comparison metaphlan.xml @ 12:1a037928504c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/metaphlan/ commit 671a5fc6d4c02bd3eb830c1886a31ecffd134ceb
author iuc
date Sun, 11 Aug 2024 20:35:53 +0000
parents b6897977d13e
children ef65b083bd0c
comparison
equal deleted inserted replaced
11:b6897977d13e 12:1a037928504c
1 <tool id="metaphlan" name="MetaPhlAn" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> 1 <tool id="metaphlan" name="MetaPhlAn" version="@TOOL_VERSION@+galaxy1" profile="@PROFILE@">
2 <description>to profile the composition of microbial communities</description> 2 <description>to profile the composition of microbial communities</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 <xml name="tax_lev"> 5 <xml name="tax_lev">
6 <conditional name="tax_lev"> 6 <conditional name="tax_lev">
13 <option value="f">Families only</option> 13 <option value="f">Families only</option>
14 <option value="g">Genera only</option> 14 <option value="g">Genera only</option>
15 <option value="s">Species only</option> 15 <option value="s">Species only</option>
16 </param> 16 </param>
17 <when value="a"> 17 <when value="a">
18 <param name="split_levels" type='boolean' checked="false" truevalue='true' falsevalue='false' 18 <param name="split_levels" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Generate a report for each taxonomic level?" help="It will be in addition to the default output"/>
19 label="Generate a report for each taxonomic level?" help="It will be in addition to the default output"/>
20 </when> 19 </when>
21 <when value="k"/> 20 <when value="k"/>
22 <when value="p"/> 21 <when value="p"/>
23 <when value="c"/> 22 <when value="c"/>
24 <when value="o"/> 23 <when value="o"/>
259 </param> 258 </param>
260 <when value="single"> 259 <when value="single">
261 <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with microbiota reads"/> 260 <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with microbiota reads"/>
262 </when> 261 </when>
263 <when value="multiple"> 262 <when value="multiple">
264 <param name="in" type="data" format="@FILE_FORMATS@" multiple="true" label="Single-end Fasta/FastQ files with microbiota reads"/> 263 <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ files with microbiota reads" multiple="true"/>
265 </when> 264 </when>
266 <when value="paired_collection"> 265 <when value="paired_collection">
267 <param name="in" type="data_collection" format="@FILE_FORMATS@" label="Paired-end Fasta/FastQ file with microbiota reads"/> 266 <param name="in" type="data_collection" format="@FILE_FORMATS@" label="Paired-end Fasta/FastQ file with microbiota reads" collection_type="paired"/>
268 </when> 267 </when>
269 <when value="paired"> 268 <when value="paired">
270 <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with microbiota reads"/> 269 <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with microbiota reads"/>
271 <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with microbiota reads"/> 270 <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with microbiota reads"/>
272 </when> 271 </when>
284 </when> 283 </when>
285 <when value="sam"> 284 <when value="sam">
286 <param name="in" type="data" format="sam" label="Externally BowTie2-mapped SAM file" help="BowTie2 needs to be used first to map microbiota reads"/> 285 <param name="in" type="data" format="sam" label="Externally BowTie2-mapped SAM file" help="BowTie2 needs to be used first to map microbiota reads"/>
287 </when> 286 </when>
288 <when value="bowtie2out"> 287 <when value="bowtie2out">
289 <param name="in" type="data" format="tabular" label="Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run" 288 <param name="in" type="data" format="tabular" label="Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run" help="File needs to be generated with MetaPhlAn versions &gt;3.0"/>
290 help="File needs to be generated with MetaPhlAn versions >3.0"/>
291 </when> 289 </when>
292 </conditional> 290 </conditional>
293 <conditional name="db"> 291 <conditional name="db">
294 <param name="db_selector" type="select" label="Database with clade-specific marker genes"> 292 <param name="db_selector" type="select" label="Database with clade-specific marker genes">
295 <option value="cached" selected="true">Locally cached</option> 293 <option value="cached" selected="true">Locally cached</option>
315 <option value="rel_ab" selected="true">rel_ab: Profiling a microbiota in terms of relative abundances</option> 313 <option value="rel_ab" selected="true">rel_ab: Profiling a microbiota in terms of relative abundances</option>
