Mercurial > repos > earlhaminst > lotus2

comparison lotus2.xml @ 0:478e767a0e7a 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 d05728af3d4d2ffd49548a320e8e8b4c6cc2f5e7"
author earlhaminst
date Thu, 13 May 2021 17:38:45 +0000
parents
children 85da3173a488
comparison
equal deleted inserted replaced
-1:000000000000 0:478e767a0e7a
1 <tool id="lotus2" name="LotuS2" version="@VERSION@" profile="20.01">
2 <description>fast OTU processing pipeline</description>
3 <macros>
4 <token name="@VERSION@">2.04</token>
5 </macros>
6 <requirements>
7 <requirement type="package" version="@VERSION@">lotus2</requirement>
8 </requirements>
9 <version_command>lotus2 --version</version_command>
10 <command detect_errors="exit_code"><![CDATA[
11 mkdir input
12 &&
13 #if $inputs.paired_or_single == 'single':
14 #for i, f in enumerate($inputs.input):
15 #set ext = $f.ext.replace('sanger', '')
16 ln -s '$f' 'input/input${i}.${ext}' &&
17 #end for
18 #elif $inputs.paired_or_single == 'paired':
19 #for i, f in enumerate($inputs.left_input):
20 #set ext = $f.ext.replace('sanger', '')
21 ln -s '$f' 'input/input${i}.1.${ext}' &&
22 #end for
23 #for i, f in enumerate($inputs.right_input):
24 #set ext = $f.ext.replace('sanger', '')
25 ln -s '$f' 'input/input${i}.2.${ext}' &&
26 #end for
27 #else:
28 #for i, f in enumerate($inputs.pair_input):
29 #set ext = $f.forward.ext.replace('sanger', '')
30 ln -s '$f.forward' 'input/input${i}.1.${ext}' &&
31 #set ext = $f.reverse.ext.replace('sanger', '')
32 ln -s '$f.reverse' 'input/input${i}.2.${ext}' &&
33 #end for
34 #end if
35
36 lotus2 -create_map mapping.txt -i input/ &&
37 cat mapping.txt &&
38
39 lotus2
40 -i input/
41 -o output
42 -tmpDir tmp_folder
43 -threads "\${GALAXY_SLOTS:-1}"
44 -map mapping.txt
45 -platform $platform
46 #if $barcode:
47 -barcode '$barcode'
48 #end if
49 #if $forwardPrimer:
50 -forwardPrimer '$forwardPrimer'
51 #end if
52 #if $reversePrimer:
53 -reversePrimer '$reversePrimer'
54 #end if
55
56 -clustering $clu_args.clustering
57 -id $clu_args.id
58 -derepMin $clu_args.derepMin
59 -chim_skew $clu_args.chim_skew
60 -deactivateChimeraCheck $clu_args.deactivateChimeraCheck
61 -readOverlap $clu_args.readOverlap
62
63 -refDB $tax_args.refDB
64 -amplicon_type $tax_args.amplicon_type
65 -tax_group $tax_args.tax_group
66 -rdp_thr $tax_args.rdp_thr
67 -utax_thr $tax_args.utax_thr
68 -keepUnclassified $tax_args.keepUnclassified
69 -taxAligner $tax_args.taxAligner
70 -useBestBlastHitOnly $tax_args.useBestBlastHitOnly
71 -LCA_cover $tax_args.LCA_cover
72 -LCA_frac $tax_args.LCA_frac
73 -greengenesSpecies $tax_args.greengenesSpecies
74 -pseudoRefOTUcalling $tax_args.pseudoRefOTUcalling
75
76 &&
77
78 cd output/ &&
79 tar -cvzf higherLvl.tar.gz higherLvl/ &&
80 tar -cvzf ExtraFiles.tar.gz ExtraFiles/ &&
81 tar -cvzf LotuSLogS.tar.gz LotuSLogS/ &&
82 tar -cvzf primary.tar.gz primary/
83 ]]></command>
84
85 <inputs>
86 <conditional name="inputs">
87 <param name="paired_or_single" type="select" label="Paired or Single-end data?">
88 <option value="single" selected="true">Single-end</option>
89 <option value="paired">Paired-end</option>
90 <option value="paired_collection">Paired-end collection</option>
91 </param>
92 <when value="single">
93 <param name="input" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" label="Single-end reads" />
94 </when>
95 <when value="paired">
96 <param name="left_input" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" label="Left/Forward strand reads" />
