annotate tools/primers/seq_primer_clip.xml @ 3:f9ddb43ce28d draft

Uploaded v0.0.10a, fixes Biopython dependency setup
author peterjc
date Fri, 13 Sep 2013 06:09:54 -0400
parents bd151574bbf3
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
bd151574bbf3 Uploaded v0.0.10, README.rst, MIT licence, biopython dependency
peterjc
parents: 1
diff changeset
1 <tool id="seq_primer_clip" name="Primer clip sequences" version="0.0.10">
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
2 <description>Trim off 5' or 3' primers</description>
2
bd151574bbf3 Uploaded v0.0.10, README.rst, MIT licence, biopython dependency
peterjc
parents: 1
diff changeset
3 <requirements>
3
f9ddb43ce28d Uploaded v0.0.10a, fixes Biopython dependency setup
peterjc
parents: 2
diff changeset
4 <requirement type="package" version="1.61">biopython</requirement>
2
bd151574bbf3 Uploaded v0.0.10, README.rst, MIT licence, biopython dependency
peterjc
parents: 1
diff changeset
5 <requirement type="python-module">Bio</requirement>
bd151574bbf3 Uploaded v0.0.10, README.rst, MIT licence, biopython dependency
peterjc
parents: 1
diff changeset
6 </requirements>
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
7 <version_command interpreter="python">seq_primer_clip.py --version</version_command>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
8 <command interpreter="python">
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
9 seq_primer_clip.py $input_file $input_file.ext $primer_fasta $primer_type $mm $min_len $keep_negatives $output_file
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
10 </command>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
11 <stdio>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
12 <!-- Anything other than zero is an error -->
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
13 <exit_code range="1:" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
14 <exit_code range=":-1" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
15 </stdio>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
16 <inputs>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
17 <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file to clip" description="FASTA, FASTQ, or SFF format."/>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
18 <param name="primer_fasta" type="data" format="fasta" label="FASTA file containing primer(s)"/>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
19 <param name="primer_type" type="select" label="Type of primers">
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
20 <option value="Forward">Forward (5') primers</option>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
21 <option value="Reverse">Reverse (3') primers (given with respect to the forward strand)</option>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
22 <option value="Reverse-complement">Reverse (3') primers (given with respect to the reverse strand)</option>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
23 </param>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
24 <param name="mm" type="integer" value="0" label="How many mismatches to allow? (0, 1 or 2)">
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
25 <validator type="in_range" min="0" max="2" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
26 </param>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
27 <param name="keep_negatives" type="boolean" value="false" label="Keep reads with no matched primer"/>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
28 <param name="min_len" type="integer" label="Minimum length for (clipped) sequences " value="1"/>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
29 </inputs>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
30 <outputs>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
31 <data name="output_file" format="data" label="$primer_type primer clipped">
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
32 <!-- TODO - Replace this with format="input:input_fastq" if/when that works -->
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
33 <change_format>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
34 <when input_dataset="input_file" attribute="extension" value="sff" format="sff" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
35 <when input_dataset="input_file" attribute="extension" value="fasta" format="fasta" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
36 <when input_dataset="input_file" attribute="extension" value="fastq" format="fastq" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
37 <when input_dataset="input_file" attribute="extension" value="fastqsanger" format="fastqsanger" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
38 <when input_dataset="input_file" attribute="extension" value="fastqsolexa" format="fastqsolexa" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
39 <when input_dataset="input_file" attribute="extension" value="fastqillumina" format="fastqillumina" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
40 <when input_dataset="input_file" attribute="extension" value="fastqcssanger" format="fastqcssanger" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
41 </change_format>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
42 </data>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
43 </outputs>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
44 <tests>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
45 <test>
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
46 <param name="input_file" value="MID4_GLZRM4E04_rnd30.fasta" ftype="fasta" />
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
47 <param name="primer_fasta" value="dop_primers.fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
48 <param name="primer_type" value="Forward" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
49 <param name="mm" value="2" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
50 <param name="keep_negatives" value="false" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
51 <param name="min_len" value="35" />
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
52 <output name="output_file" file="MID4_GLZRM4E04_rnd30_fclip.fasta" ftype="fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
53 </test>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
54 <test>
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
55 <param name="input_file" value="MID4_GLZRM4E04_rnd30.fastqsanger" ftype="fastqsanger" />
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
56 <param name="primer_fasta" value="dop_primers.fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
57 <param name="primer_type" value="Forward" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
58 <param name="mm" value="2" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
59 <param name="keep_negatives" value="false" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
60 <param name="min_len" value="35" />
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
61 <output name="output_file" file="MID4_GLZRM4E04_rnd30_fclip.fastqsanger" ftype="fastqsanger" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
62 </test>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
63 <test>
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
64 <param name="input_file" value="MID4_GLZRM4E04_rnd30.sff" ftype="sff" />
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
65 <param name="primer_fasta" value="dop_primers.fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
