| blob | d6c40791d28fd3166a1d592a7eb8085d976005b0 |
1 <?xml version="1.0" encoding="ISO-8859-1"?>
2 <!--
3 This file shows encodings of character state data.
4 -->
5 <!--
6 For more discussion of the structure of the root element,
7 refer to 'taxa.xml'
8 -->
9 <nex:nexml
10 version="0.8"
11 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
12 xsi:schemaLocation="http://www.nexml.org/1.0 ../../nexml/xsd/nexml.xsd"
13 xmlns:nex="http://www.nexml.org/1.0"
14 xmlns="http://www.nexml.org/1.0">
16 <!-- revision control metadata -->
17 <dict id="dict1">
18 <string id="author">$Author: rvos $</string>
19 <string id="date">$Date: 2009-03-13 01:57:49 -0400 (Fri, 13 Mar 2009) $</string>
20 <string id="header">$Header: $</string>
21 <string id="id">$Id: characters.xml 970 2009-03-13 05:57:49Z rvos $</string>
22 <string id="rev">$Rev: 970 $</string>
23 <string id="url">$URL: http://nexml.svn.sourceforge.net/svnroot/nexml/trunk/nexml/examples/characters.xml $</string>
24 </dict>
26 <!--
27 For more discussion of the structure of the taxa
28 element, refer to 'taxa.xml'
29 -->
30 <otus id="taxa1" label="Primary taxa block">
31 <otu id="t1" label="Homo sapiens"/>
32 <otu id="t2" label="Pan paniscus"/>
33 <otu id="t3" label="Pan troglodytes"/>
34 <otu id="t4" label="Gorilla gorilla"/>
35 <otu id="t5" label="Pongo pygmaeus"/>
36 </otus>
37 <!--
38 This characters block encodes restriction site data, i.e.
39 presence (1) / absence (0) observations. Because the states
40 that can occur - and what they mean - are known, there is no
41 'format' element to define states (see below for examples of
42 that). In this example, restriction site data is encoded
43 as a sequence of characters (rather than individual cells),
44 hence we use the subclass xsi:type="RestrictionSeqs".
46 All characters blocks must have an id attribute and a
47 reference to a taxa block that precedes it. In addition,
48 it may have the same additional attributes (label, xml:base,
49 xml:lang, xml:id, xlink:href and class) as the taxa element.
50 -->
51 <characters otus="taxa1" id="m1" xsi:type="nex:RestrictionSeqs">
52 <format>
53 <states id="states3">
54 <state id="s1" symbol="0"/>
55 <state id="s2" symbol="1"/>
56 </states>
57 <char id="c1" states="states3"/>
58 <char id="c2" states="states3"/>
59 <char id="c3" states="states3"/>
60 <char id="c4" states="states3"/>
61 </format>
62 <matrix>
63 <!--
64 The matrix element is a container for row elements.
65 -->
66 <!--
67 Each row element must have an id and a reference
68 to a taxon element that precedes it.
69 -->
70 <row otu="t1" id="r1">
71 <!--
72 Because this characters block is an instance
73 of the subclass RestrictionSeqs it contains
74 'seq' elements with 1's and 0's.
75 -->
76 <seq>0101</seq>
77 </row>
78 <row otu="t2" id="r2">
79 <seq>0101</seq>
80 </row>
81 <row otu="t3" id="r3">
82 <seq>0101</seq>
83 </row>
84 <row otu="t4" id="r4">
85 <seq>0101</seq>
86 </row>
87 <row otu="t5" id="r5">
88 <seq>0101</seq>
89 </row>
90 </matrix>
91 </characters>
92 <!--
93 This characters block encodes 'standard' categorical characters,
94 marked up granularly, as cells.
95 -->
96 <characters otus="taxa1" id="m2" xsi:type="nex:StandardCells" label="Categorical characters">
97 <!--
98 Because categorical characters in instances of this subclass
99 don't have a priori known numbers of states, they must be
100 defined using the 'format' element.
101 -->
102 <format>
103 <!--
104 The first elements inside a format element are stateset
105 definitions. In this example, there is a set of four
106 states, each tagged with an id. The symbol attribute is
107 a shorthand token.
