bio-phyloxml 0.9.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.travis.yml +12 -0
- data/Gemfile +13 -0
- data/LICENSE.txt +20 -0
- data/README.md +199 -0
- data/README.rdoc +48 -0
- data/Rakefile +45 -0
- data/VERSION +1 -0
- data/lib/bio-phyloxml.rb +12 -0
- data/lib/bio/phyloxml.rb +3 -0
- data/lib/bio/phyloxml/elements.rb +1166 -0
- data/lib/bio/phyloxml/parser.rb +1000 -0
- data/lib/bio/phyloxml/phyloxml.xsd +582 -0
- data/lib/bio/phyloxml/writer.rb +227 -0
- data/sample/test_phyloxml_big.rb +205 -0
- data/test/data/phyloxml/apaf.xml +666 -0
- data/test/data/phyloxml/bcl_2.xml +2097 -0
- data/test/data/phyloxml/made_up.xml +144 -0
- data/test/data/phyloxml/ncbi_taxonomy_mollusca_short.xml +65 -0
- data/test/data/phyloxml/phyloxml_examples.xml +415 -0
- data/test/helper.rb +25 -0
- data/test/unit/bio/test_phyloxml.rb +821 -0
- data/test/unit/bio/test_phyloxml_writer.rb +334 -0
- metadata +155 -0
|
@@ -0,0 +1,582 @@
|
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
|
2
|
+
<!-- -->
|
|
3
|
+
<!-- phyloXML -->
|
|
4
|
+
<!-- -->
|
|
5
|
+
<!-- schema in XMLSchema -->
|
|
6
|
+
<!-- -->
|
|
7
|
+
<!-- License: The phyloXML XML Schema Definition is -->
|
|
8
|
+
<!-- dual-licensed under the LGPL or Ruby's -->
|
|
9
|
+
<!-- License. -->
|
|
10
|
+
<!-- You can redistribute and/or modify -->
|
|
11
|
+
<!-- it under either the terms of the LGPL, -->
|
|
12
|
+
<!-- or Ruby's License. -->
|
|
13
|
+
<!-- see: http://www.ruby-lang.org/en/about/license.txt -->
|
|
14
|
+
<!-- -->
|
|
15
|
+
<!-- Copyright (c) 2008-2009 Christian M Zmasek -->
|
|
16
|
+
<!-- -->
|
|
17
|
+
<!-- www.phyloxml.org -->
|
|
18
|
+
<!-- Version: 1.10 -->
|
|
19
|
+
<!-- Last modified: 2009.11.17 by Christian M Zmasek -->
|
|
20
|
+
<!-- -->
|
|
21
|
+
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:phy="http://www.phyloxml.org"
|
|
22
|
+
targetNamespace="http://www.phyloxml.org" elementFormDefault="qualified" attributeFormDefault="unqualified">
|
|
23
|
+
<xs:annotation>
|
|
24
|
+
<xs:documentation> phyloXML is an XML language to describe evolutionary trees and associated data. Version: 1.10.
|
|
25
|
+
License: dual-licensed under the LGPL or Ruby's License. Copyright (c) 2008-2009 Christian M Zmasek.</xs:documentation>
|
|
26
|
+
</xs:annotation>
|
|
27
|
+
<!-- phyloxml is the root element:-->
|
|
28
|
+
<xs:element name="phyloxml" type="phy:Phyloxml"/>
|
|
29
|
+
<!-- phyloXML definition:-->
|
|
30
|
+
<xs:complexType name="Phyloxml">
|
|
31
|
+
<xs:annotation>
|
|
32
|
+
<xs:documentation> 'phyloxml' is the name of the root element. Phyloxml contains an arbitrary number of
|
|
33
|
+
'phylogeny' elements (each representing one phylogeny) possibly followed by elements from other namespaces.
|
|
34
|
+
</xs:documentation>
|
|
35
|
+
</xs:annotation>
|
|
36
|
+
<xs:sequence maxOccurs="unbounded">
|
|
37
|
+
<xs:element name="phylogeny" type="phy:Phylogeny" minOccurs="0" maxOccurs="unbounded"/>
|
|
38
|
+
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
|
39
|
+
</xs:sequence>
|
|
40
|
+
</xs:complexType>
|
|
41
|
+
<!-- Phylogeny:-->
|
|
42
|
+
<xs:complexType name="Phylogeny">
|
|
43
|
+
<xs:annotation>
|
|
44
|
+
<xs:documentation> Element Phylogeny is used to represent a phylogeny. The required attribute 'rooted' is used
|
|
45
|
+
to indicate whether the phylogeny is rooted or not. The attribute 'rerootable' can be used to indicate that
|
|
46
|
+
the phylogeny is not allowed to be rooted differently (i.e. because it is associated with root dependent
|
|
47
|
+
data, such as gene duplications). The attribute 'type' can be used to indicate the type of phylogeny (i.e.
