Mercurial > repos > thanhlv > metaphlan4

comparison metaphlan.xml @ 0:12e29dbb7041 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/quadram-institute-bioscience/galaxy-tools/tree/master/tools/metaphlan/
author thanhlv
date Mon, 13 Feb 2023 11:36:42 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:12e29dbb7041
1 <tool id="metaphlan4" name="MetaPhlAn4" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
2 <description>to profile the composition of microbial communities</description>
3 <macros>
4 <import>macros.xml</import>
5 <xml name="tax_lev">
6 <conditional name="tax_lev">
7 <param argument="--tax_lev" type="select" label="Taxonomic level for the relative abundance output">
8 <option value="a" selected="true">All taxonomic levels</option>
9 <option value="k">Kingdoms only</option>
10 <option value="p">Phyla only</option>
11 <option value="c">Classes only</option>
12 <option value="o">Orders only</option>
13 <option value="f">Families only</option>
14 <option value="g">Genera only</option>
15 <option value="s">Species only</option>
16 </param>
17 <when value="a">
18 <param name="split_levels" type='boolean' checked="false" truevalue='true' falsevalue='false'
19 label="Generate a report for each taxonomic level?" help="It will be in addition to the default output"/>
20 </when>
21 <when value="k"/>
22 <when value="p"/>
23 <when value="c"/>
24 <when value="o"/>
25 <when value="f"/>
26 <when value="g"/>
27 <when value="s"/>
28 </conditional>
29 </xml>
30 <token name="@FILE_FORMATS@">fastq,fastq.gz,fastq.bz2,fasta,fasta.gz,fasta.bz2</token>
31 </macros>
32 <expand macro="edam_ontology"/>
33 <expand macro="requirements"/>
34 <version_command>metaphlan -v</version_command>
35 <command detect_errors="aggressive"><![CDATA[
36 #if $inputs.in.selector == "raw"
37 #if $inputs.in.raw_in.selector == "single"
38 #set full_ext=$inputs.in.raw_in.in.datatype.file_ext
39 #if $full_ext.endswith("gz")
40 #set $file_path="in"
41 zcat '$inputs.in.raw_in.in' > '$file_path'
42 &&
43 #else if $full_ext.endswith("bz2")
44 #set $file_path="in"
45 bzcat '$inputs.in.raw_in.in' > '$file_path'
46 &&
47 #else
48 #set $file_path=$inputs.in.raw_in.in
49 #end if
50 #else if $inputs.in.raw_in.selector == "multiple"
51 #set full_ext=$inputs.in.raw_in.in[0].datatype.file_ext
52 #set file_path=""
53 #set sep=""
54 #for $i, $f in enumerate($inputs.in.raw_in.in)
55 #if $f.datatype.file_ext != $full_ext
56 echo "Different datatypes for input files"
57 &&
58 exit 1
59 #end if
60 #if $full_ext.endswith("gz")
61 #set fp="input_%s" % ($i)
62 zcat '$f' > '$fp'
63 &&
64 #else if $full_ext.endswith("bz2")
65 #set fp="input_%s" % ($i)
66 bzcat '$f' > '$fp'
67 &&
68 #else
69 #set fp=$f
70 #end if
71 #set $file_path+="%s%s" % ($sep, $fp)
72 #set $sep=","
73 #end for
74 #else if $inputs.in.raw_in.selector == "paired"
75 #set full_ext=$inputs.in.raw_in.in_f.datatype.file_ext
76 #if $full_ext != $inputs.in.raw_in.in_r.datatype.file_ext
77 echo "Different datatypes for input paired-end files"
78 &&
79 exit 1
80 #end if
81 #if $full_ext.endswith("gz")
82 zcat '$inputs.in.raw_in.in_f' > 'in_f'
83 &&
84 zcat '$inputs.in.raw_in.in_r' > 'in_r'
85 &&
86 #set file_path="in_f,in_r"
87 #else if $full_ext.endswith("bz2")
88 bzcat '$inputs.in.raw_in.in_f' > 'in_f'
89 &&
90 bzcat '$inputs.in.raw_in.in_r' > 'in_r'
91 &&
92 #set file_path="in_f,in_r"
93 #else
94 #set file_path="%s,%s" % ($inputs.in.raw_in.in_f,$inputs.in.raw_in.in_r)
95 #end if
96 #end if
97
98 #if $full_ext.startswith("fastq")
99 #set ext='fastq'
100 #else if $full_ext.startswith("fasta") and $full_ext.endswith(("gz","bz2"))
101 #set ext='fasta'
102 #else
103 #set ext=$full_ext
104 #end if
105 #end if
106
107 #if $inputs.db.db_selector == "history"
108 mkdir 'ref_db'
109 &&
110 bowtie2-build --large-index '$inputs.db.bowtie2db' 'ref_db/custom_db'
111 &&
112 python '$__tool_directory__/customizemetadata.py'
113 transform_json_to_pkl
114 --json '$inputs.db.mpa_pkl'
115 --pkl 'ref_db/custom_db.pkl'
116 &&
117 #end if
118
119 metaphlan
120 #if $inputs.in.selector == "raw"
121 '$file_path'
122 --input_type '$ext'
123 --read_min_len $inputs.in.read_min_len
124 --bt2_ps '$inputs.in.mapping.bt2_ps'
125 --min_mapq_val $inputs.in.mapping.min_mapq_val
126 #if $ext == "sam"
127 --nreads \$(cat '$file_path' | grep -c -v '^@')
128 #end if
129 #else
130 '$inputs.in.in'
131 --input_type '$inputs.in.selector'
132 #if $inputs.in.selector == "sam"
133 --nreads \$(cat '$inputs.in.in' | grep -c -v '^@')
134 #end if
135 #end if
136 #if $inputs.db.db_selector == "cached"
137 --bowtie2db '$inputs.db.cached_db.fields.path'
138 --index '$inputs.db.cached_db.fields.dbkey'
139 #else
140 --bowtie2db 'ref_db/'
141 --index 'custom_db'
142 #end if
143 -t '$analysis.analysis_type.t'
144 #if $analysis.analysis_type.t == "rel_ab" or $analysis.analysis_type.t == "rel_ab_w_read_stats"
145 --tax_lev '$analysis.analysis_type.tax_lev.tax_lev'
146 #else if $analysis.analysis_type.t == "clade_specific_strain_tracker"
147 --clade '$analysis.analysis_type.clade'
148 #if str($analysis.analysis_type.min_ab) != ''
149 --min_ab $analysis.analysis_type.min_ab
150 #end if
151 #else if $analysis.analysis_type.t == "marker_ab_table" and str($analysis.analysis_type.nreads) != ''
152 --nreads $$analysis.analysis_type.nreads
153 #else if $analysis.analysis_type.t == "marker_pres_table" and str($analysis.analysis_type.pres_th) != ''
154 --pres_th $analysis.analysis_type.pres_th
155 #end if
156 --min_cu_len $analysis.min_cu_len
157 #if str($analysis.min_alignment_len) != ''
