annotate sickle.xml @ 0:8656a7c1d6c4 draft

Uploaded
author amol
date Thu, 27 Jun 2013 10:57:16 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
1 <tool id="sickle" name="Sickle">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
2 <description>Windowed Adaptive Trimming of FastQ data</description>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
3 <requirements>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
4 <requirement type="package" version="123">sickle</requirement>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
5 </requirements>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
6 <command>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
7 /Users/amol/Desktop/galaxy-galaxy-dist-cea3ddf6cdda/tools/mytools/sickle $readtype.single_or_paired --quiet
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
8
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
9 #if str($readtype.single_or_paired) == "se":
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
10 -f $input_single -t $qual_type -o $output_single
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
11 #end if
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
12
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
13 #if str($readtype.single_or_paired) == "pe":
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
14 -f $input_paired1 -r $input_paired2 -o $output_paired1 -p $output_paired2 -s $output_paired_single -t $qual_type
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
15 #end if
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
16
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
17 #if str($qual_threshold) != "":
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
18 -q $qual_threshold
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
19 #end if
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
20
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
21 #if str($length_threshold) != "":
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
22 -l $length_threshold
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
23 #end if
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
24
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
25 #if $no_five_prime:
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
26 -x
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
27 #end if
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
28
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
29 #if $discard_n:
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
30 -n
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
31 #end if
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
32 </command>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
33
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
34 <inputs>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
35 <conditional name="readtype">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
36 <param name="single_or_paired" type="select" optional="false" label="Single-End or Paired-End reads?">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
37 <option value="se" selected="true">Single-End</option>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
38 <option value="pe">Paired-End</option>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
39 </param>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
40
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
41 <when value="se">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
42 <param format="fastq, fastqsanger" name="input_single" type="data" optional="false" label="Single-End FastQ Reads"/>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
43 </when>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
44
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
45 <when value="pe">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
46 <param format="fastq, fastqsanger" name="input_paired1" type="data" optional="false" label="Paired-End Forward Strand FastQ Reads"/>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
47 <param format="fastq, fastqsanger" name="input_paired2" type="data" optional="false" label="Paired-End Reverse Strand FastQ Reads"/>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
48 </when>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
49 </conditional>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
50
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
51 <param name="qual_type" type="select" optional="false" label="Quality type">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
52 <option value="illumina" selected="true">Illumina</option>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
53 <option value="solexa">Solexa</option>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
54 <option value="sanger">Sanger</option>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
55 </param>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
56
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
57 <param name="qual_threshold" value="20" type="integer" optional="true" label="Quality Threshold">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
58 <validator type="in_range" min="0" message="Minimum value is 0"/>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
59 </param>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
60
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
61 <param name="length_threshold" value="20" type="integer" optional="true" label="Length Threshold">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
62 <validator type="in_range" min="0" message="Minimum value is 0"/>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
63 </param>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
64
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
65 <param name="no_five_prime" type="boolean" label="Don't do 5' trimming"/>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
66 <param name="discard_n" type="boolean" label="Discard sequences with Ns"/>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
67 </inputs>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
68
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
69 <outputs>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
70 <data format_source="input_single" name="output_single" label="Single-End output of ${tool.name} on ${on_string}">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
71 <filter>(readtype['single_or_paired'] == 'se')</filter>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
72 </data>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
73
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
74 <data format_source="input_paired1" name="output_paired1" label="Paired-End forward strand output of ${tool.name} on ${on_string}">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
75 <filter>(readtype['single_or_paired'] == 'pe')</filter>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
76 </data>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
77
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
78 <data format_source="input_paired2" name="output_paired2" label="Paired-End reverse strand output of ${tool.name} on ${on_string}">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
79 <filter>(readtype['single_or_paired'] == 'pe')</filter>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
80 </data>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
81
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
82 <data format_source="input_paired1" name="output_paired_single" label="Singletons from Paired-End output of ${tool.name} on ${on_string}">
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
83 <filter>(readtype['single_or_paired'] == 'pe')</filter>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
84 </data>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
85 </outputs>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
86
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
87 <help>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
88 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.
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
89
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
90 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.
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
91
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
92 Sickle also has an option to discard reads with any Ns in them.
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
93
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
94 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.
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
95
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
96 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.
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
97
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
98 Sickle also supports gzipped file inputs.
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
99 </help>
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
100
8656a7c1d6c4 Uploaded
amol
parents:
diff changeset
101 </tool>