diff meme_psp_gen.xml @ 0:e7b8db2b9246 draft

Uploaded
author greg
date Thu, 17 Aug 2017 09:05:48 -0400
parents
children c32084cb7fe7
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/meme_psp_gen.xml	Thu Aug 17 09:05:48 2017 -0400
@@ -0,0 +1,184 @@
+<tool id="meme_psp_gen" name="MEME psp-gen" version="4.11.2.0">
+    <description>- perform discriminative motif discovery</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command detect_errors="exit_code"><![CDATA[
+psp-gen
+-pos '$primary_sequence'
+-neg '$control_sequence'
+-minw $adv.minw
+-maxw $adv.maxw
+$adv.alphabet
+#if str($adv.triples_cond.triples) == 'yes':
+    -triples
+    #if str($adv.triples_cond.fixed_start) == 'yes':
+        -fixedstart
+    #end if
+#end if
+#if str($adv.equiv) == 'yes':
+    -equiv
+#end if
+#if str($adv.consider_both_strands) == 'yes':
+    -revcomp
+#end if
+#if str($adv.scale_min) == 'yes':
+    -scalemin
+#end if
+#if str($adv.scale_max) == 'yes':
+    -scalemax
+#end if
+#if str($adv.max_range) == 'yes':
+    -maxrange
+#end if
+#if str($adv.raw) == 'yes':
+    -raw
+#end if
+#if str($adv.report_scores_cond.report_scores) == 'yes':
+    -reportscores
+    #if str($adv.report_scores_cond.verbose) == 'yes':
+        -verbose
+    #end if
+#end if
+    ]]></command>
+    <inputs>
+        <param format="fasta" name="primary_sequence" type="data" label="Primary sequence file"/>
+        <param format="fasta" name="control_sequence" type="data" label="Control sequence file"/>
+        <section name="adv" title="Additional Options">
+            <param name="minw" type="integer" value="4" min="0" label="Minimum width to use for position specific priors"/>
+            <param name="maxw" type="integer" value="20" min="0" label="Maximum width to use for position specific priors"/>
+            <param name="alphabet" type="select" label="Alphabet">
+                <option value="-dna" selected="true">DNA</option>
+                <option value="-protein">protein</option>
+                <option value="-rna">RNA</option>
+            </param>
+            <conditional name="triples_cond">
+                <param name="triples" type="select" label="Use spaced triples instead of whole-word matches?" help="Recommended for protein">
+                    <option value="no" selected="true">No</option>
+                    <option value="yes">yes</option>
+                </param>
+                <when value="no"/>
+                <when value="yes">
+                    <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">
+                        <option value="yes" selected="true">Yes</option>
+                        <option value="no">No</option>
+                    </param>
+                </when>
+            </conditional>
+            <param name="equiv" type="select" display="radio" label="Match as equal sequences of letters that appear together?">
+                <option value="no" selected="true">No</option>
+                <option value="yes">Yes</option>
+            </param>
+            <param name="consider_both_strands" type="select" display="radio" label="Consider both strands when calculating position specific priors for alphabets?">
+                <option value="no" selected="true">No</option>
+                <option value="yes">Yes</option>
+            </param>
+            <param name="scale_min" type="select" display="radio" label="Set the lowest score value after scaling?">
+                <option value="no" selected="true">No</option>
+                <option value="yes">Yes</option>
+            </param>
+            <param name="scale_max" type="select" display="radio" label="Set the highest score value after scaling?">
+                <option value="no" selected="true">No</option>
+                <option value="yes">Yes</option>
+            </param>
+            <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)">
+                <option value="no" selected="true">No</option>
+                <option value="yes">Yes</option>
+            </param>
+            <param name="raw" type="select" display="radio" label="Output scores instead of priors?">
+                <option value="no" selected="true">No</option>
+                <option value="yes">Yes</option>
+            </param>
+            <conditional name="report_scores_cond">
+                <param name="report_scores" type="select" label="Output primary and control file names, scores and widths?">
+                    <option value="no" selected="true">No</option>
+                    <option value="yes">yes</option>
+                </param>
+                <when value="no"/>
+                <when value="yes">
+                    <param name="verbose" type="select" display="radio" label="Report frequency of each score?">
+                        <option value="no" selected="true">No</option>
+                        <option value="yes">Yes</option>
+                    </param>
+                </when>
+            </conditional>
+        </section>
+        <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">
+            <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
+        </param>
+    </inputs>
+    <outputs>
+        <data format="html" name="html_outfile" label="${tool.name} on ${on_string} (html)"/>
+        <data format="txt" name="txt_outfile" label="${tool.name} on ${on_string} (text)"/>
+        <data format="memexml" name="xml_outfile" label="${tool.name} on ${on_string} (xml)"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="input1" value="meme_input_1.fasta" ftype="fasta" dbkey="hg19"/>
+            <param name="options_type_selector" value="basic"/>
+            <param name="non_commercial_use" value="True"/>
+            <output name="html_outfile" file="meme_output_html_1.html" compare="contains"/>
+            <output name="txt_outfile" file="meme_output_txt_1.txt" lines_diff="12"/>
+            <output name="xml_outfile" file="meme_output_xml_1.xml" lines_diff="8"/>
+        </test>
+    </tests>
+    <help>
+
+.. class:: warningmark
+
+**WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted.
+Before using, be sure to review, agree, and comply with the license.**
+
+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.
+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
+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
+records its chosen motif width in the file, and MEME is able to adjust the data when it tries different motif widths.
+
+.. class:: infomark
+
+For detailed information on psp-gen, click here_, or view the license_.
+
+.. _here: http://meme-suite.org/doc/psp-gen.html?man_type=web
+.. _license: http://meme-suite.org/doc/copyright.html?man_type=web
+
+-----
+
+**Required options**
+
+ * **Primary sequence file** - a file containing FASTA formatted sequences which are to be used as the primary set in PSP calculation.
+ * **Control sequence file** - a file containing FASTA formatted sequences which are to be used as the control set in PSP calculation.
+
+**Advanced options**
+
+* **Minimum width to use for position specific priors** - the minimum width to use with selecting the "best" width for PSPs.
+* **Maximum width to use for position specific priors** - the maximum width to use with selecting the "best" width for PSPs.
+* **Alphabet** - The alphabet to be used, one of DNA, protein or RNA.
+* **Use spaced triples instead of whole-word matches** - use spaced triples instead of whole-word matches (recommended when using the protein alphabet).
+
+   * **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.
+
+* **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.
+* **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.
+* **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.
+* **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.
+* **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.
+* **Output scores instead of priors** - select 'Yes' to output scores instead of position specific priors.
+* **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.
+
+   * **Report frequency of each score** - select 'Yes' to include the frequency of each score in the output.
+
+    </help>
+    <citations>
+        <citation type="bibtex">
+            @article{Bailey2010,
+            journal = {BMC Bioinformatics}
+            author = {Bailey Timothy L, Bodén Mikael, Whitington Tom, Machanick Philip},
+            title = {The value of position-specific priors in motif discovery using MEME},
+            year = {2010},
+            volume = {11},
+            number = {1},
+            pages = {179}
+        }</citation>
+    </citations>
+</tool>