Mercurial > repos > petr-novak > repeat_annotation_pipeline3
annotate repeat_annotate_custom.xml @ 10:276efc4cb17f draft
Uploaded
author | petr-novak |
---|---|
date | Thu, 04 May 2023 09:27:43 +0000 |
parents | 4a068d23fda6 |
children | 5366d5ea04bc |
rev | line source |
---|---|
10 | 1 <tool id="repeat_annotate" name="Library Based Assembly Annotation" version="0.1.5" python_template_version="3.5"> |
0 | 2 <requirements> |
9 | 3 <requirement type="package" version="4.1.2.p1">repeatmasker</requirement> |
0 | 4 <requirement type="package">bioconductor-rtracklayer</requirement> |
5 </requirements> | |
6 <command detect_errors="exit_code"><![CDATA[ | |
3 | 7 |
8 #if $sensitivity.value == 'default': | |
8 | 9 RepeatMasker -dir \$(pwd) '$input' -pa 32 -lib '$repeat_library' -xsmall ${nolow} -no_is -e ncbi |
3 | 10 #else: |
8 | 11 RepeatMasker -dir \$(pwd) '$input' -pa 32 -lib '$repeat_library' -xsmall ${nolow} -no_is -e ncbi $sensitivity |
3 | 12 #end if |
0 | 13 && |
14 ls -l * >&2 && | |
15 cp `basename $input`.out $output2 | |
16 && | |
17 Rscript ${__tool_directory__}/clean_rm_output.R $output2 $output1 | |
18 | |
19 ]]></command> | |
20 <inputs> | |
7
acf12f2e8355
"planemo upload commit 363c9be36812ce7623dad670f881d155209ed2ba"
petr-novak
parents:
6
diff
changeset
|
21 <param type="data" name="input" format="fasta" label="Genome assembly to annotate" /> |
0 | 22 <param type="data" name="repeat_library" format="fasta" label="RepeatExplorer based Library of Repetitive Sequences" |
23 help="custom database of repetitive sequences should be provided in fasta format. Sequence header should specify repeat class: | |
24 >sequence_id#classification_level1/classification_level2/..." /> | |
3 | 25 <param type="select" label="sensitivity" name="sensitivity" > |
26 <option value="default" selected="true" >Default sensitivity </option> | |
27 <option value="-s">Slow search, more sensitive </option> | |
6
b53f5a456d01
"planemo upload commit 3aefb0555456837d10fe69e4ad25de08d5972cb2"
petr-novak
parents:
4
diff
changeset
|
28 <option value="-q">Quick search, less sensitive </option> |
3 | 29 </param> |
10 | 30 <param argument="-nolow" type="boolean" truevalue="-nolow" falsevalue="" checked="false" label="Perform masking of low complexity and simple repeats" /> |
0 | 31 </inputs> |
32 <outputs> | |
6
b53f5a456d01
"planemo upload commit 3aefb0555456837d10fe69e4ad25de08d5972cb2"
petr-novak
parents:
4
diff
changeset
|
33 <data name="output1" format="gff3" label="Repeat Annotation (GFF3) on ${on_string}"/> |
0 | 34 <data name="output2" format="tabular" label="Raw output from RepeatMasker on ${on_string}" /> |
35 </outputs> | |
36 <help><![CDATA[ | |
3 | 37 This tools uses RepeatMasker to annotate repetitive sequences in the genome assemblies using custom library of repeats created either from RepeatExplorer output or from DANTE_LTR transposable element library. |
38 Library of repeats can be created from RepeatExplorer output from contigs and TAREAN consensus sequences. | |
39 Fasta formatted library of repeats must contain header containing information about classification of repeats as **>sequence_id#classification_level1/classification_level2/...** | |
0 | 40 |
3 | 41 Classification in RepeatExplorer based library follows predetermined classification levels. User can however specify additional classification levels or custom classifications. |
42 Conflicts in annotations are resolved based on classification hierarchy. | |
0 | 43 ]]></help> |
44 </tool> | |
45 |