158 --min_alignment_len $analysis.min_alignment_len
159 #end if
160 #if 'add_viruses' in $analysis.organism_profiling
161 --add_viruses
162 #end if
163 #if 'ignore_eukaryotes' in $analysis.organism_profiling
164 --ignore_eukaryotes
165 #end if
166 #if 'ignore_bacteria' in $analysis.organism_profiling
167 --ignore_bacteria
168 #end if
169 #if 'ignore_archaea' in $analysis.organism_profiling
170 --ignore_archaea
171 #end if
172 --stat_q $analysis.stat_q
173 --perc_nonzero $analysis.perc_nonzero
174 #if $analysis.ignore_markers
175 --ignore_markers '$analysis.ignore_markers'
176 #end if
177 $analysis.avoid_disqm
178 --sample_id_key '$out.sample_id_key'
179 --sample_id '$out.sample_id'
180 $out.use_group_representative
181 $out.legacy_output
182 $out.CAMI_format_output
183 $out.unknown_estimation
184 -o '$output_file'
185 --bowtie2out 'bowtie2out'
186 -s '$sam_output_file'
187 --biom '$biom_output_file'
188 --nproc \${GALAXY_SLOTS:-4}
189
190 #if $inputs.in.selector == "raw"
191 &&
192 mv 'bowtie2out' '$bowtie2out'
193 #end if
194
195 #if $analysis.analysis_type.tax_lev.tax_lev == 'a' and $analysis.analysis_type.tax_lev.split_levels
196 &&
197 mkdir 'split_levels'
198 &&
199 python '$__tool_directory__/formatoutput.py'
200 split_levels
201 --metaphlan_output '$output_file'
202 --outdir 'split_levels'
203 $out.legacy_output
204
205 #end if
206
207 #if $out.krona_output
208 &&
209 python '$__tool_directory__/formatoutput.py'
210 format_for_krona
211 --metaphlan_output '$output_file'
212 --krona_output '$krona_output_file'
213 #end if
214 ]]></command>
215 <inputs>
216 <section name="inputs" title="Inputs" expanded="true">
217 <conditional name="in">
218 <param name="selector" type="select" label="Input(s)">
219 <option value="raw" selected="true">Fasta/FastQ file(s) with microbiota reads</option>
220 <option value="sam">Externally BowTie2-mapped SAM file</option>
221 <option value="bowtie2out">Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run</option>
222 </param>
223 <when value="raw">
224 <conditional name="raw_in">
225 <param name="selector" type="select" label="Fasta/FastQ file(s) with microbiota reads">
226 <option value="single" selected="true">One single-end file</option>
227 <option value="multiple">Multiple single-end files</option>
228 <option value="paired">Paired-end files</option>
229 </param>
230 <when value="single">
231 <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with microbiota reads"/>
232 </when>
233 <when value="multiple">
234 <param name="in" type="data" format="@FILE_FORMATS@" multiple="true" label="Single-end Fasta/FastQ files with microbiota reads"/>
235 </when>
236 <when value="paired">
237 <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with microbiota reads"/>
238 <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with microbiota reads"/>
239 </when>
240 </conditional>
241 <param argument="--read_min_len" type="integer" value="70" label="Minimum length of the reads to be considered when parsing the input file"/>
242 <section name="mapping" title="Mapping" expanded="true">
243 <param argument="--bt2_ps" type="select" label="Presets options for BowTie2" help="Applied only with FASTA files">
244 <option value="sensitive">Sensitive</option>
245 <option value="very-sensitive" selected="true">Very sensitive</option>
246 <option value="sensitive-local">Sensitive local</option>
247 <option value="very-sensitive-local">Very sensitive local</option>
248 </param>
249 <param argument="--min_mapq_val" type="integer" value="5" label="Minimum mapping quality value (MAPQ)"/>
250 </section>
251 </when>
252 <when value="sam">
253 <param name="in" type="data" format="sam" label="Externally BowTie2-mapped SAM file" help="BowTie2 needs to be used first to map microbiota reads"/>
254 </when>
255 <when value="bowtie2out">
256 <param name="in" type="data" format="tabular" label="Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run"
257 help="File needs to be generated with MetaPhlAn versions >3.0"/>
258 </when>
259 </conditional>
260 <conditional name="db">
261 <param name="db_selector" type="select" label="Database with clade-specific marker genes">
262 <option value="cached" selected="true">Locally cached</option>
263 <option value="history">From history</option>
264 </param>
265 <when value="cached">
266 <param name="cached_db" type="select" label="Cached database with clade-specific marker genes">
267 <options from_data_table="@IDX_DATA_TABLE@">
268 <filter type="static_value" column="4" value="@IDX_VERSION@"/>
269 <validator message="No compatible MetaPhlAn database is available" type="no_options"/>
270 </options>
271 </param>
272 </when>
273 <when value="history">
274 <param argument="--bowtie2db" type="data" format="fasta" label="Database with clade-specific marker genes from history"/>
275 <param argument="--mpa_pkl" type="data" format="json" label="Metadata associated to the database with clade-specific marker genes from history"/>
276 </when>
277 </conditional>
278 </section>
279 <section name="analysis" title="Analysis" expanded="true">
280 <conditional name="analysis_type">
281 <param argument="-t" type="select" label="Type of analysis to perform">
282 <option value="rel_ab" selected="true">rel_ab: Profiling a microbiota in terms of relative abundances</option>
283 <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>
284 <option value="reads_map">reads_map: Mapping from reads to clades (only reads hitting a marker)</option>
285 <option value="clade_profiles">clade_profiles: Normalized marker counts for clades with at least a non-null marker</option>
