Mercurial > repos > earlhaminst > lotus2

comparison lotus2.xml @ 4:59b8864c9fa0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/lotus2 commit ac59e1bfb1ef3b5104e84d4d65fb9bef50fed8ae"
author earlhaminst
date Thu, 03 Jun 2021 15:44:44 +0000
parents 77cb867e9608
children 7f33525b85d0
comparison
equal deleted inserted replaced
3:77cb867e9608 4:59b8864c9fa0
1 <tool id="lotus2" name="LotuS2" version="@VERSION@+galaxy1" profile="20.01"> 1 <tool id="lotus2" name="LotuS2" version="@VERSION@+galaxy2" profile="20.01">
2 <description>fast OTU processing pipeline</description> 2 <description>fast OTU processing pipeline</description>
3 <macros> 3 <macros>
4 <token name="@VERSION@">2.06</token> 4 <token name="@VERSION@">2.06</token>
5 <xml name="refDB_macro"> 5 <xml name="refDB_macro">
6 <param argument="-refDB" type="select" label="Reference Database"> 6 <conditional name="refDB_cond">
7 <option value="SLV" selected="true">Silva LSU (23/28S) or SSU (16/18S) (SLV)</option> 7 <param argument="-refDB" type="select" label="Taxonomy reference database">
8 <option value="GG">Greengenes (GG)</option> 8 <option value="cached">Use a built-in taxonomy database</option>
9 <option value="UNITE">ITS focused on fungi (UNITE)</option> 9 <option value="history">Use a taxonomy from history</option>
10 <option value="PR2">SSU focused on Protists (PR2)</option> 10 </param>
11 <option value="beetax">Bee gut specific database and tax names (beetax)</option> 11 <when value="cached">
12 <option value="HITdb">Human gut microbiota (HITdb)</option> 12 <param argument="ref_db" type="select" label="Using reference database" help="Select database from the list">
13 </param> 13 <option value="SLV" selected="true">Silva LSU (23/28S) or SSU (16/18S) (SLV)</option>
14 <option value="GG">Greengenes (GG)</option>
15 <option value="UNITE">ITS focused on fungi (UNITE)</option>
16 <option value="PR2">SSU focused on Protists (PR2)</option>
17 <option value="beetax">Bee gut specific database and tax names (beetax)</option>
18 <option value="HITdb">Human gut microbiota (HITdb)</option>
19 </param>
20 <param argument="-greengenesSpecies" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Create greengenes output labels instead of OTU" />
21 </when>
22 <when value="history">
23 <param name="ref_fasta" type="data" format="fasta" label="Taxonomy reference sequences" help="In FASTA format" />
24 <param argument="-tax4refDB" type="data" format="tabular" label="Taxonomy reference lineages" help="Tab-separated file with 2 columns mapping each FASTA header of the reference sequences to a GTDB-style taxonomy string" />
25 </when>
26 </conditional>
14 <param argument="-useBestBlastHitOnly" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use the best Blast hit only" help="Do not use LCA (lowest common ancestor) to determine the most likely taxonomic level (not recommended)" /> 27 <param argument="-useBestBlastHitOnly" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use the best Blast hit only" help="Do not use LCA (lowest common ancestor) to determine the most likely taxonomic level (not recommended)" />
15 </xml> 28 </xml>
16 <xml name="id_macro"> 29 <xml name="id_macro">
17 <param argument="-id" type="float" min="0" max="1" value="0.97" label="Clustering threshold for OTUs" /> 30 <param argument="-id" type="float" min="0" max="1" value="0.97" label="Clustering threshold for OTUs" />
31 </xml>
32 <xml name="ITSx_macro">
33 <param argument="-ITSx" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Use ITSx to only retain OTUs fitting to ITS1/ITS2 hmm models" />
18 </xml> 34 </xml>
19 </macros> 35 </macros>
20 <requirements> 36 <requirements>
21 <requirement type="package" version="@VERSION@">lotus2</requirement> 37 <requirement type="package" version="@VERSION@">lotus2</requirement>
22 </requirements> 38 </requirements>
61 #set ext = $f.reverse.ext.replace('sanger', '') 77 #set ext = $f.reverse.ext.replace('sanger', '')
62 ln -s '$f.reverse' 'input/${symlink_basename(f)}.2.${ext}' && 78 ln -s '$f.reverse' 'input/${symlink_basename(f)}.2.${ext}' &&
63 #end for 79 #end for
64 #end if 80 #end if
65 81
66 lotus2 -create_map mapping.txt -i input/ && 82 #if not $map:
