Mercurial > repos > iuc > semibin

comparison semibin.xml @ 3:8673617e7e09 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/semibin commit 2c08a2e49a2844efe92340c5a9e9c8323e4a33d6
author iuc
date Tue, 28 Oct 2025 08:15:27 +0000
parents 9de6b5e570df
children
comparison
equal deleted inserted replaced
2:9de6b5e570df 3:8673617e7e09
8 <expand macro="biotools"/> 8 <expand macro="biotools"/>
9 <expand macro="requirements"/> 9 <expand macro="requirements"/>
10 <expand macro="version"/> 10 <expand macro="version"/>
11 <command detect_errors="exit_code"><![CDATA[ 11 <command detect_errors="exit_code"><![CDATA[
12 #import re 12 #import re
13 @BAM_FILES@ 13 #if $mode.select != "single":
14 #if $mode.align_select.align_select == "bam":
15 @BAM_FILES@
16 #else:
17 @STROBEALIGN_FILES@
18 #end if
19 #else:
20 @BAM_FILES@
21 #end if
14 @FASTA_FILES@ 22 @FASTA_FILES@
15 SemiBin2 23 SemiBin2
16 #if $mode.select == 'single' or $mode.select == 'co' 24 #if $mode.select == 'single' or $mode.select == 'co'
17 single_easy_bin 25 single_easy_bin
18 #if $mode.select == 'single' and str($mode.environment) != '' 26 #if $mode.select == 'single' and str($mode.environment) != ''
35 #for $e in $mode.ref.taxonomy_annotation_table 43 #for $e in $mode.ref.taxonomy_annotation_table
36 '$e' 44 '$e'
37 #end for 45 #end for
38 #end if 46 #end if
39 #end if 47 #end if
40 --input-fasta 'contigs.fasta' 48 --input-fasta 'contigs.$input_fasta.ext'
41 --input-bam *.bam 49 #if $mode.select == "single":
50 --input-bam *.bam
51 #else:
52 #if $mode.align_select.align_select == "bam":
53 --input-bam *.bam
54 #else:
55 -a *.txt
56 #end if
57 #end if
42 --output 'output' 58 --output 'output'
43 --cannot-name 'cannot' 59 --cannot-name 'cannot'
44 @MIN_LEN@ 60 @MIN_LEN@
45 --orf-finder '$orf_finder' 61 --orf-finder '$orf_finder'
46 --random-seed $random_seed 62 --random-seed $random_seed
66 <inputs> 82 <inputs>
67 <conditional name="mode"> 83 <conditional name="mode">
68 <expand macro="mode_select"/> 84 <expand macro="mode_select"/>
69 <when value="single"> 85 <when value="single">
70 <expand macro="input-fasta-single"/> 86 <expand macro="input-fasta-single"/>
71 <expand macro="input-bam-single"/> 87 <expand macro="input-bam-single"/>
72 <expand macro="ref-single"/> 88 <expand macro="ref-single"/>
73 <expand macro="environment"/> 89 <expand macro="environment"/>
74 </when> 90 </when>
75 <when value="co"> 91 <when value="co">
76 <expand macro="input-fasta-single"/> 92 <expand macro="input-fasta-single"/>
77 <expand macro="input-bam-multi"/> 93 <conditional name="align_select">
94 <expand macro="bam_or_strobealign"/>
95 <when value="bam">
96 <expand macro="input-bam-multi"/>
97 </when>
98 <when value="txt">
99 <expand macro="input-txt"/>
100 </when>
101 </conditional>
78 <expand macro="ref-single"/> 102 <expand macro="ref-single"/>
79 </when> 103 </when>
80 <when value="multi"> 104 <when value="multi">
81 <expand macro="input-fasta-multi"/> 105 <expand macro="input-fasta-multi"/>
82 <expand macro="input-bam-multi"/> 106 <conditional name="align_select">
107 <expand macro="bam_or_strobealign"/>
108 <when value="bam">
109 <expand macro="input-bam-multi"/>
110 </when>
111 <when value="txt">
112 <expand macro="input-txt"/>
113 </when>
114 </conditional>
83 <expand macro="ref-multi"/> 115 <expand macro="ref-multi"/>
84 </when> 116 </when>
85 </conditional> 117 </conditional>
86 <expand macro="min_len"/> 118 <expand macro="min_len"/>
87 <expand macro="orf-finder"/> 119 <expand macro="orf-finder"/>
105 <option value="pre_reclustering_bins">Pre-reclustering bins (only single sample and co-assembly)</option> 137 <option value="pre_reclustering_bins">Pre-reclustering bins (only single sample and co-assembly)</option>
106 </param> 138 </param>
107 </inputs> 139 </inputs>
108 <outputs> 140 <outputs>
109 <collection name="output_pre_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering"> 141 <collection name="output_pre_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering">
