Mercurial > repos > petr-novak > dante_ltr

comparison dante_ltr_search.xml @ 7:c33d6583e548 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
author petr-novak
date Fri, 24 Jun 2022 14:19:48 +0000
parents b91ca438a1cb
children 9de392f2fc02
comparison
equal deleted inserted replaced
6:b91ca438a1cb 7:c33d6583e548
1 <tool id="dante_ltr_search" name="DANTE_LTR retrotransposon identification" version="0.1.5" python_template_version="3.5"> 1 <tool id="dante_ltr_search" name="DANTE_LTR retrotransposon identification" version="0.1.6" python_template_version="3.5">
2 <requirements> 2 <requirements>
3 <requirement type="package">blast</requirement> 3 <requirement type="package">blast</requirement>
4 <requirement type="package">r-optparse</requirement> 4 <requirement type="package">r-optparse</requirement>
5 <requirement type="package">bioconductor-bsgenome</requirement> 5 <requirement type="package">bioconductor-bsgenome</requirement>
6 <requirement type="package">bioconductor-biostrings</requirement> 6 <requirement type="package">bioconductor-biostrings</requirement>
7 <requirement type="package">bioconductor-rtracklayer</requirement> 7 <requirement type="package">bioconductor-rtracklayer</requirement>
8 8
9 </requirements> 9 </requirements>
10 <command detect_errors="exit_code"><![CDATA[ 10 <command detect_errors="exit_code"><![CDATA[
11 Rscript ${__tool_directory__}/extract_putative_ltr.R --gff3 '$dante' --reference_sequence '$reference' --output output --cpu 32 11 Rscript ${__tool_directory__}/extract_putative_ltr.R --gff3 '$dante' --reference_sequence '$reference' -M $max_missing --output output --cpu 32
12 && 12 &&
13 mv output.gff3 $te_ltr_gff 13 mv output.gff3 $te_ltr_gff
14 &&
15 mv output_statistics.csv $statistics
14 ]]></command> 16 ]]></command>
15 <inputs> 17 <inputs>
16 <param type="data" name="dante" format="gff3" label="Filtered GFF3 output from DANTE pipeline"/> 18 <param type="data" name="dante" format="gff3" label="Filtered GFF3 output from DANTE pipeline"/>
17 <param type="data" name="reference" format="fasta" label="Reference sequence matching DANTE output" /> 19 <param type="data" name="reference" format="fasta" label="Reference sequence matching DANTE output" />
20 <param type="integer" name="max_missing" min="0" max="3" value="1" label="Maximum number of missing protein domains to tolerate in full length retrotransposon" />
18 </inputs> 21 </inputs>
19 <outputs> 22 <outputs>
20 <data name="te_ltr_gff" format="gff3" label="LTR retrotransposons annotation (GFF3) 23 <data name="te_ltr_gff" format="gff3" label="LTR retrotransposons annotation (GFF3)
21 based on DANTE annotation $dante.hid and reference $reference.hid" /> 24 based on DANTE annotation $dante.hid and reference $reference.hid" />
25 <data name="statistics" format="tabular" label="LTR retrotransposons detection
26 summary based on $dante.hid and reference $reference.hid" />
22 </outputs> 27 </outputs>
23 <help><![CDATA[ 28 <help><![CDATA[
24 This tool uses output from DANTE annotation pipeline to identify full length LTR 29 This tool uses output from DANTE annotation pipeline to identify full length LTR
25 transposable elements. Output is in the GFF3 format and include annotation of 30 transposable elements. Output is in the GFF3 format and include annotation of
26 5' and 3' Longe Terminal Repeats, Target Site Duplication (TSD) and primer binding site (PBS). 31 5' and 3' Long Terminal Repeats, Target Site Duplication (TSD) and primer binding site (PBS).
27 32
28 All identified elements contains complete set of protein domains as defined in 33 All identified elements contains set of protein domains as defined in
29 REXdb_. Based on the results detection structural feature, 34 REXdb_.Based on the results of detection of structural features,
30 elements falls into four categories: 35 elements falls into five categories:
31 36
32 - elements with domains, 5'LTR, 3'LTR, TSD and PBS 37 - elements with domains, 5'LTR, 3'LTR, TSD and PBS - rank DLTP
33 - elements with domains, 5'LTR, 3'LTR and PBS (TSD was not found) 38 - elements with domains, 5'LTR, 3'LTR and PBS (TSD was not found) rank DLP
34 - elements with domains, 5' LTR, 3'LTR, TSD (PBS was not found) 39 - elements with domains, 5' LTR, 3'LTR, TSD (PBS was not found) - rank DTL
35 - elements with protein domains, 5'LTR and 3'LTR (PBS and LDS were not found) 40 - elements with protein domains, 5'LTR and 3'LTR (PBS and LDS were not found) - rank DL
41 - elements as cluster of proteins domains with same classification, no LTRs - rank D
36 42
37 .. _REXdb: https://doi.org/10.1186/s13100-018-0144-1 43 .. _REXdb: https://doi.org/10.1186/s13100-018-0144-1
38 44
39 ]]></help> 45 ]]></help>
40 </tool> 46 </tool>