|
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 $adv.alphabet
|
|
|
14 #if str($adv.triples_cond.triples) == 'yes':
|
|
|
15 -triples
|
|
|
16 #if str($adv.triples_cond.fixed_start) == 'yes':
|
|
|
17 -fixedstart
|
|
|
18 #end if
|
|
|
19 #end if
|
|
|
20 #if str($adv.equiv) == 'yes':
|
|
|
21 -equiv
|
|
|
22 #end if
|
|
|
23 #if str($adv.consider_both_strands) == 'yes':
|
|
|
24 -revcomp
|
|
|
25 #end if
|
|
|
26 #if str($adv.scale_min) == 'yes':
|
|
|
27 -scalemin
|
|
|
28 #end if
|
|
|
29 #if str($adv.scale_max) == 'yes':
|
|
|
30 -scalemax
|
|
|
31 #end if
|
|
|
32 #if str($adv.max_range) == 'yes':
|
|
|
33 -maxrange
|
|
|
34 #end if
|
|
|
35 #if str($adv.raw) == 'yes':
|
|
|
36 -raw
|
|
|
37 #end if
|
|
|
38 #if str($adv.report_scores_cond.report_scores) == 'yes':
|
|
|
39 -reportscores
|
|
|
40 #if str($adv.report_scores_cond.verbose) == 'yes':
|
|
|
41 -verbose
|
|
|
42 #end if
|
|
2
|
43 2> '$output_tabular'
|
|
0
|
44 #end if
|
|
2
|
45 > '$output_psp'
|
|
0
|
46 ]]></command>
|
|
|
47 <inputs>
|
|
|
48 <param format="fasta" name="primary_sequence" type="data" label="Primary sequence file"/>
|
|
|
49 <param format="fasta" name="control_sequence" type="data" label="Control sequence file"/>
|
|
|
50 <section name="adv" title="Additional Options">
|
|
|
51 <param name="minw" type="integer" value="4" min="0" label="Minimum width to use for position specific priors"/>
|
|
|
52 <param name="maxw" type="integer" value="20" min="0" label="Maximum width to use for position specific priors"/>
|
|
|
53 <param name="alphabet" type="select" label="Alphabet">
|
|
|
54 <option value="-dna" selected="true">DNA</option>
|
|
|
55 <option value="-protein">protein</option>
|
|
|
56 <option value="-rna">RNA</option>
|
|
|
57 </param>
|
|
|
58 <conditional name="triples_cond">
|
|
|
59 <param name="triples" type="select" label="Use spaced triples instead of whole-word matches?" help="Recommended for protein">
|
|
|
60 <option value="no" selected="true">No</option>
|
|
|
61 <option value="yes">yes</option>
|
|
|
62 </param>
|
|
|
63 <when value="no"/>
|
|
|
64 <when value="yes">
|
|
|
65 <param name="fixed_start" type="select" display="radio" label="Allow triples to start anywhere within a site?" help="Select 'No' to only consider triples starting at the start of the site">
|
|
|
66 <option value="yes" selected="true">Yes</option>
|
|
|
67 <option value="no">No</option>
|
|
|
68 </param>
|
|
|
69 </when>
|
|
|
70 </conditional>
|
|
|
71 <param name="equiv" type="select" display="radio" label="Match as equal sequences of letters that appear together?">
|
|
|
72 <option value="no" selected="true">No</option>
|
|
|
73 <option value="yes">Yes</option>
|
|
|
74 </param>
|
|
|
75 <param name="consider_both_strands" type="select" display="radio" label="Consider both strands when calculating position specific priors for alphabets?">
|
|
|
76 <option value="no" selected="true">No</option>
|
|
|
77 <option value="yes">Yes</option>
|
|
|
78 </param>
|
|
|
79 <param name="scale_min" type="select" display="radio" label="Set the lowest score value after scaling?">
|
|
|
80 <option value="no" selected="true">No</option>
|
|
|
81 <option value="yes">Yes</option>
|
|
|
82 </param>
|
|
|
83 <param name="scale_max" type="select" display="radio" label="Set the highest score value after scaling?">
|
|
|
84 <option value="no" selected="true">No</option>
|
|
|
85 <option value="yes">Yes</option>
|
|
|
86 </param>
|
|
|
87 <param name="max_range" type="select" display="radio" 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)">
|
|
|
88 <option value="no" selected="true">No</option>
|
|
|
89 <option value="yes">Yes</option>
|
|
|
90 </param>
|
|
|
91 <param name="raw" type="select" display="radio" label="Output scores instead of priors?">
|
|
|
92 <option value="no" selected="true">No</option>
|
|
|
93 <option value="yes">Yes</option>
|
|
|
94 </param>
|
|
|
95 <conditional name="report_scores_cond">
|
|
|
96 <param name="report_scores" type="select" label="Output primary and control file names, scores and widths?">
|
|
|
97 <option value="no" selected="true">No</option>
|
|
|
98 <option value="yes">yes</option>
|
|
|
99 </param>
|
|
|
100 <when value="no"/>
|
|
|
101 <when value="yes">
|
|
|