286 <option value="clade_specific_strain_tracker">clade_specific_strain_tracker: List of markers present for a specific clade and all its subclades</option>
287 <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>
288 <option value="marker_counts">marker_counts: Non-normalized marker counts (use with extreme caution)</option>
289 <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>
290 </param>
291 <when value="rel_ab">
292 <expand macro="tax_lev"/>
293 </when>
294 <when value="rel_ab_w_read_stats">
295 <expand macro="tax_lev"/>
296 </when>
297 <when value="reads_map"/>
298 <when value="clade_profiles"/>
299 <when value="clade_specific_strain_tracker">
300 <param argument="--clade" type="text" value="" label="Clade for which to extract list of markers present"
301 help="Markers are also extracted for subclades" />
302 <param argument="--min_ab" type="float" optional="true" label="The minimum percentage abundance for the clade"/>
303 </when>
304 <when value="marker_ab_table">
305 <param argument="--nreads" type="integer" optional="true" label="Total number of reads in the original microbiota"
306 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"/>
307 </when>
308 <when value="marker_counts"/>
309 <when value="marker_pres_table">
310 <param argument="--pres_th" type="integer" optional="true" label="Threshold for calling a marker present"/>
311 </when>
312 </conditional>
313 <param argument="--min_cu_len" type="integer" value="2000"
314 label="Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances"/>
315 <param argument="--min_alignment_len" type="integer" optional="true"
316 label="Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded."/>
317 <param name="organism_profiling" type="select" multiple="true" optional="true" label="Organisms to profile">
318 <option value="add_viruses" selected="true">Profile viral organisms (add_viruses)</option>
319 <option value="ignore_eukaryotes">Ignore eukaryotic organisms (ignore_eukaryotes)</option>
320 <option value="ignore_bacteria">Ignore bacteria organisms (ignore_bacteria)</option>
321 <option value="ignore_archaea">Ignore archea organisms (ignore_archaea)</option>
322 </param>
323 <param argument="--stat" type="select" label="Statistical approach for converting marker abundances into clade abundances">
324 <option value="avg_g">avg_g: Clade global (i.e. normalizing all markers together) average (avg_g)</option>
325 <option value="avg_l">avg_l: Average of length-normalized marker counts</option>
326 <option value="tavg_g" selected="true">tavg_g: Truncated clade global average at --stat_q quantile</option>
327 <option value="tavg_l">tavg_l: Truncated average of length-normalized marker counts (at --stat_q)</option>
328 <option value="wavg_g">wavg_g: Winsorized clade global average (at --stat_q)</option>
329 <option value="wavg_l">wavg_l: Winsorized average of length-normalized marker counts (at --stat_q)</option>
330 <option value="med">med: Median of length-normalized marker counts</option>
331 </param>
332 <param argument="--stat_q" type="float" value="0.2" label="Quantile value for the robust average"/>
333 <param argument="--perc_nonzero" type="float" value="0.33" label="Percentage of markers with a non zero relative abundance for misidentify a species"/>
334 <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"/>
335 <param argument="--avoid_disqm" type='boolean' checked="true" truevalue='--avoid_disqm' falsevalue=''
336 label="Deactivate the procedure of disambiguating the quasi-markers based on the marker abundance pattern found in the sample?"
337 help="It is generally recommended to keep the disambiguation procedure in order to minimize false positives"/>
338 </section>
339 <section name="out" title="Outputs" expanded="true">
340 <param argument="--sample_id_key" type="text" value="SampleID" label="Sample ID key for this analysis"/>
341 <param argument="--sample_id" type="text" value="Metaphlan_Analysis" label="Sample ID for this analysis"/>
342 <param argument="--use_group_representative" type='boolean' checked="false" truevalue='--use_group_representative' falsevalue=''
343 label="Use a species as representative for species groups?"/>
344 <param argument="--legacy-output" type='boolean' checked="false" truevalue='--legacy-output' falsevalue=''
345 label="Old MetaPhlAn2 two columns output?"/>
346 <param argument="--CAMI_format_output" type='boolean' checked="false" truevalue='--CAMI_format_output' falsevalue=''
347 label="Report the profiling using the CAMI output format?"/>
348 <param argument="--unknown_estimation" type='boolean' checked="false" truevalue='--unknown_estimation' falsevalue=''
349 label="Scale relative abundances to the number of reads mapping to known clades in order to estimate unknowness?"/>
350 <param name="krona_output" type='boolean' checked="false" truevalue='true' falsevalue='false' label="Output for Krona?"/>
351 </section>
352 </inputs>
353 <outputs>
354 <data name="output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances" />
355 <data name="bowtie2out" format="tabular" label="${tool.name} on ${on_string}: Bowtie2 output">
356 <filter>inputs['in']['selector'] == "raw"</filter>
357 </data>
358 <data name="sam_output_file" format="sam" label="${tool.name} on ${on_string}: SAM file">
359 <filter>inputs['in']['selector'] == "raw"</filter>
360 </data>
361 <data name="biom_output_file" format="biom1" label="${tool.name} on ${on_string}: BIOM file" />
