Mercurial > repos > iuc > metaphlan

comparison metaphlan.xml @ 2:a92a632c4d9b draft

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/master/tools/metaphlan/ commit f1c6f4fe1e572ace84cf9106bc253603f55aac55"
author iuc
date Mon, 14 Jun 2021 12:48:10 +0000
parents b89b0765695d
children ff8f55893e7d
comparison
equal deleted inserted replaced
1:b89b0765695d 2:a92a632c4d9b
193 python '$__tool_directory__/formatoutput.py' 193 python '$__tool_directory__/formatoutput.py'
194 split_levels 194 split_levels
195 --metaphlan_output '$output_file' 195 --metaphlan_output '$output_file'
196 --outdir 'split_levels' 196 --outdir 'split_levels'
197 $out.legacy_output 197 $out.legacy_output
198 && 198
199 ls split_levels
200 #end if 199 #end if
201 200
202 #if $out.krona_output 201 #if $out.krona_output
203 && 202 &&
204 python '$__tool_directory__/formatoutput.py' 203 python '$__tool_directory__/formatoutput.py'
209 ]]></command> 208 ]]></command>
210 <inputs> 209 <inputs>
211 <section name="inputs" title="Inputs" expanded="true"> 210 <section name="inputs" title="Inputs" expanded="true">
212 <conditional name="in"> 211 <conditional name="in">
213 <param name="selector" type="select" label="Input(s)"> 212 <param name="selector" type="select" label="Input(s)">
214 <option value="raw" selected="true">Fasta/FastQ file(s) with metagenomic reads</option> 213 <option value="raw" selected="true">Fasta/FastQ file(s) with microbiota reads</option>
215 <option value="sam">Externally BowTie2-mapped SAM file</option> 214 <option value="sam">Externally BowTie2-mapped SAM file</option>
216 <option value="bowtie2out">Intermediary mapping file of the metagenome generated by a previous MetaPhlAn run</option> 215 <option value="bowtie2out">Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run</option>
217 </param> 216 </param>
218 <when value="raw"> 217 <when value="raw">
219 <conditional name="raw_in"> 218 <conditional name="raw_in">
220 <param name="selector" type="select" label="Fasta/FastQ file(s) with metagenomic reads"> 219 <param name="selector" type="select" label="Fasta/FastQ file(s) with microbiota reads">
221 <option value="single" selected="true">One single-end file</option> 220 <option value="single" selected="true">One single-end file</option>
222 <option value="multiple">Multiple single-end files</option> 221 <option value="multiple">Multiple single-end files</option>
223 <option value="paired">Paired-end files</option> 222 <option value="paired">Paired-end files</option>
224 </param> 223 </param>
225 <when value="single"> 224 <when value="single">
226 <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with metagenomic reads"/> 225 <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with microbiota reads"/>
227 </when> 226 </when>
228 <when value="multiple"> 227 <when value="multiple">
229 <param name="in" type="data" format="@FILE_FORMATS@" multiple="true" label="Single-end Fasta/FastQ files with metagenomic reads"/> 228 <param name="in" type="data" format="@FILE_FORMATS@" multiple="true" label="Single-end Fasta/FastQ files with microbiota reads"/>
230 </when> 229 </when>
231 <when value="paired"> 230 <when value="paired">
232 <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with metagenomic reads"/> 231 <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with microbiota reads"/>
233 <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with metagenomic reads"/> 232 <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with microbiota reads"/>
234 </when> 233 </when>
235 </conditional> 234 </conditional>
236 <param argument="--read_min_len" type="integer" value="70" label="Minimum length of the reads to be considered when parsing the input file"/> 235 <param argument="--read_min_len" type="integer" value="70" label="Minimum length of the reads to be considered when parsing the input file"/>
237 <section name="mapping" title="Mapping" expanded="true"> 236 <section name="mapping" title="Mapping" expanded="true">
238 <param argument="--bt2_ps" type="select" label="Presets options for BowTie2" help="Applied only with FASTA files"> 237 <param argument="--bt2_ps" type="select" label="Presets options for BowTie2" help="Applied only with FASTA files">
243 </param> 242 </param>