102 <param name="verbose" type="select" display="radio" label="Report frequency of each score?">
|
|
|
103 <option value="no" selected="true">No</option>
|
|
|
104 <option value="yes">Yes</option>
|
|
|
105 </param>
|
|
|
106 </when>
|
|
|
107 </conditional>
|
|
|
108 </section>
|
|
|
109 <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">
|
|
|
110 <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
|
|
|
111 </param>
|
|
|
112 </inputs>
|
|
|
113 <outputs>
|
|
2
|
114 <data format="memepsp" name="output_psp"/>
|
|
|
115 <data format="tabular" name="output_tabular" label="${tool.name} (report) on ${on_string}">
|
|
|
116 <filter>adv['report_scores_cond'] == 'yes'</filter>
|
|
|
117 </data>
|
|
0
|
118 </outputs>
|
|
|
119 <tests>
|
|
|
120 <test>
|
|
|
121 <param name="input1" value="meme_input_1.fasta" ftype="fasta" dbkey="hg19"/>
|
|
|
122 <param name="options_type_selector" value="basic"/>
|
|
|
123 <param name="non_commercial_use" value="True"/>
|
|
|
124 <output name="html_outfile" file="meme_output_html_1.html" compare="contains"/>
|
|
|
125 <output name="txt_outfile" file="meme_output_txt_1.txt" lines_diff="12"/>
|
|
|
126 <output name="xml_outfile" file="meme_output_xml_1.xml" lines_diff="8"/>
|
|
|
127 </test>
|
|
|
128 </tests>
|
|
|
129 <help>
|
|
|
130
|
|
|
131 .. class:: warningmark
|
|
|
132
|
|
|
133 **WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted.
|
|
|
134 Before using, be sure to review, agree, and comply with the license.**
|
|
|
135
|
|
|
136 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.
|
|
|
137 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
|
|
|
138 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
|
|
|
139 records its chosen motif width in the file, and MEME is able to adjust the data when it tries different motif widths.
|
|
|
140
|
|
|
141 .. class:: infomark
|
|
|
142
|
|
|
143 For detailed information on psp-gen, click here_, or view the license_.
|
|
|
144
|
|
|
145 .. _here: http://meme-suite.org/doc/psp-gen.html?man_type=web
|
|
|
146 .. _license: http://meme-suite.org/doc/copyright.html?man_type=web
|
|
|
147
|
|
|
148 -----
|
|
|
149
|
|
|
150 **Required options**
|
|
|
151
|
|
|
152 * **Primary sequence file** - a file containing FASTA formatted sequences which are to be used as the primary set in PSP calculation.
|
|
|
153 * **Control sequence file** - a file containing FASTA formatted sequences which are to be used as the control set in PSP calculation.
|
|
|
154
|
|
|
155 **Advanced options**
|
|
|
156
|
|
|
157 * **Minimum width to use for position specific priors** - the minimum width to use with selecting the "best" width for PSPs.
|
|
|
158 * **Maximum width to use for position specific priors** - the maximum width to use with selecting the "best" width for PSPs.
|
|
|
159 * **Alphabet** - The alphabet to be used, one of DNA, protein or RNA.
|
|
|
160 * **Use spaced triples instead of whole-word matches** - use spaced triples instead of whole-word matches (recommended when using the protein alphabet).
|
|
|
161
|
|
|
162 * **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.
|
|
|
163
|
|
|
164 * **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.
|
|
|
165 * **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.
|
|
|
166 * **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.
|
|
|
167 * **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.
|
|
|
168 * **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.
|
|
|
169 * **Output scores instead of priors** - select 'Yes' to output scores instead of position specific priors.
|
|
|
170 * **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.
|
|
|
171
|
|
|
172 * **Report frequency of each score** - select 'Yes' to include the frequency of each score in the output.
|
|
|
173
|
|
|
174 </help>
|
|
|
175 <citations>
|
|
|
176 <citation type="bibtex">
|
|
|
177 @article{Bailey2010,
|
|
|
178 journal = {BMC Bioinformatics}
|
|
|
179 author = {Bailey Timothy L, Bodén Mikael, Whitington Tom, Machanick Philip},
|
|
|
180 title = {The value of position-specific priors in motif discovery using MEME},
|
|
|
181 year = {2010},
|
|
|
182 volume = {11},
|
|
|
183 number = {1},
|
|
|
184 pages = {179}
|
|
|
185 }</citation>
|
|
|
186 </citations>
|
|
|
187 </tool>
|