67 cat mapping.txt && 83 lotus2 -create_map mapping.txt -i input/ &&
84 cat mapping.txt &&
85 #set map = 'mapping.txt'
86 #end if
68 87
69 lotus2 88 lotus2
70 -i input/ 89 -i input/
71 -o output 90 -o output
72 -tmpDir tmp_folder 91 -tmpDir tmp_folder
73 -threads "\${GALAXY_SLOTS:-1}" 92 -threads "\${GALAXY_SLOTS:-1}"
74 -map mapping.txt 93 -map '$map'
75 -platform $platform 94 -platform $platform
76 #if $barcode: 95 #if $barcode:
77 -barcode '$barcode' 96 -barcode '$barcode'
78 #end if 97 #end if
79 #if $forwardPrimer: 98 #if $forwardPrimer:
95 #if $clu_args.derepMin: 114 #if $clu_args.derepMin:
96 -derepMin '$clu_args.derepMin' 115 -derepMin '$clu_args.derepMin'
97 #end if 116 #end if
98 -deactivateChimeraCheck $clu_args.deactivateChimeraCheck 117 -deactivateChimeraCheck $clu_args.deactivateChimeraCheck
99 -chim_skew $clu_args.chim_skew 118 -chim_skew $clu_args.chim_skew
100 -readOverlap $clu_args.readOverlap
101 119
102 -taxAligner $tax_args.aligner_cond.taxAligner 120 -taxAligner $tax_args.aligner_cond.taxAligner
103 #if $tax_args.aligner_cond.taxAligner == '0': 121 #if $tax_args.aligner_cond.taxAligner == '0':
104 -rdp_thr $tax_args.aligner_cond.rdp_thr 122 -rdp_thr $tax_args.aligner_cond.rdp_thr
105 #elif $tax_args.aligner_cond.taxAligner == '3': 123 #elif $tax_args.aligner_cond.taxAligner == '3':
106 -utax_thr $tax_args.aligner_cond.utax_thr 124 -utax_thr $tax_args.aligner_cond.utax_thr
107 #else: 125 #else:
108 -refDB $tax_args.aligner_cond.refDB 126 #if $tax_args.aligner_cond.refDB_cond.refDB == 'cached':
127 -refDB $tax_args.aligner_cond.refDB_cond.ref_db
128 -greengenesSpecies $tax_args.aligner_cond.refDB_cond.greengenesSpecies
129 #else:
130 -refDB $tax_args.aligner_cond.refDB_cond.ref_fasta
131 -tax4refDB $tax_args.aligner_cond.refDB_cond.tax4refDB
132 #end if
109 -useBestBlastHitOnly $tax_args.aligner_cond.useBestBlastHitOnly 133 -useBestBlastHitOnly $tax_args.aligner_cond.useBestBlastHitOnly
110 #end if 134 #end if
111 -amplicon_type $tax_args.amplicon_type 135 -amplicon_type $tax_args.amplicon_cond.amplicon_type
136 #if $tax_args.amplicon_cond.amplicon_type in ('ITS', 'ITS1', 'ITS2'):
137 -ITSx $tax_args.amplicon_cond.ITSx_macro
138 #end if
112 -tax_group $tax_args.tax_group 139 -tax_group $tax_args.tax_group
113 -keepUnclassified $tax_args.keepUnclassified 140 -keepUnclassified $tax_args.keepUnclassified
114 -useBestBlastHitOnly $tax_args.useBestBlastHitOnly 141 -useBestBlastHitOnly $tax_args.useBestBlastHitOnly
115 -LCA_cover $tax_args.LCA_cover 142 -LCA_cover $tax_args.LCA_cover
116 -LCA_frac $tax_args.LCA_frac 143 -LCA_frac $tax_args.LCA_frac
117 -greengenesSpecies $tax_args.greengenesSpecies
118 -lulu $tax_args.lulu 144 -lulu $tax_args.lulu
119 -buildPhylo $tax_args.buildPhylo 145 -buildPhylo $tax_args.buildPhylo
120 146
121 ; EXIT_VALUE=\$? ; 147 ; EXIT_VALUE=\$? ;
122 148
142 --> 168 -->
143 <when value="paired_collection"> 169 <when value="paired_collection">
144 <param name="pair_input" type="data_collection" collection_type="list:paired" format="fastqsanger,fastqsanger.gz" label="List of paired reads" /> 170 <param name="pair_input" type="data_collection" collection_type="list:paired" format="fastqsanger,fastqsanger.gz" label="List of paired reads" />
145 </when> 171 </when>
146 </conditional> 172 </conditional>
173 <param argument="-map" type="data" format="tabular" optional="true" label="Mapping file (optional)" help="Needed to demultiplex the FASTQ files using sdm. If the FASTQ are already demultiplexed, this can be omitted." />
147 <param argument="-platform" type="select" label="Sequencing platform"> 174 <param argument="-platform" type="select" label="Sequencing platform">
148 <option value="miSeq" selected="true">miSeq</option> 175 <option value="miSeq" selected="true">miSeq</option>
149 <option value="hiSeq">hiSeq</option> 176 <option value="hiSeq">hiSeq</option>
150 <option value="454">454</option> 177 <option value="454">454</option>
151 <option value="PacBio">PacBio</option> 178 <option value="PacBio">PacBio</option>
201 <option value="1">No chimera check at all</option> 228 <option value="1">No chimera check at all</option>
202 <option value="2">Disable deNovo chimera check</option> 229 <option value="2">Disable deNovo chimera check</option>