110 <filter>mode["select"]!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter> 142 <filter>mode['select']!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter>
111 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_prerecluster_bins"/> 143 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_prerecluster_bins"/>
112 </collection> 144 </collection>
113 <collection name="output_after_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins after reclustering"> 145 <collection name="output_after_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins after reclustering">
114 <filter>mode["select"]!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter> 146 <filter>mode['select']!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter>
115 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_recluster_bins"/> 147 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_recluster_bins"/>
116 </collection> 148 </collection>
117 <collection name="output_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins"> 149 <collection name="output_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins">
118 <filter>mode["select"]!="multi" and not "pre_reclustering_bins" in extra_output</filter> 150 <filter>mode['select']!="multi" and not "pre_reclustering_bins" in extra_output</filter>
119 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins"/> 151 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins"/>
120 </collection> 152 </collection>
121 <collection name="multi_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering (multi_bins)"> 153 <collection name="multi_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering (multi_bins)">
122 <filter>mode["select"]=="multi"</filter> 154 <filter>mode['select']=="multi"</filter>
123 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/bins"/> 155 <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/bins"/>
124 </collection> 156 </collection>
125 <data name="single_data" format="csv" from_work_dir="output/data.csv" label="${tool.name} on ${on_string}: Training data"> 157 <data name="single_data" format="csv" from_work_dir="output/data.csv" label="${tool.name} on ${on_string}: Training data">
126 <filter>(mode["select"]=="single" or mode["select"]=="co") and extra_output and "data" in extra_output</filter> 158 <filter>(mode['select']=="single" or mode['select']=="co") and extra_output and "data" in extra_output</filter>
127 </data> 159 </data>
128 <data name="single_data_split" format="csv" from_work_dir="output/data_split.csv" label="${tool.name} on ${on_string}: Split training data"> 160 <data name="single_data_split" format="csv" from_work_dir="output/data_split.csv" label="${tool.name} on ${on_string}: Split training data">
129 <filter>(mode["select"]=="single" or mode["select"]=="co") and extra_output and "data" in extra_output</filter> 161 <filter>(mode['select']=="single" or mode['select']=="co") and extra_output and "data" in extra_output</filter>
130 </data> 162 </data>
131 <collection name="multi_data" type="list" label="${tool.name} on ${on_string}: Training data per sample"> 163 <collection name="multi_data" type="list" label="${tool.name} on ${on_string}: Training data per sample">
132 <filter>mode["select"]=="multi" and extra_output and "data" in extra_output</filter> 164 <filter>mode['select']=="multi" and extra_output and "data" in extra_output</filter>
133 <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/> 165 <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
134 </collection> 166 </collection>
135 <collection name="multi_data_split" type="list" label="${tool.name} on ${on_string}: Split training data per sample"> 167 <collection name="multi_data_split" type="list" label="${tool.name} on ${on_string}: Split training data per sample">
136 <filter>mode["select"]=="multi" and extra_output and "data" in extra_output</filter> 168 <filter>mode['select']=="multi" and extra_output and "data" in extra_output</filter>
