<?xml version="1.0" encoding="ISO-8859-1"?>
<!--
This file shows encodings of character state data.
-->
<!--
For more discussion of the structure of the root element,
refer to 'taxa.xml'
-->
<nex:nexml
version="0.8"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.nexml.org/1.0 ../xsd/nexml.xsd"
xmlns:nex="http://www.nexml.org/1.0"
xmlns="http://www.nexml.org/1.0">
<!--
For more discussion of the structure of the taxa
element, refer to 'taxa.xml'
-->
<otus id="taxa1" label="Primary taxa block">
<otu id="t1" label="Homo sapiens"/>
<otu id="t2" label="Pan paniscus"/>
<otu id="t3" label="Pan troglodytes"/>
<otu id="t4" label="Gorilla gorilla"/>
<otu id="t5" label="Pongo pygmaeus"/>
</otus>
<!--
This characters block encodes restriction site data, i.e.
presence (1) / absence (0) observations. Because the states
that can occur - and what they mean - are known, there is no
'format' element to define states (see below for examples of
that). In this example, restriction site data is encoded
as a sequence of characters (rather than individual cells),
hence we use the subclass xsi:type="RestrictionSeqs".
All characters blocks must have an id attribute and a
reference to a taxa block that precedes it. In addition,
it may have the same additional attributes (label, xml:base,
xml:lang, xml:id, xlink:href and class) as the taxa element.
-->
<characters otus="taxa1" id="m1" xsi:type="nex:RestrictionSeqs" label="Restriction site sequences">
<format>
<states id="states3">
<state id="s1" symbol="0"/>
<state id="s2" symbol="1"/>
</states>
<char id="c1" states="states3"/>
<char id="c2" states="states3"/>
<char id="c3" states="states3"/>
<char id="c4" states="states3"/>
</format>
<matrix>
<!--
The matrix element is a container for row elements.
-->
<!--
Each row element must have an id and a reference
to a taxon element that precedes it.
-->
<row otu="t1" id="r1">
<!--
Because this characters block is an instance
of the subclass RestrictionSeqs it contains
'seq' elements with 1's and 0's.
-->
<seq>0101</seq>
</row>
<row otu="t2" id="r2">
<seq>0101</seq>
</row>
<row otu="t3" id="r3">
<seq>0101</seq>
</row>
<row otu="t4" id="r4">
<seq>0101</seq>
</row>
<row otu="t5" id="r5">
<seq>0101</seq>
</row>
</matrix>
</characters>
<!--
This characters block encodes 'standard' categorical characters,
marked up granularly, as cells.
-->
<characters otus="taxa1" id="m2" xsi:type="nex:StandardCells" label="Categorical characters">
<!--
Because categorical characters in instances of this subclass
don't have a priori known numbers of states, they must be
defined using the 'format' element.
-->
<format>
<!--
The first elements inside a format element are stateset
definitions. In this example, there is a set of four
states, each tagged with an id. The symbol attribute is
a shorthand token.
-->
<states id="states1">
<state id="s1" symbol="1"/>
<state id="s2" symbol="2"/>
<state id="s3" symbol="3"/>
<polymorphic_state_set symbol="4" id="s4">
<member state="s1"/>
<member state="s2"/>
</polymorphic_state_set>
<uncertain_state_set symbol="5" id="s5">
<member state="s3"/>
<member state="s1"/>
</uncertain_state_set>
</states>
<!--
The matrix in this example contains two columns, both
referring to the same stateset - and so cells in both
columns can occupy one of four states.
-->
<char states="states1" id="c1"/>
<char states="states1" id="c2"/>
</format>
<!--
In this subclass, the matrix contains rows consisting of
individual cells.
-->
<matrix>
<row id="r1" otu="t1">
<!--
Each cell must contain a reference to the column
it belongs to, and to a state allowed within that
column.
-->
<cell char="c1" state="s1"/>
<cell char="c2" state="s2"/>
</row>
<row id="r2" otu="t2">
<cell char="c1" state="s2"/>
<cell char="c2" state="s2"/>
</row>
<row id="r3" otu="t3">
<cell char="c1" state="s3"/>
<cell char="c2" state="s4"/>
</row>
<row id="r4" otu="t4">
<cell char="c1" state="s2"/>
<cell char="c2" state="s3"/>
</row>
<row id="r5" otu="t5">
<cell char="c1" state="s4"/>
<cell char="c2" state="s1"/>
</row>
</matrix>
</characters>
<!--
This example is a characters block for continuous characters, marked
up as individual cells.