203 <option value="3">Disable ref based chimera check</option> 230 <option value="3">Disable ref based chimera check</option>
204 </param> 231 </param>
205 <param argument="-chim_skew" type="integer" min="0" value="2" label="Skew in chimeric fragment abundance" /> 232 <param argument="-chim_skew" type="integer" min="0" value="2" label="Skew in chimeric fragment abundance" />
206 <param argument="-readOverlap" type="integer" min="0" value="300" label="Maximum number of basepairs that two reads are overlapping" />
207 </section> 233 </section>
208 <section name="tax_args" title="Taxonomy Options"> 234 <section name="tax_args" title="Taxonomy Options">
209 <conditional name="aligner_cond"> 235 <conditional name="aligner_cond">
210 <param argument="-taxAligner" type="select" label="Taxonomy aligner for taxonomic profiling of OTUs"> 236 <param argument="-taxAligner" type="select" label="Taxonomy aligner for taxonomic profiling of OTUs">
211 <option value="0" selected="true">RDPclassifier (max likelihood)</option> 237 <option value="0" selected="true">RDPclassifier (max likelihood)</option>
228 </when> 254 </when>
229 <when value="4"> 255 <when value="4">
230 <expand macro="refDB_macro" /> 256 <expand macro="refDB_macro" />
231 </when> 257 </when>
232 </conditional> 258 </conditional>
233 <param argument="-amplicon_type" type="select" label="Amplicon type"> 259 <conditional name="amplicon_cond">
234 <option value="LSU">LSU Large subunit (23S/28S)</option> 260 <param argument="-amplicon_type" type="select" label="Amplicon type">
235 <option value="SSU" selected="true">SSU small subunit (16S/18S)</option> 261 <option value="LSU">LSU Large subunit (23S/28S)</option>
236 <option value="ITS">ITS internal transcribed spacer</option> 262 <option value="SSU" selected="true">SSU small subunit (16S/18S)</option>
237 <option value="ITS1">ITS1</option> 263 <option value="ITS">ITS internal transcribed spacer</option>
238 <option value="ITS2">ITS2</option> 264 <option value="ITS1">ITS1</option>
239 </param> 265 <option value="ITS2">ITS2</option>
266 </param>
267 <when value="ITS">
268 <expand macro="ITSx_macro" />
269 </when>
270 <when value="ITS1">
271 <expand macro="ITSx_macro" />
272 </when>
273 <when value="ITS2">
274 <expand macro="ITSx_macro" />
275 </when>
276 </conditional>
240 <param argument="-tax_group" type="select" label="Tax group"> 277 <param argument="-tax_group" type="select" label="Tax group">
241 <option value="bacteria" selected="true">bacterial 16S rDNA annnotation</option> 278 <option value="bacteria" selected="true">bacterial 16S rDNA annnotation</option>
242 <option value="fungi">fungal 18S/23S/ITS annotation</option> 279 <option value="fungi">fungal 18S/23S/ITS annotation</option>
243 </param> 280 </param>
244 <param argument="-keepUnclassified" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Keep unclassified OTUs" help="Includes unclassified OTUs (i.e. no match in RDP/Blast database) in OTU and taxa abundance matrix calculations" /> 281 <param argument="-keepUnclassified" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Keep unclassified OTUs" help="Includes unclassified OTUs (i.e. no match in RDP/Blast database) in OTU and taxa abundance matrix calculations" />
245 <param argument="-useBestBlastHitOnly" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use best blast hit only" help="If selected, do not use LCA (lowest common ancestor) to determine most likely taxonomic level (not recommended)" /> 282 <param argument="-useBestBlastHitOnly" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use best blast hit only" help="If selected, do not use LCA (lowest common ancestor) to determine most likely taxonomic level (not recommended)" />
246 <param argument="-LCA_cover" type="float" min="0" max="1" value="0.9" label="Minimum horizontal coverage of an OTU sequence against ref DB"/> 283 <param argument="-LCA_cover" type="float" min="0" max="1" value="0.9" label="Minimum horizontal coverage of an OTU sequence against ref DB"/>
247 <param argument="-LCA_frac" type="float" min="0" max="1" value="0.9" label="Minimum fraction of reads with identical taxonomy"/> 284 <param argument="-LCA_frac" type="float" min="0" max="1" value="0.9" label="Minimum fraction of reads with identical taxonomy"/>