244 <param argument="--min_mapq_val" type="integer" value="5" label="Minimum mapping quality value (MAPQ)"/> 243 <param argument="--min_mapq_val" type="integer" value="5" label="Minimum mapping quality value (MAPQ)"/>
245 </section> 244 </section>
246 </when> 245 </when>
247 <when value="sam"> 246 <when value="sam">
248 <param name="in" type="data" format="sam" label="Externally BowTie2-mapped SAM file" help="BowTie2 needs to be used first to map metagenom reads"/> 247 <param name="in" type="data" format="sam" label="Externally BowTie2-mapped SAM file" help="BowTie2 needs to be used first to map microbiota reads"/>
249 </when> 248 </when>
250 <when value="bowtie2out"> 249 <when value="bowtie2out">
251 <param name="in" type="data" format="tabular" label="Intermediary mapping file of the metagenome generated by a previous MetaPhlAn run" 250 <param name="in" type="data" format="tabular" label="Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run"
252 help="File needs to be generated with MetaPhlAn versions >3.0"/> 251 help="File needs to be generated with MetaPhlAn versions >3.0"/>
253 </when> 252 </when>
254 </conditional> 253 </conditional>
255 <conditional name="db"> 254 <conditional name="db">
256 <param name="db_selector" type="select" label="Database with clade-specific marker genes"> 255 <param name="db_selector" type="select" label="Database with clade-specific marker genes">
271 </conditional> 270 </conditional>
272 </section> 271 </section>
273 <section name="analysis" title="Analysis" expanded="true"> 272 <section name="analysis" title="Analysis" expanded="true">
274 <conditional name="analysis_type"> 273 <conditional name="analysis_type">
275 <param argument="-t" type="select" label="Type of analysis to perform"> 274 <param argument="-t" type="select" label="Type of analysis to perform">
276 <option value="rel_ab" selected="true">rel_ab: Profiling a metagenomes in terms of relative abundances</option> 275 <option value="rel_ab" selected="true">rel_ab: Profiling a microbiota in terms of relative abundances</option>
277 <option value="rel_ab_w_read_stats">rel_ab_w_read_stats: Profiling a metagenomes in terms of relative abundances and estimate the number of reads comming from each clade</option> 276 <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>
278 <option value="reads_map">reads_map: Mapping from reads to clades (only reads hitting a marker)</option> 277 <option value="reads_map">reads_map: Mapping from reads to clades (only reads hitting a marker)</option>
279 <option value="clade_profiles">clade_profiles: Normalized marker counts for clades with at least a non-null marker</option> 278 <option value="clade_profiles">clade_profiles: Normalized marker counts for clades with at least a non-null marker</option>
280 <option value="clade_specific_strain_tracker">clade_specific_strain_tracker: List of markers present for a specific clade and all its subclades</option> 279 <option value="clade_specific_strain_tracker">clade_specific_strain_tracker: List of markers present for a specific clade and all its subclades</option>
281 <option value="marker_ab_table">marker_ab_table: Normalized marker counts (only when > 0.0 and normalized by metagenome size if number of reads is specified)</option> 280 <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>
282 <option value="marker_counts">marker_counts: Non-normalized marker counts (use with extreme caution)</option> 281 <option value="marker_counts">marker_counts: Non-normalized marker counts (use with extreme caution)</option>
283 <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> 282 <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>
284 </param> 283 </param>
285 <when value="rel_ab"> 284 <when value="rel_ab">
286 <expand macro="tax_lev"/> 285 <expand macro="tax_lev"/>
294 <param argument="--clade" type="text" value="" label="Clade for which to extract list of markers present" 293 <param argument="--clade" type="text" value="" label="Clade for which to extract list of markers present"
295 help="Markers are also extracted for subclades" /> 294 help="Markers are also extracted for subclades" />
296 <param argument="--min_ab" type="float" optional="true" label="The minimum percentage abundance for the clade"/> 295 <param argument="--min_ab" type="float" optional="true" label="The minimum percentage abundance for the clade"/>