316 <option value="rel_ab_w_read_stats">rel_ab_w_read_stats: Profiling a microbiota in terms of relative abundances and estimate the number of reads comming from each clade</option> 314 <option value="rel_ab_w_read_stats">rel_ab_w_read_stats: Profiling a microbiota in terms of relative abundances and estimate the number of reads comming from each clade</option>
317 <option value="reads_map">reads_map: Mapping from reads to clades (only reads hitting a marker)</option> 315 <option value="reads_map">reads_map: Mapping from reads to clades (only reads hitting a marker)</option>
318 <option value="clade_profiles">clade_profiles: Normalized marker counts for clades with at least a non-null marker</option> 316 <option value="clade_profiles">clade_profiles: Normalized marker counts for clades with at least a non-null marker</option>
319 <option value="clade_specific_strain_tracker">clade_specific_strain_tracker: List of markers present for a specific clade and all its subclades</option> 317 <option value="clade_specific_strain_tracker">clade_specific_strain_tracker: List of markers present for a specific clade and all its subclades</option>
320 <option value="marker_ab_table">marker_ab_table: Normalized marker counts (only when > 0.0 and normalized by microbiota size if number of reads is specified)</option> 318 <option value="marker_ab_table">marker_ab_table: Normalized marker counts (only when &gt; 0.0 and normalized by microbiota size if number of reads is specified)</option>
321 <option value="marker_counts">marker_counts: Non-normalized marker counts (use with extreme caution)</option> 319 <option value="marker_counts">marker_counts: Non-normalized marker counts (use with extreme caution)</option>
322 <option value="marker_pres_table">marker_pres_table: List of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th</option> 320 <option value="marker_pres_table">marker_pres_table: List of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th</option>
323 </param> 321 </param>
324 <when value="rel_ab"> 322 <when value="rel_ab">
325 <expand macro="tax_lev"/> 323 <expand macro="tax_lev"/>
328 <expand macro="tax_lev"/> 326 <expand macro="tax_lev"/>
329 </when> 327 </when>
330 <when value="reads_map"/> 328 <when value="reads_map"/>
331 <when value="clade_profiles"/> 329 <when value="clade_profiles"/>
332 <when value="clade_specific_strain_tracker"> 330 <when value="clade_specific_strain_tracker">
333 <param argument="--clade" type="text" value="" label="Clade for which to extract list of markers present" 331 <param argument="--clade" type="text" value="" label="Clade for which to extract list of markers present" help="Markers are also extracted for subclades"/>
334 help="Markers are also extracted for subclades" />
335 <param argument="--min_ab" type="float" optional="true" label="The minimum percentage abundance for the clade"/> 332 <param argument="--min_ab" type="float" optional="true" label="The minimum percentage abundance for the clade"/>
336 </when> 333 </when>
337 <when value="marker_ab_table"> 334 <when value="marker_ab_table">
338 <param argument="--nreads" type="integer" optional="true" label="Total number of reads in the original microbiota" 335 <param argument="--nreads" type="integer" optional="true" label="Total number of reads in the original microbiota" help="It is used for normalizing the length-normalized counts with the microbiota size as well. No normalization applied if the value is not specified"/>
339 help="It is used for normalizing the length-normalized counts with the microbiota size as well. No normalization applied if the value is not specified"/>
340 </when> 336 </when>
341 <when value="marker_counts"/> 337 <when value="marker_counts"/>
342 <when value="marker_pres_table"> 338 <when value="marker_pres_table">
343 <param argument="--pres_th" type="integer" optional="true" label="Threshold for calling a marker present"/> 339 <param argument="--pres_th" type="integer" optional="true" label="Threshold for calling a marker present"/>
344 </when> 340 </when>
345 </conditional> 341 </conditional>
346 <param argument="--min_cu_len" type="integer" value="2000" 342 <param argument="--min_cu_len" type="integer" value="2000" label="Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances"/>
347 label="Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances"/> 343 <param argument="--min_alignment_len" type="integer" optional="true" label="Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded."/>
348 <param argument="--min_alignment_len" type="integer" optional="true" 344 <param name="organism_profiling" type="select" optional="true" label="Organisms to profile" multiple="true">
