Mercurial > repos > iuc > dada2_plotqualityprofile

comparison dada2_plotQualityProfile.xml @ 0:944958061b0f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/dada2 commit f8b6b6e72914ad6bcca8423dfa03f59bde80992e"
author iuc
date Fri, 08 Nov 2019 18:46:40 -0500
parents
children 73c03d6288f1
comparison
equal deleted inserted replaced
-1:000000000000 0:944958061b0f
1 <tool id="dada2_plotQualityProfile" name="dada2: plotQualityProfile" version="@DADA2_VERSION@+galaxy@WRAPPER_VERSION@" profile="19.09">
2 <description>plot a visual summary of the quality scores</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="stdio"/>
8 <expand macro="version_command"/>
9 <command detect_errors="exit_code"><![CDATA[
10 ##name files by linking
11 #import re
12 mkdir forward &&
13 #if $batch_cond.paired_cond.paired_select != "single"
14 mkdir reverse &&
15 #end if
16
17 #if $batch_cond.batch_select == "batch":
18 #set elid = re.sub('[^\w\-\.]', '_', str($batch_cond.paired_cond.reads.element_identifier))
19 #if $batch_cond.paired_cond.paired_select != "paired"
20 ln -s '$batch_cond.paired_cond.reads' forward/'$elid' &&
21 #else
22 ln -s '$batch_cond.paired_cond.reads.forward' forward/'$elid' &&
23 ln -s '$batch_cond.paired_cond.reads.reverse' reverse/'$elid' &&
24 #end if
25 #if $batch_cond.paired_cond.paired_select == "separate"
26 ln -s '$batch_cond.paired_cond.sdaer' reverse/'$elid' &&
27 #end if
28 #else
29 #for $read in $batch_cond.paired_cond.reads:
30 #set elid = re.sub('[^\w\-\.]', '_', str($read.element_identifier))
31 #if $batch_cond.paired_cond.paired_select != "paired"
32 ln -s '$read' forward/'$elid' &&
33 #else
34 ln -s '$read.forward' forward/'$elid' &&
35 ln -s '$read.reverse' reverse/'$elid' &&
36 #end if
37 #end for
38 #if $batch_cond.paired_cond.paired_select == "separate"
39 #for $read in $batch_cond.paired_cond.sdaer:
40 #set elid = re.sub('[^\w\-\.]', '_', str($read.element_identifier))
41 ln -s '$read' reverse/'$elid' &&
42 #end for
43 #end if
44 #end if
45
46 Rscript --slave '$dada2_script'
47 ]]></command>
48 <configfiles>
49 <configfile name="dada2_script"><![CDATA[
50 #import re
51 library(ggplot2, quietly=T)
52 library(dada2, quietly=T)
53
54 #if $batch_cond.batch_select != "batch"
55 agg = $batch_cond.aggregate
56 #else
57 agg = FALSE
58 #end if
59
60 fwd_files = list.files("forward", full.names=T)
61 qp <- plotQualityProfile(fwd_files, n=$n, aggregate = agg)
62 ggsave('output.pdf', qp, width = 20,height = 15,units = c("cm"))
63
64 #if $batch_cond.paired_cond.paired_select != "single"
65 rev_files = list.files("reverse", full.names=T)
66 qp <- plotQualityProfile(rev_files, n=$n, aggregate = agg)
67 ggsave('output_rev.pdf', qp, width = 20,height = 15,units = c("cm"))
68 #end if
69 ]]></configfile>
70 </configfiles>
71 <inputs>
72 <conditional name="batch_cond">
73 <param name="batch_select" type="select" label="Processing mode" help="Joint processing processes all reads at once in a single job creating a single output (two in the case of paired data). Batch processes the samples in separate jobs and creates separate output for each">
74 <option value="joint">Joint</option>
75 <option value="batch">Batch</option>
76 </param>
77 <when value="joint">
78 <expand macro="fastq_input" multiple="True" collection_type="list:paired" argument_fwd="fl" argument_rev="fl"/>
79 <param argument="aggregate" type="boolean" label="Aggregate data" checked="True" truevalue="TRUE" falsevalue="FALSE" help="Create a single plot for all data sets (default) or a separate plot for each data set"/>
80 </when>
81 <when value="batch">
82 <expand macro="fastq_input" multiple="False" collection_type="paired" argument_fwd="fl" argument_rev="fl"/>
83 </when>
84 </conditional>
85 <param argument="n" type="integer" value="500000" label="sample number" help="number of records to sample from the fastq file"/>
86 </inputs>
87 <outputs>
88 <data name="output" format="pdf" from_work_dir="output.pdf">
89 <filter>batch_cond['paired_cond']['paired_select'] == "single"</filter>
90 </data>
91 <data name="output_fwd" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: forward reads">
92 <filter>batch_cond['paired_cond']['paired_select'] != "single"</filter>
93 </data>
94 <data name="output_rev" format="pdf" from_work_dir="output_rev.pdf" label="${tool.name} on ${on_string}: reverse reads">
95 <filter>batch_cond['paired_cond']['paired_select'] != "single"</filter>
96 </data>
97 </outputs>
98 <tests>
99 <!-- all tests are against the same file using a delta that should ensure that the pdf contains a plot -->