297 </when> 296 </when>
298 <when value="marker_ab_table"> 297 <when value="marker_ab_table">
299 <param argument="--nreads" type="integer" optional="true" label="Total number of reads in the original metagenome" 298 <param argument="--nreads" type="integer" optional="true" label="Total number of reads in the original microbiota"
300 help="It is used for normalizing the length-normalized counts with the metagenome size as well. No normalization applied if the value is not specified"/> 299 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"/>
301 </when> 300 </when>
302 <when value="marker_counts"/> 301 <when value="marker_counts"/>
303 <when value="marker_pres_table"> 302 <when value="marker_pres_table">
304 <param argument="--pres_th" type="integer" optional="true" label="Threshold for calling a marker present"/> 303 <param argument="--pres_th" type="integer" optional="true" label="Threshold for calling a marker present"/>
305 </when> 304 </when>
367 <conditional name="in"> 366 <conditional name="in">
368 <param name="selector" value="raw"/> 367 <param name="selector" value="raw"/>
369 <conditional name="raw_in"> 368 <conditional name="raw_in">
370 <!-- Single GZ file --> 369 <!-- Single GZ file -->
371 <param name="selector" value="single"/> 370 <param name="selector" value="single"/>
371 <param name="in" value="no_taxon_input.fasta"/>
372 </conditional>
373 <param name="read_min_len" value="70"/>
374 <section name="mapping">
375 <param name="bt2_ps" value="sensitive"/>
376 <param name="min_mapq_val" value="5"/>
377 </section>
378 </conditional>
379 <conditional name="db">
380 <!-- Cached db -->
381 <param name="db_selector" value="cached"/>
382 <param name="cached_db" value="test-db-20210409"/>
383 </conditional>
384 </section>
385 <section name="analysis">
386 <conditional name="analysis_type">
387 <param name="t" value="rel_ab"/>
388 <conditional name="tax_lev">
389 <param name="tax_lev" value="a"/>
390 <param name="split_levels" value="true"/>
391 </conditional>
392 </conditional>
393 <param name="min_cu_len" value="2000"/>
394 <param name="organism_profiling" value="add_viruses"/>
395 <param name="stat" value="avg_g"/>
396 <param name="stat_q" value="0.2"/>
397 <param name="perc_nonzero" value="0.33"/>
398 <param name="avoid_disqm" value="true"/>
399 </section>
400 <section name="out">
401 <param name="sample_id_key" value="SampleID"/>
402 <param name="sample_id" value="Metaphlan_Analysis"/>
403 <param name="use_group_representative" value="false"/>
404 <param name="legacy_output" value="false"/>
405 <param name="CAMI_format_output" value="false"/>
406 <param name="unknown_estimation" value="false"/>
407 <param name="krona_output" value="true"/>
408 </section>
409 <output name="output_file" ftype="tabular">
410 <assert_contents>
411 <has_text text="UNKNOWN"/>
412 </assert_contents>
413 </output>
414 <output name="bowtie2out" ftype="tabular">
415 <assert_contents>
416 <not_has_text text="HWI-EAS109_102883399:3:104:7342:14360/1"/>
417 <has_n_lines n="2"/>
418 </assert_contents>
419 </output>
420 <output name="sam_output_file" ftype="sam">
421 <assert_contents>
422 <has_text text="SN:13076__A0A2I1PE66__CYJ72_10760"/>
423 </assert_contents>
424 </output>
425 <output name="biom_output_file" ftype="biom1">
426 <assert_contents>
427 <not_has_text text="k__Bacteria"/>
428 <not_has_text text="p__Actinobacteria"/>
429 </assert_contents>
430 </output>
431 <output_collection name="levels" type="list" >
432 <element name="all" ftype="tabular">
433 <assert_contents>
434 <has_text text="class"/>
435 <has_n_columns n="17"/>
436 <has_n_lines n="1"/>
437 </assert_contents>
438 </element>
439 <element name="kingdom" ftype="tabular">
440 <assert_contents>
441 <has_text text="kingdom_id"/>
442 <has_n_columns n="3"/>
443 <has_n_lines n="1"/>
444 </assert_contents>
445 </element>
446 <element name="phylum" ftype="tabular">
447 <assert_contents>
448 <has_text text="phylum_id"/>
449 <not_has_text text="kingdom_id"/>
450 <has_n_columns n="3"/>
451 <has_n_lines n="1"/>
452 </assert_contents>
453 </element>
454 <element name="class" ftype="tabular">
455 <assert_contents>
456 <has_text text="class_id"/>
457 <not_has_text text="phylum_id"/>
458 <has_n_columns n="3"/>