97 <param name="right_input" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" label="Right/Reverse strand reads" />
98 </when>
99 <when value="paired_collection">
100 <param name="pair_input" type="data_collection" collection_type="list:paired" format="fastqsanger,fastqsanger.gz" label="List of paired reads" />
101 </when>
102 </conditional>
103 <param argument="-platform" type="select" label="Sequencing platform">
104 <option value="miSeq" selected="true">miSeq</option>
105 <option value="hiSeq">hiSeq</option>
106 <option value="454">454</option>
107 <option value="PacBio">PacBio</option>
108 </param>
109 <param argument="-barcode" type="data" format="fastqsanger" optional="true" label="Barcodes (MIDs)" help="FASTQ file with barcodes (in the processed mi/hiSeq format)" />
110 <param argument="-forwardPrimer" type="text" value="" label="Forward primer used to amplify DNA region" help="E.g. 16S primer fwd" />
111 <param argument="-reversePrimer" type="text" value="" label="Reverse primer used to amplify DNA region" help="E.g. 16S primer rev" />
112 <section name="clu_args" title="Clustering Options">
113 <param argument="-clustering" type="select" label="Clustering algorithm">
114 <option value="1">UPARSE</option>
115 <option value="2">swarm</option>
116 <option value="3" selected="true">cd-hit</option>
117 <option value="6">unoise3</option>
118 <option value="7">dada2</option>
119 </param>
120 <param argument="-id" type="float" min="0" max="1" value="0.97" label="Clustering threshold for OTUs" />
121 <param argument="-derepMin" type="integer" min="0" value="1" label="Minimum size of dereplicated clustered" />
122 <param argument="-chim_skew" type="integer" min="0" value="2" label="Skew in chimeric fragment abundance" />
123 <param argument="-deactivateChimeraCheck" type="select" label="Chimera check">
124 <option value="0" selected="true">OTU chimera checks</option>
125 <option value="1">No chimera check at all</option>
126 <option value="2">Deactivate deNovo chimera check</option>
127 <option value="3">Deactivate ref based chimera check</option>
128 </param>
129 <param argument="-readOverlap" type="integer" min="0" value="300" label="Maximum number of basepairs that two reads are overlapping" />
130 </section>
131 <section name="tax_args" title="Taxonomy Options">
132 <param argument="-refDB" type="select" label="Reference Database">
133 <option value="SLV" selected="true">Silva LSU (23/28S) or SSU (16/18S)</option>
134 <option value="GG">Greengenes</option>
135 <option value="UNITE">ITS focused on fungi</option>
136 <option value="PR2">SSU focused on Protists</option>
137 <option value="beetax">Bee gut specific database and tax names</option>
138 <option value="HITdb">Human gut microbiota</option>
139 </param>
140 <param argument="-amplicon_type" type="select" label="Amplicon type">
141 <option value="LSU">LSU Large subunit (23S/28S)</option>
142 <option value="SSU" selected="true">SSU small subunit (16S/18S)</option>
143 <option value="ITS">ITS internal transcribed spacer</option>
144 <option value="ITS1">ITS1</option>
145 <option value="ITS2">ITS2</option>
146 </param>
147 <param argument="-tax_group" type="select" label="Tax group">
148 <option value="bacteria" selected="true">bacterial 16S rDNA annnotation</option>
149 <option value="fungi">fungal 18S/23S/ITS annotation</option>
150 </param>
151 <param argument="-rdp_thr" type="float" min="0" max="1" value="0.8" label="Confidence threshold for RDP"/>
152 <param argument="-utax_thr" type="float" min="0" max="1" value="0.8" label="Confidence threshold for UTAX"/>