100 <!-- paired joint, no-aggregate -->
101 <test expect_num_outputs="2">
102 <param name="batch_cond|batch_select" value="joint"/>
103 <param name="batch_cond|paired_cond|paired_select" value="paired"/>
104 <param name="batch_cond|paired_cond|reads">
105 <collection type="list:paired">
106 <element name="F3D0_S188_L001">
107 <collection type="paired">
108 <element name="forward" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
109 <element name="reverse" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
110 </collection>
111 </element>
112 </collection>
113 </param>
114 <param name="batch_cond|aggregate" value="FALSE"/>
115 <output name="output_fwd" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
116 <output name="output_rev" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
117 </test>
118 <!-- paired-separate joint, no-aggregate (sim_size because element ids differ) -->
119 <test expect_num_outputs="2">
120 <param name="batch_cond|batch_select" value="joint"/>
121 <param name="batch_cond|paired_cond|paired_select" value="separate"/>
122 <param name="batch_cond|paired_cond|reads" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
123 <param name="batch_cond|paired_cond|sdaer" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
124 <param name="batch_cond|aggregate" value="FALSE"/>
125 <output name="output_fwd" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
126 <output name="output_rev" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
127 </test>
128 <!-- single, non-batch, aggregate, small sample -->
129 <test expect_num_outputs="1">
130 <param name="batch_cond|batch_select" value="joint"/>
131 <param name="batch_cond|paired_cond|paired_select" value="single"/>
132 <param name="batch_cond|paired_cond|reads" value="F3D0_S188_L001_R1_001.fastq.gz,F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
133 <param name="n" value="10000"/>
134 <param name="batch_cond|aggregate" value="TRUE"/>
135 <output name="output" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
136 </test>
137
138 <!-- paired, batch -->
139 <test expect_num_outputs="2">
140 <param name="batch_cond|batch_select" value="batch"/>
141 <param name="batch_cond|paired_cond|paired_select" value="paired"/>
142 <param name="batch_cond|paired_cond|reads">
143 <collection type="paired">
144 <element name="forward" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
145 <element name="reverse" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
146 </collection>
147 </param>
148 <output name="output_fwd" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
149 <output name="output_rev" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
150 </test>
151 <!-- paired-separate batch (sim_size because element ids differ)-->
152 <test expect_num_outputs="2">
153 <param name="batch_cond|batch_select" value="batch"/>
154 <param name="batch_cond|paired_cond|paired_select" value="separate"/>
155 <param name="batch_cond|paired_cond|reads" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
156 <param name="batch_cond|paired_cond|sdaer" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
157 <output name="output_fwd" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
158 <output name="output_rev" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
159 </test>
160 <!-- single, batch -->
161 <test expect_num_outputs="1">
162 <param name="batch_cond|batch_select" value="batch"/>
163 <param name="batch_cond|paired_cond|paired_select" value="single"/>
164 <param name="batch_cond|paired_cond|reads" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
165 <param name="n" value="10000"/>
166 <output name="output" value="qualityProfile.pdf" ftype="pdf" compare="sim_size" delta="15000"/>
167 </test>
168 </tests>
169 <help><![CDATA[
170 Summary
171 .......
172
173 This function plots a visual summary of the distribution of quality scores as a function of sequence position for the input fastq datasets.
174
175 Details
176 .......
177
178 The distribution of quality scores at each position is shown as a grey-scale heat map, with dark colors corresponding to higher frequency. The plotted lines show positional summary statistics: green is the mean, orange is the median, and the dashed orange lines are the 25th and 75th quantiles. If the sequences vary in length, a red line will be plotted showing the percentage of reads that extend
179 to at least that position.
180
181 @HELP_OVERVIEW@
182 ]]></help>
183 <expand macro="citations"/>
184 </tool>