362 <collection name="levels" type="list" label="${tool.name} on ${on_string}: Predicted taxon relative abundances at each taxonomic levels" >
363 <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="split_levels/" format="tabular"/>
364 <filter>analysis['analysis_type']['tax_lev']['tax_lev'] == "a" and analysis['analysis_type']['tax_lev']['split_levels']</filter>
365 </collection>
366 <data name="krona_output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances for Krona">
367 <filter>out['krona_output']</filter>
368 </data>
369 </outputs>
370 <tests>
371 <test expect_num_outputs="6">
372 <section name="inputs">
373 <conditional name="in">
374 <param name="selector" value="raw"/>
375 <conditional name="raw_in">
376 <!-- Single GZ file -->
377 <param name="selector" value="single"/>
378 <param name="in" value="no_taxon_input.fasta"/>
379 </conditional>
380 <param name="read_min_len" value="70"/>
381 <section name="mapping">
382 <param name="bt2_ps" value="sensitive"/>
383 <param name="min_mapq_val" value="5"/>
384 </section>
385 </conditional>
386 <conditional name="db">
387 <!-- Cached db -->
388 <param name="db_selector" value="cached"/>
389 <param name="cached_db" value="test-db-20210409"/>
390 </conditional>
391 </section>
392 <section name="analysis">
393 <conditional name="analysis_type">
394 <param name="t" value="rel_ab"/>
395 <conditional name="tax_lev">
396 <param name="tax_lev" value="a"/>
397 <param name="split_levels" value="true"/>
398 </conditional>
399 </conditional>
400 <param name="min_cu_len" value="2000"/>
401 <param name="organism_profiling" value="add_viruses"/>
402 <param name="stat" value="avg_g"/>
403 <param name="stat_q" value="0.2"/>
404 <param name="perc_nonzero" value="0.33"/>
405 <param name="avoid_disqm" value="true"/>
406 </section>
407 <section name="out">
408 <param name="sample_id_key" value="SampleID"/>
409 <param name="sample_id" value="Metaphlan_Analysis"/>
410 <param name="use_group_representative" value="false"/>
411 <param name="legacy_output" value="false"/>
412 <param name="CAMI_format_output" value="false"/>
413 <param name="unknown_estimation" value="false"/>
414 <param name="krona_output" value="true"/>
415 </section>
416 <output name="output_file" ftype="tabular">
417 <assert_contents>
418 <has_text text="UNCLASSIFIED"/>
419 </assert_contents>
420 </output>
421 <output name="bowtie2out" ftype="tabular">
422 <assert_contents>
423 <not_has_text text="HWI-EAS109_102883399:3:104:7342:14360/1"/>
424 <has_n_lines n="2"/>
425 </assert_contents>
426 </output>
427 <output name="sam_output_file" ftype="sam">
428 <assert_contents>
429 <has_text text="SN:13076__A0A2I1PE66__CYJ72_10760"/>
430 </assert_contents>
431 </output>
432 <output name="biom_output_file" ftype="biom1">
433 <assert_contents>
434 <not_has_text text="k__Bacteria"/>
435 <not_has_text text="p__Actinobacteria"/>
436 </assert_contents>
437 </output>
438 <output_collection name="levels" type="list" >
439
440 <element name="all" ftype="tabular">
441 <assert_contents>
442 <has_text text="class"/>
443 <has_n_columns n="17"/>
444 <has_n_lines n="1"/>
445 </assert_contents>
446 </element>
447 <element name="class" ftype="tabular">
448 <assert_contents>
449 <has_text text="class_id"/>
450 <not_has_text text="phylum_id"/>
451 <has_n_columns n="3"/>
452 <has_n_lines n="1"/>
453 </assert_contents>
454 </element>
455 <element name="family" ftype="tabular">
456 <assert_contents>
457 <has_text text="family_id"/>
458 <not_has_text text="order"/>
459 <has_n_columns n="3"/>
460 <has_n_lines n="1"/>
461 </assert_contents>
462 </element>
463 <element name="genus" ftype="tabular">
464 <assert_contents>
465 <has_text text="genus_id"/>
466 <not_has_text text="family"/>
467 <has_n_columns n="3"/>
468 <has_n_lines n="1"/>
469 </assert_contents>
470 </element>
471 <element name="kingdom" ftype="tabular">
472 <assert_contents>
473 <has_text text="kingdom_id"/>
474 <has_n_columns n="3"/>
475 <has_n_lines n="1"/>
476 </assert_contents>
477 </element>
478 <element name="order" ftype="tabular">
479 <assert_contents>
480 <has_text text="order_id"/>
481 <not_has_text text="class_id"/>
482 <has_n_columns n="3"/>
483 <has_n_lines n="1"/>
484 </assert_contents>
485 </element>
486 <element name="phylum" ftype="tabular">
487 <assert_contents>
488 <has_text text="phylum_id"/>
489 <not_has_text text="kingdom_id"/>
490 <has_n_columns n="3"/>
491 <has_n_lines n="1"/>
492 </assert_contents>
493 </element>
494 <element name="species" ftype="tabular">
495 <assert_contents>
496 <has_text text="species_id"/>
497 <not_has_text text="genus"/>
498 <has_n_columns n="3"/>
499 <has_n_lines n="1"/>
500 </assert_contents>
501 </element>
502 <element name="strains" ftype="tabular">
503 <assert_contents>
504 <has_text text="strains_id"/>
505 <not_has_text text="species_id"/>
506 <has_n_columns n="3"/>
507 <has_n_lines n="1"/>
508 </assert_contents>
509 </element>
510 </output_collection>
511 <output name="krona_output_file" ftype="tabular">
512 <assert_contents>
513 <not_has_text text="k__Bacteria"/>
514 <has_n_lines n="1" delta="1"/>
515 <has_size value="1" delta="1"/>
516 </assert_contents>
517 </output>
518 </test>
519 <test expect_num_outputs="6">
520 <section name="inputs">
521 <conditional name="in">
522 <param name="selector" value="raw"/>
523 <conditional name="raw_in">
524 <!-- Single GZ file -->
525 <param name="selector" value="single"/>
526 <param name="in" value="SRS014464-Anterior_nares.fasta.gz"/>
527 </conditional>
528 <param name="read_min_len" value="70"/>
529 <section name="mapping">
530 <param name="bt2_ps" value="sensitive"/>
