Mercurial > repos > petr-novak > repeatexplorer2

comparison repex_full_clustering.xml @ 7:65d1a27e9339 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit ccbd120278facd9aa39c1c46665ee994ebd3cff2-dirty
author petr-novak
date Mon, 16 Oct 2023 09:19:52 +0000
parents 335d138b654b
children
comparison
equal deleted inserted replaced
6:335d138b654b 7:65d1a27e9339
1 <tool id="repeatexplorer2" name="RepeatExplorer2 clustering: " version="2.3.8.1" > 1 <tool id="repeatexplorer2" name="RepeatExplorer2 clustering: " version="2.3.8.2" >
2 <stdio> 2 <stdio>
3 <regex match="lastdb: can't open file: NEAR" source="stderr" level="fatal" description="Version of last is too old, use ver 956 or higher\n" /> 3 <regex match="lastdb: can't open file: NEAR" source="stderr" level="fatal" description="Version of last is too old, use ver 956 or higher\n" />
4 <regex match="Traceback" source="stderr" level="fatal" description="Unknown error" /> 4 <regex match="Traceback" source="stderr" level="fatal" description="Unknown error" />
5 <regex match="error" source="stderr" level="fatal" description="Unknown error" /> 5 <regex match="error" source="stderr" level="fatal" description="Unknown error" />
6 <regex match="Warning" source="stderr" level="warning" description="Unknown error" /> 6 <regex match="Warning" source="stderr" level="warning" description="Unknown error" />
7 <exit_code range="1:" level="fatal" description="Error" /> 7 <exit_code range="1:" level="fatal" description="Error" />
8 </stdio> 8 </stdio>
9 <description>Improved version or repeat discovery and characterization using graph-based sequence clustering</description> 9 <description>Improved version or repeat discovery and characterization using graph-based sequence clustering</description>
10 <requirements> 10 <requirements>
11 <requirement type="package">last</requirement> 11 <container type="singularity">library://repeatexplorer/default/repex_tarean:0.3.8-dbaa07f</container>
12 <requirement type="package">imagemagick</requirement>
13 <requirement type="package">mafft</requirement>
14 <requirement type="package">blast</requirement>
15 <requirement type="package" version="0.9.29" >diamond</requirement>
16 <requirement type="package">blast-legacy</requirement>
17 <requirement type="package">r-igraph</requirement>
18 <requirement type="package">r-data.tree</requirement>
19 <requirement type="package">r-stringr</requirement>
20 <requirement type="package">r-r2html</requirement>
21 <requirement type="package">r-hwriter</requirement>
22 <requirement type="package">r-dt</requirement>
23 <requirement type="package">r-scales</requirement>
24 <requirement type="package">r-plotrix</requirement>
25 <requirement type="package">r-png</requirement>
26 <requirement type="package">r-plyr</requirement>
27 <requirement type="package">r-dplyr</requirement>
28 <requirement type="package">r-optparse</requirement>
29 <requirement type="package">r-dbi</requirement>
30 <requirement type="package">r-rsqlite</requirement>
31 <requirement type="package">r-rserve</requirement>
32 <requirement type="package">bioconductor-biostrings</requirement>
33 <requirement type="package" version="2.3.8.1">repex_tarean</requirement>
34 <requirement type="set_environment">REPEX</requirement>
35 <requirement type="set_environment">REPEX_VERSION</requirement>
36 <requirement type="package" version="0.9.1" >pyrserve</requirement>
37 </requirements> 12 </requirements>
38 <command > 13 <command>
39 export PYTHONHASHSEED=0; 14 export PYTHONHASHSEED=0;
40 \${REPEX}/seqclust --sample ${read_sampling.sample} --output_dir=tarean_output --logfile=${log} --cleanup $paired --taxon $taxon 15 export TAREAN_CPU=\$GALAXY_SLOTS;
16 export TAREAN_MAX_MEM=\$GALAXY_MEMORY_MB;
17 seqclust --sample ${read_sampling.sample} --output_dir=tarean_output --logfile=${log} --cleanup $paired --taxon $taxon
41 18
42 #if $advanced_options.advanced: 19 #if $advanced_options.advanced:
43 --mincl $advanced_options.size_threshold $advanced_options.keep_names $advanced_options.automatic_filtering -D $advanced_options.blastx.options_blastx 20 --mincl $advanced_options.size_threshold $advanced_options.keep_names $advanced_options.automatic_filtering -D $advanced_options.blastx.options_blastx
44 --assembly_min $advanced_options.assembly_min_cluster_size 21 --assembly_min $advanced_options.assembly_min_cluster_size
45 22
58 ${FastaFile} >stdout.log 2> stderr.log ; 35 ${FastaFile} >stdout.log 2> stderr.log ;
59 echo "STDOUT CONTENT:" >> ${log} ; 36 echo "STDOUT CONTENT:" >> ${log} ;
60 cat stdout.log >> ${log} ; 37 cat stdout.log >> ${log} ;
61 echo "STDERR CONTENT:" >> ${log}; 38 echo "STDERR CONTENT:" >> ${log};