108 -->
109 <states id="states1">
110 <state id="s1" symbol="1"/>
111 <state id="s2" symbol="2"/>
112 <state id="s3" symbol="3"/>
113 <polymorphic_state_set symbol="4" id="s4">
114 <member state="s1"/>
115 <member state="s2"/>
116 </polymorphic_state_set>
117 <uncertain_state_set symbol="5" id="s5">
118 <member state="s3"/>
119 <member state="s1"/>
120 </uncertain_state_set>
121 </states>
122 <!--
123 The matrix in this example contains two columns, both
124 referring to the same stateset - and so cells in both
125 columns can occupy one of four states.
126 -->
127 <char states="states1" id="c1"/>
128 <char states="states1" id="c2"/>
129 </format>
130 <!--
131 In this subclass, the matrix contains rows consisting of
132 individual cells.
133 -->
134 <matrix>
135 <row id="r1" otu="t1">
136 <!--
137 Each cell must contain a reference to the column
138 it belongs to, and to a state allowed within that
139 column.
140 -->
141 <cell char="c1" state="s1"/>
142 <cell char="c2" state="s2"/>
143 </row>
144 <row id="r2" otu="t2">
145 <cell char="c1" state="s2"/>
146 <cell char="c2" state="s2"/>
147 </row>
148 <row id="r3" otu="t3">
149 <cell char="c1" state="s3"/>
150 <cell char="c2" state="s4"/>
151 </row>
152 <row id="r4" otu="t4">
153 <cell char="c1" state="s2"/>
154 <cell char="c2" state="s3"/>
155 </row>
156 <row id="r5" otu="t5">
157 <cell char="c1" state="s4"/>
158 <cell char="c2" state="s1"/>
159 </row>
160 </matrix>
161 </characters>
162 <!--
163 This example is a characters block for continuous characters, marked
164 up as individual cells.
165 -->
166 <characters otus="taxa1" id="m3" xsi:type="nex:ContinuousCells" label="Continuous characters">
167 <format>
168 <!--
169 Because in this subclass, characters are marked up granularly -
170 as cells - we must define the columns these cells belong to.
171 Because this is continuous data, we don't (can't) define the
172 states cells in these columns may occupy, hence there are no
173 'states' elements in this subclass.
174 -->
175 <char id="c1" label="this is character 1" class="something"/>
176 <char id="c2"/>
177 <char id="c3"/>
178 <char id="c4"/>
179 <char id="c5"/>
180 </format>
181 <matrix>
182 <row id="r1" otu="t1">
183 <!--
184 In this subclass, the 'state' attribute holds the raw
185 value of the cell (i.e. a floating point number), not
186 a reference to a state defined previously.
187 -->
188 <cell char="c1" state="-1.545414144070023"/>
189 <cell char="c2" state="-2.3905621575431044"/>
190 <cell char="c3" state="-2.9610221833467265"/>
191 <cell char="c4" state="0.7868662069161243"/>
192 <cell char="c5" state="0.22968509237534918"/>
193 </row>
194 <row id="r2" otu="t2">
195 <cell char="c1" state="-1.6259836379710066"/>
196 <cell char="c2" state="3.649352410850134"/>
197 <cell char="c3" state="1.778885099660406"/>
198 <cell char="c4" state="-1.2580877968480846"/>
199 <cell char="c5" state="0.22335354995610862"/>
200 </row>
201 <row id="r3" otu="t3">
202 <cell char="c1" state="-1.5798979984134964"/>
203 <cell char="c2" state="2.9548251411133157"/>
204 <cell char="c3" state="1.522005675256233"/>
205 <cell char="c4" state="-0.8642016921755289"/>
206 <cell char="c5" state="-0.938129801832388"/>
207 </row>
208 <row id="r4" otu="t4">
209 <cell char="c1" state="2.7436692306788086"/>
210 <cell char="c2" state="-0.7151148143399818"/>
211 <cell char="c3" state="4.592207937774776"/>
212 <cell char="c4" state="-0.6898841440534845"/>
213 <cell char="c5" state="0.5769509574453064"/>
214 </row>
215 <row id="r5" otu="t5">
216 <cell char="c1" state="3.1060827493657683"/>
217 <cell char="c2" state="-1.0453787389160105"/>
218 <cell char="c3" state="2.67416332763427"/>
219 <cell char="c4" state="-1.4045634106692808"/>
220 <cell char="c5" state="0.019890469925520196"/>
221 </row>
222 </matrix>
223 </characters>
224 <!--
225 This subclass encodes DNA as sequences (not cells). Like the restriction
226 site data block shown above, the states are known (being IUPAC single
227 character nucleotide symbols), hence there is no 'format' element. In
228 addition to the IUPAC symbols, '-' is used for gaps, '?' is used for
229 missing. Spaces are allowed (so that long lines can be broken up, some
230 parsers might otherwise complain) but have no meaning.