349 label="Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded."/>
350 <param name="organism_profiling" type="select" multiple="true" optional="true" label="Organisms to profile">
351 <option value="add_viruses" selected="true">Profile viral organisms (add_viruses)</option> 345 <option value="add_viruses" selected="true">Profile viral organisms (add_viruses)</option>
352 <option value="ignore_eukaryotes">Ignore eukaryotic organisms (ignore_eukaryotes)</option> 346 <option value="ignore_eukaryotes">Ignore eukaryotic organisms (ignore_eukaryotes)</option>
353 <option value="ignore_bacteria">Ignore bacteria organisms (ignore_bacteria)</option> 347 <option value="ignore_bacteria">Ignore bacteria organisms (ignore_bacteria)</option>
354 <option value="ignore_archaea">Ignore archea organisms (ignore_archaea)</option> 348 <option value="ignore_archaea">Ignore archea organisms (ignore_archaea)</option>
355 </param> 349 </param>
363 <option value="med">med: Median of length-normalized marker counts</option> 357 <option value="med">med: Median of length-normalized marker counts</option>
364 </param> 358 </param>
365 <param argument="--stat_q" type="float" value="0.2" label="Quantile value for the robust average"/> 359 <param argument="--stat_q" type="float" value="0.2" label="Quantile value for the robust average"/>
366 <param argument="--perc_nonzero" type="float" value="0.33" label="Percentage of markers with a non zero relative abundance for misidentify a species"/> 360 <param argument="--perc_nonzero" type="float" value="0.33" label="Percentage of markers with a non zero relative abundance for misidentify a species"/>
367 <param argument="--ignore_markers" type="data" format="txt,tabular" optional="true" label="File containing a list of markers to ignore" help="One marker per line"/> 361 <param argument="--ignore_markers" type="data" format="txt,tabular" optional="true" label="File containing a list of markers to ignore" help="One marker per line"/>
368 <param argument="--avoid_disqm" type='boolean' checked="true" truevalue='--avoid_disqm' falsevalue='' 362 <param argument="--avoid_disqm" type="boolean" truevalue="--avoid_disqm" falsevalue="" checked="true" label="Deactivate the procedure of disambiguating the quasi-markers based on the marker abundance pattern found in the sample?" help="It is generally recommended to keep the disambiguation procedure in order to minimize false positives"/>
369 label="Deactivate the procedure of disambiguating the quasi-markers based on the marker abundance pattern found in the sample?"
370 help="It is generally recommended to keep the disambiguation procedure in order to minimize false positives"/>
371 </section> 363 </section>
372 <conditional name="subsample"> 364 <conditional name="subsample">
373 <param name="selector" type="select" label="Subsample" help="Subsampling only works for fastq input"> 365 <param name="selector" type="select" label="Subsample" help="Subsampling only works for fastq input">
374 <option value="no">No</option> 366 <option value="no">No</option>
375 <option value="single">Yes: specify number of reads</option> 367 <option value="single">Yes: specify number of reads</option>
376 <option value="paired">Yes: specify number of paired reads</option> 368 <option value="paired">Yes: specify number of paired reads</option>
377 </param> 369 </param>
378 <when value="no"/> 370 <when value="no"/>
379 <when value="single"> 371 <when value="single">
380 <param argument="--subsampling" type="integer" value="" min="1" label="Sumbsample reads" help="Specify the number of reads to be considered"/> 372 <param argument="--subsampling" type="integer" min="1" value="" label="Sumbsample reads" help="Specify the number of reads to be considered"/>
381 <expand macro="subsample_common"/> 373 <expand macro="subsample_common"/>
382 </when> 374 </when>
383 <when value="paired"> 375 <when value="paired">
384 <param argument="--subsampling_paired" type="integer" value="" min="1" label="Sumbsample reads" help="Specify the number of paired reads to be considered. For N there will be floor(N/2) reads selected from the forward and reverse reads each."/> 376 <param argument="--subsampling_paired" type="integer" min="1" value="" label="Sumbsample reads" help="Specify the number of paired reads to be considered. For N there will be floor(N/2) reads selected from the forward and reverse reads each."/>
385 <expand macro="subsample_common"/> 377 <expand macro="subsample_common"/>
386 </when> 378 </when>
387 </conditional> 379 </conditional>