137 <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/> 169 <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
138 </collection> 170 </collection>
139 <expand macro="generate_sequence_features_extra_outputs"/> 171 <expand macro="generate_sequence_features_extra_outputs_main"/>
140 </outputs> 172 </outputs>
141 <tests> 173 <tests>
142 <test expect_num_outputs="5"> 174 <test expect_num_outputs="5">
143 <conditional name="mode"> 175 <conditional name="mode">
144 <param name="select" value="single"/> 176 <param name="select" value="single"/>
145 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/> 177 <param name="input_fasta" ftype="fasta.gz" value="input_single.fasta.gz"/>
146 <param name="input_bam" ftype="bam" value="input_single.bam"/> 178 <param name="input_bam" ftype="bam" value="input_single.bam"/>
147 <conditional name="ref"> 179 <conditional name="ref">
148 <param name="select" value="taxonomy"/> 180 <param name="select" value="taxonomy"/>
149 <param name="taxonomy_annotation_table" value="taxonomy.tsv"/> 181 <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
150 </conditional> 182 </conditional>
164 <param name="max_node" value="1"/> 196 <param name="max_node" value="1"/>
165 <param name="max_edges" value="200"/> 197 <param name="max_edges" value="200"/>
166 <param name="minfasta_kbs" value="200"/> 198 <param name="minfasta_kbs" value="200"/>
167 </section> 199 </section>
168 <param name="extra_output" value="data,coverage,contigs"/> 200 <param name="extra_output" value="data,coverage,contigs"/>
169 <output_collection name="output_bins" count="0"/>
170 <output name="single_data" ftype="csv"> 201 <output name="single_data" ftype="csv">
171 <assert_contents> 202 <assert_contents>
172 <has_text text="g1k_0"/> 203 <has_text text="g1k_0"/>
173 <has_text text="g4k_7"/> 204 <has_text text="g4k_7"/>
174 </assert_contents> 205 </assert_contents>
192 </output> 223 </output>
193 </test> 224 </test>
194 <test expect_num_outputs="5"> 225 <test expect_num_outputs="5">
195 <conditional name="mode"> 226 <conditional name="mode">
196 <param name="select" value="single"/> 227 <param name="select" value="single"/>
197 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/> 228 <param name="input_fasta" ftype="fasta.bz2" value="input_single.fasta.bz2"/>
198 <param name="input_bam" ftype="bam" value="input_single.bam"/> 229 <param name="input_bam" ftype="bam" value="input_single.bam"/>
199 <conditional name="ref"> 230 <conditional name="ref">
200 <param name="select" value="ml"/> 231 <param name="select" value="ml"/>
201 </conditional> 232 </conditional>
202 <param name="environment" value="human_gut"/> 233 <param name="environment" value="human_gut"/>
215 <param name="max_node" value="1"/> 246 <param name="max_node" value="1"/>
216 <param name="max_edges" value="200"/> 247 <param name="max_edges" value="200"/>
217 <param name="minfasta_kbs" value="200"/> 248 <param name="minfasta_kbs" value="200"/>
218 </section> 249 </section>
219 <param name="extra_output" value="data,coverage,contigs"/> 250 <param name="extra_output" value="data,coverage,contigs"/>
220 <output_collection name="output_bins" count="0"/>
221 <output name="single_data" ftype="csv"> 251 <output name="single_data" ftype="csv">
222 <assert_contents> 252 <assert_contents>
223 <has_text text="g1k_0"/> 253 <has_text text="g1k_0"/>
224 <has_text text="g4k_7"/> 254 <has_text text="g4k_7"/>
225 </assert_contents> 255 </assert_contents>
244 </test> 274 </test>
245 <test expect_num_outputs="3"> 275 <test expect_num_outputs="3">
246 <conditional name="mode"> 276 <conditional name="mode">
247 <param name="select" value="co"/> 277 <param name="select" value="co"/>
248 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/> 278 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
249 <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/> 279 <conditional name="align_select">