231 -->
232 <characters otus="taxa1" id="c3" xsi:type="nex:DnaSeqs" label="DNA sequences">
233 <format>
234 <states id="states7">
235 <state id="s1" symbol="A" />
236 <state id="s2" symbol="C" />
237 <state id="s3" symbol="G" />
238 <state id="s4" symbol="T" />
239 <uncertain_state_set id="s5" symbol="K">
240 <member state="s3" />
241 <member state="s4" />
242 </uncertain_state_set>
243 <uncertain_state_set id="s6" symbol="M">
244 <member state="s1" />
245 <member state="s2" />
246 </uncertain_state_set>
247 <uncertain_state_set id="s7" symbol="R">
248 <member state="s1" />
249 <member state="s3" />
250 </uncertain_state_set>
251 <uncertain_state_set id="s8" symbol="S">
252 <member state="s2" />
253 <member state="s3" />
254 </uncertain_state_set>
255 <uncertain_state_set id="s9" symbol="W">
256 <member state="s1" />
257 <member state="s4" />
258 </uncertain_state_set>
259 <uncertain_state_set id="s10" symbol="Y">
260 <member state="s2" />
261 <member state="s4" />
262 </uncertain_state_set>
263 <uncertain_state_set id="s11" symbol="B">
264 <member state="s2" />
265 <member state="s3" />
266 <member state="s4" />
267 </uncertain_state_set>
268 <uncertain_state_set id="s12" symbol="D">
269 <member state="s1" />
270 <member state="s3" />
271 <member state="s4" />
272 </uncertain_state_set>
273 <uncertain_state_set id="s13" symbol="H">
274 <member state="s1" />
275 <member state="s2" />
276 <member state="s4" />
277 </uncertain_state_set>
278 <uncertain_state_set id="s14" symbol="V">
279 <member state="s1" />
280 <member state="s2" />
281 <member state="s3" />
282 </uncertain_state_set>
283 <uncertain_state_set id="s15" symbol="N">
284 <member state="s3" />
285 <member state="s1" />
286 <member state="s4" />
287 <member state="s2" />
288 </uncertain_state_set>
289 <uncertain_state_set id="s16" symbol="X">
290 <member state="s3" />
291 <member state="s1" />
292 <member state="s4" />
293 <member state="s2" />
294 </uncertain_state_set>
295 <uncertain_state_set id="s17" symbol="-" />
296 <uncertain_state_set id="s18" symbol="?">
297 <member state="s1" />
298 <member state="s2" />
299 <member state="s3" />
300 <member state="s4" />
301 <member state="s5" />
302 <member state="s6" />
303 <member state="s7" />
304 <member state="s8" />
305 <member state="s9" />
306 <member state="s10" />
307 <member state="s11" />
308 <member state="s12" />
309 <member state="s13" />
310 <member state="s14" />
311 <member state="s15" />
312 <member state="s16" />
313 <member state="s17" />
314 </uncertain_state_set>
315 </states>
316 <char id="c1" states="states7" />
317 <char id="c2" states="states7" />
318 <char id="c3" states="states7" />
319 <char id="c4" states="states7" />
320 <char id="c5" states="states7" />
321 <char id="c6" states="states7" />
322 <char id="c7" states="states7" />
323 <char id="c8" states="states7" />
324 <char id="c9" states="states7" />
325 <char id="c10" states="states7" />
326 <char id="c11" states="states7" />
327 <char id="c12" states="states7" />
328 <char id="c13" states="states7" />
329 <char id="c14" states="states7" />
330 <char id="c15" states="states7" />
331 <char id="c16" states="states7" />
332 </format>
333 <matrix>
334 <row otu="t1" id="r1" label="dna_seq_1">
335 <seq>A C G C T C G C A T C G C A T C</seq>
336 </row>
337 <row otu="t2" id="r2" label="dna_seq_2">
338 <seq>A C G C T C G C A T C G C A T T</seq>
339 </row>
340 <row otu="t3" id="r3" label="dna_seq_3">
341 <seq>A C G C T C G C A T C G C A T G</seq>
342 </row>
343 </matrix>
344 </characters>
345 <!--
346 RNA only differs from the previous example by using U instead of T
347 -->
348 <characters otus="taxa1" id="rnaseqs4" xsi:type="nex:RnaSeqs" label="RNA sequences">
