diff beta_minus.xml @ 0:20453b656907

Imported from capsule None
author jjohnson
date Tue, 16 Sep 2014 13:35:24 -0400
parents
children 9c5241259454
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/beta_minus.xml	Tue Sep 16 13:35:24 2014 -0400
@@ -0,0 +1,111 @@
+<tool id="beta_minus" name="BETA-minus: Targets prediction with binding only" version="0.1.0">
+  <description>Predict the factors (TFs or CRs) direct target genes by only binding data</description>
+  <macros>
+    <import>beta_macros.xml</import>
+  </macros>
+  <expand macro="requirements" />
+  <command>
+  BETA minus 
+  #include source=$common_opts#
+  #include source=$genome_opts#
+  &amp;> $log
+  </command>
+  <inputs>
+    <expand macro="common_params" />
+    <expand macro="genome_params" />
+  </inputs>
+  <expand macro="stdio" />
+  <outputs>
+    <data format="txt" name="log" label="Log of BETA minus"/>
+    <data format="tabular" name="targetsoutput" label="BETA predicted Targets" from_work_dir="BETA_OUTPUT/NA_targets.txt"/>
+    <data format="tabular" name="targetpeaks" label="BETA Target gene's associated peaks" from_work_dir="BETA_OUTPUT/NA_targets_associated_peaks.txt"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name='peakfile' value="peaks.bed" ftype="bed" dbkey="hg19"/>
+      <param name="distance" value="100000"/>
+      <param name="peaknumber" value="10000"/>
+      <param name="genomeName" value="hg19"/>
+      <output name="log">
+        <assert_contents>
+            <has_text_matching expression="Finished" />
+        </assert_contents>
+      </output>
+      <output name="targetsoutput">
+        <assert_contents>
+            <has_text_matching expression="chr19\t4675243\t4723855\tNM_139159\t1.1.*\t-\tDPP" />
+        </assert_contents>
+      </output>
+      <output name="targetpeaks">
+        <assert_contents>
+            <has_text_matching expression="chr19\t4723422\t4724314\tregion_9\tNM_139159\tDPP9\t13\t0.6.*" />
+        </assert_contents>
+      </output>
+    </test>
+  </tests>
+ <help>
+** BETA minus **
+
+@EXTERNAL_DOCUMENTATION@
+
+@CITATION_SECTION@
+
+This tool annotates the given intervals and scores with genome
+features such as gene body. It's the major module in CEAS package
+which is written by Hyunjin Gene Shin, published in Bioinformatics
+(pubmed id:19689956).
+
+.. class:: warningmark
+
+**NEED IMPROVEMENT**
+
+-----
+
+**Parameters**
+
+- **PEAKFILE file** contains peaks for the experiment in a bed
+  format file. Normally, it's produced by the peak calling tool. It's
+  required.
+- **genome** hg19 for human and mm9 for mouse. Others, don't set this parameter.
+- **REFERENCE** is the refgene info file downloaded from UCSC genome browser.
+  It is a tab delimited text file with gene annotation with refseq and gene symbol.
+  Input this file only if your genome is neither hg19 nor mm9.
+  profiling
+- **OUTPUT** to specify the output files directory
+- **bl** Whether or not to use CTCF boundary file to get the contributed peaks
+- **NAME** specify the name of the output files.
+- **DISTANCE** specify the distance wich peaks within it will be considered.
+
+
+-----
+
+**script parameter list of BETA minus**
+
+::
+
+  -h, --help            show this help message and exit
+  -p PEAKFILE, --peakfile PEAKFILE
+                        The bed format of peaks binding sites. 
+                        BETA supports 3 or 5 columns bed format: CHROM, START, END [NAME, SCORE]
+  -g {hg19,mm9}, --genome {hg19,mm9}
+                        Specify your species, {hg19, mm9}
+  -r REFERENCE, --reference REFERENCE
+                        the refgene info file downloaded from UCSC genome
+                        browser.input this file only if your genome is neither
+                        hg19 nor mm9
+  -o OUTPUT, --output OUTPUT
+                        the directory to store all the output files, if you
+                        don't set this, files will be output into the current
+                        directory
+  --bl                  whether or not use CTCF boundary to filter peaks
+                        around a gene, DEFAULT=FALSE
+  --pn PEAKNUMBER       the number of peaks you want to consider, DEFAULT=10000
+  -n NAME, --name NAME  this argument is used to name the result file.If not
+                        set, the peakfile name will be used instead
+  -d DISTANCE, --distance DISTANCE
+                        Set a number which unit is 'base'. It will get peaks
+                        within this distance from gene TSS. default:100000 (100kb)
+
+  </help>
+
+</tool>