-->
<characters otus="taxa1" id="m3" xsi:type="nex:ContinuousCells" label="Continuous characters">
<format>
<!--
Because in this subclass, characters are marked up granularly -
as cells - we must define the columns these cells belong to.
Because this is continuous data, we don't (can't) define the
states cells in these columns may occupy, hence there are no
'states' elements in this subclass.
-->
<char id="c1" label="this is character 1" class="something"/>
<char id="c2"/>
<char id="c3"/>
<char id="c4"/>
<char id="c5"/>
</format>
<matrix>
<row id="r1" otu="t1">
<!--
In this subclass, the 'state' attribute holds the raw
value of the cell (i.e. a floating point number), not
a reference to a state defined previously.
-->
<cell char="c1" state="-1.545414144070023"/>
<cell char="c2" state="-2.3905621575431044"/>
<cell char="c3" state="-2.9610221833467265"/>
<cell char="c4" state="0.7868662069161243"/>
<cell char="c5" state="0.22968509237534918"/>
</row>
<row id="r2" otu="t2">
<cell char="c1" state="-1.6259836379710066"/>
<cell char="c2" state="3.649352410850134"/>
<cell char="c3" state="1.778885099660406"/>
<cell char="c4" state="-1.2580877968480846"/>
<cell char="c5" state="0.22335354995610862"/>
</row>
<row id="r3" otu="t3">
<cell char="c1" state="-1.5798979984134964"/>
<cell char="c2" state="2.9548251411133157"/>
<cell char="c3" state="1.522005675256233"/>
<cell char="c4" state="-0.8642016921755289"/>
<cell char="c5" state="-0.938129801832388"/>
</row>
<row id="r4" otu="t4">
<cell char="c1" state="2.7436692306788086"/>
<cell char="c2" state="-0.7151148143399818"/>
<cell char="c3" state="4.592207937774776"/>
<cell char="c4" state="-0.6898841440534845"/>
<cell char="c5" state="0.5769509574453064"/>
</row>
<row id="r5" otu="t5">
<cell char="c1" state="3.1060827493657683"/>
<cell char="c2" state="-1.0453787389160105"/>
<cell char="c3" state="2.67416332763427"/>
<cell char="c4" state="-1.4045634106692808"/>
<cell char="c5" state="0.019890469925520196"/>
</row>
</matrix>
</characters>
<!--
This subclass encodes DNA as sequences (not cells). Like the restriction
site data block shown above, the states are known (being IUPAC single
character nucleotide symbols), hence there is no 'format' element. In
addition to the IUPAC symbols, '-' is used for gaps, '?' is used for
missing. Spaces are allowed (so that long lines can be broken up, some
parsers might otherwise complain) but have no meaning.
-->
<characters otus="taxa1" id="c3" xsi:type="nex:DnaSeqs" label="DNA sequences">
<format>
<states id="states7">
<state id="s1" symbol="A" />
<state id="s2" symbol="C" />
<state id="s3" symbol="G" />
<state id="s4" symbol="T" />
<uncertain_state_set id="s5" symbol="K">
<member state="s3" />
<member state="s4" />
</uncertain_state_set>
<uncertain_state_set id="s6" symbol="M">
<member state="s1" />
<member state="s2" />
</uncertain_state_set>
<uncertain_state_set id="s7" symbol="R">
<member state="s1" />
<member state="s3" />
</uncertain_state_set>
<uncertain_state_set id="s8" symbol="S">
<member state="s2" />
<member state="s3" />
</uncertain_state_set>
<uncertain_state_set id="s9" symbol="W">
<member state="s1" />
<member state="s4" />
</uncertain_state_set>
<uncertain_state_set id="s10" symbol="Y">
<member state="s2" />
<member state="s4" />
</uncertain_state_set>
<uncertain_state_set id="s11" symbol="B">
<member state="s2" />
<member state="s3" />
<member state="s4" />
</uncertain_state_set>
<uncertain_state_set id="s12" symbol="D">
<member state="s1" />
<member state="s3" />
<member state="s4" />
</uncertain_state_set>
<uncertain_state_set id="s13" symbol="H">
<member state="s1" />
<member state="s2" />
