|
0
|
1 <tool id="meme_psp_gen" name="MEME psp-gen" version="4.11.2.0">
|
|
|
2 <description>- perform discriminative motif discovery</description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements" />
|
|
|
7 <command detect_errors="exit_code"><![CDATA[
|
|
|
8 psp-gen
|
|
|
9 -pos '$primary_sequence'
|
|
|
10 -neg '$control_sequence'
|
|
|
11 -minw $adv.minw
|
|
|
12 -maxw $adv.maxw
|
|
|
13 $adv.alphabet
|
|
4
|
14 #if $adv.report_scores_cond.report_scores:
|
|
2
|
15 2> '$output_tabular'
|
|
0
|
16 #end if
|
|
2
|
17 > '$output_psp'
|
|
0
|
18 ]]></command>
|
|
|
19 <inputs>
|
|
|
20 <param format="fasta" name="primary_sequence" type="data" label="Primary sequence file"/>
|
|
|
21 <param format="fasta" name="control_sequence" type="data" label="Control sequence file"/>
|
|
|
22 <section name="adv" title="Additional Options">
|
|
|
23 <param name="minw" type="integer" value="4" min="0" label="Minimum width to use for position specific priors"/>
|
|
|
24 <param name="maxw" type="integer" value="20" min="0" label="Maximum width to use for position specific priors"/>
|
|
|
25 <param name="alphabet" type="select" label="Alphabet">
|
|
|
26 <option value="-dna" selected="true">DNA</option>
|
|
|
27 <option value="-protein">protein</option>
|
|
|
28 <option value="-rna">RNA</option>
|
|
|
29 </param>
|
|
|
30 <conditional name="triples_cond">
|
|
4
|
31 <param name="triples" type="boolean" truevalue="-triples" falsevalue="" checked="False" label="Use spaced triples instead of whole-word matches?" help="Recommended for protein"/>
|
|
0
|
32 <when value="no"/>
|
|
|
33 <when value="yes">
|
|
4
|
34 <param name="fixed_start" type="boolean" truevalue="-fixedstart" falsevalue="" checked="False" label="Allow triples to start anywhere within a site?" help="Select 'No' to only consider triples starting at the start of the site"/>
|
|
0
|
35 </when>
|
|
|
36 </conditional>
|
|
4
|
37 <param name="equiv" type="boolean" truevalue="-equiv" falsevalue="" checked="False" label="Match as equal sequences of letters that appear together?"/>
|
|
|
38 <param name="consider_both_strands" type="boolean" truevalue="-revcomp" falsevalue="" checked="False" label="Consider both strands when calculating position specific priors for alphabets?"/>
|
|
|
39 <param name="scale_min" type="boolean" truevalue="-scalemin" falsevalue="" checked="False" label="Set the lowest score value after scaling?"/>
|
|
|
40 <param name="scale_max" type="boolean" truevalue="-scalemax" falsevalue="" checked="False" label="Set the highest score value after scaling?"/>
|
|
|
41 <param name="max_range" type="boolean" truevalue="-maxrange" falsevalue="" checked="False" label="Choose the width with the biggest difference between minimum and maximum scores before scaling?" help="Select 'No' to choose the width with the biggest maximum score (before scaling)"/>
|
|
|
42 <param name="raw" type="boolean" truevalue="-raw" falsevalue="" checked="False" label="Output scores instead of priors?"/>
|
|
0
|
43 <conditional name="report_scores_cond">
|
|
4
|
44 <param name="report_scores" type="boolean" truevalue="-reportscores" falsevalue="" checked="False" label="Output primary and control file names, scores and widths?"/>
|
|
0
|
45 <when value="no"/>
|
|
|
46 <when value="yes">
|
|
4
|
47 <param name="verbose" type="boolean" truevalue="-verbose" falsevalue="" checked="False" label="Report frequency of each score?"/>
|
|
0
|
48 </when>
|
|
|
49 </conditional>
|
|
|
50 </section>
|
|
|
51 <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False">
|
|
|
52 <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
|
|
|
53 </param>
|
|
|
54 </inputs>
|
|
|
55 <outputs>
|
|
2
|
56 <data format="memepsp" name="output_psp"/>
|
|
|
57 <data format="tabular" name="output_tabular" label="${tool.name} (report) on ${on_string}">
|
|
3
|
58 <filter>adv['report_scores_cond']['report_scores'] == 'yes'</filter>
|
|
2
|
59 </data>
|
|
0
|
60 </outputs>
|
|
|
61 <tests>
|
|
|
62 <test>
|
|
3
|
63 <param name="primary_sequence" value="meme_psp_protein_input.fasta" ftype="fasta"/>
|
|
|
64 <param name="control_sequence" value="meme_psp_protein_input.fasta" ftype="fasta"/>
|
|
|
65 <param name="alphabet" value="protein"/>
|
|
0
|
66 <param name="non_commercial_use" value="True"/>
|
|
3
|
67 <output name="output_psp" file="output.memepsp"/>
|
|
0
|
68 </test>
|
|
|
69 </tests>
|
|
|
70 <help>
|
|
|
71
|
|
|
72 .. class:: warningmark
|
|
|
73
|
|
|
74 **WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted.
