orthoxml.xsd

<?xml version="1.0" encoding="UTF-8"?>
<xs:schema xmlns:ortho="http://orthoXML.org/2011/" version="0.5rc1" targetNamespace="http://orthoXML.org/2011/" xmlns:xs="http://www.w3.org/2001/XMLSchema" elementFormDefault="qualified">
	<xs:annotation>
		<xs:appinfo>OrthoXML Schema</xs:appinfo>
		<xs:documentation>
			This Schema defines the OrthoXML version 0.5rc1.
			Author(s): Sanjit Roopra, Dave Messina, Fabian Schreiber, Thomas Schmitt, and Erik Sonnhammer.
			SBC - Stockholm Bioinformatics Centre. 2011. More info at http://orthoxml.org
		</xs:documentation>
	</xs:annotation>
	<!-- OrthoXML root element ................................................................................ -->
	<xs:element name="orthoXML">
		<xs:annotation>
			<xs:documentation>
				The OrthoXML root element.
		</xs:documentation>
		</xs:annotation>
		<xs:complexType>
			<xs:sequence>
				<xs:element minOccurs="0" name="notes" type="ortho:notes" />
				<xs:element minOccurs="1" maxOccurs="unbounded" name="species"
					type="ortho:species" />
				<xs:element minOccurs="0" name="taxonomy" type="ortho:taxonomy" />
				<xs:element name="scores" type="ortho:scores" minOccurs="0"/>
				<xs:element name="groups" type="ortho:groups" />
			</xs:sequence>
			<xs:attribute name="origin" use="required" type="xs:string">
				<xs:annotation>
					<xs:documentation>
						The source program/database of the file for
						instance OMA or InParanoid.
					</xs:documentation>
				</xs:annotation>
			</xs:attribute>
			<xs:attribute name="version" use="required" type="xs:decimal">
				<xs:annotation>
					<xs:documentation>
						The version number of the file.
					</xs:documentation>
				</xs:annotation>
			</xs:attribute>
			<xs:attribute name="originVersion" use="required" type="xs:token">
				<xs:annotation>
					<xs:documentation>
						The version or release number of the source
						program/database at time the file was generated.
					</xs:documentation>
				</xs:annotation>
			</xs:attribute>
		</xs:complexType>
		<xs:key name="geneidKey">
			<xs:selector xpath="ortho:species/ortho:database/ortho:genes/ortho:gene" />
			<xs:field xpath="@id" />
		</xs:key>
		<xs:key name="scoreidKey">
			<xs:selector xpath="ortho:scores/ortho:scoreDef" />
			<xs:field xpath="@id" />
		</xs:key>
		<xs:key name="taxonidKey">
			<xs:selector xpath=".//ortho:taxon" />
			<xs:field xpath="@id" />
		</xs:key>
		<xs:keyref name="geneidRef" refer="ortho:geneidKey">
			<xs:selector xpath=".//ortho:geneRef" />
			<xs:field xpath="@id" />
		</xs:keyref>
		<xs:keyref name="scoreidRef" refer="ortho:scoreidKey">
			<xs:selector xpath=".//ortho:score" />
			<xs:field xpath="@id" />
		</xs:keyref>
		<xs:keyref name="taxonidRef" refer="ortho:taxonidKey">
			<xs:selector xpath=".//ortho:taxon" />
			<xs:field xpath="@id" />
		</xs:keyref>
		<xs:unique name="uniqueGroupId">
			<xs:selector xpath=".//ortho:paralogGroup | .//ortho:orthologGroup" />
			<xs:field xpath="@id" />
		</xs:unique>
	</xs:element>
	<!-- Species ............................................................................................... -->
	<xs:complexType name="species">
		<xs:annotation>
			<xs:documentation>
				The species element contains all sequences of one
				species.