<member state="s4" />
</uncertain_state_set>
<uncertain_state_set id="s14" symbol="V">
<member state="s1" />
<member state="s2" />
<member state="s3" />
</uncertain_state_set>
<uncertain_state_set id="s15" symbol="N">
<member state="s3" />
<member state="s1" />
<member state="s4" />
<member state="s2" />
</uncertain_state_set>
<uncertain_state_set id="s16" symbol="X">
<member state="s3" />
<member state="s1" />
<member state="s4" />
<member state="s2" />
</uncertain_state_set>
<uncertain_state_set id="s17" symbol="-" />
<uncertain_state_set id="s18" symbol="?">
<member state="s1" />
<member state="s2" />
<member state="s3" />
<member state="s4" />
<member state="s5" />
<member state="s6" />
<member state="s7" />
<member state="s8" />
<member state="s9" />
<member state="s10" />
<member state="s11" />
<member state="s12" />
<member state="s13" />
<member state="s14" />
<member state="s15" />
<member state="s16" />
<member state="s17" />
</uncertain_state_set>
</states>
<char id="c1" states="states7" />
<char id="c2" states="states7" />
<char id="c3" states="states7" />
<char id="c4" states="states7" />
<char id="c5" states="states7" />
<char id="c6" states="states7" />
<char id="c7" states="states7" />
<char id="c8" states="states7" />
<char id="c9" states="states7" />
<char id="c10" states="states7" />
<char id="c11" states="states7" />
<char id="c12" states="states7" />
<char id="c13" states="states7" />
<char id="c14" states="states7" />
<char id="c15" states="states7" />
<char id="c16" states="states7" />
</format>
<matrix>
<row otu="t1" id="r1">
<seq>A C G C T C G C A T C G C A T C</seq>
</row>
<row otu="t2" id="r2">
<seq>A C G C T C G C A T C G C A T C</seq>
</row>
<row otu="t3" id="r3">
<seq>A C G C T C G C A T C G C A T C</seq>
</row>
</matrix>
</characters>
<!--
RNA only differs from the previous example by using U instead of T
-->
<characters otus="taxa1" id="rnaseqs4" xsi:type="nex:RnaSeqs" label="RNA sequences">
<format>
<states id="states3">
<state id="s1" symbol="A"/>
<state id="s2" symbol="C"/>
<state id="s3" symbol="G"/>
<state id="s4" symbol="U"/>
<uncertain_state_set id="s5" symbol="K">
<member state="s3"/>
<member state="s4"/>
</uncertain_state_set>
<uncertain_state_set id="s6" symbol="M">
<member state="s1"/>
<member state="s2"/>
</uncertain_state_set>
<uncertain_state_set id="s7" symbol="R">
<member state="s1"/>
<member state="s3"/>
</uncertain_state_set>
<uncertain_state_set id="s8" symbol="S">
<member state="s2"/>
<member state="s3"/>
</uncertain_state_set>
<uncertain_state_set id="s9" symbol="W">
<member state="s1"/>
<member state="s4"/>
</uncertain_state_set>
<uncertain_state_set id="s10" symbol="Y">
<member state="s2"/>
<member state="s4"/>
</uncertain_state_set>
<uncertain_state_set id="s11" symbol="B">
<member state="s2"/>
<member state="s3"/>
<member state="s4"/>
</uncertain_state_set>
<uncertain_state_set id="s12" symbol="D">
<member state="s1"/>
<member state="s3"/>
<member state="s4"/>
</uncertain_state_set>
<uncertain_state_set id="s13" symbol="H">
<member state="s1"/>
<member state="s2"/>
<member state="s4"/>
</uncertain_state_set>
<uncertain_state_set id="s14" symbol="V">
<member state="s1"/>
<member state="s2"/>
<member state="s3"/>
</uncertain_state_set>
<uncertain_state_set id="s15" symbol="N">
<member state="s3"/>
<member state="s1"/>
<member state="s4"/>
<member state="s2"/>
</uncertain_state_set>
<uncertain_state_set id="s16" symbol="X">
<member state="s3"/>
<member state="s1"/>
<member state="s4"/>
<member state="s2"/>
</uncertain_state_set>
<uncertain_state_set id="s17" symbol="-"/>
<uncertain_state_set id="s18" symbol="?">
<member state="s1"/>
