phy:SequenceRelation" minOccurs="0"
+ maxOccurs="unbounded"/>
<xs:element name="property" type="phy:Property" minOccurs="0" maxOccurs="unbounded"/>
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
</xs:sequence>
<!-- Clade:-->
<xs:complexType name="Clade">
<xs:annotation>
- <xs:documentation> Element Clade is used in a recursive manner to describe the topology of a phylogenetic tree.
- The parent branch length of a clade can be described either with the 'branch_length' element or the
- 'branch_length' attribute (it is not recommended to use both at the same time, though). Usage of the
- 'branch_length' attribute allows for a less verbose description. Element 'confidence' is used to indicate
- the support for a clade/parent branch. Element 'events' is used to describe such events as gene-duplications
- at the root node/parent branch of a clade. Element 'width' is the branch width for this clade (including
- parent branch). Both 'color' and 'width' elements apply for the whole clade unless overwritten in-sub
- clades. Attribute 'id_source' is used to link other elements to a clade (on the xml-level).
- </xs:documentation>
+ <xs:documentation> Element Clade is used in a recursive manner to describe the topology of
+ a phylogenetic tree. The parent branch length of a clade can be described either with
+ the 'branch_length' element or the 'branch_length' attribute (it is not recommended to
+ use both at the same time, though). Usage of the 'branch_length' attribute allows for a
+ less verbose description. Element 'confidence' is used to indicate the support for a
+ clade/parent branch. Element 'events' is used to describe such events as
+ gene-duplications at the root node/parent branch of a clade. Element 'width' is the
+ branch width for this clade (including parent branch). Both 'color' and 'width' elements
+ apply for the whole clade unless overwritten in-sub clades. Attribute 'id_source' is
+ used to link other elements to a clade (on the xml-level). </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="name" type="xs:token" minOccurs="0"/>
<!-- Taxonomy:-->
<xs:complexType name="Taxonomy">
<xs:annotation>
- <xs:documentation> Element Taxonomy is used to describe taxonomic information for a clade. Element 'code' is
- intended to store UniProt/Swiss-Prot style organism codes (e.g. 'APLCA' for the California sea hare 'Aplysia
- californica') or other styles of mnemonics (e.g. 'Aca'). Element 'authority' is used to keep the authority,
- such as 'J. G. Cooper, 1863', associated with the 'scientific_name'. Element 'id' is used for a unique
- identifier of a taxon (for example '6500' with 'ncbi_taxonomy' as 'provider' for the California sea hare).
- Attribute 'id_source' is used to link other elements to a taxonomy (on the xml-level).</xs:documentation>
+ <xs:documentation> Element Taxonomy is used to describe taxonomic information for a clade.
+ Element 'code' is intended to store UniProt/Swiss-Prot style organism codes (e.g.
+ 'APLCA' for the California sea hare 'Aplysia californica'). Element 'authority' is used
+ to keep the authority, such as 'J. G. Cooper, 1863', associated with the
+ 'scientific_name'. Element 'id' is used for a unique identifier of a taxon (for example
+ '6500' with 'ncbi_taxonomy' as 'provider' for the California sea hare). Attribute
+ 'id_source' is used to link other elements to a taxonomy (on the
+ xml-level).</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="id" type="phy:Id" minOccurs="0"/>
<!-- Sequence:-->
<xs:complexType name="Sequence">
<xs:annotation>
- <xs:documentation> Element Sequence is used to represent a molecular sequence (Protein, DNA, RNA) associated
- with a node. 'symbol' is a short (maximal 20 characters) symbol of the sequence (e.g. 'ACTM') whereas
- 'name' is used for the full name (e.g. 'muscle Actin'). 'gene_name' can be used when protein and gene names differ.
- 'location' is used for the location of a sequence on a genome/chromosome. The actual sequence can be stored with the
- 'mol_seq' element. Attribute 'type' is used to indicate the type of sequence ('dna', 'rna', or 'protein').
