Mercurial > repos > bebatut > qiime

comparison pick_open_reference_otus.xml @ 0:c1bd0c560018 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/master/tools/qiime commit bcbe76277f3e60303faf826f8ce7f018bc663a9a-dirty
author bebatut
date Tue, 02 Feb 2016 05:50:37 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:c1bd0c560018
1 <tool id="pick_open_reference_otus" name="Perform open-reference OTU picking"
2 version="1.9.1">
3
4 <description></description>
5
6 <macros>
7 <import>macros.xml</import>
8 </macros>
9
10 <expand macro="requirements" />
11
12 <version_command><![CDATA[
13 pick_open_reference_otus.py --version
14 ]]></version_command>
15
16 <command><![CDATA[
17 pick_open_reference_otus.py
18
19 -i $input_seq_files
20
21 -o otus
22
23 -m $otu_picking_method
24
25 #if str( $reference_sequences.reference_sequences_selector ) == 'history'
26 #set $ref = $reference_sequences.history_database
27 #else:
28 #set $data_table = dict([(_[0], _[2]) for _ in $reference_sequences.cached_database.input.options.tool_data_table.data])
29 #set $db = $reference_sequences.cached_database.value
30 #set $ref = $data_table[$db]
31 #end if
32 -r $ref
33
34 #if $prefilter_refseqs_fp.difference_test
35 #if str( $prefilter_refseqs_fp.prefilter_reference_sequences.reference_sequences_selector ) == 'history'
36 #set $ref = $prefilter_refseqs_fp.prefilter_reference_sequences.history_database
37 #else:
38 #set $data_table = dict([(_[0], _[2]) for _ in $prefilter_refseqs_fp.prefilter_reference_sequences.cached_database.input.options.tool_data_table.data])
39 #set $db = $prefilter_refseqs_fp.prefilter_reference_sequences.cached_database.value
40 #set $ref = $data_table[$db]
41 #end if
42 --prefilter_refseqs_fp $ref
43 #end if
44
45 -n $new_ref_set_id
46
47 $parallel
48 -O "\${GALAXY_SLOTS:-4}"
49
50 -s $percent_subsample
51 --prefilter_percent_id $prefilter_percent_id
52
53 #if str($step1_otu_map_fp) != 'None':
54 --step1_otu_map_fp $step1_otu_map_fp
55 #end if
56
57 #if str($step1_failures_fasta_fp) != 'None':
58 --step1_failures_fasta_fp=$step1_failures_fasta_fp
59 #end if
60
61 --minimum_failure_threshold $minimum_failure_threshold
62
63 $suppress_step4
64
65 --min_otu_size $min_otu_size
66
67 $suppress_taxonomy_assignment
68 $suppress_align_and_tree
69
70 &&
71
72 biom convert
73 -i otus/otu_table_mc2.biom
74 -o $output_otu_table
75 --to-tsv
76 --header-key taxonomy
77
78 #if not $suppress_taxonomy_assignment
79 &&
80 biom convert
81 -i otus/otu_table_mc2_w_tax.biom
82 -o $output_otu_table_taxonomy
83 --to-tsv
84 --header-key taxonomy
85 #end if
86
87 #if not $suppress_align_and_tree
88 &&
89 biom convert
90 -i otus/otu_table_mc_no_pynast_failures.biom
91 -o $output_otu_table_no_failures
92 --to-tsv
93 --header-key taxonomy
94 #end if
95
96 ]]>
97 </command>
98
99 <inputs>
100 <param name="input_seq_files" type="data" format="fasta,fastq"
101 label="Input sequence files" multiple="True" help="(-i/--input_fps)"/>
102
103 <param name="otu_picking_method" label="The OTU picking method to use for
104 reference and de novo steps" type="select"
105 help="-m/--otu_picking_method">
106 <option value="uclust" selected="True">uclust</option>
107 <option value="usearch61">usearch61</option>
108 <option value="sortmerna_sumaclust">sortmerna_sumaclust</option>
109 </param>
110
111 <conditional name="reference_sequences">
112 <param name="reference_sequences_selector" type="select"
113 label="Reference sequences to query"
114 help="(-r, --reference_fp)">
115 <option value="cached" selected="True">Public databases</option>
116 <option value="history">Databases from your history</option>
117 </param>
118 <when value="cached">
119 <param name="cached_database" label="QIIME databases of reference
120 sequences" type="select">