|
|
|
75 Before using, be sure to review, agree, and comply with the license.**
|
|
|
76
|
|
|
77 psp-gen is used to allow MEME to perform discriminative motif discovery—to find motifs overrepresented in one set of sequences compared to in another set.
|
|
|
78 It takes two files as input—the sequence file to be input to MEME, (the "primary" file) and a "control" sequence file of sequences believed not to contain
|
|
|
79 the same motifs as in the "primary" file. psp-gen creates a file for use by MEME that encapsulates information about probable discriminative motifs. psp-gen
|
|
|
80 records its chosen motif width in the file, and MEME is able to adjust the data when it tries different motif widths.
|
|
|
81
|
|
|
82 .. class:: infomark
|
|
|
83
|
|
|
84 For detailed information on psp-gen, click here_, or view the license_.
|
|
|
85
|
|
|
86 .. _here: http://meme-suite.org/doc/psp-gen.html?man_type=web
|
|
|
87 .. _license: http://meme-suite.org/doc/copyright.html?man_type=web
|
|
|
88
|
|
|
89 -----
|
|
|
90
|
|
|
91 **Required options**
|
|
|
92
|
|
|
93 * **Primary sequence file** - a file containing FASTA formatted sequences which are to be used as the primary set in PSP calculation.
|
|
|
94 * **Control sequence file** - a file containing FASTA formatted sequences which are to be used as the control set in PSP calculation.
|
|
|
95
|
|
|
96 **Advanced options**
|
|
|
97
|
|
|
98 * **Minimum width to use for position specific priors** - the minimum width to use with selecting the "best" width for PSPs.
|
|
|
99 * **Maximum width to use for position specific priors** - the maximum width to use with selecting the "best" width for PSPs.
|
|
|
100 * **Alphabet** - The alphabet to be used, one of DNA, protein or RNA.
|
|
|
101 * **Use spaced triples instead of whole-word matches** - use spaced triples instead of whole-word matches (recommended when using the protein alphabet).
|
|
|
102
|
|
|
103 * **Allow triples to start anywhere within a site** - when using the -triples option, select 'Yes' to only consider triples starting at the start of the site or 'No' to allow triples to start anywhere in a width 'w' site.
|
|
|
104
|
|
|
105 * **Match as equal sequences of letters that appear together** - select 'Yes' to match as equal any sequence of letter that appears together. Separate letter groups using "-" (e.g. -equiv "IVL-HKR") means treat all occurrences of I, V or L as the same, and all occurrences of H, K or R as the same.
|
|
|
106 * **Consider both strands when calculating position specific priors for alphabets** - select 'Yes' to consider both strands when calculating PSPs for complementable alphabets or 'No to consider only the given strand.
|
|
|
107 * **Set the lowest score value after scaling** - select 'Yes' to set the lowest score to 0.1 unless the the following "highest score" option is selected, in which case the lowest score is highest score - 1.
|
|
|
108 * **Set the highest score value after scaling** - select 'Yes' to set the highest score to 0.9 unless the previous "lowest score" option is selected, in which case the highest score is lowest score + 1.
|
|
|
109 * **Choose the width with the biggest difference between minimum and maximum scores before scaling** - select 'Yes' to choose the width with the biggest difference between minimum and maximum scores before scaling, or 'No' to choose the width with the biggest maximum score before scaling.
|
|
|
110 * **Output scores instead of priors** - select 'Yes' to output scores instead of position specific priors.
|
|
|
111 * **Output primary and control file names, scores and widths** - select 'Yes' to produce an additional tabular output consisting of control file names, lowest and highest scores and lowest and highest widths.
|
|
|
112
|
|
|
113 * **Report frequency of each score** - select 'Yes' to include the frequency of each score in the output.
|
|
|
114
|
|
|
115 </help>
|
|
|
116 <citations>
|
|
4
|
117 <citation type="doi">10.1186/1471-2105-11-179</citation>
|
|
0
|
118 </citations>
|
|
|
119 </tool>
|