531 <param name="min_mapq_val" value="5"/>
532 </section>
533 </conditional>
534 <conditional name="db">
535 <!-- Cached db -->
536 <param name="db_selector" value="cached"/>
537 <param name="cached_db" value="test-db-20210409"/>
538 </conditional>
539 </section>
540 <section name="analysis">
541 <conditional name="analysis_type">
542 <param name="t" value="rel_ab"/>
543 <conditional name="tax_lev">
544 <param name="tax_lev" value="a"/>
545 <param name="split_levels" value="true"/>
546 </conditional>
547 </conditional>
548 <param name="min_cu_len" value="2000"/>
549 <param name="organism_profiling" value="add_viruses"/>
550 <param name="stat" value="avg_g"/>
551 <param name="stat_q" value="0.2"/>
552 <param name="perc_nonzero" value="0.33"/>
553 <param name="avoid_disqm" value="true"/>
554 </section>
555 <section name="out">
556 <param name="sample_id_key" value="SampleID"/>
557 <param name="sample_id" value="Metaphlan_Analysis"/>
558 <param name="use_group_representative" value="false"/>
559 <param name="legacy_output" value="false"/>
560 <param name="CAMI_format_output" value="false"/>
561 <param name="unknown_estimation" value="false"/>
562 <param name="krona_output" value="true"/>
563 </section>
564 <output name="output_file" ftype="tabular" file="SRS014464-Anterior_nares-abundances.tabular" compare="sim_size">
565 <assert_contents>
566 <has_text text="k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_accolens"/>
567 </assert_contents>
568 </output>
569 <output name="bowtie2out" ftype="tabular" file="SRS014464-Anterior_nares-bowtie2out.tabular" compare="sim_size">
570 <assert_contents>
571 <has_text text="HWI-EAS109_102883399:3:104:7342:14360/1"/>
572 <has_text text="37637__U2I1U8__N579_01580"/>
573 </assert_contents>
574 </output>
575 <output name="sam_output_file" ftype="sam" file="SRS014464-Anterior_nares.sam" compare="sim_size">
576 <assert_contents>
577 <has_text text="SN:13076__A0A2I1PE66__CYJ72_10760"/>
578 </assert_contents>
579 </output>
580 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
581 <assert_contents>
582 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
583 </assert_contents>
584 </output>
585 <output_collection name="levels" type="list" >
586 <element name="all" ftype="tabular">
587 <assert_contents>
588 <has_text text="Gammaproteobacteria"/>
589 <has_text text="Corynebacterium accolens"/>
590 <has_n_columns n="17"/>
591 </assert_contents>
592 </element>
593 <element name="class" ftype="tabular">
594 <assert_contents>
595 <has_text text="class_id"/>
596 <not_has_text text="phylum_id"/>
597 <has_text text="Actinobacteria"/>
598 <has_n_columns n="3"/>
599 </assert_contents>
600 </element>
601 <element name="family" ftype="tabular">
602 <assert_contents>
603 <has_text text="family_id"/>
604 <not_has_text text="order"/>
605 <has_text text="Propionibacteriaceae"/>
606 <has_n_columns n="3"/>
607 </assert_contents>
608 </element>
609 <element name="genus" ftype="tabular">
610 <assert_contents>
611 <has_text text="genus_id"/>
612 <not_has_text text="family"/>
613 <has_text text="Cutibacterium"/>
614 <has_n_columns n="3"/>
615 </assert_contents>
616 </element>
617 <element name="kingdom" ftype="tabular">
618 <assert_contents>
619 <has_text text="kingdom_id"/>
620 <has_text text="Bacteria"/>
621 <has_n_columns n="3"/>
622 </assert_contents>
623 </element>
624 <element name="order" ftype="tabular">
625 <assert_contents>
626 <has_text text="order_id"/>
627 <not_has_text text="class_id"/>
628 <has_text text="Propionibacteriales"/>
629 <has_n_columns n="3"/>
630 </assert_contents>
631 </element>
632 <element name="phylum" ftype="tabular">
633 <assert_contents>
634 <has_text text="phylum_id"/>
635 <not_has_text text="kingdom_id"/>
636 <has_text text="Firmicutes"/>
637 <has_n_columns n="3"/>
638 </assert_contents>
639 </element>
640 <element name="species" ftype="tabular">
641 <assert_contents>
642 <has_text text="species_id"/>
643 <not_has_text text="genus"/>
644 <has_text text="Corynebacterium accolens"/>
645 <has_n_columns n="3"/>
646 </assert_contents>
647 </element>
648 <element name="strains" ftype="tabular">
649 <assert_contents>
650 <has_text text="strains_id"/>
651 <not_has_text text="species_id"/>
652 <has_n_columns n="3"/>
653 </assert_contents>
654 </element>
655 </output_collection>
656 <output name="krona_output_file" ftype="tabular">
657 <assert_contents>
658 <not_has_text text="k__Bacteria"/>
659 <has_text text="Corynebacterium accolens"/>
660 <has_n_columns n="9"/>
661 </assert_contents>
662 </output>
663 </test>
664 <test expect_num_outputs="4">
665 <section name="inputs">
666 <conditional name="in">
667 <param name="selector" value="raw"/>
668 <conditional name="raw_in">
669 <!-- Multiple GZ file -->
670 <param name="selector" value="multiple"/>
671 <param name="in" value="SRS014464-Anterior_nares.fasta.gz,SRS014464-Anterior_nares.fasta.gz"/>
672 </conditional>
673 <param name="read_min_len" value="70"/>
674 <section name="mapping">
675 <param name="bt2_ps" value="sensitive"/>
676 <param name="min_mapq_val" value="5"/>
677 </section>
678 </conditional>
679 <conditional name="db">
680 <!-- Local db -->
681 <param name="db_selector" value="history"/>
682 <param name="bowtie2db" value="test-db.fasta"/>
683 <param name="mpa_pkl" value="test-db.json"/>
684 </conditional>
685 </section>
686 <section name="analysis">
687 <conditional name="analysis_type">
688 <param name="t" value="rel_ab"/>
689 <conditional name="tax_lev">
690 <param name="tax_lev" value="a"/>
691 <param name="split_levels" value="false"/>