280 <param name="align_select" value="bam"/>
281 <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
282 </conditional>
250 <conditional name="ref"> 283 <conditional name="ref">
251 <param name="select" value="ml"/> 284 <param name="select" value="ml"/>
252 </conditional> 285 </conditional>
253 </conditional> 286 </conditional>
254 <conditional name="min_len"> 287 <conditional name="min_len">
265 <param name="max_node" value="1"/> 298 <param name="max_node" value="1"/>
266 <param name="max_edges" value="200"/> 299 <param name="max_edges" value="200"/>
267 <param name="minfasta_kbs" value="200"/> 300 <param name="minfasta_kbs" value="200"/>
268 </section> 301 </section>
269 <param name="extra_output" value="coverage"/> 302 <param name="extra_output" value="coverage"/>
270 <output_collection name="output_bins" count="0"/> 303 <output_collection name="co_cov_bam" count="5">
271 <output_collection name="co_cov" count="5">
272 <element name="0" ftype="csv"> 304 <element name="0" ftype="csv">
273 <assert_contents> 305 <assert_contents>
274 <has_text text="g1k_0"/> 306 <has_text text="g1k_0"/>
275 <has_text text="g2k_7"/> 307 <has_text text="g2k_7"/>
276 </assert_contents> 308 </assert_contents>
286 <has_text text="g1k_0"/> 318 <has_text text="g1k_0"/>
287 <has_text text="g2k_7"/> 319 <has_text text="g2k_7"/>
288 </assert_contents> 320 </assert_contents>
289 </element> 321 </element>
290 </output_collection> 322 </output_collection>
291 <output_collection name="co_split_cov" count="5"> 323 <output_collection name="co_split_cov_bam" count="5">
292 <element name="0" ftype="csv"> 324 <element name="0" ftype="csv">
293 <assert_contents> 325 <assert_contents>
294 <has_text text="g1k_0_1"/> 326 <has_text text="g1k_0_1"/>
295 <has_text text="g2k_7_2"/> 327 <has_text text="g2k_7_2"/>
296 </assert_contents> 328 </assert_contents>
311 </test> 343 </test>
312 <test expect_num_outputs="3"> 344 <test expect_num_outputs="3">
313 <conditional name="mode"> 345 <conditional name="mode">
314 <param name="select" value="co"/> 346 <param name="select" value="co"/>
315 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/> 347 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
316 <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/> 348 <conditional name="align_select">
349 <param name="align_select" value="bam"/>
350 <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
351 </conditional>
317 <conditional name="ref"> 352 <conditional name="ref">
318 <param name="select" value="taxonomy"/> 353 <param name="select" value="taxonomy"/>
319 <param name="taxonomy_annotation_table" value="taxonomy.tsv"/> 354 <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
320 </conditional> 355 </conditional>
321 </conditional> 356 </conditional>
333 <param name="max_node" value="1"/> 368 <param name="max_node" value="1"/>
334 <param name="max_edges" value="200"/> 369 <param name="max_edges" value="200"/>
335 <param name="minfasta_kbs" value="200"/> 370 <param name="minfasta_kbs" value="200"/>
336 </section> 371 </section>
337 <param name="extra_output" value="coverage"/> 372 <param name="extra_output" value="coverage"/>
338 <output_collection name="output_bins" count="0"/> 373 <output_collection name="co_cov_bam" count="5">
339 <output_collection name="co_cov" count="5">
340 <element name="0" ftype="csv"> 374 <element name="0" ftype="csv">
341 <assert_contents> 375 <assert_contents>
342 <has_text text="g1k_0"/> 376 <has_text text="g1k_0"/>
343 <has_text text="g2k_7"/> 377 <has_text text="g2k_7"/>
344 </assert_contents> 378 </assert_contents>
354 <has_text text="g1k_0"/> 388 <has_text text="g1k_0"/>
355 <has_text text="g2k_7"/> 389 <has_text text="g2k_7"/>
356 </assert_contents> 390 </assert_contents>
357 </element> 391 </element>
358 </output_collection> 392 </output_collection>
359 <output_collection name="co_split_cov" count="5"> 393 <output_collection name="co_split_cov_bam" count="5">
360 <element name="0" ftype="csv"> 394 <element name="0" ftype="csv">