- 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. </xs:documentation>
+ <xs:documentation> Element Sequence is used to represent a molecular sequence (Protein,
+ DNA, RNA) associated with a node. 'symbol' is a short (maximal 20 characters) symbol of
+ the sequence (e.g. 'ACTM') whereas 'name' is used for the full name (e.g. 'muscle
+ Actin'). 'gene_name' can be used when protein and gene names differ. 'location' is used
+ for the location of a sequence on a genome/chromosome. The actual sequence can be stored
+ with the 'mol_seq' element. Attribute 'type' is used to indicate the type of sequence
+ ('dna', 'rna', or 'protein'). 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. </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="symbol" type="phy:SequenceSymbol" minOccurs="0"/>
</xs:simpleType>
<xs:complexType name="MolSeq">
<xs:annotation>
- <xs:documentation> Element 'mol_seq' is used to store molecular sequences. The 'is_aligned' attribute is used
- to indicated that this molecular sequence is aligned with all other sequences in the same phylogeny for
- which 'is aligned' is true as well (which, in most cases, means that gaps were introduced, and that all
- sequences for which 'is aligned' is true must have the same length).</xs:documentation>
+ <xs:documentation> Element 'mol_seq' is used to store molecular sequences. The 'is_aligned'
+ attribute is used to indicated that this molecular sequence is aligned with all other
+ sequences in the same phylogeny for which 'is aligned' is true as well (which, in most
+ cases, means that gaps were introduced, and that all sequences for which 'is aligned' is
+ true must have the same length).</xs:documentation>
</xs:annotation>
<xs:simpleContent>
<xs:extension base="xs:token">
<!-- Accession:-->
<xs:complexType name="Accession">
<xs:annotation>
- <xs:documentation> Element Accession is used to capture the local part in a sequence identifier (e.g. 'P17304'
- in 'UniProtKB:P17304', in which case the 'source' attribute would be 'UniProtKB'). </xs:documentation>
+ <xs:documentation> Element Accession is used to capture the local part in a sequence
+ identifier (e.g. 'P17304' in 'UniProtKB:P17304', in which case the 'source' attribute
+ would be 'UniProtKB'). </xs:documentation>
</xs:annotation>
<xs:simpleContent>
<xs:extension base="xs:token">
<xs:complexType name="CrossReferences">
<xs:annotation>
<xs:documentation> Used to store accessions to additional resources. </xs:documentation>
- </xs:annotation>
+ </xs:annotation>
<xs:sequence>
<xs:element name="accession" type="phy:Accession" minOccurs="1" maxOccurs="unbounded"/>
</xs:sequence>
- </xs:complexType>
+ </xs:complexType>
<!-- DomainArchitecture: -->
<xs:complexType name="DomainArchitecture">
<xs:annotation>
- <xs:documentation> This is used describe the domain architecture of a protein. Attribute 'length' is the total
- length of the protein</xs:documentation>
+ <xs:documentation> This is used describe the domain architecture of a protein. Attribute
+ 'length' is the total length of the protein</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="domain" type="phy:ProteinDomain" minOccurs="1" maxOccurs="unbounded"/>
</xs:complexType>
<xs:complexType name="ProteinDomain">
<xs:annotation>
- <xs:documentation> To represent an individual domain in a domain architecture. The name/unique identifier is
- described via the 'id' attribute. 'confidence' can be used to store (i.e.) E-values.</xs:documentation>
+ <xs:documentation> To represent an individual domain in a domain architecture. The
+ name/unique identifier is described via the 'id' attribute. 'confidence' can be used to
+ store (i.e.) E-values.</xs:documentation>
</xs:annotation>
<xs:simpleContent>
<xs:extension base="xs:token">
<!-- Events:-->
<xs:complexType name="Events">
<xs:annotation>
- <xs:documentation> Events at the root node of a clade (e.g. one gene duplication). </xs:documentation>
+ <xs:documentation> Events at the root node of a clade (e.g. one gene duplication).
+ </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="type" type="phy:EventType" minOccurs="0"/>
<!--BinaryCharacters:-->
<xs:complexType name="BinaryCharacters">
<xs:annotation>
- <xs:documentation> The names and/or counts of binary characters present, gained, and lost at the root of a
- clade. </xs:documentation>
+ <xs:documentation> The names and/or counts of binary characters present, gained, and lost
+ at the root of a clade. </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="gained" type="phy:BinaryCharacterList" minOccurs="0"/>
<!-- Reference:-->
<xs:complexType name="Reference">
<xs:annotation>
- <xs:documentation> A literature reference for a clade. It is recommended to use the 'doi' attribute instead of
- the free text 'desc' element whenever possible. </xs:documentation>
+ <xs:documentation> A literature reference for a clade. It is recommended to use the 'doi'
+ attribute instead of the free text 'desc' element whenever possible. </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="desc" type="xs:token" minOccurs="0"/>
<!-- Annotation:-->
<xs:complexType name="Annotation">
<xs:annotation>
- <xs:documentation> 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'). Optional element 'desc' allows for a free text
- description. Optional element 'confidence' is used to state the type and value of support for a annotation.
- Similarly, optional attribute 'evidence' is used to describe the evidence for a annotation as free text
- (e.g. 'experimental'). Optional element 'property' allows for further, typed and referenced annotations from
- external resources.</xs:documentation>
+ <xs:documentation> 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'). Optional
+ element 'desc' allows for a free text description. Optional element 'confidence' is used
+ to state the type and value of support for a annotation. Similarly, optional attribute
+ 'evidence' is used to describe the evidence for a annotation as free text (e.g.
+ 'experimental'). Optional element 'property' allows for further, typed and referenced
+ annotations from external resources.</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="desc" type="xs:token" minOccurs="0"/>
<!-- Property:-->
<xs:complexType name="Property" mixed="true">
<xs:annotation>
- <xs:documentation> Property allows for typed and referenced properties from external resources to be attached
- to 'Phylogeny', 'Clade', and 'Annotation'. The value of a property is its mixed (free text) content.