692 </conditional>
693 </conditional>
694 <param name="min_cu_len" value="2000"/>
695 <param name="organism_profiling" value="add_viruses"/>
696 <param name="stat" value="avg_g"/>
697 <param name="stat_q" value="0.2"/>
698 <param name="perc_nonzero" value="0.33"/>
699 <param name="avoid_disqm" value="true"/>
700 </section>
701 <section name="out">
702 <param name="sample_id_key" value="SampleID"/>
703 <param name="sample_id" value="Metaphlan_Analysis"/>
704 <param name="use_group_representative" value="false"/>
705 <param name="legacy_output" value="false"/>
706 <param name="CAMI_format_output" value="false"/>
707 <param name="unknown_estimation" value="false"/>
708 <param name="krona_output" value="false"/>
709 </section>
710 <output name="output_file" ftype="tabular" file="SRS014464-Anterior_nares-abundances.tabular" compare="sim_size">
711 <assert_contents>
712 <has_text text="k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_accolens"/>
713 <has_text text="relative_abundance"/>
714 <has_text text="NCBI_tax_id"/>
715 <has_text text="clade_name"/>
716 </assert_contents>
717 </output>
718 <output name="bowtie2out" ftype="tabular" file="SRS014464-Anterior_nares-two-inputs-bowtie2out.tabular" compare="sim_size">
719 <assert_contents>
720 <has_text text="HWI-EAS109_102883399:3:104:7342:14360/1"/>
721 <has_text text="37637__U2I1U8__N579_01580"/>
722 </assert_contents>
723 </output>
724 <output name="sam_output_file" ftype="sam" file="SRS014464-Anterior_nares-two-inputs.sam" compare="sim_size">
725 <assert_contents>
726 <has_text text="SN:13076__A0A2I1PE66__CYJ72_10760"/>
727 </assert_contents>
728 </output>
729 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
730 <assert_contents>
731 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
732 </assert_contents>
733 </output>
734 </test>
735 <test expect_num_outputs="4">
736 <section name="inputs">
737 <conditional name="in">
738 <param name="selector" value="raw"/>
739 <conditional name="raw_in">
740 <!-- Paired GZ file -->
741 <param name="selector" value="paired"/>
742 <param name="in_f" value="SRS014464-Anterior_nares.fasta.gz"/>
743 <param name="in_r" value="SRS014464-Anterior_nares.fasta.gz"/>
744 </conditional>
745 <param name="read_min_len" value="70"/>
746 <section name="mapping">
747 <param name="bt2_ps" value="sensitive"/>
748 <param name="min_mapq_val" value="5"/>
749 </section>
750 </conditional>
751 <conditional name="db">
752 <!-- Cached db -->
753 <param name="db_selector" value="cached"/>
754 <param name="cached_db" value="test-db-20210409"/>
755 </conditional>
756 </section>
757 <section name="analysis">
758 <conditional name="analysis_type">
759 <param name="t" value="rel_ab"/>
760 <conditional name="tax_lev">
761 <param name="tax_lev" value="a"/>
762 <param name="split_levels" value="false"/>
763 </conditional>
764 </conditional>
765 <param name="min_cu_len" value="2000"/>
766 <param name="organism_profiling" value="add_viruses"/>
767 <param name="stat" value="avg_g"/>
768 <param name="stat_q" value="0.2"/>
769 <param name="perc_nonzero" value="0.33"/>
770 <param name="avoid_disqm" value="true"/>
771 </section>
772 <section name="out">
773 <param name="sample_id_key" value="SampleID"/>
774 <param name="sample_id" value="Metaphlan_Analysis"/>
775 <param name="use_group_representative" value="false"/>
776 <param name="legacy_output" value="false"/>
777 <param name="CAMI_format_output" value="false"/>
778 <param name="unknown_estimation" value="false"/>
779 <param name="krona_output" value="false"/>
780 </section>
781 <output name="output_file" ftype="tabular" file="SRS014464-Anterior_nares-abundances.tabular" compare="sim_size">
782 <assert_contents>
783 <has_text text="k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_accolens"/>
784 <has_text text="relative_abundance"/>
785 <has_text text="NCBI_tax_id"/>
786 <has_text text="clade_name"/>
787 </assert_contents>
788 </output>
789 <output name="bowtie2out" ftype="tabular" file="SRS014464-Anterior_nares-two-inputs-bowtie2out.tabular" compare="sim_size">
790 <assert_contents>
791 <has_text text="HWI-EAS109_102883399:3:104:7342:14360/1"/>
792 <has_text text="37637__U2I1U8__N579_01580"/>
793 </assert_contents>
794 </output>
795 <output name="sam_output_file" ftype="sam" file="SRS014464-Anterior_nares-two-inputs.sam" compare="sim_size">
796 <assert_contents>
797 <has_text text="SN:13076__A0A2I1PE66__CYJ72_10760"/>
798 </assert_contents>
799 </output>
800 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
801 <assert_contents>
802 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
803 </assert_contents>
804 </output>
805 </test>
806 <test expect_num_outputs="2">
807 <section name="inputs">
808 <conditional name="in">
809 <!-- SAM -->
810 <param name="selector" value="sam"/>
811 <param name="in" value="SRS014464-Anterior_nares.sam"/>
812 </conditional>
813 <conditional name="db">
814 <!-- Cached db -->
815 <param name="db_selector" value="cached"/>
816 <param name="cached_db" value="test-db-20210409"/>
817 </conditional>
818 </section>
819 <section name="analysis">
820 <conditional name="analysis_type">
821 <param name="t" value="rel_ab"/>
822 <conditional name="tax_lev">
823 <param name="tax_lev" value="a"/>
824 <param name="split_levels" value="false"/>
825 </conditional>
826 </conditional>
827 <param name="min_cu_len" value="2000"/>
828 <param name="organism_profiling" value="add_viruses"/>
829 <param name="stat" value="avg_g"/>
830 <param name="stat_q" value="0.2"/>
831 <param name="perc_nonzero" value="0.33"/>