361 <assert_contents> 395 <assert_contents>
362 <has_text text="g1k_0_1"/> 396 <has_text text="g1k_0_1"/>
363 <has_text text="g2k_7_2"/> 397 <has_text text="g2k_7_2"/>
364 </assert_contents> 398 </assert_contents>
379 </test> 413 </test>
380 <test expect_num_outputs="3"> 414 <test expect_num_outputs="3">
381 <conditional name="mode"> 415 <conditional name="mode">
382 <param name="select" value="co"/> 416 <param name="select" value="co"/>
383 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/> 417 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
384 <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/> 418 <conditional name="align_select">
419 <param name="align_select" value="bam"/>
420 <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
421 </conditional>
385 <conditional name="ref"> 422 <conditional name="ref">
386 <param name="select" value="taxonomy"/> 423 <param name="select" value="taxonomy"/>
387 <param name="taxonomy_annotation_table" value="taxonomy.tsv"/> 424 <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
388 </conditional> 425 </conditional>
389 </conditional> 426 </conditional>
390 <conditional name="min_len"> 427 <conditional name="min_len">
391 <param name="method" value="ratio"/> 428 <param name="method" value="ratio"/>
392 <param name="ratio" value="0.05"/> 429 <param name="ratio" value="0.05"/>
393 </conditional> 430 </conditional>
394 <param name="orf_finder" value="fraggenescan"/> 431 <param name="orf_finder" value="fast-naive"/>
395 <param name="random_seed" value="0"/> 432 <param name="random_seed" value="0"/>
433 <section name="annot">
434 <param name="ml_threshold" value="0"/>
435 </section>
396 <section name="training"> 436 <section name="training">
397 <param name="epoches" value="20"/> 437 <param name="epoches" value="20"/>
398 <param name="batch_size" value="2048"/> 438 <param name="batch_size" value="2048"/>
399 </section> 439 </section>
400 <section name="bin"> 440 <section name="bin">
401 <param name="max_node" value="1"/> 441 <param name="max_node" value="1"/>
402 <param name="max_edges" value="200"/> 442 <param name="max_edges" value="200"/>
403 <param name="minfasta_kbs" value="200"/> 443 <param name="minfasta_kbs" value="200"/>
404 </section> 444 </section>
405 <param name="extra_output" value="coverage"/> 445 <param name="extra_output" value="coverage"/>
406 <output_collection name="output_bins" count="0"/> 446 <output_collection name="co_cov_bam" count="5">
407 <output_collection name="co_cov" count="5">
408 <element name="0" ftype="csv"> 447 <element name="0" ftype="csv">
409 <assert_contents> 448 <assert_contents>
410 <has_text text="g1k_0"/> 449 <has_text text="g1k_0"/>
411 <has_text text="g2k_7"/> 450 <has_text text="g2k_7"/>
412 </assert_contents> 451 </assert_contents>
422 <has_text text="g1k_0"/> 461 <has_text text="g1k_0"/>
423 <has_text text="g2k_7"/> 462 <has_text text="g2k_7"/>
424 </assert_contents> 463 </assert_contents>
425 </element> 464 </element>
426 </output_collection> 465 </output_collection>
427 <output_collection name="co_split_cov" count="5"> 466 <output_collection name="co_split_cov_bam" count="5">
428 <element name="0" ftype="csv"> 467 <element name="0" ftype="csv">
429 <assert_contents> 468 <assert_contents>
430 <has_text text="g1k_0_1"/> 469 <has_text text="g1k_0_1"/>
431 <has_text text="g2k_7_2"/> 470 <has_text text="g2k_7_2"/>
432 </assert_contents> 471 </assert_contents>
457 </conditional> 496 </conditional>
458 <conditional name="min_len"> 497 <conditional name="min_len">
459 <param name="method" value="ratio"/> 498 <param name="method" value="ratio"/>
460 <param name="ratio" value="0.05"/> 499 <param name="ratio" value="0.05"/>
461 </conditional> 500 </conditional>
462 <param name="orf_finder" value="fraggenescan"/> 501 <param name="orf_finder" value="fast-naive"/>
463 <param name="random_seed" value="0"/> 502 <param name="random_seed" value="0"/>
503 <section name="annot">