121 <options from_data_table="qiime_reference_db" />
122 </param>
123 </when>
124 <when value="history">
125 <param name="history_database" type="data" format="fasta"
126 label="Reference databases"/>
127 </when>
128 </conditional>
129
130 <conditional name="prefilter_refseqs_fp">
131 <param name="difference_test" type="boolean" label="Use different
132 reference sequences for the prefilter?" checked="False" truevalue="true"
133 falsevalue="false" help="(--prefilter_refseqs_fp)" />
134 <when value="true">
135 <conditional name="prefilter_reference_sequences">
136 <param name="reference_sequences_selector" type="select"
137 label="Reference sequences to query" >
138 <option value="cached" selected="True">Public databases</option>
139 <option value="history">Databases from your history</option>
140 </param>
141 <when value="cached">
142 <param name="cached_database" label="QIIME databases of reference
143 sequences" type="select">
144 <options from_data_table="qiime_reference_db" />
145 </param>
146 </when>
147 <when value="history">
148 <param name="history_database" type="data" format="fasta"
149 label="Reference databases"/>
150 </when>
151 </conditional>
152 </when>
153 <when value="false" />
154 </conditional>
155
156 <param name="new_ref_set_id" type="text" value="New" label="Unique
157 identifier for OTUs that get created in this ref set"
158 help="This is useful to support combining of reference sets
159 (-n/--new_ref_set_id)"/>
160
161 <param name="parallel" type="boolean" label="Run in parallel where
162 available?" truevalue="--parallel" falsevalue="" checked="False"
163 help="(-a, --parallel)" />
164
165 <param name="percent_subsample" type="float" value="0.001" min="0" max="1"
166 label="Percent of failure sequences to include in the subsample to
167 cluster de novo" help="Large numbers should give more comprehensive
168 results but will be slower(-s/--percent_subsample)"/>
169
170 <param name="prefilter_percent_id" type="float" value="0.0" min="0" max="1"
171 label="Percent of sequence pre-cluster against the reference"
172 help="Any reads which fail to hit are discarded (a quality filter)
173 (--prefilter_percent_id)"/>
174
175 <param name="step1_otu_map_fp" type="data" format="txt" label="Reference
176 OTU picking OTU map to avoid rebuilding if one has already been built
177 (optional)" optional="True" help="This must be an OTU map generated
178 by this workflow, not (for example) by pick_closed_reference_otus
179 (--step1_otu_map_fp)" />
180
181 <param name="step1_failures_fasta_fp" type="data" format="fasta"
182 label="Reference OTU picking failures fasta filepath, to avoid
183 rebuilding if one has already been built (optional)" optional="True"
184 help="This must be a failures file generated by this workflow, not
185 (for example) by pick_closed_reference_otus (--step1_failures_fasta_fp)" />
186
187 <param name="minimum_failure_threshold" type="integer" value="100000"
188 label="Minimum number of sequences that must fail to hit the reference
189 for subsampling to be performed" help="If fewer than this number of
190 sequences fail to hit the reference, the de novo clustering step will
191 run serially rather than invoking the subsampled open reference approach
192 to improve performance (--minimum_failure_threshold)"/>
193
194 <param name="suppress_step4" type="boolean" label="Suppress the final de
195 novo OTU picking step?" truevalue="--suppress_step4" falsevalue=""
196 checked="False" help="It may be necessary for extremely large data
197 sets(--suppress_step4)" />
198
199 <param name="min_otu_size" type="integer" value="2" label="Minimum otu
200 size to retain the OTU" help="(--min_otu_size)"/>
201
202 <param name="suppress_taxonomy_assignment" type="boolean"
203 label="Skip the taxonomy assignment step?"