|
|
48
|
+
'gene tree'). It is recommended to use the attribute 'branch_length_unit' if the phylogeny has branch
|
|
49
|
+
lengths. Element clade is used in a recursive manner to describe the topology of a phylogenetic
|
|
50
|
+
tree.</xs:documentation>
|
|
51
|
+
</xs:annotation>
|
|
52
|
+
<xs:sequence>
|
|
53
|
+
<xs:element name="name" type="xs:token" minOccurs="0"/>
|
|
54
|
+
<xs:element name="id" type="phy:Id" minOccurs="0"/>
|
|
55
|
+
<xs:element name="description" type="xs:token" minOccurs="0"/>
|
|
56
|
+
<xs:element name="date" type="xs:dateTime" minOccurs="0"/>
|
|
57
|
+
<xs:element name="confidence" type="phy:Confidence" minOccurs="0" maxOccurs="unbounded"/>
|
|
58
|
+
<xs:element name="clade" type="phy:Clade" minOccurs="0"/>
|
|
59
|
+
<xs:element name="clade_relation" type="phy:CladeRelation" minOccurs="0" maxOccurs="unbounded"/>
|
|
60
|
+
<xs:element name="sequence_relation" type="phy:SequenceRelation" minOccurs="0" maxOccurs="unbounded"/>
|
|
61
|
+
<xs:element name="property" type="phy:Property" minOccurs="0" maxOccurs="unbounded"/>
|
|
62
|
+
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
|
63
|
+
</xs:sequence>
|
|
64
|
+
<xs:attribute name="rooted" type="xs:boolean" use="required"/>
|
|
65
|
+
<xs:attribute name="rerootable" type="xs:boolean"/>
|
|
66
|
+
<xs:attribute name="branch_length_unit" type="xs:token"/>
|
|
67
|
+
<xs:attribute name="type" type="xs:token"/>
|
|
68
|
+
</xs:complexType>
|
|
69
|
+
<!-- Clade:-->
|
|
70
|
+
<xs:complexType name="Clade">
|
|
71
|
+
<xs:annotation>
|
|
72
|
+
<xs:documentation> Element Clade is used in a recursive manner to describe the topology of a phylogenetic tree.
|
|
73
|
+
The parent branch length of a clade can be described either with the 'branch_length' element or the
|
|
74
|
+
'branch_length' attribute (it is not recommended to use both at the same time, though). Usage of the
|
|
75
|
+
'branch_length' attribute allows for a less verbose description. Element 'confidence' is used to indicate
|
|
76
|
+
the support for a clade/parent branch. Element 'events' is used to describe such events as gene-duplications
|
|
77
|
+
at the root node/parent branch of a clade. Element 'width' is the branch width for this clade (including
|
|
78
|
+
parent branch). Both 'color' and 'width' elements apply for the whole clade unless overwritten in-sub
|
|
79
|
+
clades. Attribute 'id_source' is used to link other elements to a clade (on the xml-level).
|
|
80
|
+
</xs:documentation>
|
|
81
|
+
</xs:annotation>
|
|
82
|
+
<xs:sequence>
|
|
83
|
+
<xs:element name="name" type="xs:token" minOccurs="0"/>
|
|
84
|
+
<xs:element name="branch_length" type="xs:double" minOccurs="0"/>
|
|
85
|
+
<xs:element name="confidence" type="phy:Confidence" minOccurs="0" maxOccurs="unbounded"/>
|
|
86
|
+
<xs:element name="width" type="xs:double" minOccurs="0"/>
|
|
87
|
+
<xs:element name="color" type="phy:BranchColor" minOccurs="0"/>
|
|
88
|
+
<xs:element name="node_id" type="phy:Id" minOccurs="0"/>
|
|
89
|
+
<xs:element name="taxonomy" type="phy:Taxonomy" minOccurs="0" maxOccurs="unbounded"/>
|
|
90
|
+
<xs:element name="sequence" type="phy:Sequence" minOccurs="0" maxOccurs="unbounded"/>
|
|
91
|
+
<xs:element name="events" type="phy:Events" minOccurs="0"/>
|
|
92
|
+
<xs:element name="binary_characters" type="phy:BinaryCharacters" minOccurs="0"/>
|
|
93
|
+
<xs:element name="distribution" type="phy:Distribution" minOccurs="0" maxOccurs="unbounded"/>
|
|
94
|
+
<xs:element name="date" type="phy:Date" minOccurs="0"/>
|
|
95
|
+
<xs:element name="reference" type="phy:Reference" minOccurs="0" maxOccurs="unbounded"/>
|
|
96
|
+
<xs:element name="property" type="phy:Property" minOccurs="0" maxOccurs="unbounded"/>
|
|
97
|
+
<xs:element name="clade" type="phy:Clade" minOccurs="0" maxOccurs="unbounded"/>
|
|
98
|
+
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
|
99
|
+
</xs:sequence>
|
|
100
|
+
<xs:attribute name="branch_length" type="xs:double"/>
|
|
101
|
+
<xs:attribute name="id_source" type="phy:id_source"/>
|
|
102
|
+
</xs:complexType>
|
|
103
|
+
<!-- Taxonomy:-->
|
|
104
|
+
<xs:complexType name="Taxonomy">
|
|
105
|
+
<xs:annotation>
|
|
106
|
+
<xs:documentation> Element Taxonomy is used to describe taxonomic information for a clade. Element 'code' is
|
|
107
|
+
intended to store UniProt/Swiss-Prot style organism codes (e.g. 'APLCA' for the California sea hare 'Aplysia
|
|
108
|
+
californica') or other styles of mnemonics (e.g. 'Aca'). Element 'authority' is used to keep the authority,
|
|
109
|
+
such as 'J. G. Cooper, 1863', associated with the 'scientific_name'. Element 'id' is used for a unique
|
|
110
|
+
identifier of a taxon (for example '6500' with 'ncbi_taxonomy' as 'provider' for the California sea hare).
