0
|
1 <tool id="iuc_pear" name="Pear" version="0.9.6.0">
|
|
2 <description>Paired-End read merger</description>
|
|
3 <!--<version_command>bismark version</version_command>-->
|
|
4 <requirements>
|
|
5 <requirement type="package" version="0.9.6">pear</requirement>
|
|
6 </requirements>
|
|
7 <stdio>
|
|
8 <exit_code range="1:" />
|
|
9 <exit_code range=":-1" />
|
|
10 <regex match="Error:" />
|
|
11 <regex match="Exception:" />
|
|
12 </stdio>
|
|
13 <command>
|
|
14 <![CDATA[
|
|
15 pear
|
|
16 #if str( $library.type ) == "paired":
|
|
17 -f "$library.forward"
|
|
18 -r "$library.reverse"
|
|
19 #else
|
|
20 ## prepare collection
|
|
21 -f $library.input_collection.forward
|
|
22 -r $library.input_collection.reverse
|
|
23 #end if
|
|
24
|
|
25 --output pear
|
|
26 --p-value $pvalue
|
|
27 --min-overlap $min_overlap
|
|
28 #if int($max_assembly_length) > 0:
|
|
29 --max-asm-length $max_assembly_length
|
|
30 #end if
|
|
31 --min-asm-length $min_assembly_length
|
|
32 --min-trim-length $min_trim_length
|
|
33 --quality-theshold $quality_threshold
|
|
34 --max-uncalled-base $max_uncalled_base
|
|
35 --test-method $test_method
|
|
36 --empirical-freqs $empirical_freqs
|
|
37 -j "\${GALAXY_SLOTS:-8}"
|
|
38 --score-method $score_method
|
|
39 --cap $cap
|
|
40 $nbase
|
|
41 ]]>
|
|
42 </command>
|
|
43 <inputs>
|
|
44 <conditional name="library">
|
|
45 <param name="type" type="select" label="Dataset type">
|
|
46 <option value="paired">Paired-end</option>
|
|
47 <option value="paired_collection">Paired-end Dataset Collection</option>
|
|
48 </param>
|
|
49 <when value="paired">
|
|
50 <param name="forward" type="data" format="fastqillumina, fastqsanger, fastq"
|
|
51 label="Name of file that contains the forward paired-end reads" help="-f" />
|
|
52 <param name="reverse" type="data" format="fastqillumina, fastqsanger, fastq"
|
|
53 label="Name of file that contains the reverse paired-end reads" help="-r" />
|
|
54 </when>
|
|
55 <when value="paired_collection">
|
|
56 <param name="input_collection" format="fastqillumina, fastqsanger, fastq"
|
|
57 type="data_collection" collection_type="paired"
|
|
58 label="FASTQ Paired Dataset" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33. (-f and -r)" />
|
|
59 </when>
|
|
60 </conditional>
|
|
61
|
|
62 <!-- optional -->
|
|
63 <param name="pvalue" type="float" value="0.01" min="0" optional="True" max="1" label="Specify a p-value for the statistical test"
|
|
64 help="If the computed p-value of a possible assembly exceeds the specified p-value then the paired-end read will not be assembled. Setting 1.0 disables the test. (--p-value)" />
|
|
65
|
|
66 <param name="min_overlap" type="integer" value="10" optional="True" label="Minimum overlap size"
|
|
67 help="The minimum overlap may be set to 1 when the statistical test is used. However, further restricting the minimum overlap size to a proper value may reduce false-positive assembles. (--min-overlap)" />
|
|
68
|
|
69 <param name="max_assembly_length" type="integer" value="0" optional="True" label="Maximum possible length of the assembled sequences"
|
|
70 help="Setting this value to 0 disables the restriction and assembled sequences may be arbitrary long. (--max-assembly-length)" />
|
|
71
|
|
72 <param name="min_assembly_length" type="integer" value="50" optional="True" label="Minimum possible length of the assembled sequences"
|
|
73 help="Setting this value to 0 disables the restriction and assembled sequences may be arbitrary short. (--min-assembly-length)" />
|
|
74
|
|
75 <param name="min_trim_length" type="integer" value="1" optional="True" label="Minimum length of reads after trimming the low quality part"
|
|
76 help="See option -q. (--min-trim-length)" />
|
|
77
|
|
78 <param name="quality_threshold" type="integer" value="0" optional="True" label="Quality score threshold for trimming the low quality part of a read"
|
|
79 help="If the quality scores of two consecutive bases are strictly less than the specified threshold, the rest of the read will be trimmed. (--quality-threshold)" />
|
|
80
|
|
81 <param name="max_uncalled_base" type="float" value="1.0" min="0" optional="True" max="1" label="Maximal proportion of uncalled bases in a read"
|
|
82 help="Setting this value to 0 will cause PEAR to discard all reads containing uncalled bases. The other extreme setting is 1 which causes PEAR to process all reads independent on the number of uncalled bases. (--max-uncalled-base)" />