459 <has_n_lines n="1"/>
460 </assert_contents>
461 </element>
462 <element name="order" ftype="tabular">
463 <assert_contents>
464 <has_text text="order_id"/>
465 <not_has_text text="class_id"/>
466 <has_n_columns n="3"/>
467 <has_n_lines n="1"/>
468 </assert_contents>
469 </element>
470 <element name="family" ftype="tabular">
471 <assert_contents>
472 <has_text text="family_id"/>
473 <not_has_text text="order"/>
474 <has_n_columns n="3"/>
475 <has_n_lines n="1"/>
476 </assert_contents>
477 </element>
478 <element name="genus" ftype="tabular">
479 <assert_contents>
480 <has_text text="genus_id"/>
481 <not_has_text text="family"/>
482 <has_n_columns n="3"/>
483 <has_n_lines n="1"/>
484 </assert_contents>
485 </element>
486 <element name="species" ftype="tabular">
487 <assert_contents>
488 <has_text text="species_id"/>
489 <not_has_text text="genus"/>
490 <has_n_columns n="3"/>
491 <has_n_lines n="1"/>
492 </assert_contents>
493 </element>
494 <element name="strains" ftype="tabular">
495 <assert_contents>
496 <has_text text="strains_id"/>
497 <not_has_text text="species_id"/>
498 <has_n_columns n="3"/>
499 <has_n_lines n="1"/>
500 </assert_contents>
501 </element>
502 </output_collection>
503 <output name="krona_output_file" ftype="tabular">
504 <assert_contents>
505 <not_has_text text="k__Bacteria"/>
506 <has_n_lines n="0"/>
507 </assert_contents>
508 </output>
509 </test>
510 <test expect_num_outputs="6">
511 <section name="inputs">
512 <conditional name="in">
513 <param name="selector" value="raw"/>
514 <conditional name="raw_in">
515 <!-- Single GZ file -->
516 <param name="selector" value="single"/>
372 <param name="in" value="SRS014464-Anterior_nares.fasta.gz"/> 517 <param name="in" value="SRS014464-Anterior_nares.fasta.gz"/>
373 </conditional> 518 </conditional>
374 <param name="read_min_len" value="70"/> 519 <param name="read_min_len" value="70"/>
375 <section name="mapping"> 520 <section name="mapping">
376 <param name="bt2_ps" value="sensitive"/> 521 <param name="bt2_ps" value="sensitive"/>
914 - unambiguous taxonomic assignments; 1059 - unambiguous taxonomic assignments;
915 - accurate estimation of organismal relative abundance; 1060 - accurate estimation of organismal relative abundance;
916 - species-level resolution for bacteria, archaea, eukaryotes and viruses; 1061 - species-level resolution for bacteria, archaea, eukaryotes and viruses;
917 - strain identification and tracking 1062 - strain identification and tracking
918 - orders of magnitude speedups compared to existing methods. 1063 - orders of magnitude speedups compared to existing methods.
919 - metagenomic strain-level population genomics 1064 - microbiota strain-level population genomics
920 1065
921 MetaPhlAn clade-abundance estimation 1066 MetaPhlAn clade-abundance estimation
922 ------------------------------------ 1067 ------------------------------------
923 1068
924 The basic usage of MetaPhlAn consists in the identification of the clades (from phyla to species and 1069 The basic usage of MetaPhlAn consists in the identification of the clades (from phyla to species and
925 strains in particular cases) present in the metagenome obtained from a microbiome sample and their 1070 strains in particular cases) present in the microbiota obtained from a microbiome sample and their
926 relative abundance. 1071 relative abundance.
927 1072
928 Marker level analysis 1073 Marker level analysis
929 --------------------- 1074 ---------------------
930 1075
942 1087
943 Metaphlan takes as input either: 1088 Metaphlan takes as input either:
944 1089
945 - one or several sequence files in Fasta, FastQ (compressed or not) 1090 - one or several sequence files in Fasta, FastQ (compressed or not)
946 - a BowTie2 produced SAM file 1091 - a BowTie2 produced SAM file
947 - an intermediary mapping file of the metagenome generated by a previous MetaPhlAn run 1092 - an intermediary mapping file of the microbiota generated by a previous MetaPhlAn run
948 1093
949 It also need the reference database, which can be locally installed or customized using the dedicated tools. 1094 It also need the reference database, which can be locally installed or customized using the dedicated tools.
950 1095
951 Outputs 1096 Outputs
952 ======= 1097 =======