62 cat stderr.log >> ${log} &amp;&amp; 39 cat stderr.log >> ${log} &amp;&amp;
63 \${REPEX}/stderr_filter.py stderr.log &amp;&amp; 40 /opt/repex_tarean/stderr_filter.py stderr.log &amp;&amp;
64 cd tarean_output &amp;&amp; 41 cd tarean_output &amp;&amp;
65 zip -r ${ReportArchive}.zip * &amp;&amp; 42 zip -r ${ReportArchive}.zip * &amp;&amp;
66 mv ${ReportArchive}.zip ${ReportArchive} &amp;&amp; 43 mv ${ReportArchive}.zip ${ReportArchive} &amp;&amp;
67 cp index.html ${ReportFile} &amp;&amp; 44 cp index.html ${ReportFile} &amp;&amp;
68 mkdir ${ReportFile.files_path} &amp;&amp; 45 mkdir -p ${ReportFile.extra_files_path} &amp;&amp;
69 cp -r --parents libdir ${ReportFile.files_path} &amp;&amp; 46 cp -r --parents libdir ${ReportFile.extra_files_path} &amp;&amp;
70 cp -r --parents seqclust/clustering/superclusters ${ReportFile.files_path} &amp;&amp; 47 cp -r --parents seqclust/clustering/superclusters ${ReportFile.extra_files_path} &amp;&amp;
71 cp -r --parents seqclust/clustering/clusters ${ReportFile.files_path} &amp;&amp; 48 cp -r --parents seqclust/clustering/clusters ${ReportFile.extra_files_path} &amp;&amp;
72 cp seqclust/clustering/hitsort.cls ${ReportFile.files_path}/seqclust/clustering/hitsort.cls &amp;&amp; 49 cp seqclust/clustering/hitsort.cls ${ReportFile.extra_files_path}/seqclust/clustering/hitsort.cls &amp;&amp;
73 cp *.png ${ReportFile.files_path}/ &amp;&amp; 50 cp *.png ${ReportFile.extra_files_path}/ &amp;&amp;
74 cp *.csv ${ReportFile.files_path}/ &amp;&amp; 51 cp *.csv ${ReportFile.extra_files_path}/ &amp;&amp;
75 cp *.html ${ReportFile.files_path}/ &amp;&amp; 52 cp *.html ${ReportFile.extra_files_path}/ &amp;&amp;
76 cp *.css ${ReportFile.files_path}/ &amp;&amp; 53 cp *.css ${ReportFile.extra_files_path}/ &amp;&amp;
77 cp *.fasta ${ReportFile.files_path}/ 2>>$log &amp;&amp; rm -r ../tarean_output || : 54 cp *.fasta ${ReportFile.extra_files_path}/ 2>>$log &amp;&amp; rm -r ../tarean_output || :
78 55
79 </command> 56 </command>
80 <inputs> 57 <inputs>
81 <param name="FastaFile" label="NGS reads" type="data" format="fasta" 58 <param name="FastaFile" label="NGS reads" type="data" format="fasta"
82 help="Input file must contain FASTA-formatted NGS reads. Illumina paired-end reads are recommended."/> 59 help="Input file must contain FASTA-formatted NGS reads. Illumina paired-end reads are recommended."/>
152 <param name="automatic_filtering" label="Perform automatic filtering of abundant satellite repeats" help="Automatic filtering identifies the most abundant tandem repeats and partially removes their reads from the analysis. This enables to analyze higher proportions of other less abundant repeats." type="boolean" truevalue="--automatic_filtering" falsevalue="" checked="false"/> 129 <param name="automatic_filtering" label="Perform automatic filtering of abundant satellite repeats" help="Automatic filtering identifies the most abundant tandem repeats and partially removes their reads from the analysis. This enables to analyze higher proportions of other less abundant repeats." type="boolean" truevalue="--automatic_filtering" falsevalue="" checked="false"/>
153 <param name="keep_names" label="Keep original read names" type="boolean" truevalue="--keep_names" falsevalue="" checked="false" help="By default, reads are renamed using integers. Use this option to keep original names."/> 130 <param name="keep_names" label="Keep original read names" type="boolean" truevalue="--keep_names" falsevalue="" checked="false" help="By default, reads are renamed using integers. Use this option to keep original names."/>
154 <param name="assembly_min_cluster_size" type="integer" label="Minimal cluster size for assembly" value="5" min="2" max="100"/> 131 <param name="assembly_min_cluster_size" type="integer" label="Minimal cluster size for assembly" value="5" min="2" max="100"/>
155 </when> 132 </when>
156 </conditional> 133 </conditional>
157 134 <param name="queue_select" type="select" label="Select queue">
158 135 <option value="basic_fast_queue">basic (max runtime 2 days, 4 GB RAM)</option>
136 <option value="long_slow_queue">long (max runtime 2 weeks, 64 GB RAM)</option>
137 <option value="extra_long_slow_queue">extra long (max runtime 4 weeks, 64 GB RAM)</option>
138 </param>
159 139
160 </inputs> 140 </inputs>
161 <outputs> 141 <outputs>
162 <data name="log" format="txt" label="RepeatExplorer2 - log file"/> 142 <data name="log" format="txt" label="RepeatExplorer2 - log file"/>
163 <data name="ReportArchive" format="zip" label="RepeatExplorer2 - Archive with HTML report from data ${FastaFile.hid}"/> 143 <data name="ReportArchive" format="zip" label="RepeatExplorer2 - Archive with HTML report from data ${FastaFile.hid}"/>