|
|
111
|
+
Attribute 'id_source' is used to link other elements to a taxonomy (on the xml-level).</xs:documentation>
|
|
112
|
+
</xs:annotation>
|
|
113
|
+
<xs:sequence>
|
|
114
|
+
<xs:element name="id" type="phy:Id" minOccurs="0"/>
|
|
115
|
+
<xs:element name="code" type="phy:TaxonomyCode" minOccurs="0"/>
|
|
116
|
+
<xs:element name="scientific_name" type="xs:token" minOccurs="0"/>
|
|
117
|
+
<xs:element name="authority" type="xs:token" minOccurs="0"/>
|
|
118
|
+
<xs:element name="common_name" type="xs:token" minOccurs="0" maxOccurs="unbounded"/>
|
|
119
|
+
<xs:element name="synonym" type="xs:token" minOccurs="0" maxOccurs="unbounded"/>
|
|
120
|
+
<xs:element name="rank" type="phy:Rank" minOccurs="0"/>
|
|
121
|
+
<xs:element name="uri" type="phy:Uri" minOccurs="0"/>
|
|
122
|
+
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
|
123
|
+
</xs:sequence>
|
|
124
|
+
<xs:attribute name="id_source" type="phy:id_source"/>
|
|
125
|
+
</xs:complexType>
|
|
126
|
+
<xs:simpleType name="TaxonomyCode">
|
|
127
|
+
<xs:restriction base="xs:token">
|
|
128
|
+
<xs:pattern value="[a-zA-Z0-9_]{2,10}"/>
|
|
129
|
+
</xs:restriction>
|
|
130
|
+
</xs:simpleType>
|
|
131
|
+
<xs:simpleType name="Rank">
|
|
132
|
+
<xs:restriction base="xs:token">
|
|
133
|
+
<xs:enumeration value="domain"/>
|
|
134
|
+
<xs:enumeration value="kingdom"/>
|
|
135
|
+
<xs:enumeration value="subkingdom"/>
|
|
136
|
+
<xs:enumeration value="branch"/>
|
|
137
|
+
<xs:enumeration value="infrakingdom"/>
|
|
138
|
+
<xs:enumeration value="superphylum"/>
|
|
139
|
+
<xs:enumeration value="phylum"/>
|
|
140
|
+
<xs:enumeration value="subphylum"/>
|
|
141
|
+
<xs:enumeration value="infraphylum"/>
|
|
142
|
+
<xs:enumeration value="microphylum"/>
|
|
143
|
+
<xs:enumeration value="superdivision"/>
|
|
144
|
+
<xs:enumeration value="division"/>
|
|
145
|
+
<xs:enumeration value="subdivision"/>
|
|
146
|
+
<xs:enumeration value="infradivision"/>
|
|
147
|
+
<xs:enumeration value="superclass"/>
|
|
148
|
+
<xs:enumeration value="class"/>
|
|
149
|
+
<xs:enumeration value="subclass"/>
|
|
150
|
+
<xs:enumeration value="infraclass"/>
|
|
151
|
+
<xs:enumeration value="superlegion"/>
|
|
152
|
+
<xs:enumeration value="legion"/>
|
|
153
|
+
<xs:enumeration value="sublegion"/>
|
|
154
|
+
<xs:enumeration value="infralegion"/>
|
|
155
|
+
<xs:enumeration value="supercohort"/>
|
|
156
|
+
<xs:enumeration value="cohort"/>
|
|
157
|
+
<xs:enumeration value="subcohort"/>
|
|
158
|
+
<xs:enumeration value="infracohort"/>
|
|
159
|
+
<xs:enumeration value="superorder"/>
|
|
160
|
+
<xs:enumeration value="order"/>
|
|
161
|
+
<xs:enumeration value="suborder"/>
|
|
162
|
+
<xs:enumeration value="superfamily"/>
|
|
163
|
+
<xs:enumeration value="family"/>
|
|
164
|
+
<xs:enumeration value="subfamily"/>
|
|
165
|
+
<xs:enumeration value="supertribe"/>
|
|
166
|
+
<xs:enumeration value="tribe"/>
|
|
167
|
+
<xs:enumeration value="subtribe"/>
|
|
168
|
+
<xs:enumeration value="infratribe"/>
|
|
169
|
+
<xs:enumeration value="genus"/>
|
|
170
|
+
<xs:enumeration value="subgenus"/>
|
|
171
|
+
<xs:enumeration value="superspecies"/>
|
|
172
|
+
<xs:enumeration value="species"/>
|
|
173
|
+
<xs:enumeration value="subspecies"/>
|
|
174
|
+
<xs:enumeration value="variety"/>
|
|
175
|
+
<xs:enumeration value="subvariety"/>
|
|
176
|
+
<xs:enumeration value="form"/>
|
|
177
|
+
<xs:enumeration value="subform"/>
|
|
178
|
+
<xs:enumeration value="cultivar"/>
|
|
179
|
+
<xs:enumeration value="unknown"/>
|
|
180
|
+
<xs:enumeration value="other"/>
|
|
181
|
+
</xs:restriction>
|
|
182
|
+
</xs:simpleType>
|
|
183
|
+
<!-- Sequence:-->
|
|
184
|
+
<xs:complexType name="Sequence">
|
|
185
|
+
<xs:annotation>
|
|
186
|
+
<xs:documentation> Element Sequence is used to represent a molecular sequence (Protein, DNA, RNA) associated
|
|
187
|
+
with a node. 'symbol' is a short (maximal ten characters) symbol of the sequence (e.g. 'ACTM') whereas
|
|
188
|
+
'name' is used for the full name (e.g. 'muscle Actin'). 'location' is used for the location of a sequence on
|
|
189
|
+
a genome/chromosome. The actual sequence can be stored with the 'mol_seq' element. Attribute 'type' is used
|
|
190
|
+
