Mercurial > repos > gandres > spp_eba2016

view spp_wrapper.xml @ 0:d4236b60701f draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/eba2016/spp_tool commit 2fb169b136aea9887da7ab9fdccc442443f8efa3-dirty
author gandres
date Wed, 25 May 2016 11:52:21 -0400
parents
children
line wrap: on
line source

<tool id="modencode_peakcalling_spp" name="SPP" version="1.13.0">
  <description>SPP cross-correlation analysis package</description>
  <requirements>
    <requirement type="set_environment">SCRIPT_PATH</requirement>
    <requirement type="package" version="1.13">spp</requirement>
  </requirements>
  <command>python $__tool_directory__/spp_wrapper.py $options_file $output_narrow_peak $output_region_peak $output_peakshift_file $output_rdata_file $output_plot_file $output_default_file \$SCRIPT_PATH</command>
  <configfiles>
    <configfile name="options_file">&lt;%
import simplejson
%&gt;
#set $__options ={ 'experiment_name':str($experiment_name), 'chip_file':str($major_command.input_chipseq_file1) }

#if str( $major_command.input_control_file1 ) != 'None':
	#set $__options['input_file'] = str( $major_command.input_control_file1 )
#end if

##=============================================================================
#if str($major_command.major_command_selector) == 'cross_correlation':
	#set $__options['action'] = str( "cross_correlation" )

	#set $__options['out'] = str( $major_command.save_peakshift_file )
	#set $__options['savp'] = str( $major_command.save_plot_file ) 
#end if
##=============================================================================
#if str($major_command.major_command_selector) == 'peak_calling':
	#set $__options['action'] = str( "peak_calling" )
	#set $__options['fdr'] = str( $major_command.fdr )
	#set $__options['npeak'] = str( $major_command.num_peaks )	

	#set $__options['savr'] = str( $major_command.save_regionpeak_file )
	#set $__options['savd'] = str( $major_command.save_rdata_file )
	#set $__options['savn'] = str( $major_command.save_narrowpeak_file )
	#set $__options['savp'] = str( $major_command.save_plot_file )
#end if
##=============================================================================
#if str($major_command.major_command_selector) == 'idr':
	#set $__options['action'] = str( "idr" ) 
	#set $__options['npeak'] = int( $major_command.num_peaks  )

	#set $__options['savr'] = str( $major_command.save_regionpeak_file )
	#set $__options['out'] = str( $major_command.save_peakshift_file )
	#set $__options['savp'] = str( $major_command.save_plot_file )
#end if
##=============================================================================
#if str($major_command.major_command_selector) == 'custom':
	#set $__options['action'] = str( "custom" )
        #set $__options['s'] = str( $major_command.strand_shift )
        #set $__options['x'] = str( $major_command.excluded_strand_shift  )
        #set $__options['npeak'] = int( $major_command.num_peaks )
        #set $__options['fdr'] = int( $major_command.fdr  )

	#if str($major_command.user_defined_strpeak) == '':
        	#set $__options['speak'] = str( $major_command.user_defined_strpeak )
	#else:
	       	#set $__options['speak'] = "-speak=$major_command.user_defined_strpeak"
	#end if 

	#if str($major_command.filter_char) == '':
 	       #set $__options['filtchr'] = str( $major_command.filter_char )
	#else:
 	       #set $__options['filtchr'] = "-filtchr=$major_command.filter_char"
	#end if	

	#set $__options['out'] = str( $major_command.save_peakshift_file )
        #set $__options['savr'] = str( $major_command.save_regionpeak_file )
        #set $__options['savd'] = str( $major_command.save_rdata_file )
        #set $__options['savn'] = str( $major_command.save_narrowpeak_file )
        #set $__options['savp'] = str( $major_command.save_plot_file ) 
#end if

${ simplejson.dumps( __options ) }
    </configfile>
  </configfiles>

  <inputs>
    <!--experiment name and inputs-->
    <param name="experiment_name" type="text" value="SPP in Galaxy" size="50" label="Experiment Name"/>
    
    <!--select function to perform-->
    <conditional name="major_command">
      <param name="major_command_selector" type="select" label="Select action to be performed">
	<option value="cross_correlation">Determine strand cross-correlation peak</option>
	<option value="peak_calling">Peak calling</option>
	<option value="idr">IDR analysis</option>
	<option value="custom">Custom settings</option>
      </param>
      <when value="cross_correlation">
	<!--cross correlation options-->
    	<param name="input_chipseq_file1" type="data" format="bam" label="ChIP-Seq Tag File" />
    	<param name="input_control_file1" type="data" format="bam" optional="True" label="ChIP-Seq Control File" />