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:element minOccurs="1" maxOccurs="unbounded" type="ortho:database"
				name="database" />
			<xs:element minOccurs="0" type="ortho:notes" name="notes" />
		</xs:sequence>
		<xs:attribute name="NCBITaxId" type="xs:integer">
			<xs:annotation>
				<xs:documentation>
					The NCBI Taxonomy identifier of the species to
					identify it
					unambiguously.
			</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="taxonId" type="xs:integer">
			<xs:annotation>
				<xs:documentation>
					The internal taxonomy identifier of the species to
					identify it unambiguously. Must match the id attributes of 
					the leaf taxon nodes in the taxonomy element.
			</xs:documentation>
			</xs:annotation>
		</xs:attribute>

		<xs:attribute name="name" use="required">
			<xs:annotation>
				<xs:documentation>
					The name of the species.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- Database .............................................................................................. -->
	<xs:complexType name="database">
		<xs:annotation>
			<xs:documentation>
				A database element contains all genes from a single
				database/source.
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:element name="genes" type="ortho:genes" />
		</xs:sequence>
		<xs:attribute name="geneLink" type="xs:anyURI">
			<xs:annotation>
				<xs:documentation>
					A Uniform Resource Identifier (URI) pointing to
					the gene. In the simplest case one could imagine a URL which in
					concatenation with the gene identifier links to the website of the
					gene in the source database. However, how this is used depends on
					the source of the orthoXML file.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="name" use="required" type="xs:string">
			<xs:annotation>
				<xs:documentation>
					Name of the database.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="protLink" type="xs:anyURI">
			<xs:annotation>
				<xs:documentation>
					A Uniform Resource Identifier (URI) pointing to
					the protein.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="transcriptLink" type="xs:anyURI">
			<xs:annotation>
				<xs:documentation>
					A Uniform Resource Identifier (URI) pointing to
					the transcript.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="version" use="required">
			<xs:annotation>
				<xs:documentation>
					Version number of the database.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- Genes ................................................................................................. -->
	<xs:complexType name="genes">
		<xs:annotation>
			<xs:documentation>
				A gene element represents a list of genes.
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:element minOccurs="1" maxOccurs="unbounded" name="gene"
				type="ortho:gene" />
		</xs:sequence>
	</xs:complexType>
	<!-- Gene .................................................................................................. -->
	<xs:complexType name="gene">
		<xs:annotation>
			<xs:documentation>
				The gene element represents a single gene, protein
				or transcript. It is in fact a set of identifiers: one internal
				identifier that is used to link from geneRef elements in ortholog
				clusters and gene identifiers, transcript identifiers and protein
				identifiers to identify the molecule. The proper term for this
				element would therefore rather be molecule. However, as the general
				purpose of orthoXML is to represent orthology data for genes the
				term gene is used instead. Gene, protein and transcipt identifiers 
				are optional but at least one of the three should be given. The 
				source database of the gene is defined through the database element 
				in which the gene element lies and the identifiers should stem from 
				this source. 
			</xs:documentation>
		</xs:annotation>
		<xs:attribute name="geneId" type="xs:string">
			<xs:annotation>
				<xs:documentation>
					Identifier of the gene in the source database.
					Multiple splice forms are possible by having the same geneId more
					than once.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="id" use="required" type="xs:integer">
			<xs:annotation>
				<xs:documentation>
					Internal identifier to link to the gene via the geneRef elements.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="protId" type="xs:string">
			<xs:annotation>
				<xs:documentation>
					Identifier of the protein in the source database.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="transcriptId" type="xs:string">
			<xs:annotation>
				<xs:documentation>
					Identifier of the transcript in the source database.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- Taxonomy ............................................................................................... -->
	<xs:complexType name="taxonomy">
		<xs:annotation>
			<xs:documentation>
				The taxonomy of the species analysed in this orthoxml file. Either you specify
				the taxonomy as a nested grouping of taxon elements, or link to the ncbi taxonomy
				by defining an ncbitaxonomy element within the taxonomy element.
