Mercurial > repos > iuc > dada2_primercheck

comparison dada2_primercheck.xml @ 0:40cd037434d9 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 3dd3145db6ed58efc3bf5f71e96515173967fc72
author iuc
date Sat, 07 Dec 2024 08:41:16 +0000
parents
children c7d45735c578
comparison
equal deleted inserted replaced
-1:000000000000 0:40cd037434d9
1 <tool id="dada2_primerCheck" name="dada2: primer check" version="@DADA2_VERSION@+galaxy@WRAPPER_VERSION@" profile="19.09">
2 <description></description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="bio_tools"/>
7 <expand macro="requirements"/>
8 <expand macro="stdio"/>
9 <expand macro="version_command"/>
10 <command detect_errors="exit_code"><![CDATA[
11 Rscript '$dada2_script'
12 ]]></command>
13 <configfiles>
14 <configfile name="dada2_script"><![CDATA[
15 #import re
16 library(Biostrings, quietly=T)
17 library(ShortRead, quietly=T)
18
19 FWD <- "$forward_primer"
20 REV <- "$reverse_primer"
21
22 allOrients <- function(primer) {
23 # Create all orientations of the input sequence
24 dna <- DNAString(primer) # The Biostrings works w/ DNAString objects rather than character vectors
25 orients <- c(Forward = dna, Complement = Biostrings::complement(dna), Reverse = Biostrings::reverse(dna), RevComp = Biostrings::reverseComplement(dna))
26 return(sapply(orients, toString)) # Convert back to character vector
27 }
28 FWD.orients <- allOrients(FWD)
29 REV.orients <- allOrients(REV)
30
31 primerHits <- function(primer, fn) {
32 ## Counts number of reads in which the primer is found
33 nhits <- vcountPattern(primer, sread(readFastq(fn)), fixed = FALSE)
34 return(sum(nhits > 0))
35 }
36
37 df <- NULL;
38 #for $i, $read in enumerate($paired_cond.reads):
39 #set elid = re.sub('[^\w\-\.]', '_', str($read.element_identifier))
40 #if $paired_cond.paired_select == "single"
41 #set fwd_reads = $read
42 #elif $paired_cond.paired_select == "separate"
43 #set fwd_reads = $read
44 #set rev_reads = $paired_cond.sdaer[i]
45 #else
46 #set fwd_reads = $read.forward
47 #set rev_reads = $read.reverse
48 #end if
49 df <- rbind(df, c('$elid', 'FWD', 'FWD', sapply(FWD.orients, primerHits, fn = '$fwd_reads')))
50 df <- rbind(df, c('$elid', 'REV', 'FWD', sapply(REV.orients, primerHits, fn = '$fwd_reads')))
51 #if $paired_cond.paired_select != "single"
52 #if $paired_cond.paired_select == "separate"
53 #set elid = re.sub('[^\w\-\.]', '_', str($paired_cond.sdaer[i].element_identifier))
54 #end if
55 df <- rbind(df, c('$elid', 'FWD', 'REV', sapply(FWD.orients, primerHits, fn = '$rev_reads')))
56 df <- rbind(df, c('$elid', 'REV', 'REV', sapply(REV.orients, primerHits, fn = '$rev_reads')))
57 #end if
58 #end for
59 colnames(df) <- c('Sample', 'Primer', 'ReadDir', 'Sequence', 'Complement', 'Reverse', 'RevComp')
60 write.table(df, "$out", quote=F, sep="\t", row.names = F, col.names = T)
61 ]]></configfile>
62 </configfiles>
63 <inputs>
64 <expand macro="fastq_input" multiple="True" collection_type="list:paired" argument_fwd="fl" argument_rev="fl"/>
65 <param name="forward_primer" type="text" label="Forward primer sequence">
66 <validator type="empty_field" message="You need to specify a forward primer sequence"/>
67 </param>
68 <param name="reverse_primer" type="text" label="Reverse primer sequence">
69 <validator type="empty_field" message="You need to specify a reverse primer sequence"/>
70 </param>
71 </inputs>
72 <outputs>
73 <data name="out" format="tabular"/>
74 </outputs>
75 <tests>
76 <!-- paired data in paired collection -->
77 <test expect_num_outputs="1">
78 <conditional name="paired_cond">
79 <param name="paired_select" value="paired"/>
80 <param name="reads">
81 <collection type="list:paired">
82 <element name="F3D0_S188_L001">
83 <collection type="paired">
84 <element name="forward" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
85 <element name="reverse" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
86 </collection>
87 </element>
88 <element name="F3D141_S207_L001">
89 <collection type="paired">
90 <element name="forward" value="F3D141_S207_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
91 <element name="reverse" value="F3D141_S207_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
92 </collection>
93 </element>
94 </collection>
95 </param>
96 </conditional>
97
98 <param name="forward_primer" value="ACCTGCGGARGGATCA"/>
99 <param name="reverse_primer" value="GAGATCCRTTGYTRAAAGTT"/>
100 <output name="out">
101 <assert_contents>
102 <has_n_lines n="9"/>
103 <has_n_columns n="7"/>
104 </assert_contents>
105 </output>
106 </test>
107 <!-- paired data in separate collection -->
108 <test expect_num_outputs="1">
109 <conditional name="paired_cond">
110 <param name="paired_select" value="separate"/>
111 <param name="reads" value="F3D0_S188_L001_R1_001.fastq.gz,F3D141_S207_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
112 <param name="sdaer" value="F3D0_S188_L001_R2_001.fastq.gz,F3D141_S207_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
113 </conditional>
114
115 <param name="forward_primer" value="ACCTGCGGARGGATCA"/>
116 <param name="reverse_primer" value="GAGATCCRTTGYTRAAAGTT"/>
117 <output name="out">
118 <assert_contents>
119 <has_n_lines n="9"/>
120 <has_n_columns n="7"/>
121 </assert_contents>
122 </output>
123 </test>
124 <!-- single end data -->
125 <test expect_num_outputs="1">
126 <conditional name="paired_cond">
127 <param name="paired_select" value="single"/>
128 <param name="reads" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
129 </conditional>
130 <param name="forward_primer" value="ACCTGCGGARGGATCA"/>
131 <param name="reverse_primer" value="GAGATCCRTTGYTRAAAGTT"/>
132 <output name="out">
133 <assert_contents>
134 <has_n_lines n="3"/>
135 <has_n_columns n="7"/>
136 </assert_contents>
137 </output>
138 </test>
139 </tests>
140
141 <help><![CDATA[
142 Description
143 ...........
144
145 Simple check for primer sequences in sequencing data. The tool counts the number
146 of occurrences of the primer sequence, its complement, the reverse and the
147 reverse complement.
148
149 See also: https://benjjneb.github.io/dada2/ITS_workflow.html#identify-primers
150
151 Usage
152 .....
153
154 **Input** FASTQ datasets and forward and reverse primers
155
156 **Output** a table listing the counts of the different occurrences in the read files.
157
158
159 @HELP_OVERVIEW@
160 ]]></help>
161 <expand macro="citations"/>
162 </tool>