- Attribute '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'). Attribute
- '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). Attribute 'id_ref' allows to attached a property
- specifically to one element (on the xml-level). Optional attribute 'unit' is used to indicate the unit of
- the property. An example: <property datatype="xsd:integer" ref="NOAA:depth" applies_to="clade"
- unit="METRIC:m"> 200 </property> </xs:documentation>
+ <xs:documentation> Property allows for typed and referenced properties from external
+ resources to be attached to 'Phylogeny', 'Clade', and 'Annotation'. The value of a
+ property is its mixed (free text) content. Attribute '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').
+ Attribute '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).
+ Attribute 'id_ref' allows to attached a property specifically to one element (on the
+ xml-level). Optional attribute 'unit' is used to indicate the unit of the property. An
+ example: <property datatype="xsd:integer" ref="NOAA:depth" applies_to="clade"
+ unit="METRIC:m"> 200 </property> </xs:documentation>
</xs:annotation>
<xs:attribute name="ref" type="phy:ref" use="required"/>
<xs:attribute name="unit" type="phy:ref"/>
<!--Uri-->
<xs:complexType name="Uri">
<xs:annotation>
- <xs:documentation> 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'). </xs:documentation>
+ <xs:documentation> 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'). </xs:documentation>
</xs:annotation>
<xs:simpleContent>
<xs:extension base="xs:anyURI">
<!-- Confidence:-->
<xs:complexType name="Confidence">
<xs:annotation>
- <xs:documentation> 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').</xs:documentation>
+ <xs:documentation> 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').</xs:documentation>
</xs:annotation>
<xs:simpleContent>
<xs:extension base="xs:double">
<!-- Identifier:-->
<xs:complexType name="Id">
<xs:annotation>
- <xs:documentation> A general purpose identifier element. Allows to indicate the provider (or authority) of an
- identifier. </xs:documentation>
+ <xs:documentation> A general purpose identifier element. Allows to indicate the provider
+ (or authority) of an identifier. </xs:documentation>
</xs:annotation>
<xs:simpleContent>
<xs:extension base="xs:token">
<!-- Distribution:-->
<xs:complexType name="Distribution">
<xs:annotation>
- <xs:documentation> The 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'. </xs:documentation>
+ <xs:documentation> The 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'.
+ </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="desc" type="xs:token" minOccurs="0"/>
</xs:complexType>
<xs:complexType name="Point">
<xs:annotation>
- <xs:documentation> The coordinates of a point with an optional altitude (used by element 'Distribution').
- Required attributes are the 'geodetic_datum' used to indicate the geodetic datum (also called 'map datum',
- for example Google's KML uses 'WGS84'). Attribute 'alt_unit' is the unit for the altitude (e.g. 'meter').
- </xs:documentation>
+ <xs:documentation> The coordinates of a point with an optional altitude (used by element
+ 'Distribution'). Required attributes are the 'geodetic_datum' used to indicate the
+ geodetic datum (also called 'map datum', for example Google's KML uses 'WGS84').
+ Attribute 'alt_unit' is the unit for the altitude (e.g. 'meter'). </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="lat" type="xs:decimal"/>
</xs:complexType>
<xs:complexType name="Polygon">
<xs:annotation>
- <xs:documentation> A polygon defined by a list of 'Points' (used by element 'Distribution').
- </xs:documentation>
+ <xs:documentation> A polygon defined by a list of 'Points' (used by element
+ 'Distribution'). </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="point" type="phy:Point" minOccurs="3" maxOccurs="unbounded"/>
<!-- Date:-->
<xs:complexType name="Date">
<xs:annotation>
- <xs:documentation> 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 to indicate the type of the numerical value (e.g. 'mya' for 'million years
- ago'). The elements 'minimum' and 'maximum' are used the indicate a range/confidence
- interval</xs:documentation>
+ <xs:documentation> 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 to indicate
+ the type of the numerical value (e.g. 'mya' for 'million years ago'). The elements
+ 'minimum' and 'maximum' are used the indicate a range/confidence
+ interval</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="desc" type="xs:token" minOccurs="0"/>
<!-- BranchColor:-->
<xs:complexType name="BranchColor">
<xs:annotation>
- <xs:documentation> This indicates the color of a clade when rendered (the color applies to the whole clade
- unless overwritten by the color(s) of sub clades).</xs:documentation>
+ <xs:documentation> This indicates the color of a clade when rendered (the color applies to
+ the whole clade unless overwritten by the color(s) of sub clades).</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="red" type="xs:unsignedByte"/>
<!-- SequenceRelation:-->
<xs:complexType name="SequenceRelation">
<xs:annotation>
- <xs:documentation> This is used to express a typed relationship between two sequences. For example it could be
- used to describe an orthology (in which case attribute 'type' is 'orthology'). </xs:documentation>
+ <xs:documentation> This is used to express a typed relationship between two sequences. For
+ example it could be used to describe an orthology (in which case attribute 'type' is
+ 'orthology'). </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
<!-- CladeRelation:-->
<xs:complexType name="CladeRelation">
<xs:annotation>
- <xs:documentation> This is used to express a typed relationship between two clades. For example it could be
- used to describe multiple parents of a clade.</xs:documentation>
+ <xs:documentation> This is used to express a typed relationship between two clades. For
+ example it could be used to describe multiple parents of a clade.</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>