to indicate the type of sequence ('dna', 'rna', or 'protein'). One intended use for 'id_ref' is to link a
|
|
191
|
+
sequence to a taxonomy (via the taxonomy's 'id_source') in case of multiple sequences and taxonomies per
|
|
192
|
+
node. </xs:documentation>
|
|
193
|
+
</xs:annotation>
|
|
194
|
+
<xs:sequence>
|
|
195
|
+
<xs:element name="symbol" type="phy:SequenceSymbol" minOccurs="0"/>
|
|
196
|
+
<xs:element name="accession" type="phy:Accession" minOccurs="0"/>
|
|
197
|
+
<xs:element name="name" type="xs:token" minOccurs="0"/>
|
|
198
|
+
<xs:element name="location" type="xs:token" minOccurs="0"/>
|
|
199
|
+
<xs:element name="mol_seq" type="phy:MolSeq" minOccurs="0"/>
|
|
200
|
+
<xs:element name="uri" type="phy:Uri" minOccurs="0"/>
|
|
201
|
+
<xs:element name="annotation" type="phy:Annotation" minOccurs="0" maxOccurs="unbounded"/>
|
|
202
|
+
<xs:element name="domain_architecture" type="phy:DomainArchitecture" minOccurs="0"/>
|
|
203
|
+
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
|
204
|
+
</xs:sequence>
|
|
205
|
+
<xs:attribute name="type" type="phy:SequenceType"/>
|
|
206
|
+
<xs:attribute name="id_source" type="phy:id_source"/>
|
|
207
|
+
<xs:attribute name="id_ref" type="phy:id_ref"/>
|
|
208
|
+
</xs:complexType>
|
|
209
|
+
<xs:simpleType name="SequenceSymbol">
|
|
210
|
+
<xs:restriction base="xs:token">
|
|
211
|
+
<xs:pattern value="\S{1,10}"/>
|
|
212
|
+
</xs:restriction>
|
|
213
|
+
</xs:simpleType>
|
|
214
|
+
<xs:complexType name="MolSeq">
|
|
215
|
+
<xs:annotation>
|
|
216
|
+
<xs:documentation> Element 'mol_seq' is used to store molecular sequences. The 'is_aligned' attribute is used
|
|
217
|
+
to indicated that this molecular sequence is aligned with all other sequences in the same phylogeny for
|
|
218
|
+
which 'is aligned' is true as well (which, in most cases, means that gaps were introduced, and that all
|
|
219
|
+
sequences for which 'is aligned' is true must have the same length).</xs:documentation>
|
|
220
|
+
</xs:annotation>
|
|
221
|
+
<xs:simpleContent>
|
|
222
|
+
<xs:extension base="phy:MolSeqChars">
|
|
223
|
+
<xs:attribute name="is_aligned" type="xs:boolean"/>
|
|
224
|
+
</xs:extension>
|
|
225
|
+
</xs:simpleContent>
|
|
226
|
+
</xs:complexType>
|
|
227
|
+
<xs:simpleType name="MolSeqChars">
|
|
228
|
+
<xs:restriction base="xs:token">
|
|
229
|
+
<xs:pattern value="[a-zA-Z\.\-\?\*_]+"/>
|
|
230
|
+
</xs:restriction>
|
|
231
|
+
</xs:simpleType>
|
|
232
|
+
<xs:simpleType name="SequenceType">
|
|
233
|
+
<xs:restriction base="xs:token">
|
|
234
|
+
<xs:enumeration value="rna"/>
|
|
235
|
+
<xs:enumeration value="dna"/>
|
|
236
|
+
<xs:enumeration value="protein"/>
|
|
237
|
+
</xs:restriction>
|
|
238
|
+
</xs:simpleType>
|
|
239
|
+
<!-- Accession:-->
|
|
240
|
+
<xs:complexType name="Accession">
|
|
241
|
+
<xs:annotation>
|
|
242
|
+
<xs:documentation> Element Accession is used to capture the local part in a sequence identifier (e.g. 'P17304'
|
|
243
|
+
in 'UniProtKB:P17304', in which case the 'source' attribute would be 'UniProtKB'). </xs:documentation>
|
|
244
|
+
</xs:annotation>
|
|
245
|
+
<xs:simpleContent>
|
|
246
|
+
<xs:extension base="xs:token">
|
|
247
|
+
<xs:attribute name="source" type="xs:token" use="required"/>
|
|
248
|
+
</xs:extension>
|
|
249
|
+
</xs:simpleContent>
|
|
250
|
+
</xs:complexType>
|
|
251
|
+
<!-- DomainArchitecture: -->
|
|
252
|
+
<xs:complexType name="DomainArchitecture">
|
|
253
|
+
<xs:annotation>
|
|
254
|
+
<xs:documentation> This is used describe the domain architecture of a protein. Attribute 'length' is the total
|
|
255
|
+
length of the protein</xs:documentation>
|
|
256
|
+
</xs:annotation>
|
|
257
|
+
<xs:sequence>
|
|
258
|
+
<xs:element name="domain" type="phy:ProteinDomain" minOccurs="1" maxOccurs="unbounded"/>
|
|
259
|
+
</xs:sequence>
|
|
260
|
+
<xs:attribute name="length" type="xs:nonNegativeInteger"/>
|
|
261
|
+
</xs:complexType>
|
|
262
|
+
<xs:complexType name="ProteinDomain">
|
|
263
|
+
<xs:annotation>
|
|
264
|
+
<xs:documentation> To represent an individual domain in a domain architecture. The name/unique identifier is
|
|
265
|
+
described via the 'id' attribute. 'confidence' can be used to store (i.e.) E-values.</xs:documentation>
|
|
266
|
+
