17
|
1 <tool id="plot_comparative" name="Visualization of comparative clustering" version="1.0.0">
|
|
2 <description> Simple utility to create visualization of RepeatExplorer conmparative analysis</description>
|
|
3 <requirements>
|
|
4 <requirement type="package">r-optparse</requirement>
|
|
5 </requirements>
|
|
6
|
|
7 <command interpreter="Rscript" detect_errors="exit_code" >
|
|
8 $__tool_directory__/plot_comparative_clustering_summary.R
|
|
9 --cluster_table=$cluster_table
|
|
10 --comparative_counts=$counts
|
|
11 --number_of_colors=$number_of_colors
|
|
12 --output=$outpdf
|
|
13 $nuclear_only
|
|
14
|
|
15 #if $normalization.use_genome_size:
|
|
16 --genome_size $normalization.genome_size_table
|
|
17 #end if
|
|
18 </command>
|
|
19
|
|
20 <inputs>
|
|
21 <param format="txt" type="data" name="cluster_table" label="file from RepeatExplorer2 clustering - CLUSTER_TABLE.csv"/>
|
|
22 <param format="txt" type="data" name="counts" label="file from RepeatExplorer2 output - COMPARATIVE_ANALYSIS_COUNTS.csv"/>
|
|
23 <param value="10" min="2" max="20" type="integer" name="number_of_colors" label="Maximum number of color used for plottting"/>
|
|
24 <param value="false" type="boolean" truevalue="--nuclear_only" falsevalue="" name="nuclear_only" label="Remove all non-nuclear sequences (organel and contamination)"/>
|
|
25 <conditional name="normalization">
|
|
26 <param name="use_genome_size" type="boolean" checked="False" label="Normalize to genome size" help="Note that if this option is used, non-nuclear sequences are always removed."/>
|
|
27 <when value="false">
|
|
28 <!-- pass -->
|
|
29 </when>
|
|
30 <when value="true">
|
|
31 <param name="genome_size_table" type="data" format="txt" label="table with genome sizes"/>
|
|
32
|
|
33 </when>
|
|
34
|
|
35 </conditional>
|
|
36 </inputs>
|
|
37
|
|
38 <outputs>
|
|
39 <data format="pdf" name="outpdf" label="Comparative analysis summary"/>
|
|
40 </outputs>
|
|
41 <help>
|
|
42 **Visualization of comparative clustering**
|
|
43 Visualization can be created two output files from RepeatExplorer pipeline.
|
|
44
|
|
45 Input file CLUSTER_TABLE.csv contains automatic annotation, information about cluster sizes and the total number of reads used for analysis
|
|
46 Example of CLUSTER_TABLE.csv: ::
|
|
47
|
|
48 "Number_of_reads_in_clusters" 3002
|
|
49 "Number_of_clusters" 895
|
|
50 "Number_of_superclusters" 895
|
|
51 "Number_of_singlets" 6998
|
|
52
|
|
53 "Number_of_analyzed_reads" 10000
|
|
54
|
|
55 "Cluster" "Supercluster" "Size" "Size_adjusted" "Automatic_annotation" "TAREAN_classification" "Final_annotation"
|
|
56 1 1 61 61 "All" "Other"
|
|
57 2 2 59 59 "All/repeat/satellite" "Putative satellites (high confidence)"
|
|
58 3 3 45 45 "All/repeat/satellite" "Putative satellites (low confidence)"
|
|
59 4 4 38 38 "All" "Other"
|
|
60 5 5 32 32 "All" "Other"
|
|
61 6 6 28 28 "All" "Other"
|
|
62 7 7 25 25 "All" "Other"
|
|
63 8 8 24 24 "All" "Other"
|
|
64 9 9 23 23 "All" "Other"
|
|
65 10 10 22 22 "All/repeat/mobile_element/Class_I/LTR/Ty3_gypsy/non-chromovirus/OTA/Tat/Ogre" "Other"
|
|
66 11 11 20 20 "All" "Other"
|
|
67 12 12 20 20 "All" "Other"
|
|
68
|
|
69
|
|
70 </help>
|
|
71 </tool>
|