|
|
83
|
|
84 <param name="cap" type="integer" value="40" optional="True" label="Specify the upper bound for the resulting quality score"
|
|
85 help="If set to zero, capping is disabled. (--cap)" />
|
|
86
|
|
87 <param name="test_method" type="select" label="Type of statistical test" help="(--test-method)">
|
|
88 <option value="1" selected="True">Given the minimum allowed overlap, test using the highest OES (1)</option>
|
|
89 <option value="2">Use the acceptance probability (2)</option>
|
|
90 </param>
|
|
91
|
|
92 <param name="empirical_freqs" type="boolean" truevalue="-e" falsevalue="" checked="false"
|
|
93 label="Disable empirical base frequencies" help="(--empirical-freqs)" />
|
|
94 <param name="nbase" type="boolean" truevalue="--nbase" falsevalue="" checked="false"
|
|
95 label="Use N base if uncertain" help="When merging a base-pair that consists of two non-equal bases out of which none is degenerate, set the merged base to N and use the highest quality score of the two bases. (--nbase)" />
|
|
96
|
|
97 <param name="score_method" type="select" label="Scoring method" help="(--score-method)">
|
|
98 <option value="1">OES with +1 for match and -1 for mismatch</option>
|
|
99 <option value="2" selected="True">Assembly score (AS) use +1 for match and -1 for mismatch multiplied by base quality scores</option>
|
|
100 <option value="3">Ignore quality scores and use +1 for a match and -1 for a mismatch</option>
|
|
101 </param>
|
|
102
|
|
103 <param name="outputs" type="select" display="checkboxes" optional="False" multiple="True" label="Output files">
|
|
104 <option value="assembled" selected="True">Assembled reads</option>
|
|
105 <option value="forward">Forward unassembled reads</option>
|
|
106 <option value="reverse">Reverse unassembled reads</option>
|
|
107 <option value="discarded">Discarded reads</option>
|
|
108 </param>
|
|
109 </inputs>
|
|
110 <outputs>
|
|
111 <data format="fastq" name="assembled_reads" from_work_dir="pear.assembled.fastq" label="${tool.name} on ${on_string}: Assembled reads">
|
|
112 <filter>'assembled' in outputs</filter>
|
|
113 </data>
|
|
114 <data format="fastq" name="unassembled_forward_reads" from_work_dir="pear.unassembled.forward.fastq" label="${tool.name} on ${on_string}: Unassembled forward reads">
|
|
115 <filter>'forward' in outputs</filter>
|
|
116 </data>
|
|
117 <data format="fastq" name="unassembled_reverse_reads" from_work_dir="pear.unassembled.reverse.fastq" label="${tool.name} on ${on_string}: Unassembled reverse reads">
|
|
118 <filter>'reverse' in outputs</filter>
|
|
119 </data>
|
|
120 <data format="fastq" name="discarded_reads" from_work_dir="pear.discarded.fastq" label="${tool.name} on ${on_string}: Discarded reads">
|
|
121 <filter>'discarded' in outputs</filter>
|
|
122 </data>
|
|
123 </outputs>
|
|
124 <tests>
|
|
125 <test>
|
|
126 <param name="forward" value="forward.fastq" ftype="fastq" />
|
|
127 <param name="reverse" value="reverse.fastq" ftype="fastq" />
|
|
128 <param name="min_overlap" value="10" />
|
|
129 <param name="min_assembly_length" value="50" />
|
|
130 <param name="cap" value="0" />
|
|
131 <param name="outputs" value="assembled,forward" />
|
|
132 <output name="assembled_reads" file="pear_assembled_results1.fastq" ftype="fastq"/>
|
|
133 <output name="unassembled_forward_reads" file="pear_unassembled_forward_results1.fastq" ftype="fastq"/>
|
|
134 </test>
|
|
135 </tests>
|
|
136 <help>
|
|
137 <![CDATA[
|
|
138
|
|
139
|
|
140 **What it does**
|
|
141
|
|
142 PEAR_ is an ultrafast, memory-efficient and highly accurate pair-end read merger.
|
|
143 PEAR evaluates all possible paired-end read overlaps and without requiring the target fragment
|
|
144 size as input. In addition, it implements a statistical test for minimizing false-positive results.
|
|
145 Together with a highly optimized implementation, it can merge millions of paired end reads within a couple of minutes
|
|
146 on a standard desktop computer.
|
|
147
|
|
148 For more information please look at the documentation_ and `github repository`_.
|
|
149
|
|
150 .. _PEAR: http://sco.h-its.org/exelixis/web/software/pear/
|
|
151 .. _documentation: http://sco.h-its.org/exelixis/web/software/pear/doc.html
|
|
152 .. _github repository: https://github.com/xflouris/PEAR
|
|
153
|
|
154
|
|
155 ]]>
|
|
156 </help>
|
|
157 <citations>
|
|
158 <citation type="doi">10.1093/bioinformatics/btt593</citation>
|
|
159 </citations>
|
|
160 </tool>
|