	<param name="save_peakshift_file" truevalue="-out=peakshift.txt" falsevalue="" type="boolean" checked="True" label="Save peakshift file" help="(-out)"/>
	<param name="save_plot_file" truevalue="-savp" falsevalue="" type="boolean" checked="True" label="Save plot file" help="(-savp)"/>
      </when>
      <when value="peak_calling">
	<!--peak calling options-->
	<param name="input_chipseq_file1" type="data" format="bam" label="ChIP-Seq Tag File" />
	<param name="input_control_file1" type="data" format="bam" label="ChIP-Seq Control File" />

	<param name="fdr" type="text" label="False discovery rate threshold" value="0" help="default=0 (-fdr)"/>
	<param name="num_peaks" type="text" label="Threshold on number of peaks to call" value="0" help="default=0 (-npeak)"/>

	<param name="save_regionpeak_file" truevalue="-savr" falsevalue="" type="boolean" checked="True" label="Save regionpeak file " help="(-savr)"/>   
	<param name="save_rdata_file" truevalue="-savd" falsevalue="" type="boolean" checked="True" label="Save Rdata file" help="(-savd)"/>
	<param name="save_narrowpeak_file" truevalue="-savn" falsevalue="" type="boolean" checked="True" label="Save narrowpeak file" help="(-savn)"/>
	<param name="save_plot_file" truevalue="-savp" falsevalue="" type="boolean" checked="True" label="Save plot file" help="(-savp)"/>
      </when>
      <when value="idr">
	<!--idr options-->
    	<param name="input_chipseq_file1" type="data" format="bam" label="ChIP-Seq Tag File" />
    	<param name="input_control_file1" type="data" format="bam" label="ChIP-Seq Control File" />
	
	<param name="num_peaks" type="integer" label="Threshold on number of peaks to call" value="300000" help="default=300000 (-npeak)"/>

	<param name="save_regionpeak_file" truevalue="-savr" falsevalue="" type="boolean" checked="True" label="Save regionpeak file" help="(-savr)"/>   
	<param name="save_peakshift_file" truevalue="-out=peakshift.txt" falsevalue="" type="boolean" checked="True" label="Save peakshift file" help="(-out)"/>
	<param name="save_plot_file" truevalue="-savp" falsevalue="" type="boolean" checked="True" label="Save plot file" help="(-savp)"/>
      </when> 
      <when value="custom">
	<!--custom settings, includes all relevant options here-->
    	<param name="input_chipseq_file1" type="data" format="bam" label="ChIP-Seq Tag File" />
    	<param name="input_control_file1" type="data" format="bam" optional="True" label="ChIP-Seq Control File" />

	<param name="strand_shift" type="text" label="Strand shifts at which cross-correlation is evaluated" size="30" value="-100:5:600" help="default=-100:5:600 (-s)"/>
	<param name="excluded_strand_shift" type="text" label="Strand shifts to exclude" value="10:10" help="default=10:(readlen+10) (-x)"/>
	<param name="user_defined_strpeak" type="text" label="User defined cross-correlation peak strand shift" help="(-speak)"/>
	<param name="num_peaks" type="integer" label="Threshold on number of peaks to call" value="0" help="default=0 (-npeak)"/>
	<param name="fdr" type="integer" label="False discovery rate threshold" value="0" help="default=0 (-fdr)"/>
	<param name="filter_char" type="text" label="Pattern to use to remove tags that map to specific chromosomes" help="(-filtchr)"/>

	<param name="save_regionpeak_file" truevalue="-savr" falsevalue="" type="boolean" checked="False" label="Save regionpeak file" help="(-savr)"/>   
	<param name="save_peakshift_file" truevalue="-out=peakshift.txt" falsevalue="" type="boolean" checked="False" label="Save peakshift file" help="(-out)"/>
	<param name="save_rdata_file" truevalue="-savd" falsevalue="" type="boolean" checked="False" label="Save Rdata file" help="(-savd)"/>
	<param name="save_narrowpeak_file" truevalue="-savn" falsevalue="" type="boolean" checked="False" label="Save narrowpeak file" help="(-savn)"/>
	<param name="save_plot_file" truevalue="-savp" falsevalue="" type="boolean" checked="False" label="Save plot file" help="(-savp)"/>
      </when>
    </conditional>
  </inputs>