			</xs:documentation>
		</xs:annotation>
		<xs:choice maxOccurs="1">
			<xs:element name="taxon" type="ortho:taxonDef" />
			<xs:element name="ncbitaxonomy" type="ortho:ncbiDef" />
		</xs:choice>
	</xs:complexType>
	<!-- Taxon Def............................................................................................... -->
	<xs:complexType name="taxonDef">
		<xs:annotation>
			<xs:documentation>
				A node in the taxonomy, identifying a clade of species
			</xs:documentation>
		</xs:annotation>
		<xs:sequence minOccurs="0" maxOccurs="unbounded">
			<xs:element name="taxon" type="ortho:taxonDef" />
		</xs:sequence>
		<xs:attribute name="id" type="xs:integer" use="required">
			<xs:annotation>
				<xs:documentation>
					(Internal) identifier of the clade / taxon.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="name" type="xs:string">
			<xs:annotation>
				<xs:documentation>
					Name of the clade / taxon.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- NCBI Def............................................................................................... -->
	<xs:complexType name="ncbiDef">
		<xs:annotation>
			<xs:documentation>
				crosslink to the ncbi taxonomy
			</xs:documentation>
		</xs:annotation>
		<xs:attribute name="link" type="xs:anyURI">
			<xs:annotation>
				<xs:documentation>
					A link to the used ncbi taxonomy.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="version" type="xs:string">
			<xs:annotation>
				<xs:documentation>
					The version of the ncbi taxonomy that is used.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- Scores ................................................................................................. -->
	<xs:complexType name="scores">
		<xs:annotation>
			<xs:documentation>
				A list of score definitions.
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:element maxOccurs="unbounded" name="scoreDef" type="ortho:scoreDef" />
		</xs:sequence>
	</xs:complexType>
	<!-- Groups ................................................................................................. -->
	<xs:complexType name="groups">
		<xs:annotation>
			<xs:documentation>
				Represents the list of ortholog groups. Normally 
				the top level is an ortholog group, but in order to express
				a duplication at the root, a paralog group may also be the top level.
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:choice minOccurs="1" maxOccurs="unbounded">
				<xs:element name="orthologGroup" type="ortho:group" maxOccurs="unbounded" />
				<xs:element name="paralogGroup" type="ortho:group" maxOccurs="unbounded" />
			</xs:choice>
		</xs:sequence>
	</xs:complexType>
	<!-- Group .................................................................................................. -->
	<xs:complexType name="group">
		<xs:annotation>
			<xs:documentation>
				A group of genes or nested groups. In case of a
				orothologGroup element, all genes in the group or in the nested groups are
				orthologs to each other i.e. stem from the same gene in the last common
				ancester of the species. In case of a paralogGroup the genes are
				paralogs to each other. Subgroups within the group allow the
				represention of phylogenetic trees. For more details and examples
				see http://orthoxml.org/orthoxml_doc.html.
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:element minOccurs="0" maxOccurs="unbounded" name="score" type="ortho:score" />
			<xs:element minOccurs="0" maxOccurs="unbounded" name="property" type="ortho:property"/>
			<xs:choice minOccurs="2" maxOccurs="unbounded">
				<xs:annotation>
					<xs:documentation>
						A group can may contain two or more of the three alternatives
						geneRef, paralogGroup, and orthologGroup. By combining these, 
						complex phylogenies are possible.
				</xs:documentation>
				</xs:annotation>
				<xs:element name="geneRef" type="ortho:geneRef" />
				<xs:element name="paralogGroup" type="ortho:group" />
				<xs:element name="orthologGroup" type="ortho:group" />
			</xs:choice>
			<xs:element minOccurs="0" name="notes" type="ortho:notes" />
		</xs:sequence>
		<xs:attribute name="id" type="xs:string">
		<xs:annotation>
			<xs:documentation>
				Identifier for the group in context of the resource. This attribute is 
				not required but if your resource provides identifiers for the ortholog 
				groups we strongly recommend to use it at least for the top level groups.