</xs:annotation>
|
|
267
|
+
<xs:simpleContent>
|
|
268
|
+
<xs:extension base="xs:token">
|
|
269
|
+
<xs:attribute name="from" type="xs:nonNegativeInteger" use="required"/>
|
|
270
|
+
<xs:attribute name="to" type="xs:nonNegativeInteger" use="required"/>
|
|
271
|
+
<xs:attribute name="confidence" type="xs:double"/>
|
|
272
|
+
<xs:attribute name="id" type="xs:token"/>
|
|
273
|
+
</xs:extension>
|
|
274
|
+
</xs:simpleContent>
|
|
275
|
+
</xs:complexType>
|
|
276
|
+
<!-- Events:-->
|
|
277
|
+
<xs:complexType name="Events">
|
|
278
|
+
<xs:annotation>
|
|
279
|
+
<xs:documentation> Events at the root node of a clade (e.g. one gene duplication). </xs:documentation>
|
|
280
|
+
</xs:annotation>
|
|
281
|
+
<xs:sequence>
|
|
282
|
+
<xs:element name="type" type="phy:EventType" minOccurs="0"/>
|
|
283
|
+
<xs:element name="duplications" type="xs:nonNegativeInteger" minOccurs="0"/>
|
|
284
|
+
<xs:element name="speciations" type="xs:nonNegativeInteger" minOccurs="0"/>
|
|
285
|
+
<xs:element name="losses" type="xs:nonNegativeInteger" minOccurs="0"/>
|
|
286
|
+
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
|
287
|
+
</xs:sequence>
|
|
288
|
+
</xs:complexType>
|
|
289
|
+
<xs:simpleType name="EventType">
|
|
290
|
+
<xs:restriction base="xs:token">
|
|
291
|
+
<xs:enumeration value="transfer"/>
|
|
292
|
+
<xs:enumeration value="fusion"/>
|
|
293
|
+
<xs:enumeration value="speciation_or_duplication"/>
|
|
294
|
+
<xs:enumeration value="other"/>
|
|
295
|
+
<xs:enumeration value="mixed"/>
|
|
296
|
+
<xs:enumeration value="unassigned"/>
|
|
297
|
+
</xs:restriction>
|
|
298
|
+
</xs:simpleType>
|
|
299
|
+
<!--BinaryCharacters:-->
|
|
300
|
+
<xs:complexType name="BinaryCharacters">
|
|
301
|
+
<xs:annotation>
|
|
302
|
+
<xs:documentation> The names and/or counts of binary characters present, gained, and lost at the root of a
|
|
303
|
+
clade. </xs:documentation>
|
|
304
|
+
</xs:annotation>
|
|
305
|
+
<xs:sequence>
|
|
306
|
+
<xs:element name="gained" type="phy:BinaryCharacterList" minOccurs="0"/>
|
|
307
|
+
<xs:element name="lost" type="phy:BinaryCharacterList" minOccurs="0"/>
|
|
308
|
+
<xs:element name="present" type="phy:BinaryCharacterList" minOccurs="0"/>
|
|
309
|
+
<xs:element name="absent" type="phy:BinaryCharacterList" minOccurs="0"/>
|
|
310
|
+
</xs:sequence>
|
|
311
|
+
<xs:attribute name="type" type="xs:token"/>
|
|
312
|
+
<xs:attribute name="gained_count" type="xs:nonNegativeInteger"/>
|
|
313
|
+
<xs:attribute name="lost_count" type="xs:nonNegativeInteger"/>
|
|
314
|
+
<xs:attribute name="present_count" type="xs:nonNegativeInteger"/>
|
|
315
|
+
<xs:attribute name="absent_count" type="xs:nonNegativeInteger"/>
|
|
316
|
+
</xs:complexType>
|
|
317
|
+
<xs:complexType name="BinaryCharacterList">
|
|
318
|
+
<xs:sequence>
|
|
319
|
+
<xs:element name="bc" type="xs:token" maxOccurs="unbounded"/>
|
|
320
|
+
</xs:sequence>
|
|
321
|
+
</xs:complexType>
|
|
322
|
+
<!-- Reference:-->
|
|
323
|
+
<xs:complexType name="Reference">
|
|
324
|
+
<xs:annotation>
|
|
325
|
+
<xs:documentation> A literature reference for a clade. It is recommended to use the 'doi' attribute instead of
|
|
326
|
+
the free text 'desc' element whenever possible. </xs:documentation>
|
|
327
|
+
</xs:annotation>
|
|
328
|
+
<xs:sequence>
|
|
329
|
+
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
|
330
|
+
</xs:sequence>
|
|
331
|
+
<xs:attribute name="doi" type="phy:Doi"/>
|
|
332
|
+
</xs:complexType>
|
|
333
|
+
<xs:simpleType name="Doi">
|
|
334
|
+
<xs:restriction base="xs:token">
|
|
335
|
+
<xs:pattern value="[a-zA-Z0-9_\.]+/\S+"/>
|
|
336
|
+
</xs:restriction>
|
|
337
|
+
</xs:simpleType>
|
|
338
|
+
<!-- Annotation:-->
|
|
339
|
+
<xs:complexType name="Annotation">
|
|
340
|
+
<xs:annotation>
|
|
341
|
+
<xs:documentation> The annotation of a molecular sequence. It is recommended to annotate by using the optional
|
|
342
|
+
'ref' attribute (some examples of acceptable values for the ref attribute: 'GO:0008270',
|
|
343
|
+
'KEGG:Tetrachloroethene degradation', 'EC:1.1.1.1'). Optional element 'desc' allows for a free text
|
|
344
|
+
description. Optional element 'confidence' is used to state the type and value of support for a annotation.