504 <param name="ml_threshold" value="0"/>
505 </section>
464 <section name="training"> 506 <section name="training">
465 <param name="epoches" value="20"/> 507 <param name="epoches" value="20"/>
466 <param name="batch_size" value="2048"/> 508 <param name="batch_size" value="2048"/>
467 </section> 509 </section>
468 <section name="bin"> 510 <section name="bin">
469 <param name="max_node" value="1"/> 511 <param name="max_node" value="1"/>
470 <param name="max_edges" value="200"/> 512 <param name="max_edges" value="200"/>
471 <param name="minfasta_kbs" value="200"/> 513 <param name="minfasta_kbs" value="200"/>
472 </section> 514 </section>
473 <output_collection name="output_bins" count="1">
474 <element name="SemiBin_30" ftype="fasta">
475 <assert_contents>
476 <has_text text=">g3k_0"/>
477 </assert_contents>
478 </element>
479 </output_collection>
480 </test> 515 </test>
481 <test expect_num_outputs="2"> 516 <test expect_num_outputs="2">
482 <conditional name="mode"> 517 <conditional name="mode">
483 <param name="select" value="single"/> 518 <param name="select" value="single"/>
484 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/> 519 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
490 </conditional> 525 </conditional>
491 <conditional name="min_len"> 526 <conditional name="min_len">
492 <param name="method" value="ratio"/> 527 <param name="method" value="ratio"/>
493 <param name="ratio" value="0.05"/> 528 <param name="ratio" value="0.05"/>
494 </conditional> 529 </conditional>
495 <param name="orf_finder" value="fraggenescan"/> 530 <param name="orf_finder" value="fast-naive"/>
496 <param name="random_seed" value="0"/> 531 <param name="random_seed" value="0"/>
532 <section name="annot">
533 <param name="ml_threshold" value="0"/>
534 </section>
497 <section name="training"> 535 <section name="training">
498 <param name="epoches" value="20"/> 536 <param name="epoches" value="20"/>
499 <param name="batch_size" value="2048"/> 537 <param name="batch_size" value="2048"/>
500 </section> 538 </section>
501 <section name="bin"> 539 <section name="bin">
502 <param name="max_node" value="1"/> 540 <param name="max_node" value="1"/>
503 <param name="max_edges" value="200"/> 541 <param name="max_edges" value="200"/>
504 <param name="minfasta_kbs" value="200"/> 542 <param name="minfasta_kbs" value="200"/>
505 </section> 543 </section>
506 <param name="extra_output" value="pre_reclustering_bins"/> 544 <param name="extra_output" value="pre_reclustering_bins"/>
507 <output_collection name="output_pre_recluster_bins" count="3"> 545 <output_collection name="output_pre_recluster_bins">
508 <element name="SemiBin_0" ftype="fasta"> 546 <element name="SemiBin_0" ftype="fasta">
509 <assert_contents> 547 <assert_contents>
510 <has_text text="g1k_0"/> 548 <has_text text="g1k_0"/>
511 </assert_contents> 549 </assert_contents>
512 </element> 550 </element>
534 <param name="select" value="multi"/> 572 <param name="select" value="multi"/>
535 <conditional name="multi_fasta"> 573 <conditional name="multi_fasta">
536 <param name="select" value="concatenated"/> 574 <param name="select" value="concatenated"/>
537 <param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/> 575 <param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/>
538 </conditional> 576 </conditional>
539 <param name="input_bam" ftype="bam" value="input_multi_sorted1.bam,input_multi_sorted2.bam,input_multi_sorted3.bam,input_multi_sorted4.bam,input_multi_sorted5.bam,input_multi_sorted6.bam,input_multi_sorted7.bam,input_multi_sorted8.bam,input_multi_sorted9.bam,input_multi_sorted10.bam"/> 577 <conditional name="align_select">
578 <param name="align_select" value="bam"/>
579 <param name="input_bam" ftype="bam" value="input_multi_sorted1.bam,input_multi_sorted2.bam,input_multi_sorted3.bam,input_multi_sorted4.bam,input_multi_sorted5.bam,input_multi_sorted6.bam,input_multi_sorted7.bam,input_multi_sorted8.bam,input_multi_sorted9.bam,input_multi_sorted10.bam"/>