388 <conditional name="viral_analysis"> 380 <conditional name="viral_analysis">
389 <param argument="--profile_vsc" type="select" label="Profile Viruses with VSCs approach"> 381 <param argument="--profile_vsc" type="select" label="Profile Viruses with VSCs approach">
396 <when value=""/> 388 <when value=""/>
397 </conditional> 389 </conditional>
398 <section name="out" title="Outputs" expanded="true"> 390 <section name="out" title="Outputs" expanded="true">
399 <param argument="--sample_id_key" type="text" value="SampleID" label="Sample ID key for this analysis"/> 391 <param argument="--sample_id_key" type="text" value="SampleID" label="Sample ID key for this analysis"/>
400 <param argument="--sample_id" type="text" value="Metaphlan_Analysis" label="Sample ID for this analysis"/> 392 <param argument="--sample_id" type="text" value="Metaphlan_Analysis" label="Sample ID for this analysis"/>
401 <param argument="--use_group_representative" type='boolean' checked="false" truevalue='--use_group_representative' falsevalue='' 393 <param argument="--use_group_representative" type="boolean" truevalue="--use_group_representative" falsevalue="" checked="false" label="Use a species as representative for species groups?"/>
402 label="Use a species as representative for species groups?"/> 394 <param argument="--legacy-output" type="boolean" truevalue="--legacy-output" falsevalue="" checked="false" label="Old MetaPhlAn2 two columns output?"/>
403 <param argument="--legacy-output" type='boolean' checked="false" truevalue='--legacy-output' falsevalue='' 395 <param argument="--CAMI_format_output" type="boolean" truevalue="--CAMI_format_output" falsevalue="" checked="false" label="Report the profiling using the CAMI output format?"/>
404 label="Old MetaPhlAn2 two columns output?"/> 396 <param argument="--unclassified_estimation" type="boolean" truevalue="--unclassified_estimation" falsevalue="" checked="false" label="Scale relative abundances to the number of reads mapping to known clades in order to estimate unknowness?"/>
405 <param argument="--CAMI_format_output" type='boolean' checked="false" truevalue='--CAMI_format_output' falsevalue='' 397 <param name="krona_output" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Output for Krona?"/>
406 label="Report the profiling using the CAMI output format?"/>
407 <param argument="--unclassified_estimation" type='boolean' checked="false" truevalue='--unclassified_estimation' falsevalue=''
408 label="Scale relative abundances to the number of reads mapping to known clades in order to estimate unknowness?"/>
409 <param name="krona_output" type='boolean' checked="false" truevalue='true' falsevalue='false' label="Output for Krona?"/>
410 </section> 398 </section>
411 <!-- enabling this in tests will allow metaphlan to download reference data (we do this only with the smallish TOY DB) --> 399 <!-- enabling this in tests will allow metaphlan to download reference data (we do this only with the smallish TOY DB) -->
412 <param name="test" type="hidden" value="false"/> 400 <param name="test" type="hidden" value="false"/>
413 </inputs> 401 </inputs>
414 <outputs> 402 <outputs>
415 <data name="output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances" /> 403 <data name="output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances"/>
416 <data name="bowtie2out" format="tabular" label="${tool.name} on ${on_string}: Bowtie2 output"> 404 <data name="bowtie2out" format="tabular" label="${tool.name} on ${on_string}: Bowtie2 output">
417 <filter>inputs['in']['selector'] == "raw"</filter> 405 <filter>inputs['in']['selector'] == "raw"</filter>
418 </data> 406 </data>
419 <data name="sam_output_file" format="sam" label="${tool.name} on ${on_string}: SAM file"> 407 <data name="sam_output_file" format="sam" label="${tool.name} on ${on_string}: SAM file">
420 <filter>inputs['in']['selector'] == "raw"</filter> 408 <filter>inputs['in']['selector'] == "raw"</filter>
421 </data> 409 </data>
422 <data name="biom_output_file" format="biom1" label="${tool.name} on ${on_string}: BIOM file" /> 410 <data name="biom_output_file" format="biom1" label="${tool.name} on ${on_string}: BIOM file"/>
423 <collection name="levels" type="list" label="${tool.name} on ${on_string}: Predicted taxon relative abundances at each taxonomic levels" > 411 <collection name="levels" type="list" label="${tool.name} on ${on_string}: Predicted taxon relative abundances at each taxonomic levels">
424 <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="split_levels/" format="tabular"/> 412 <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="split_levels/" format="tabular"/>