248 <param argument="-greengenesSpecies" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Create greengenes output labels instead of OTU" /> 285 <param argument="-lulu" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use LULU to merge OTUs based on their occurrence" />
249 <param argument="-lulu" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use LULU to merge OTUs based on their occurence" />
250 <param argument="-buildPhylo" type="select" label="Build OTU phylogeny"> 286 <param argument="-buildPhylo" type="select" label="Build OTU phylogeny">
251 <option value="0">Disable</option> 287 <option value="0">Disable</option>
252 <option value="1" selected="true">Use fasttree2</option> 288 <option value="1" selected="true">Use fasttree2</option>
253 <option value="2">Use iqtree2</option> 289 <option value="2">Use iqtree2</option>
254 </param> 290 </param>
259 <data name="otu" format="tabular" label="${tool.name} on ${on_string}: OTU abundance matrix" from_work_dir="output/OTU.txt" /> 295 <data name="otu" format="tabular" label="${tool.name} on ${on_string}: OTU abundance matrix" from_work_dir="output/OTU.txt" />
260 <data name="otu_biom" format="biom1" label="${tool.name} on ${on_string}: biom-formatted OTU abundance matrix" from_work_dir="output/OTU.biom" /> 296 <data name="otu_biom" format="biom1" label="${tool.name} on ${on_string}: biom-formatted OTU abundance matrix" from_work_dir="output/OTU.biom" />
261 <data name="otu_fna" format="fasta" label="${tool.name} on ${on_string}: FASTA-formatted extended OTU seed sequences" from_work_dir="output/OTU.fna" /> 297 <data name="otu_fna" format="fasta" label="${tool.name} on ${on_string}: FASTA-formatted extended OTU seed sequences" from_work_dir="output/OTU.fna" />
262 <data name="OTUphylo_nwk" format="newick" label="${tool.name} on ${on_string}: Newick-formatted phylogenetic tree between sequences" from_work_dir="output/OTUphylo.nwk" /> 298 <data name="OTUphylo_nwk" format="newick" label="${tool.name} on ${on_string}: Newick-formatted phylogenetic tree between sequences" from_work_dir="output/OTUphylo.nwk" />
263 <data name="mapping" format="tabular" label="${tool.name} on ${on_string}: mapping file" from_work_dir="output/primary/in.map" /> 299 <data name="mapping" format="tabular" label="${tool.name} on ${on_string}: mapping file" from_work_dir="output/primary/in.map" />
300 <data name="runlog" format="txt" label="${tool.name} on ${on_string}: main log file" from_work_dir="output/LotuSLogS/LotuS_run.log" />
264 <data name="outputs" format="tar" label="${tool.name} on ${on_string}: All output files" from_work_dir="output.tar.gz" /> 301 <data name="outputs" format="tar" label="${tool.name} on ${on_string}: All output files" from_work_dir="output.tar.gz" />
265 </outputs> 302 </outputs>
266 303
267 <tests> 304 <tests>
268 <test> 305 <test>
272 <param name="clustering" value="3" /> 309 <param name="clustering" value="3" />
273 <output name="otu" file="OTU.txt" compare="sim_size" /> 310 <output name="otu" file="OTU.txt" compare="sim_size" />
274 <output name="otu_fna" file="OTU.fna" compare="sim_size" /> 311 <output name="otu_fna" file="OTU.fna" compare="sim_size" />
275 <output name="mapping" file="mapping.txt" /> 312 <output name="mapping" file="mapping.txt" />
276 </test> 313 </test>
314 <test>
315 <param name="paired_or_single" value="single"/>
316 <param name="input" value="Anh_sample1.fastq.gz,Anh_sample2.fastq.gz" ftype="fastqsanger.gz"/>
317 <param name="mapping" value="mapping.txt" />
318 <param name="platform" value="454" />
319 <param name="clustering" value="3" />
320 <output name="otu" file="OTU.txt" compare="sim_size" />
321 <output name="otu_fna" file="OTU.fna" compare="sim_size" />
322 </test>
277 </tests> 323 </tests>
278 324
279 <help><![CDATA[ 325 <help><![CDATA[
280 If you have separate FASTA and quality files, these can be combined in a FASTQ file using the "Combine FASTA and QUAL into FASTQ" tool. 326 If you have separate FASTA and quality files, these can be combined in a FASTQ file using the "Combine FASTA and QUAL into FASTQ" tool.
281 327