349 <format>
350 <states id="states3">
351 <state id="s1" symbol="A"/>
352 <state id="s2" symbol="C"/>
353 <state id="s3" symbol="G"/>
354 <state id="s4" symbol="U"/>
355 <uncertain_state_set id="s5" symbol="K">
356 <member state="s3"/>
357 <member state="s4"/>
358 </uncertain_state_set>
359 <uncertain_state_set id="s6" symbol="M">
360 <member state="s1"/>
361 <member state="s2"/>
362 </uncertain_state_set>
363 <uncertain_state_set id="s7" symbol="R">
364 <member state="s1"/>
365 <member state="s3"/>
366 </uncertain_state_set>
367 <uncertain_state_set id="s8" symbol="S">
368 <member state="s2"/>
369 <member state="s3"/>
370 </uncertain_state_set>
371 <uncertain_state_set id="s9" symbol="W">
372 <member state="s1"/>
373 <member state="s4"/>
374 </uncertain_state_set>
375 <uncertain_state_set id="s10" symbol="Y">
376 <member state="s2"/>
377 <member state="s4"/>
378 </uncertain_state_set>
379 <uncertain_state_set id="s11" symbol="B">
380 <member state="s2"/>
381 <member state="s3"/>
382 <member state="s4"/>
383 </uncertain_state_set>
384 <uncertain_state_set id="s12" symbol="D">
385 <member state="s1"/>
386 <member state="s3"/>
387 <member state="s4"/>
388 </uncertain_state_set>
389 <uncertain_state_set id="s13" symbol="H">
390 <member state="s1"/>
391 <member state="s2"/>
392 <member state="s4"/>
393 </uncertain_state_set>
394 <uncertain_state_set id="s14" symbol="V">
395 <member state="s1"/>
396 <member state="s2"/>
397 <member state="s3"/>
398 </uncertain_state_set>
399 <uncertain_state_set id="s15" symbol="N">
400 <member state="s3"/>
401 <member state="s1"/>
402 <member state="s4"/>
403 <member state="s2"/>
404 </uncertain_state_set>
405 <uncertain_state_set id="s16" symbol="X">
406 <member state="s3"/>
407 <member state="s1"/>
408 <member state="s4"/>
409 <member state="s2"/>
410 </uncertain_state_set>
411 <uncertain_state_set id="s17" symbol="-"/>
412 <uncertain_state_set id="s18" symbol="?">
413 <member state="s1"/>
414 <member state="s2"/>
415 <member state="s3"/>
416 <member state="s4"/>
417 <member state="s5"/>
418 <member state="s6"/>
419 <member state="s7"/>
420 <member state="s8"/>
421 <member state="s9"/>
422 <member state="s10"/>
423 <member state="s11"/>
424 <member state="s12"/>
425 <member state="s13"/>
426 <member state="s14"/>
427 <member state="s15"/>
428 <member state="s16"/>
429 <member state="s17"/>
430 </uncertain_state_set>
431 </states>
432 <char id="c1" states="states3"/>
433 <char id="c2" states="states3"/>
434 <char id="c3" states="states3"/>
435 <char id="c4" states="states3"/>
436 <char id="c5" states="states3"/>
437 <char id="c6" states="states3"/>
438 <char id="c7" states="states3"/>
439 <char id="c8" states="states3"/>
440 <char id="c9" states="states3"/>
441 <char id="c10" states="states3"/>
442 <char id="c11" states="states3"/>
443 <char id="c12" states="states3"/>
444 <char id="c13" states="states3"/>
445 <char id="c14" states="states3"/>
446 <char id="c15" states="states3"/>
447 <char id="c16" states="states3"/>
448 <char id="c17" states="states3"/>
449 <char id="c18" states="states3"/>