<member state="s2"/>
<member state="s3"/>
<member state="s4"/>
<member state="s5"/>
<member state="s6"/>
<member state="s7"/>
<member state="s8"/>
<member state="s9"/>
<member state="s10"/>
<member state="s11"/>
<member state="s12"/>
<member state="s13"/>
<member state="s14"/>
<member state="s15"/>
<member state="s16"/>
<member state="s17"/>
</uncertain_state_set>
</states>
<char id="c1" states="states3"/>
<char id="c2" states="states3"/>
<char id="c3" states="states3"/>
<char id="c4" states="states3"/>
<char id="c5" states="states3"/>
<char id="c6" states="states3"/>
<char id="c7" states="states3"/>
<char id="c8" states="states3"/>
<char id="c9" states="states3"/>
<char id="c10" states="states3"/>
<char id="c11" states="states3"/>
<char id="c12" states="states3"/>
<char id="c13" states="states3"/>
<char id="c14" states="states3"/>
<char id="c15" states="states3"/>
<char id="c16" states="states3"/>
<char id="c17" states="states3"/>
<char id="c18" states="states3"/>
<char id="c19" states="states3"/>
<char id="c20" states="states3"/>
</format>
<matrix>
<row otu="t1" id="r1">
<seq>ACGCUCGCAUCGCAUC</seq>
</row>
<row otu="t2" id="r2">
<seq>ACGCUCGCAUCGCAUC</seq>
</row>
<row otu="t3" id="r3">
<seq>ACGCUCGCAUCGCAUC</seq>
</row>
</matrix>
</characters>
<!--
A more compact example of encoding of continuous characters as raw sequences.
-->
<characters otus="taxa1" id="c5" xsi:type="nex:ContinuousSeqs" label="Continuous sequences">
<format>
<char id="c1"/>
<char id="c2"/>
<char id="c3"/>
<char id="c4"/>
<char id="c5"/>
</format>
<matrix>
<row id="r1" otu="t1">
<seq>-1.545414144070023 -2.3905621575431044 -2.9610221833467265 0.7868662069161243 0.22968509237534918</seq>
</row>
<row id="r2" otu="t2">
<seq>-1.6259836379710066 3.649352410850134 1.778885099660406 -1.2580877968480846 0.22335354995610862</seq>
</row>
<row id="r3" otu="t3">
<seq>-1.5798979984134964 2.9548251411133157 1.522005675256233 -0.8642016921755289 -0.938129801832388</seq>
</row>
<row id="r4" otu="t4">
<seq>2.7436692306788086 -0.7151148143399818 4.592207937774776 -0.6898841440534845 0.5769509574453064</seq>
</row>
<row id="r5" otu="t5">
<seq>3.1060827493657683 -1.0453787389160105 2.67416332763427 -1.4045634106692808 0.019890469925520196</seq>
</row>
</matrix>
</characters>
<!--
A more compact example of encoding of standard data. Note that the symbols used here
are integers (also above 9) and so characters must be space-separated. The symbols used
here are the same as the symbol attributes used in characters block m2, earlier.
-->
<characters otus="taxa1" id="c6" xsi:type="nex:StandardSeqs" label="Standard sequences">
<format>
<!--
The first elements inside a format element are stateset
definitions. In this example, there is a set of four
states, each tagged with an id. The symbol attribute is
a shorthand token.
-->
<states id="states1">
<state id="s1" symbol="1"/>
<state id="s2" symbol="2"/>
<state id="s3" symbol="3"/>
<polymorphic_state_set symbol="4" id="s4">
<member state="s1"/>
<member state="s2"/>
</polymorphic_state_set>
<uncertain_state_set symbol="5" id="s5">
<member state="s3"/>
<member state="s1"/>
</uncertain_state_set>
</states>
<!--
The matrix in this example contains two columns, both
referring to the same stateset - and so cells in both
columns can occupy one of four states.
-->
<char states="states1" id="c1"/>
<char states="states1" id="c2"/>
</format>
<matrix>
<row id="r1" otu="t1">
<seq>1 2</seq>
</row>
<row id="r2" otu="t2">
<seq>2 2</seq>
</row>
<row id="r3" otu="t3">
<seq>3 4</seq>
</row>
<row id="r4" otu="t4">
<seq>2 3</seq>
</row>
<row id="r5" otu="t5">
<seq>4 1</seq>
</row>
</matrix>
</characters>
</nex:nexml>