|
|
345
|
+
Similarly, optional attribute 'evidence' is used to describe the evidence for a annotation as free text
|
|
346
|
+
(e.g. 'experimental'). Optional element 'property' allows for further, typed and referenced annotations from
|
|
347
|
+
external resources.</xs:documentation>
|
|
348
|
+
</xs:annotation>
|
|
349
|
+
<xs:sequence>
|
|
350
|
+
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
|
351
|
+
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
|
352
|
+
<xs:element name="property" type="phy:Property" minOccurs="0" maxOccurs="unbounded"/>
|
|
353
|
+
<xs:element name="uri" type="phy:Uri" minOccurs="0"/>
|
|
354
|
+
</xs:sequence>
|
|
355
|
+
<xs:attribute name="ref" type="phy:ref"/>
|
|
356
|
+
<xs:attribute name="source" type="xs:token"/>
|
|
357
|
+
<xs:attribute name="evidence" type="xs:token"/>
|
|
358
|
+
<xs:attribute name="type" type="xs:token"/>
|
|
359
|
+
</xs:complexType>
|
|
360
|
+
<!-- Property:-->
|
|
361
|
+
<xs:complexType name="Property" mixed="true">
|
|
362
|
+
<xs:annotation>
|
|
363
|
+
<xs:documentation> Property allows for typed and referenced properties from external resources to be attached
|
|
364
|
+
to 'Phylogeny', 'Clade', and 'Annotation'. The value of a property is its mixed (free text) content.
|
|
365
|
+
Attribute 'datatype' indicates the type of a property and is limited to xsd-datatypes (e.g. 'xsd:string',
|
|
366
|
+
'xsd:boolean', 'xsd:integer', 'xsd:decimal', 'xsd:float', 'xsd:double', 'xsd:date', 'xsd:anyURI'). Attribute
|
|
367
|
+
'applies_to' indicates the item to which a property applies to (e.g. 'node' for the parent node of a clade,
|
|
368
|
+
'parent_branch' for the parent branch of a clade). Attribute 'id_ref' allows to attached a property
|
|
369
|
+
specifically to one element (on the xml-level). Optional attribute 'unit' is used to indicate the unit of
|
|
370
|
+
the property. An example: <property datatype="xsd:integer" ref="NOAA:depth" applies_to="clade"
|
|
371
|
+
unit="METRIC:m"> 200 </property> </xs:documentation>
|
|
372
|
+
</xs:annotation>
|
|
373
|
+
<xs:attribute name="ref" type="phy:ref" use="required"/>
|
|
374
|
+
<xs:attribute name="unit" type="phy:ref"/>
|
|
375
|
+
<xs:attribute name="datatype" type="phy:PropertyDataType" use="required"/>
|
|
376
|
+
<xs:attribute name="applies_to" type="phy:AppliesTo" use="required"/>
|
|
377
|
+
<xs:attribute name="id_ref" type="phy:id_ref"/>
|
|
378
|
+
</xs:complexType>
|
|
379
|
+
<xs:simpleType name="ref">
|
|
380
|
+
<xs:restriction base="xs:token">
|
|
381
|
+
<xs:pattern value="[a-zA-Z0-9_]+:[a-zA-Z0-9_\.\-\s]+"/>
|
|
382
|
+
</xs:restriction>
|
|
383
|
+
</xs:simpleType>
|
|
384
|
+
<xs:simpleType name="AppliesTo">
|
|
385
|
+
<xs:restriction base="xs:token">
|
|
386
|
+
<xs:enumeration value="phylogeny"/>
|
|
387
|
+
<xs:enumeration value="clade"/>
|
|
388
|
+
<xs:enumeration value="node"/>
|
|
389
|
+
<xs:enumeration value="annotation"/>
|
|
390
|
+
<xs:enumeration value="parent_branch"/>
|
|
391
|
+
<xs:enumeration value="other"/>
|
|
392
|
+
</xs:restriction>
|
|
393
|
+
</xs:simpleType>
|
|
394
|
+
<xs:simpleType name="PropertyDataType">
|
|
395
|
+
<xs:restriction base="xs:token">
|
|
396
|
+
<xs:enumeration value="xsd:string"/>
|
|
397
|
+
<xs:enumeration value="xsd:boolean"/>
|
|
398
|
+
<xs:enumeration value="xsd:decimal"/>
|
|
399
|
+
<xs:enumeration value="xsd:float"/>
|
|
400
|
+
<xs:enumeration value="xsd:double"/>
|
|
401
|
+
<xs:enumeration value="xsd:duration"/>
|
|
402
|
+
<xs:enumeration value="xsd:dateTime"/>
|
|
403
|
+
<xs:enumeration value="xsd:time"/>
|
|
404
|
+
<xs:enumeration value="xsd:date"/>
|
|
405
|
+
<xs:enumeration value="xsd:gYearMonth"/>
|
|
406
|
+
<xs:enumeration value="xsd:gYear"/>
|
|
407
|
+
<xs:enumeration value="xsd:gMonthDay"/>
|
|
408
|
+
<xs:enumeration value="xsd:gDay"/>
|
|
409
|
+
<xs:enumeration value="xsd:gMonth"/>
|
|
410
|
+
<xs:enumeration value="xsd:hexBinary"/>
|
|
411
|
+
<xs:enumeration value="xsd:base64Binary"/>
|
|
412
|
+
<xs:enumeration value="xsd:anyURI"/>
|
|
413
|
+
<xs:enumeration value="xsd:normalizedString"/>
|
|
414
|
+
<xs:enumeration value="xsd:token"/>
|
|
415
|
+
<xs:enumeration value="xsd:integer"/>
|
|
416
|
+
<xs:enumeration value="xsd:nonPositiveInteger"/>
|
|
417
|
+
<xs:enumeration value="xsd:negativeInteger"/>
|
|
418
|
+