450 <char id="c19" states="states3"/>
451 <char id="c20" states="states3"/>
452 </format>
453 <matrix>
454 <row otu="t1" id="r1">
455 <seq>ACGCUCGCAUCGCAUC</seq>
456 </row>
457 <row otu="t2" id="r2">
458 <seq>ACGCUCGCAUCGCAUC</seq>
459 </row>
460 <row otu="t3" id="r3">
461 <seq>ACGCUCGCAUCGCAUC</seq>
462 </row>
463 </matrix>
464 </characters>
465 <!--
466 A more compact example of encoding of continuous characters as raw sequences.
467 -->
468 <characters otus="taxa1" id="c5" xsi:type="nex:ContinuousSeqs" label="Continuous sequences">
469 <format>
470 <char id="c1"/>
471 <char id="c2"/>
472 <char id="c3"/>
473 <char id="c4"/>
474 <char id="c5"/>
475 </format>
476 <matrix>
477 <row id="r1" otu="t1">
478 <seq>-1.545414144070023 -2.3905621575431044 -2.9610221833467265 0.7868662069161243 0.22968509237534918</seq>
479 </row>
480 <row id="r2" otu="t2">
481 <seq>-1.6259836379710066 3.649352410850134 1.778885099660406 -1.2580877968480846 0.22335354995610862</seq>
482 </row>
483 <row id="r3" otu="t3">
484 <seq>-1.5798979984134964 2.9548251411133157 1.522005675256233 -0.8642016921755289 -0.938129801832388</seq>
485 </row>
486 <row id="r4" otu="t4">
487 <seq>2.7436692306788086 -0.7151148143399818 4.592207937774776 -0.6898841440534845 0.5769509574453064</seq>
488 </row>
489 <row id="r5" otu="t5">
490 <seq>3.1060827493657683 -1.0453787389160105 2.67416332763427 -1.4045634106692808 0.019890469925520196</seq>
491 </row>
492 </matrix>
493 </characters>
494 <!--
495 A more compact example of encoding of standard data. Note that the symbols used here
496 are integers (also above 9) and so characters must be space-separated. The symbols used
497 here are the same as the symbol attributes used in characters block m2, earlier.
498 -->
499 <characters otus="taxa1" id="c6" xsi:type="nex:StandardSeqs" label="Standard sequences">
500 <format>
501 <!--
502 The first elements inside a format element are stateset
503 definitions. In this example, there is a set of four
504 states, each tagged with an id. The symbol attribute is
505 a shorthand token.
506 -->
507 <states id="states1">
508 <state id="s1" symbol="1"/>
509 <state id="s2" symbol="2"/>
510 <state id="s3" symbol="3"/>
511 <polymorphic_state_set symbol="4" id="s4">
512 <member state="s1"/>
513 <member state="s2"/>
514 </polymorphic_state_set>
515 <uncertain_state_set symbol="5" id="s5">
516 <member state="s3"/>
517 <member state="s1"/>
518 </uncertain_state_set>
519 </states>
520 <!--
521 The matrix in this example contains two columns, both
522 referring to the same stateset - and so cells in both
523 columns can occupy one of four states.
524 -->
525 <char states="states1" id="c1"/>
526 <char states="states1" id="c2"/>
527 </format>
528 <matrix>
529 <row id="r1" otu="t1">
530 <seq>1 2</seq>
531 </row>
532 <row id="r2" otu="t2">
533 <seq>2 2</seq>
534 </row>
535 <row id="r3" otu="t3">
536 <seq>3 4</seq>
537 </row>
538 <row id="r4" otu="t4">
539 <seq>2 3</seq>
540 </row>
541 <row id="r5" otu="t5">
542 <seq>4 1</seq>
543 </row>
544 </matrix>
545 </characters>
546 </nex:nexml>