204 truevalue="--suppress_taxonomy_assignment" falsevalue=""
205 checked="False" help="It results in an OTU table without taxonomy
206 (--suppress_taxonomy_assignment)" />
207
208 <param name="suppress_align_and_tree" type="boolean"
209 label="Skip the sequence alignment and tree-building steps?"
210 truevalue="--suppress_align_and_tree" falsevalue=""
211 checked="False" help="(--suppress_align_and_tree)" />
212 </inputs>
213
214 <outputs>
215 <data name="output_rep_set" format="fasta"
216 from_work_dir="otus/rep_set.fna"
217 label="${tool.name} on ${on_string}: OTU representative sequences"/>
218 <data name="output_ref_set" format="fasta"
219 from_work_dir="otus/new_refseqs.fna"
220 label="${tool.name} on ${on_string}: New reference sequences (OTU +
221 input reference sequences)"/>
222 <data name="output_otu_table" format="tsv"
223 label="${tool.name} on ${on_string}: OTU table"/>
224 <data name="output_otu_table_taxonomy" format="tsv"
225 label="${tool.name} on ${on_string}: OTU table with taxonomy">
226 <filter>suppress_taxonomy_assignment is False</filter>
227 </data>
228 <data name="output_otu_table_no_failures" format="tsv"
229 label="${tool.name} on ${on_string}: OTU without sequences that
230 failed to align">
231 <filter>suppress_align_and_tree is False</filter>
232 </data>
233 <data name="output_otu_map" format="txt"
234 from_work_dir="otus/final_otu_map_mc2.txt"
235 label="${tool.name} on ${on_string}: OTU map"/>
236 <data name="output_rep_set_tree" format="txt"
237 from_work_dir="otus/rep_set.tre"
238 label="${tool.name} on ${on_string}: representative set tree">
239 <filter>suppress_align_and_tree is False</filter>
240 </data>
241 </outputs>
242
243 <tests>
244 <test>
245 <param name="input_seq_files"
246 value="split_fastq_libraries_sequences.fasta"/>
247 <param name="otu_picking_method" value="uclust"/>
248 <param name="reference_sequences_selector" value="history"/>
249 <param name="history_database" value="gg_13_8_97_otus.fasta"/>
250 <param name="difference_test" value="false"/>
251 <param name="new_ref_set_id" value="New" />
252 <param name="parallel" value="--parallel"/>
253 <param name="percent_subsample" value="0.001" />
254 <param name="prefilter_percent_id" value="0.0" />
255 <param name="minimum_failure_threshold" value="100000" />
256 <param name="suppress_step4" value=""/>
257 <param name="min_otu_size" value="2" />
258 <param name="suppress_taxonomy_assignment" value="" />
259 <param name="suppress_align_and_tree" value="" />
260
261 <output name="output_rep_set"
262 value="pick_open_reference_otus_representative_sequences.fasta"/>
263 <output name="output_ref_set"
264 value="pick_open_reference_otus_reference_sequences.fasta"/>
265 <output name="output_otu_table"
266 value="pick_open_reference_otus_otu_table.txt"/>
267 <output name="output_otu_table_taxonomy"
268 value="pick_open_reference_otus_otu_table_with_taxo.txt" />
269 <output name="output_otu_map"
270 value="pick_open_reference_otus_otu_map.txt"/>
271 <output name="output_otu_table_no_failures"
272 value="pick_open_reference_otus_otu_table_with_taxo_without_pynast_failure.txt" />
273 <output name="output_rep_set_tree"
274 value="pick_open_reference_otus_representative_set_tree.txt" />
275 </test>
276 </tests>
277
278 <help><![CDATA[
279
280 **What it does**
281
282 This tool performs open-reference OTU picking from sequences.
283
284 This script is broken down into 4 possible OTU picking steps, and 2 steps
285 involving the creation of OTU tables and trees.
286
287 More information about this tool is available on
288 `QIIME documentation <http://qiime.org/scripts/pick_open_reference_otus.html>`_.
289 ]]>
290 </help>
291
292 <citations>
293 <expand macro="citations" />
294 </citations>
295 </tool>