<xs:enumeration value="xsd:long"/>
|
|
419
|
+
<xs:enumeration value="xsd:int"/>
|
|
420
|
+
<xs:enumeration value="xsd:short"/>
|
|
421
|
+
<xs:enumeration value="xsd:byte"/>
|
|
422
|
+
<xs:enumeration value="xsd:nonNegativeInteger"/>
|
|
423
|
+
<xs:enumeration value="xsd:unsignedLong"/>
|
|
424
|
+
<xs:enumeration value="xsd:unsignedInt"/>
|
|
425
|
+
<xs:enumeration value="xsd:unsignedShort"/>
|
|
426
|
+
<xs:enumeration value="xsd:unsignedByte"/>
|
|
427
|
+
<xs:enumeration value="xsd:positiveInteger"/>
|
|
428
|
+
</xs:restriction>
|
|
429
|
+
</xs:simpleType>
|
|
430
|
+
<!--Uri-->
|
|
431
|
+
<xs:complexType name="Uri">
|
|
432
|
+
<xs:annotation>
|
|
433
|
+
<xs:documentation> A uniform resource identifier. In general, this is expected to be an URL (for example, to
|
|
434
|
+
link to an image on a website, in which case the 'type' attribute might be 'image' and 'desc' might be
|
|
435
|
+
'image of a California sea hare'). </xs:documentation>
|
|
436
|
+
</xs:annotation>
|
|
437
|
+
<xs:simpleContent>
|
|
438
|
+
<xs:extension base="xs:anyURI">
|
|
439
|
+
<xs:attribute name="desc" type="xs:token"/>
|
|
440
|
+
<xs:attribute name="type" type="xs:token"/>
|
|
441
|
+
</xs:extension>
|
|
442
|
+
</xs:simpleContent>
|
|
443
|
+
</xs:complexType>
|
|
444
|
+
<!-- Confidence:-->
|
|
445
|
+
<xs:complexType name="Confidence">
|
|
446
|
+
<xs:annotation>
|
|
447
|
+
<xs:documentation> A general purpose confidence element. For example this can be used to express the bootstrap
|
|
448
|
+
support value of a clade (in which case the 'type' attribute is 'bootstrap').</xs:documentation>
|
|
449
|
+
</xs:annotation>
|
|
450
|
+
<xs:simpleContent>
|
|
451
|
+
<xs:extension base="xs:double">
|
|
452
|
+
<xs:attribute name="type" type="xs:token" use="required"/>
|
|
453
|
+
</xs:extension>
|
|
454
|
+
</xs:simpleContent>
|
|
455
|
+
</xs:complexType>
|
|
456
|
+
<!-- Identifier:-->
|
|
457
|
+
<xs:complexType name="Id">
|
|
458
|
+
<xs:annotation>
|
|
459
|
+
<xs:documentation> A general purpose identifier element. Allows to indicate the provider (or authority) of an
|
|
460
|
+
identifier. </xs:documentation>
|
|
461
|
+
</xs:annotation>
|
|
462
|
+
<xs:simpleContent>
|
|
463
|
+
<xs:extension base="xs:token">
|
|
464
|
+
<xs:attribute name="provider" type="xs:token"/>
|
|
465
|
+
</xs:extension>
|
|
466
|
+
</xs:simpleContent>
|
|
467
|
+
</xs:complexType>
|
|
468
|
+
<!-- Distribution:-->
|
|
469
|
+
<xs:complexType name="Distribution">
|
|
470
|
+
<xs:annotation>
|
|
471
|
+
<xs:documentation> The geographic distribution of the items of a clade (species, sequences), intended for
|
|
472
|
+
phylogeographic applications. The location can be described either by free text in the 'desc' element and/or
|
|
473
|
+
by the coordinates of one or more 'Points' (similar to the 'Point' element in Google's KML format) or by
|
|
474
|
+
'Polygons'. </xs:documentation>
|
|
475
|
+
</xs:annotation>
|
|
476
|
+
<xs:sequence>
|
|
477
|
+
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
|
478
|
+
<xs:element name="point" type="phy:Point" minOccurs="0" maxOccurs="unbounded"/>
|
|
479
|
+
<xs:element name="polygon" type="phy:Polygon" minOccurs="0" maxOccurs="unbounded"/>
|
|
480
|
+
</xs:sequence>
|
|
481
|
+
</xs:complexType>
|
|
482
|
+
<xs:complexType name="Point">
|
|
483
|
+
<xs:annotation>
|
|
484
|
+
<xs:documentation> The coordinates of a point with an optional altitude (used by element 'Distribution').
|
|
485
|
+
Required attributes are the 'geodetic_datum' used to indicate the geodetic datum (also called 'map datum',
|
|
486
|
+
for example Google's KML uses 'WGS84'). Attribute 'alt_unit' is the unit for the altitude (e.g. 'meter').
|
|
487
|
+
</xs:documentation>
|
|
488
|
+
</xs:annotation>
|
|
489
|
+
<xs:sequence>
|
|
490
|
+
<xs:element name="lat" type="xs:decimal"/>
|
|
491
|
+
<xs:element name="long" type="xs:decimal"/>
|
|
492
|
+
<xs:element name="alt" type="xs:decimal" minOccurs="0"/>
|
|
493
|
+
</xs:sequence>
|
|
494
|
+
<xs:attribute name="geodetic_datum" type="xs:token" use="required"/>
|
|
495
|
+
<xs:attribute name="alt_unit" type="xs:token"/>
|
|
496
|
+
</xs:complexType>
|
|
497
|
+
<xs:complexType name="Polygon">
|
|
498
|
+
<xs:annotation>
|
|
499
|
+
<xs:documentation> A polygon defined by a list of 'Points' (used by element 'Distribution').