832 <param name="avoid_disqm" value="true"/>
833 </section>
834 <section name="out">
835 <param name="sample_id_key" value="SampleID"/>
836 <param name="sample_id" value="Metaphlan_Analysis"/>
837 <param name="use_group_representative" value="false"/>
838 <param name="legacy_output" value="false"/>
839 <param name="CAMI_format_output" value="false"/>
840 <param name="unknown_estimation" value="false"/>
841 <param name="krona_output" value="false"/>
842 </section>
843 <output name="output_file" ftype="tabular" file="SRS014464-Anterior_nares-abundances.tabular" compare="sim_size">
844 <assert_contents>
845 <has_text text="k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_accolens"/>
846 <has_text text="relative_abundance"/>
847 <has_text text="NCBI_tax_id"/>
848 <has_text text="clade_name"/>
849 </assert_contents>
850 </output>
851 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
852 <assert_contents>
853 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
854 </assert_contents>
855 </output>
856 </test>
857 <test expect_num_outputs="2">
858 <section name="inputs">
859 <conditional name="in">
860 <!-- bowtie2out -->
861 <param name="selector" value="bowtie2out"/>
862 <param name="in" value="SRS014464-Anterior_nares-bowtie2out.tabular"/>
863 </conditional>
864 <conditional name="db">
865 <!-- Cached db -->
866 <param name="db_selector" value="cached"/>
867 <param name="cached_db" value="test-db-20210409"/>
868 </conditional>
869 </section>
870 <conditional name="in">
871 <param name="selector" value="bowtie2out"/>
872 <param name="in" value="SRS014464-Anterior_nares-bowtie2out.tabular"/>
873 </conditional>
874 <section name="mapping">
875 <param name="bt2_ps" value="sensite"/>
876 <param name="min_mapq_val" value="5"/>
877 </section>
878 <section name="analysis">
879 <conditional name="analysis_type">
880 <param name="t" value="rel_ab"/>
881 <conditional name="tax_lev">
882 <param name="tax_lev" value="a"/>
883 <param name="split_levels" value="false"/>
884 </conditional>
885 </conditional>
886 <param name="min_cu_len" value="2000"/>
887 <param name="organism_profiling" value="add_viruses"/>
888 <param name="stat" value="avg_g"/>
889 <param name="stat_q" value="0.2"/>
890 <param name="perc_nonzero" value="0.33"/>
891 <param name="avoid_disqm" value="true"/>
892 </section>
893 <section name="out">
894 <param name="sample_id_key" value="SampleID"/>
895 <param name="sample_id" value="Metaphlan_Analysis"/>
896 <param name="use_group_representative" value="false"/>
897 <param name="legacy_output" value="false"/>
898 <param name="CAMI_format_output" value="false"/>
899 <param name="unknown_estimation" value="false"/>
900 <param name="krona_output" value="false"/>
901 </section>
902 <output name="output_file" ftype="tabular" file="SRS014464-Anterior_nares-abundances.tabular" compare="sim_size">
903 <assert_contents>
904 <has_text text="k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_accolens"/>
905 <has_text text="relative_abundance"/>
906 <has_text text="NCBI_tax_id"/>
907 <has_text text="clade_name"/>
908 </assert_contents>
909 </output>
910 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
911 <assert_contents>
912 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
913 </assert_contents>
914 </output>
915 </test>
916 <test expect_num_outputs="6">
917 <section name="inputs">
918 <conditional name="in">
919 <param name="selector" value="raw"/>
920 <conditional name="raw_in">
921 <!-- Single FASTA file -->
922 <param name="selector" value="single"/>
923 <param name="in" value="SRS014464-Anterior_nares.fasta"/>
924 </conditional>
925 <param name="read_min_len" value="70"/>
926 <section name="mapping">
927 <param name="bt2_ps" value="sensitive"/>
928 <param name="min_mapq_val" value="5"/>
929 </section>
930 </conditional>
931 <conditional name="db">
932 <!-- Cached db -->
933 <param name="db_selector" value="cached"/>
934 <param name="cached_db" value="test-db-20210409"/>
935 </conditional>
936 </section>
937 <section name="analysis">
938 <conditional name="analysis_type">
939 <param name="t" value="rel_ab"/>
940 <conditional name="tax_lev">
941 <param name="tax_lev" value="a"/>
942 <param name="split_levels" value="true"/>
943 </conditional>
944 </conditional>
945 <param name="min_cu_len" value="2000"/>
946 <param name="organism_profiling" value="add_viruses"/>
947 <param name="stat" value="avg_g"/>
948 <param name="stat_q" value="0.2"/>
949 <param name="perc_nonzero" value="0.33"/>
950 <param name="ignore_markers" value="marker.txt"/>
951 <param name="avoid_disqm" value="true"/>
952 </section>
953 <section name="out">
954 <param name="sample_id_key" value="SampleID"/>
955 <param name="sample_id" value="Metaphlan_Analysis"/>
956 <param name="use_group_representative" value="false"/>
957 <param name="legacy_output" value="true"/>
958 <param name="CAMI_format_output" value="false"/>
959 <param name="unknown_estimation" value="false"/>
960 <param name="krona_output" value="true"/>
961 </section>
962 <output name="output_file" ftype="tabular" file="SRS014464-Anterior_nares-legacy-abundances.tabular" compare="sim_size">
963 <assert_contents>
964 <has_text text="k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_accolens"/>
965 <has_text text="SampleID"/>
966 <has_text text="Metaphlan_Analysis"/>
967 </assert_contents>
968 </output>
969 <output name="bowtie2out" ftype="tabular" file="SRS014464-Anterior_nares-bowtie2out.tabular" compare="sim_size">
970 <assert_contents>
971 <has_text text="HWI-EAS109_102883399:3:104:7342:14360/1"/>