153 <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" />
154 <param argument="-taxAligner" type="select" label="Taxonomy aligner">
155 <option value="0" selected="true">Deactivated (just use RDP)</option>
156 <option value="1">Blast</option>
157 <option value="2">Use LAMBDA to search against a 16S reference database for taxonomic profiling of OTUs</option>
158 <option value="3">Use UTAX with custom databases</option>
159 <option value="4">Use VSEARCH to align OTUs to custom databases</option>
160 <option value="5">Use USEARCH to align OTUs to custom databases</option>
161 </param>
162 <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)" />
163 <param argument="-LCA_cover" type="float" min="0" max="1" value="0.9" label="Minimum horizontal coverage of an OTU sequence against ref DB"/>
164 <param argument="-LCA_frac" type="float" min="0" max="1" value="0.9" label="Minimum fraction of reads with identical taxonomy"/>
165 <param argument="-greengenesSpecies" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Create greengenes output labels instead of OTU" />
166 <param argument="-pseudoRefOTUcalling" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Create Reference based (open) OTUs" />
167 </section>
168 </inputs>
169
170 <outputs>
171 <data name="otu" format="tabular" label="${tool.name} on ${on_string}: OTU abundance matrix" from_work_dir="output/OTU.txt" />
172 <data name="otu_biom" format="biom" label="${tool.name} on ${on_string}: biom-formatted OTU abundance matrix" from_work_dir="output/OTU.biom" />
173 <data name="otu_fna" format="fasta" label="${tool.name} on ${on_string}: FASTA-formatted extended OTU seed sequences" from_work_dir="output/OTU.fna" />
174 <data name="OTUphylo_nwk" format="newick" label="${tool.name} on ${on_string}: Newick-formatted phylogenetic tree between sequences" from_work_dir="output/OTUphylo.nwk" />
175 <data name="hiera_blast" format="tabular" label="${tool.name} on ${on_string}: OTU taxonomy assignments based on Blastn" from_work_dir="output/hiera_BLAST.txt" />
176 <data name="hiera_rdp" format="tabular" label="${tool.name} on ${on_string}: OTU taxonomy assignments based on RDP classifier" from_work_dir="output/hiera_RDP.txt" />
177 <data name="primary" format="tar" label="${tool.name} on ${on_string}: Copies of sdm options and mapping file" from_work_dir="output/primary.tar.gz" />
178 <data name="higherlvl" format="tar" label="${tool.name} on ${on_string}: Abundance matrices" from_work_dir="output/higherLvl.tar.gz" />
179 <data name="lotuslogs" format="tar" label="${tool.name} on ${on_string}: Log files" from_work_dir="output/LotuSLogS.tar.gz" />
180 <data name="extrafiles" format="tar" label="${tool.name} on ${on_string}: Extra files" from_work_dir="output/ExtraFiles.tar.gz" />
181 </outputs>
182
183 <tests>
184 <test>
185 <param name="paired_or_single" value="single"/>
186 <param name="input" value="Anh_sample1.fastq.gz,Anh_sample2.fastq.gz" ftype="fastqsanger.gz"/>
187 <param name="platform" value="454" />
188 <output name="otu" file="OTU.txt" compare="sim_size" />
189 <output name="otu_fna" file="OTU.fna" compare="sim_size" />
190 <output name="hiera_rdp" file="hiera_RDP.txt" compare="sim_size" />
191 </test>
192 </tests>
193
194 <help><![CDATA[
195 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.
196
197 Documentation can be found at `<http://lotus2.earlham.ac.uk/>`_.
198 ]]></help>
199 <citations>
200 <citation type="doi">10.1186/2049-2618-2-30</citation>
201 </citations>
202 </tool>