66 <param name="primer_type" value="Forward" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
67 <param name="mm" value="2" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
68 <param name="keep_negatives" value="false" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
69 <param name="min_len" value="35" />
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
70 <output name="output_file" file="MID4_GLZRM4E04_rnd30_fclip.sff" ftype="sff" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
71 </test>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
72 <test>
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
73 <param name="input_file" value="MID4_GLZRM4E04_rnd30_fclip.fasta" ftype="fasta" />
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
74 <param name="primer_fasta" value="dop_primers.fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
75 <param name="primer_type" value="Reverse" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
76 <param name="mm" value="2" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
77 <param name="keep_negatives" value="true" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
78 <param name="min_len" value="35" />
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
79 <output name="output_file" file="MID4_GLZRM4E04_rnd30_frclip.fasta" ftype="fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
80 </test>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
81 <test>
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
82 <param name="input_file" value="MID4_GLZRM4E04_rnd30_fclip.fastqsanger" ftype="fastqsanger" />
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
83 <param name="primer_fasta" value="dop_primers.fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
84 <param name="primer_type" value="Reverse" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
85 <param name="mm" value="2" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
86 <param name="keep_negatives" value="true" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
87 <param name="min_len" value="35" />
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
88 <output name="output_file" file="MID4_GLZRM4E04_rnd30_frclip.fastqsanger" ftype="fastqsanger" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
89 </test>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
90 <test>
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
91 <param name="input_file" value="MID4_GLZRM4E04_rnd30_fclip.sff" ftype="sff" />
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
92 <param name="primer_fasta" value="dop_primers.fasta" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
93 <param name="primer_type" value="Reverse" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
94 <param name="mm" value="2" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
95 <param name="keep_negatives" value="true" />
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
96 <param name="min_len" value="35" />
1
06e6112091aa Uploaded v0.0.9, modifies tests to cope with current Tool Shed limitation.
peterjc
parents: 0
diff changeset
97 <output name="output_file" file="MID4_GLZRM4E04_rnd30_frclip.sff" ftype="sff" />
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
98 </test>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
99 </tests>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
100 <requirements>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
101 <requirement type="python-module">Bio</requirement>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
102 </requirements>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
103 <help>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
104
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
105 **What it does**
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
106
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
107 Looks for the given primer sequences (within the existing clipped sequence) and
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
108 further clips the reads to remove the primers and any preceding/trailing sequence.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
109
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
110 Reads containing a forward primer are reduced to just the sequence after (and
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
111 excluding) the forward primer.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
112
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
113 Reads containing a reverse primer are reduced to just the sequence before (and
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
114 excluding) the reverse primer.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
115
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
116 Degenerate primers can be specified using the standard IUPAC ambiguity codes,
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
117 thus a primer with an N would match A, C, T or G (or any of the IUPAC ambiguity
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
118 codes) and so on.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
119
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
120 Note that for SFF files only the clip/trim positions are edited - you will still
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
121 be able to extract the original full read (with any adapter sequence and poor
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
122 quality sequence) if you need to.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
123
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
124 .. class:: warningmark
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
125
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
126 **Note**. This tool was initially written for Roche 454 data, and should also
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
127 work fine on Sanger or Ion Torrent as well. However, it is probably too slow
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
128 for use on large Illumina datasets.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
129
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
130
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
131 **Citation**
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
132
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
133 This tool uses Biopython. If you use this tool in scientific work leading to a
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
134 publication, please cite:
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
135
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
136 Cock et al 2009. Biopython: freely available Python tools for computational
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
137 molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
138 http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
139
2
bd151574bbf3 Uploaded v0.0.10, README.rst, MIT licence, biopython dependency
peterjc
parents: 1
diff changeset
140 This tool is available to install into other Galaxy Instances via the Galaxy
bd151574bbf3 Uploaded v0.0.10, README.rst, MIT licence, biopython dependency
peterjc
parents: 1
diff changeset
141 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/seq_primer_clip
0
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
142 </help>
b8ca95338e77 Uploaded v0.0.8, first public release.
peterjc
parents:
diff changeset
143 </tool>