			</xs:documentation>
		</xs:annotation>
		</xs:attribute>
		<xs:attribute name="taxonId" type="xs:integer">
		<xs:annotation>
			<xs:documentation>
				Taxonomy identifier that defines the speciation event of reference for this 
				group. The taxonId references either a node in the defined taxonomy structure
				(where the nummeric IDs can be defined as needed) or it should be the taxonomy
				identifier in the NCBI taxonomy. 
			</xs:documentation>
		</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- GeneRef ................................................................................................. -->
	<xs:complexType name="geneRef">
		<xs:annotation>
			<xs:documentation>
				The geneRef element is a link to the gene
				definition under the species element. It defines the members of an
				ortholog or paralog group. The same gene can be referenced muliple
				times. The geneRef element can have multiple score elements and a
				notes elements as children. The notes element can for instance be
				used for special, ortholog-database-specific information (with InParanoid,
				for example, we could use it to mark the seed orthologs).
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:element minOccurs="0" maxOccurs="unbounded" type="ortho:score" name="score" />
			<xs:element minOccurs="0" type="ortho:notes" name="notes" />
		</xs:sequence>
		<xs:attribute name="id" use="required" type="xs:integer">
			<xs:annotation>
				<xs:documentation>
					Internal identifier for a gene element defined under the species element.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- ScoreDef ................................................................................................. -->
	<xs:complexType name="scoreDef">
		<xs:annotation>
			<xs:documentation>
				The scoreDef element defines a score. One of the
				concepts of orthoXML is to be as flexible as possible but still
				uniformly parsable. Part of this is to allow every
				ortholog resource to give their own types of scores for groups or
				group members, which is done using score elements. Score elements
				can be defined to apply to either groups or geneRefs. It is possible to define multiple scores. 
			</xs:documentation>
		</xs:annotation>
		<xs:attribute name="id" use="required" type="xs:NCName">
			<xs:annotation>
				<xs:documentation>
					An internal identifier to link to the
					scoreDef from a score element.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="desc" use="required">
			<xs:annotation>
				<xs:documentation>
					Description of the score.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- Score .................................................................................................... -->
	<xs:complexType name="score">
		<xs:annotation>
			<xs:documentation>
				The score element gives the value of a score and
				links it to the scoreDef element, which defines the score. It can be
				child of a group or a geneRef element to allow scoring on
				different levels.
			</xs:documentation>
		</xs:annotation>
		<xs:attribute name="id" use="required" type="xs:NCName">
			<xs:annotation>
				<xs:documentation>
					An identifier linking to the scoreDef element,
					which defines the score.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="value" use="required" type="xs:decimal">
			<xs:annotation>
				<xs:documentation>
					The actual value of the score. For instance a
					confidence score of a group member.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- Property ...............................................................................................-->
	<xs:complexType name="property">
		<xs:annotation>
			<xs:documentation>
				Key-value pair for group annotations, for instance
				statistics about the group members.
			</xs:documentation>
		</xs:annotation>
		<xs:attribute name="name" use="required" type="xs:string">
			<xs:annotation>
				<xs:documentation>
					The key of the key-value annotation pair.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
		<xs:attribute name="value">
			<xs:annotation>
				<xs:documentation>
					The value of the key-value annotation pair. Optional
					to allow flag like annotations.
				</xs:documentation>
			</xs:annotation>
		</xs:attribute>
	</xs:complexType>
	<!-- Notes .................................................................................................... -->
	<xs:complexType mixed="true" name="notes">
		<xs:annotation>
			<xs:documentation>
				The notes element is a special element, which
				allows adding information that is not general enough to be part
				of the standard. I.e. something specific to a particular ortholog
				database or algorithm. Notes elements will not be validated,
				so any child elements are legal. Notes elements can be children of the
				root element orthoXML, the species element, the orthologGroup
				element, the paralogGroup element, or the geneRef element.
			</xs:documentation>
		</xs:annotation>
		<xs:sequence>
			<xs:any processContents="skip" minOccurs="0" maxOccurs="unbounded" />
		</xs:sequence>
	</xs:complexType>
</xs:schema>