580 </conditional>
540 <conditional name="ref"> 581 <conditional name="ref">
541 <param name="select" value="taxonomy"/> 582 <param name="select" value="taxonomy"/>
542 <param name="taxonomy_annotation_table" value="taxonomy.tsv,taxonomy_2.tsv,taxonomy_3.tsv,taxonomy_4.tsv,taxonomy_5.tsv,taxonomy_6.tsv,taxonomy_7.tsv,taxonomy_8.tsv,taxonomy_9.tsv,taxonomy_10.tsv"/> 583 <param name="taxonomy_annotation_table" value="taxonomy.tsv,taxonomy_2.tsv,taxonomy_3.tsv,taxonomy_4.tsv,taxonomy_5.tsv,taxonomy_6.tsv,taxonomy_7.tsv,taxonomy_8.tsv,taxonomy_9.tsv,taxonomy_10.tsv"/>
543 </conditional> 584 </conditional>
544 </conditional> 585 </conditional>
545 <conditional name="min_len"> 586 <conditional name="min_len">
546 <param name="method" value="ratio"/> 587 <param name="method" value="ratio"/>
547 <param name="ratio" value="0.05"/> 588 <param name="ratio" value="0.05"/>
548 </conditional> 589 </conditional>
549 <param name="orf_finder" value="fraggenescan"/> 590 <param name="orf_finder" value="fast-naive"/>
550 <param name="random_seed" value="0"/> 591 <param name="random_seed" value="0"/>
551 <section name="training"> 592 <section name="training">
552 <param name="epoches" value="20"/> 593 <param name="epoches" value="20"/>
553 <param name="batch_size" value="2048"/> 594 <param name="batch_size" value="2048"/>
554 </section> 595 </section>
571 <assert_contents> 612 <assert_contents>
572 <has_text text="g1k_0_1,"/> 613 <has_text text="g1k_0_1,"/>
573 </assert_contents> 614 </assert_contents>
574 </element> 615 </element>
575 </output_collection> 616 </output_collection>
576 <output_collection name="multi_cov" count="10"> 617 <output_collection name="multi_cov_bam" count="10">
577 <element name="8" ftype="csv"> 618 <element name="8" ftype="csv">
578 <assert_contents> 619 <assert_contents>
579 <has_text text="S1:g1k_5,"/> 620 <has_text text="S1:g1k_5,"/>
580 </assert_contents> 621 </assert_contents>
581 </element> 622 </element>
582 </output_collection> 623 </output_collection>
583 <output_collection name="multi_cov_sample" count="10"> 624 <output_collection name="multi_cov_sample_bam" count="10">
584 <element name="S8" ftype="csv"> 625 <element name="S8" ftype="csv">
585 <assert_contents> 626 <assert_contents>
586 <has_text text="g1k_3"/> 627 <has_text text="g1k_3"/>
587 </assert_contents> 628 </assert_contents>
588 </element> 629 </element>
589 </output_collection> 630 </output_collection>
590 <output_collection name="multi_split_cov" count="10"> 631 <output_collection name="multi_split_cov_bam" count="10">
591 <element name="8" ftype="csv"> 632 <element name="8" ftype="csv">
592 <assert_contents> 633 <assert_contents>
593 <has_text text="S1:g1k_5_1,0."/> 634 <has_text text="S1:g1k_5_1,0."/>
594 </assert_contents> 635 </assert_contents>
595 </element> 636 </element>
596 </output_collection> 637 </output_collection>
597 <output_collection name="multi_split_cov_sample" count="10"> 638 <output_collection name="multi_split_cov_sample_bam" count="10">
598 <element name="S8" ftype="csv"> 639 <element name="8" ftype="csv">
599 <assert_contents> 640 <assert_contents>
600 <has_text text="g1k_3_1"/> 641 <has_text text="g1k_3_1"/>
601 </assert_contents> 642 </assert_contents>
602 </element> 643 </element>
603 </output_collection> 644 </output_collection>
607 <has_text text=">g1k_0"/> 648 <has_text text=">g1k_0"/>
608 </assert_contents> 649 </assert_contents>
609 </element> 650 </element>
610 </output_collection> 651 </output_collection>
611 </test> 652 </test>
653 <test expect_num_outputs="6">
654 <conditional name="mode">
655 <param name="select" value="co"/>
656 <param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/>
657 <conditional name="align_select">
658 <param name="align_select" value="txt"/>
659 <param name="abundance" ftype="txt" value="strobealign_1.txt,strobealign_2.txt,strobealign_3.txt,strobealign_4.txt,strobealign_5.txt"/>
660 </conditional>
661 <conditional name="ref">