|
|
500
|
+
</xs:documentation>
|
|
501
|
+
</xs:annotation>
|
|
502
|
+
<xs:sequence>
|
|
503
|
+
<xs:element name="point" type="phy:Point" minOccurs="3" maxOccurs="unbounded"/>
|
|
504
|
+
</xs:sequence>
|
|
505
|
+
</xs:complexType>
|
|
506
|
+
<!-- Date:-->
|
|
507
|
+
<xs:complexType name="Date">
|
|
508
|
+
<xs:annotation>
|
|
509
|
+
<xs:documentation> A date associated with a clade/node. Its value can be numerical by using the 'value' element
|
|
510
|
+
and/or free text with the 'desc' element' (e.g. 'Silurian'). If a numerical value is used, it is recommended
|
|
511
|
+
to employ the 'unit' attribute to indicate the type of the numerical value (e.g. 'mya' for 'million years
|
|
512
|
+
ago'). The elements 'minimum' and 'maximum' are used the indicate a range/confidence
|
|
513
|
+
interval</xs:documentation>
|
|
514
|
+
</xs:annotation>
|
|
515
|
+
<xs:sequence>
|
|
516
|
+
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
|
517
|
+
<xs:element name="value" type="xs:decimal" minOccurs="0"/>
|
|
518
|
+
<xs:element name="minimum" type="xs:decimal" minOccurs="0"/>
|
|
519
|
+
<xs:element name="maximum" type="xs:decimal" minOccurs="0"/>
|
|
520
|
+
</xs:sequence>
|
|
521
|
+
<xs:attribute name="unit" type="xs:token"/>
|
|
522
|
+
</xs:complexType>
|
|
523
|
+
<!-- BranchColor:-->
|
|
524
|
+
<xs:complexType name="BranchColor">
|
|
525
|
+
<xs:annotation>
|
|
526
|
+
<xs:documentation> This indicates the color of a clade when rendered (the color applies to the whole clade
|
|
527
|
+
unless overwritten by the color(s) of sub clades).</xs:documentation>
|
|
528
|
+
</xs:annotation>
|
|
529
|
+
<xs:sequence>
|
|
530
|
+
<xs:element name="red" type="xs:unsignedByte"/>
|
|
531
|
+
<xs:element name="green" type="xs:unsignedByte"/>
|
|
532
|
+
<xs:element name="blue" type="xs:unsignedByte"/>
|
|
533
|
+
</xs:sequence>
|
|
534
|
+
</xs:complexType>
|
|
535
|
+
<!-- SequenceRelation:-->
|
|
536
|
+
<xs:complexType name="SequenceRelation">
|
|
537
|
+
<xs:annotation>
|
|
538
|
+
<xs:documentation> This is used to express a typed relationship between two sequences. For example it could be
|
|
539
|
+
used to describe an orthology (in which case attribute 'type' is 'orthology'). </xs:documentation>
|
|
540
|
+
</xs:annotation>
|
|
541
|
+
<xs:sequence>
|
|
542
|
+
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
|
543
|
+
</xs:sequence>
|
|
544
|
+
<xs:attribute name="id_ref_0" type="phy:id_ref" use="required"/>
|
|
545
|
+
<xs:attribute name="id_ref_1" type="phy:id_ref" use="required"/>
|
|
546
|
+
<xs:attribute name="distance" type="xs:double"/>
|
|
547
|
+
<xs:attribute name="type" type="phy:SequenceRelationType" use="required"/>
|
|
548
|
+
</xs:complexType>
|
|
549
|
+
<xs:simpleType name="SequenceRelationType">
|
|
550
|
+
<xs:restriction base="xs:token">
|
|
551
|
+
<xs:enumeration value="orthology"/>
|
|
552
|
+
<xs:enumeration value="one_to_one_orthology"/>
|
|
553
|
+
<xs:enumeration value="super_orthology"/>
|
|
554
|
+
<xs:enumeration value="paralogy"/>
|
|
555
|
+
<xs:enumeration value="ultra_paralogy"/>
|
|
556
|
+
<xs:enumeration value="xenology"/>
|
|
557
|
+
<xs:enumeration value="unknown"/>
|
|
558
|
+
<xs:enumeration value="other"/>
|
|
559
|
+
</xs:restriction>
|
|
560
|
+
</xs:simpleType>
|
|
561
|
+
<!-- CladeRelation:-->
|
|
562
|
+
<xs:complexType name="CladeRelation">
|
|
563
|
+
<xs:annotation>
|
|
564
|
+
<xs:documentation> This is used to express a typed relationship between two clades. For example it could be
|
|
565
|
+
used to describe multiple parents of a clade.</xs:documentation>
|
|
566
|
+
</xs:annotation>
|
|
567
|
+
<xs:sequence>
|
|
568
|
+
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
|
569
|
+
</xs:sequence>
|
|
570
|
+
<xs:attribute name="id_ref_0" type="phy:id_ref" use="required"/>
|
|
571
|
+
<xs:attribute name="id_ref_1" type="phy:id_ref" use="required"/>
|
|
572
|
+
<xs:attribute name="distance" type="xs:double"/>
|
|
573
|
+
<xs:attribute name="type" type="xs:token" use="required"/>
|
|
574
|
+
</xs:complexType>
|
|
575
|
+
<!-- Used to link elements together on the xml level:-->
|
|
576
|
+
<xs:simpleType name="id_source">
|
|
577
|
+
<xs:restriction base="xs:ID"/>
|
|
578
|
+
</xs:simpleType>
|
|
579
|
+
<xs:simpleType name="id_ref">
|
|
580
|
+
<xs:restriction base="xs:IDREF"/>
|
|
581
|
+
</xs:simpleType>
|
|
582
|
+
</xs:schema>
|