annotate dante_ltr_search.xml @ 7:c33d6583e548 draft

"planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
author petr-novak
date Fri, 24 Jun 2022 14:19:48 +0000
parents b91ca438a1cb
children 9de392f2fc02
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
7
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
1 <tool id="dante_ltr_search" name="DANTE_LTR retrotransposon identification" version="0.1.6" python_template_version="3.5">
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
2 <requirements>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
3 <requirement type="package">blast</requirement>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
4 <requirement type="package">r-optparse</requirement>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
5 <requirement type="package">bioconductor-bsgenome</requirement>
1
c1498f679b50 "planemo upload commit e3385df50052b11d3bdd5c997abae5fb1b87ed56"
petr-novak
parents: 0
diff changeset
6 <requirement type="package">bioconductor-biostrings</requirement>
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
7 <requirement type="package">bioconductor-rtracklayer</requirement>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
8
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
9 </requirements>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
10 <command detect_errors="exit_code"><![CDATA[
7
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
11 Rscript ${__tool_directory__}/extract_putative_ltr.R --gff3 '$dante' --reference_sequence '$reference' -M $max_missing --output output --cpu 32
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
12 &&
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
13 mv output.gff3 $te_ltr_gff
7
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
14 &&
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
15 mv output_statistics.csv $statistics
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
16 ]]></command>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
17 <inputs>
6
b91ca438a1cb "planemo upload commit 9633fb98932151f059ce02a0ce202a4374ef8d68"
petr-novak
parents: 3
diff changeset
18 <param type="data" name="dante" format="gff3" label="Filtered GFF3 output from DANTE pipeline"/>
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
19 <param type="data" name="reference" format="fasta" label="Reference sequence matching DANTE output" />
7
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
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" />
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
21 </inputs>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
22 <outputs>
6
b91ca438a1cb "planemo upload commit 9633fb98932151f059ce02a0ce202a4374ef8d68"
petr-novak
parents: 3
diff changeset
23 <data name="te_ltr_gff" format="gff3" label="LTR retrotransposons annotation (GFF3)
b91ca438a1cb "planemo upload commit 9633fb98932151f059ce02a0ce202a4374ef8d68"
petr-novak
parents: 3
diff changeset
24 based on DANTE annotation $dante.hid and reference $reference.hid" />
7
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
25 <data name="statistics" format="tabular" label="LTR retrotransposons detection
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
26 summary based on $dante.hid and reference $reference.hid" />
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
27 </outputs>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
28 <help><![CDATA[
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
29 This tool uses output from DANTE annotation pipeline to identify full length LTR
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
30 transposable elements. Output is in the GFF3 format and include annotation of
7
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
31 5' and 3' Long Terminal Repeats, Target Site Duplication (TSD) and primer binding site (PBS).
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
32
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
33 All identified elements contains set of protein domains as defined in
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
34 REXdb_.Based on the results of detection of structural features,
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
35 elements falls into five categories:
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
36
7
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
37 - elements with domains, 5'LTR, 3'LTR, TSD and PBS - rank DLTP
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
38 - elements with domains, 5'LTR, 3'LTR and PBS (TSD was not found) rank DLP
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
39 - elements with domains, 5' LTR, 3'LTR, TSD (PBS was not found) - rank DTL
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
40 - elements with protein domains, 5'LTR and 3'LTR (PBS and LDS were not found) - rank DL
c33d6583e548 "planemo upload commit 50884f7f0269a0bbde078f24fe5020975693bcd9"
petr-novak
parents: 6
diff changeset
41 - elements as cluster of proteins domains with same classification, no LTRs - rank D
0
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
42
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
43 .. _REXdb: https://doi.org/10.1186/s13100-018-0144-1
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
44
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
45 ]]></help>
7b0bbe7477c4 "planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
petr-novak
parents:
diff changeset
46 </tool>