662 <param name="select" value="taxonomy"/>
663 <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
664 </conditional>
665 </conditional>
666 <conditional name="min_len">
667 <param name="method" value="ratio"/>
668 <param name="ratio" value="0.05"/>
669 </conditional>
670 <param name="orf_finder" value="fast-naive"/>
671 <param name="random_seed" value="0"/>
672 <section name="annot">
673 <param name="ml_threshold" value="0"/>
674 </section>
675 <section name="training">
676 <param name="epoches" value="20"/>
677 <param name="batch_size" value="2048"/>
678 </section>
679 <section name="bin">
680 <param name="max_node" value="0.15"/>
681 <param name="max_edges" value="20"/>
682 <param name="minfasta_kbs" value="20"/>
683 </section>
684 <param name="extra_output" value="data,coverage,contigs,pre_reclustering_bins"/>
685 </test>
686 <test expect_num_outputs="6">
687 <conditional name="mode">
688 <param name="select" value="multi"/>
689 <conditional name="multi_fasta">
690 <param name="select" value="concatenated"/>
691 <param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/>
692 </conditional>
693 <conditional name="align_select">
694 <param name="align_select" value="txt"/>
695 <param name="abundance" ftype="txt" value="strobealign_1.txt,strobealign_2.txt,strobealign_3.txt,strobealign_4.txt,strobealign_5.txt"/>
696 </conditional>
697 <conditional name="ref">
698 <param name="select" value="taxonomy"/>
699 <param name="taxonomy_annotation_table" value="taxonomy.tsv,taxonomy_2.tsv,taxonomy_3.tsv,taxonomy_4.tsv,taxonomy_5.tsv,taxonomy_6.tsv,taxonomy_7.tsv,taxonomy_8.tsv,taxonomy_9.tsv,taxonomy_10.tsv"/>
700 </conditional>
701 </conditional>
702 <conditional name="min_len">
703 <param name="method" value="ratio"/>
704 <param name="ratio" value="0.05"/>
705 </conditional>
706 <param name="orf_finder" value="fast-naive"/>
707 <param name="random_seed" value="0"/>
708 <section name="annot">
709 <param name="ml_threshold" value="0"/>
710 </section>
711 <section name="training">
712 <param name="epoches" value="20"/>
713 <param name="batch_size" value="2048"/>
714 </section>
715 <section name="bin">
716 <param name="max_node" value="0.15"/>
717 <param name="max_edges" value="30"/>
718 <param name="minfasta_kbs" value="30"/>
719 </section>
720 <param name="extra_output" value="data,coverage,contigs"/>
721 <output_collection name="multi_bins" count="10"/>
722 <output_collection name="multi_data" count="10">
723 <element name="S8" ftype="csv">
724 <assert_contents>
725 <has_text text="g1k_0,"/>
726 </assert_contents>
727 </element>
728 </output_collection>
729 <output_collection name="multi_data_split" count="10">
730 <element name="S8" ftype="csv">
731 <assert_contents>
732 <has_text text="g1k_0_1,"/>
733 </assert_contents>
734 </element>
735 </output_collection>
736 <output_collection name="multi_cov_txt" count="10">
737 <element name="S8" ftype="csv">
738 <assert_contents>
739 <has_text text="g1k_5,"/>
740 </assert_contents>
741 </element>
742 </output_collection>
743 <output_collection name="multi_split_cov_txt" count="10">
744 <element name="S8" ftype="csv">
745 <assert_contents>
746 <has_text text="g1k_5_1,1."/>
747 </assert_contents>
748 </element>
749 </output_collection>
750 <output_collection name="multi_contigs" count="10">
751 <element name="S8" ftype="fasta">
752 <assert_contents>
753 <has_text text=">g1k_0"/>
754 </assert_contents>
755 </element>
756 </output_collection>
757 </test>
612 </tests> 758 </tests>
613 <help><![CDATA[ 759 <help><![CDATA[
760 **Please note that there is a known issue with Semibin2 where results may be inconsistent across runs on different, despite a set seed. This may cause issues with reproducibility.**
761 For more information, see this [issue]{https://github.com/BigDataBiology/SemiBin/issues/186} on their repository: https://github.com/BigDataBiology/SemiBin/issues/186
762
614 @HELP_HEADER@ 763 @HELP_HEADER@
615 764
616 Inputs 765 Inputs
617 ====== 766 ======
618 767