425 <filter>analysis['analysis_type']['t'] in ['rel_ab', 'rel_ab_w_read_stats'] and analysis['analysis_type']['tax_lev']['tax_lev'] == "a" and analysis['analysis_type']['tax_lev']['split_levels']</filter> 413 <filter>analysis['analysis_type']['t'] in ['rel_ab', 'rel_ab_w_read_stats'] and analysis['analysis_type']['tax_lev']['tax_lev'] == "a" and analysis['analysis_type']['tax_lev']['split_levels']</filter>
426 </collection> 414 </collection>
427 <data name="krona_output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances for Krona"> 415 <data name="krona_output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances for Krona">
428 <filter>out['krona_output']</filter> 416 <filter>out['krona_output']</filter>
652 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size"> 640 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
653 <assert_contents> 641 <assert_contents>
654 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/> 642 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
655 </assert_contents> 643 </assert_contents>
656 </output> 644 </output>
657 <output_collection name="levels" type="list" > 645 <output_collection name="levels" type="list">
658 <element name="all" ftype="tabular"> 646 <element name="all" ftype="tabular">
659 <assert_contents> 647 <assert_contents>
660 <has_text text="Gammaproteobacteria"/> 648 <has_text text="Gammaproteobacteria"/>
661 <has_text text="Corynebacterium accolens"/> 649 <has_text text="Corynebacterium accolens"/>
662 <has_n_columns n="17"/> 650 <has_n_columns n="17"/>
894 <assert_contents> 882 <assert_contents>
895 <has_line_matching expression="^@.*" n="10128"/> 883 <has_line_matching expression="^@.*" n="10128"/>
896 </assert_contents> 884 </assert_contents>
897 </element> 885 </element>
898 </output_collection> 886 </output_collection>
899
900 <assert_stderr> 887 <assert_stderr>
901 <has_text text="Downloading" negate="true"/> 888 <has_text text="Downloading" negate="true"/>
902 </assert_stderr> 889 </assert_stderr>
903 </test> 890 </test>
904 <!-- Paired GZ file as collection, Cached db (note sumsample_paired and the included forward and reverse reads are counted separatelym because they are all statically defined) --> 891 <!-- Paired GZ file as collection, Cached db (note sumsample_paired and the included forward and reverse reads are counted separatelym because they are all statically defined) -->
990 <assert_contents> 977 <assert_contents>
991 <has_line_matching expression="^@.*" n="10128"/> 978 <has_line_matching expression="^@.*" n="10128"/>
992 </assert_contents> 979 </assert_contents>
993 </element> 980 </element>
994 </output_collection> 981 </output_collection>
995
996 <assert_stderr> 982 <assert_stderr>
997 <has_text text="Downloading" negate="true"/> 983 <has_text text="Downloading" negate="true"/>
998 </assert_stderr> 984 </assert_stderr>
999 </test> 985 </test>
1000 <!-- SAM, cached DB --> 986 <!-- SAM, cached DB -->
1177 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size"> 1163 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
1178 <assert_contents> 1164 <assert_contents>
1179 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/> 1165 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
1180 </assert_contents> 1166 </assert_contents>
1181 </output> 1167 </output>
1182 <output_collection name="levels" type="list" > 1168 <output_collection name="levels" type="list">
1183 <element name="all" ftype="tabular"> 1169 <element name="all" ftype="tabular">
1184 <assert_contents> 1170 <assert_contents>
1185 <has_text text="Gammaproteobacteria"/> 1171 <has_text text="Gammaproteobacteria"/>
1186 <has_text text="Corynebacterium accolens"/> 1172 <has_text text="Corynebacterium accolens"/>
1187 <has_n_columns n="9"/> 1173 <has_n_columns n="9"/>
1307 <has_text text="--profile_vsc"/> 1293 <has_text text="--profile_vsc"/>
1308 <has_text text="--vsc_breadth 0.75"/> 1294 <has_text text="--vsc_breadth 0.75"/>
1309 <has_text text="--vsc_out"/> 1295 <has_text text="--vsc_out"/>
1310 </assert_command> 1296 </assert_command>
1311 <assert_stderr> 1297 <assert_stderr>
1312 <has_text text="Downloading"/> <!-- due to test=true and the absence of the TOY reference DB Metaphlan will download to ~10MB--> 1298 <has_text text="Downloading"/>
1299 <!-- due to test=true and the absence of the TOY reference DB Metaphlan will download to ~10MB-->
1313 <has_text text="No reads aligning to VSC markers"/> 1300 <has_text text="No reads aligning to VSC markers"/>
1314 </assert_stderr> 1301 </assert_stderr>
1315 </test> 1302 </test>
1316 </tests> 1303 </tests>
1317 <help><![CDATA[ 1304 <help><![CDATA[