  <outputs>
    <data name="output_default_file" format="txt" label="${tool.name}-${major_command.major_command_selector} on ${on_string}"/>
    <data name="output_narrow_peak" format="txt" label="${tool.name}-${major_command.major_command_selector} on ${on_string} (narrowpeaks)">
	<filter>major_command['save_narrowpeak_file'] is True</filter>
	<filter>major_command['major_command_selector'] == 'peak_calling' or major_command['major_command_selector'] == 'custom'</filter> 
    </data>
    <data name="output_plot_file" format="pdf" label="${tool.name}-${major_command.major_command_selector} on ${on_string} (plot)">
	<filter>major_command['save_plot_file'] is True</filter>
    </data>
    <data name="output_region_peak" format="txt" label="${tool.name}-${major_command.major_command_selector} on ${on_string} (regionpeaks)">
	<filter>major_command['save_regionpeak_file'] is True</filter>
    	<filter>major_command['major_command_selector'] == 'peak_calling' or major_command['major_command_selector'] == 'custom' or major_command['major_command_selector'] == 'idr' </filter> 
    </data>
    <data name="output_peakshift_file" format="txt" label="${tool.name}-${major_command.major_command_selector} on ${on_string} (peakshift/phantompeak)">
	<filter>major_command['save_peakshift_file'] is True</filter>
    	<filter>major_command['major_command_selector'] == 'cross_correlation' or major_command['major_command_selector'] == 'custom' or major_command['major_command_selector'] == 'idr' </filter> 
    </data>
    <data name="output_rdata_file" format="txt" label="${tool.name}-${major_command.major_command_selector} on ${on_string} (Rdata)">
	<filter>major_command['save_rdata_file'] is True</filter>
	<filter>major_command['major_command_selector'] == 'peak_calling' or major_command['major_command_selector'] == 'custom' </filter> 
    </data>
  </outputs>

  <tests>
	<!--none yet for spp-->
	<test>
		<param name="major_command_selector" value="cross_correlation"/>
		<param name="input_chipseq_file1" value="tag_file.bam"/>
		<param name="input_control_file1" value="control_file.bam"/>
		<output name="output_peakshift_file">
			<assert_contents>
				<has_line_matching expression="^.*\t192996\t100\t0.552186886771392\t45\t0.4766414\t600\t0.1428672\t3.865035\t1.226337\t1$" />
				<has_n_columns n="11" />
			</assert_contents>
		</output>
		<output name="output_default_file">
			<assert_contents>
				<has_line line="done. read 192996 fragments" />
				<has_line line="ChIP data read length 37 " />
				<has_line line="Minimum cross-correlation value 0.1428672 " />
				<has_line line="Peak cross-correlation value 0.552186886771392 " />
				<has_line line="Peak strand shift 100 " />
				<has_line line="Window half size 260 " />
				<has_line line="Phantom peak location 45 " />
				<has_line line="Phantom peak Correlation 0.4766414 " />
				<has_line line="Normalized cross-correlation coefficient (NCCC) 3.865035 " />
				<has_line line="Relative Cross correlation Coefficient (RCCC) 1.226337 " />
				<has_line line="Phantom Peak Quality Tag 1 " />
			</assert_contents>
		</output>
	</test>
	<test>
                <param name="major_command_selector" value="cross_correlation"/>
                <param name="input_chipseq_file1" value="tag_file.bam"/>
                <output name="output_peakshift_file">
	                <assert_contents>
		                <has_line_matching expression="^.*\t192996\t100\t0.552186886771392\t45\t0.4766414\t600\t0.1428672\t3.865035\t1.226337\t1$" />
	                        <has_n_columns n="11" />
	                </assert_contents>
	        </output>
	</test>
  </tests>
  <help>
**What it does**

This tool allows ChIP-seq peak calling using SPP

This set of programs operate on mapped Illumina single-end read datasets in tagAlign or BAM format.

View the modified SPP documentation: http://code.google.com/p/phantompeakqualtools/

------

**Usage**

**Determine strand cross-correlation peak**: Compute the predominant insert-size (fragment length) based on strand cross-correlation peak.

**Peak calling**: Call Peaks and regions for punctate binding datasets.

**IDR analysis**: Compute Data quality measures based on relative phantom peak.

**Custom settings**: Enables all options available to SPP for custom analysis. 

------

**Output**


The column names of narrow- and region-peaks datasets (produced by **Peak calling**) are provided below:

- col 1: chrom
- col 2: start
- col 3: end
- col 4: name
- col 5: score
- col 6: strand
- col 7: signalValue
- col 8 : -1
- col 9: -log10(fdr)
- col 10: Point-source called for this peak.

------


**Citation**

Anshul Kundaje, Computer Science Dept., Stanford University, ENCODE Consortium, Personal Communication, Oct 2010
Kharchenko PK, Tolstorukov MY, Park PJ, Design and analysis of ChIP-seq experiments for DNA-binding proteins Nat Biotechnol. 2008 Dec;26(12):1351-9

Integration of SPP with Galaxy performed by Ziru Zhou ( ziruzhou@gmail.com ). Please send your comments/questions to help@modencode.org.
  </help>
  <citations>
  	<citation type="doi">doi:10.1038/nbt.1508</citation>
  </citations>
</tool>