annotate sickle.xml @ 3:8d697edc2f55

Uploaded
author nilesh
date Wed, 10 Jul 2013 00:16:36 -0400
parents
children 98e35d7ce5c9
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
3
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
1 <tool id="sickle" name="Sickle">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
2 <description>Windowed Adaptive Trimming of FastQ data</description>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
3 <requirements>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
4 <requirement type="package" version="1.2.8">zlib</requirement>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
5 <requirement type="package" version="1.2.8">sickle</requirement>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
6 </requirements>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
7 <command>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
8 sickle $readtype.single_or_paired --quiet
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
9
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
10 #if str($readtype.single_or_paired) == "se":
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
11 -f $input_single -t $qual_type -o $output_single
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
12 #end if
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
13
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
14 #if str($readtype.single_or_paired) == "pe":
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
15 -f $input_paired1 -r $input_paired2 -o $output_paired1 -p $output_paired2 -s $output_paired_single -t $qual_type
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
16 #end if
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
17
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
18 #if str($qual_threshold) != "":
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
19 -q $qual_threshold
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
20 #end if
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
21
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
22 #if str($length_threshold) != "":
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
23 -l $length_threshold
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
24 #end if
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
25
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
26 #if $no_five_prime:
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
27 -x
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
28 #end if
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
29
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
30 #if $discard_n:
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
31 -n
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
32 #end if
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
33 </command>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
34
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
35 <inputs>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
36 <conditional name="readtype">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
37 <param name="single_or_paired" type="select" optional="false" label="Single-End or Paired-End reads?">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
38 <option value="se" selected="true">Single-End</option>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
39 <option value="pe">Paired-End</option>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
40 </param>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
41
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
42 <when value="se">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
43 <param format="fastq, fastqsanger" name="input_single" type="data" optional="false" label="Single-End FastQ Reads"/>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
44 </when>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
45
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
46 <when value="pe">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
47 <param format="fastq, fastqsanger" name="input_paired1" type="data" optional="false" label="Paired-End Forward Strand FastQ Reads"/>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
48 <param format="fastq, fastqsanger" name="input_paired2" type="data" optional="false" label="Paired-End Reverse Strand FastQ Reads"/>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
49 </when>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
50 </conditional>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
51
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
52 <param name="qual_type" type="select" optional="false" label="Quality type">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
53 <option value="illumina" selected="true">Illumina</option>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
54 <option value="solexa">Solexa</option>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
55 <option value="sanger">Sanger</option>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
56 </param>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
57
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
58 <param name="qual_threshold" value="20" type="integer" optional="true" label="Quality Threshold">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
59 <validator type="in_range" min="0" message="Minimum value is 0"/>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
60 </param>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
61
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
62 <param name="length_threshold" value="20" type="integer" optional="true" label="Length Threshold">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
63 <validator type="in_range" min="0" message="Minimum value is 0"/>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
64 </param>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
65
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
66 <param name="no_five_prime" type="boolean" label="Don't do 5' trimming"/>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
67 <param name="discard_n" type="boolean" label="Discard sequences with Ns"/>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
68 </inputs>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
69
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
70 <outputs>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
71 <data format_source="input_single" name="output_single" label="Single-End output of ${tool.name} on ${on_string}">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
72 <filter>(readtype['single_or_paired'] == 'se')</filter>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
73 </data>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
74
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
75 <data format_source="input_paired1" name="output_paired1" label="Paired-End forward strand output of ${tool.name} on ${on_string}">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
76 <filter>(readtype['single_or_paired'] == 'pe')</filter>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
77 </data>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
78
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
79 <data format_source="input_paired2" name="output_paired2" label="Paired-End reverse strand output of ${tool.name} on ${on_string}">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
80 <filter>(readtype['single_or_paired'] == 'pe')</filter>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
81 </data>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
82
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
83 <data format_source="input_paired1" name="output_paired_single" label="Singletons from Paired-End output of ${tool.name} on ${on_string}">
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
84 <filter>(readtype['single_or_paired'] == 'pe')</filter>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
85 </data>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
86 </outputs>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
87
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
88 <help>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
89 Most modern sequencing technologies produce reads that have deteriorating quality towards the 3'-end and some towards the 5'-end as well. Incorrectly called bases in both regions negatively impact assembles, mapping, and downstream bioinformatics analyses.
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
90
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
91 Sickle is a tool that uses sliding windows along with quality and length thresholds to determine when quality is sufficiently low to trim the 3'-end of reads and also determines when the quality is sufficiently high enough to trim the 5'-end of reads. It will also discard reads based upon the length threshold. It takes the quality values and slides a window across them whose length is 0.1 times the length of the read. If this length is less than 1, then the window is set to be equal to the length of the read. Otherwise, the window slides along the quality values until the average quality in the window rises above the threshold, at which point the algorithm determines where within the window the rise occurs and cuts the read and quality there for the 5'-end cut. Then when the average quality in the window drops below the threshold, the algorithm determines where in the window the drop occurs and cuts both the read and quality strings there for the 3'-end cut. However, if the length of the remaining sequence is less than the minimum length threshold, then the read is discarded entirely. 5'-end trimming can be disabled.
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
92
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
93 Sickle also has an option to discard reads with any Ns in them.
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
94
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
95 Sickle supports three types of quality values: Illumina, Solexa, and Sanger. Note that the Solexa quality setting is an approximation (the actual conversion is a non-linear transformation). The end approximation is close. Illumina quality refers to qualities encoded with the CASAVA pipeline between versions 1.3 and 1.7. Illumina quality using CASAVA >= 1.8 is Sanger encoded.
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
96
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
97 Note that Sickle will remove the 2nd fastq record header (on the "+" line) and replace it with simply a "+". This is the default format for CASAVA >= 1.8.
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
98
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
99 Sickle also supports gzipped file inputs.
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
100 </help>
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
101
8d697edc2f55 Uploaded
nilesh
parents:
diff changeset
102 </tool>