972 <has_text text="37637__U2I1U8__N579_01580"/>
973 </assert_contents>
974 </output>
975 <output name="sam_output_file" ftype="sam" file="SRS014464-Anterior_nares.sam" compare="sim_size">
976 <assert_contents>
977 <has_text text="SN:13076__A0A2I1PE66__CYJ72_10760"/>
978 </assert_contents>
979 </output>
980 <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
981 <assert_contents>
982 <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
983 </assert_contents>
984 </output>
985 <output_collection name="levels" type="list" >
986 <element name="all" ftype="tabular">
987 <assert_contents>
988 <has_text text="Gammaproteobacteria"/>
989 <has_text text="Corynebacterium accolens"/>
990 <has_n_columns n="9"/>
991 </assert_contents>
992 </element>
993 <element name="class" ftype="tabular">
994 <assert_contents>
995 <has_text text="class"/>
996 <has_text text="Actinobacteria"/>
997 <has_n_columns n="2"/>
998 </assert_contents>
999 </element>
1000 <element name="family" ftype="tabular">
1001 <assert_contents>
1002 <has_text text="family"/>
1003 <has_text text="Propionibacteriaceae"/>
1004 <has_n_columns n="2"/>
1005 </assert_contents>
1006 </element>
1007 <element name="genus" ftype="tabular">
1008 <assert_contents>
1009 <has_text text="genus"/>
1010 <has_text text="Cutibacterium"/>
1011 <has_n_columns n="2"/>
1012 </assert_contents>
1013 </element>
1014 <element name="kingdom" ftype="tabular">
1015 <assert_contents>
1016 <has_text text="kingdom"/>
1017 <has_text text="Bacteria"/>
1018 <has_n_columns n="2"/>
1019 </assert_contents>
1020 </element>
1021 <element name="order" ftype="tabular">
1022 <assert_contents>
1023 <has_text text="order"/>
1024 <has_text text="Propionibacteriales"/>
1025 <has_n_columns n="2"/>
1026 </assert_contents>
1027 </element>
1028 <element name="phylum" ftype="tabular">
1029 <assert_contents>
1030 <has_text text="phylum"/>
1031 <has_text text="Firmicutes"/>
1032 <has_n_columns n="2"/>
1033 </assert_contents>
1034 </element>
1035 <element name="species" ftype="tabular">
1036 <assert_contents>
1037 <has_text text="species"/>
1038 <has_text text="Corynebacterium accolens"/>
1039 <has_n_columns n="2"/>
1040 </assert_contents>
1041 </element>
1042 <element name="strains" ftype="tabular">
1043 <assert_contents>
1044 <has_text text="strains"/>
1045 <has_n_columns n="2"/>
1046 </assert_contents>
1047 </element>
1048 </output_collection>
1049 <output name="krona_output_file" ftype="tabular">
1050 <assert_contents>
1051 <not_has_text text="k__Bacteria"/>
1052 <has_text text="Corynebacterium accolens"/>
1053 <has_n_columns n="9"/>
1054 </assert_contents>
1055 </output>
1056 </test>
1057 </tests>
1058 <help><![CDATA[
1059 What it does
1060 ============
1061
1062 MetaPhlAn is a computational tool for profiling the composition of microbial communities (Bacteria,
1063 Archaea and Eukaryotes) from metagenomic shotgun sequencing data (i.e. not 16S) at species-level.
1064
1065 MetaPhlAn relies on ~1.1M unique clade-specific marker genes identified from ~100,000 reference genomes
1066 (~99,500 bacterial and archaeal and ~500 eukaryotic), allowing:
1067
1068 - unambiguous taxonomic assignments;
1069 - accurate estimation of organismal relative abundance;
1070 - species-level resolution for bacteria, archaea, eukaryotes and viruses;
1071 - strain identification and tracking
1072 - orders of magnitude speedups compared to existing methods.
1073 - microbiota strain-level population genomics
1074
1075 MetaPhlAn clade-abundance estimation
1076 ------------------------------------
1077
1078 The basic usage of MetaPhlAn consists in the identification of the clades (from phyla to species and
1079 strains in particular cases) present in the microbiota obtained from a microbiome sample and their
1080 relative abundance.
1081
1082 Marker level analysis
1083 ---------------------
1084
1085 MetaPhlAn introduces the capability of characterizing organisms at the strain level using non
1086 aggregated marker information. Such capability comes with several slightly different flavours and
1087 are a way to perform strain tracking and comparison across multiple samples.
1088
1089 Usually, MetaPhlAn is first ran with default parameters for the type of analysis to profile the
1090 species present in the community, and then a strain-level profiling can be performed to zoom-in on
1091 specific species of interest. This operation can be performed quickly as it exploits the bowtie2out
1092 intermediate file saved during the execution of the default analysis type.
1093
1094 Inputs
1095 ======
1096
1097 Metaphlan takes as input either:
1098
1099 - one or several sequence files in Fasta, FastQ (whether compressed or not)
1100 - a BowTie2 produced SAM file
1101 - an intermediary mapping file of the microbiota generated by a previous MetaPhlAn run
1102
1103 It also needs the reference database, which can be locally installed or customized using the dedicated tools.
1104
1105 Outputs
1106 =======
1107
1108 The main output is a tab-separated file with the predicted taxon relative abundances.
1109
1110 It also generates a BIOM file and some intermediate files (SAM and BowTie2out) if sequence files are given as inputs.
1111
1112
1113 More help and use cases
1114 =======================
1115
1116 To get more information about MetaPhlAn usage and use cases, please refer to the `Metaphlan documentation`_.
1117
1118 .. _Metaphlan documentation: https://github.com/biobakery/MetaPhlAn/wiki/MetaPhlAn-4#Basic-Usage
1119
1120 ]]></help>
1121 <expand macro="citations"/>
1122 </tool>