annotate repeat_annotate_custom.xml @ 0:d14182506989 draft default tip

"planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
author petrn
date Tue, 15 Feb 2022 16:44:31 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
1 <tool id="repeat_annotate" name="RepeatExplorer Based Assembly Annotation" version="0.1.1" python_template_version="3.5">
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
2 <requirements>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
3 <requirement type="package">repeatmasker</requirement>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
4 <requirement type="package">bioconductor-rtracklayer</requirement>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
5 </requirements>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
6 <command detect_errors="exit_code"><![CDATA[
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
7 RepeatMasker -dir \$(pwd) '$input' -pa 32 -lib '$repeat_library' -xsmall -nolow -no_is -e ncbi -s
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
8 &&
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
9 ls -l * >&2 &&
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
10 cp `basename $input`.out $output2
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
11 &&
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
12 Rscript ${__tool_directory__}/clean_rm_output.R $output2 $output1
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
13
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
14 ]]></command>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
15 <inputs>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
16 <param type="data" name="input" format="fasta" label="Genome/ Assembly to annotate" />
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
17 <param type="data" name="repeat_library" format="fasta" label="RepeatExplorer based Library of Repetitive Sequences"
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
18 help="custom database of repetitive sequences should be provided in fasta format. Sequence header should specify repeat class:
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
19 >sequence_id#classification_level1/classification_level2/..." />
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
20 </inputs>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
21 <outputs>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
22 <data name="output1" format="gff3" label="Repeat Annotation on ${on_string}, cleaned gff"/>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
23 <data name="output2" format="tabular" label="Raw output from RepeatMasker on ${on_string}" />
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
24 </outputs>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
25 <help><![CDATA[
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
26 This tools uses RepeatMasker to annotate repetitive sequences in the genome assemblie using custom library of repeats created from RepeatExplorer output.
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
27 Library of repeats can be created from RepeatExplorer ouputt from contigs and TAREAN consensus sequences. Fasta formated library of repeats must contain header containg information about classification of repeats as **>sequence_id#classification_level1/classification_level2/...**
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
28
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
29 Classification in RepeatExplorer based library follows predetermined classification levels. User can however specify additional classification levels or completelly custom classifications. Conflicts in annotations are resolved based on classification hierarchy.
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
30 ]]></help>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
31 </tool>
d14182506989 "planemo upload commit d7966a292ed4209f4058e77ab8c0e49a67847b16-dirty"
petrn
parents:
diff changeset
32