view pyCRAC/pyMotif.xml @ 0:19b20927172d draft

Uploaded
author swebb
date Tue, 18 Jun 2013 09:11:00 -0400
parents
children
line wrap: on
line source

 <tool id ="pyMotif" name="pyMotif">
	<requirements>
        	<requirement type="package">pyCRAC</requirement>
    	</requirements>
	<command interpreter="perl"> 
	pyMotif.pl
	-f $input
	--gtf=$addGTF.gtf

       	#if $addGTF.gtfFile == "default" and $addGTF.annotate.annotations == "auto":
	  --annotation $addGTF.annotate.scan.annotation
	#else:
	  --annotation $addGTF.annotate.annotation
	#end if#

	--tab=$addTab.tab

	#if $addOpt.options == "edit":
	        --options
	        --k_min $addOpt.kmin
		--k_max $addOpt.kmax
		--numberofkmers=$addOpt.numberofkmers
		--overlap $addOpt.overlap
		--range $addOpt.range
	#end if#
	-o "$input.name"
	--id $count.id
	--count $count
	--random $random
	--features $features
	--zscores $zscores
	</command>
	<version_command>/usr/local/bin/pyMotif.py --version</version_command>
	<inputs>
		<param format="gtf" name="input" type="data" label="Input File --input_file" help="File of type .gtf" />
                <conditional name="addTab">
                        <param name="tabFile" type="select"  label="Choose Genomic Reference Sequence from">
                                <option value="default" selected="true">Defaults</option>
                                <option value="other">History</option>
                        </param>
                        <when value="default">
                                <param name="tab" type="select"  label="Genomic Reference Sequence --tab" help="Tab file containing genomic reference sequence">
                                        <options from_data_table="pycrac_tab"/>
                                </param>
                        </when>
                        <when value="other">
                                <param format="tabular" name="tab" type="data" label="Genomic Reference Sequence --tab" help="Tab file containing genomic reference sequence"/>
                        </when>
                </conditional>				
		<conditional name="addGTF">
			<param name="gtfFile" type="select"  label="Choose GTF File from">
				<option value="default" selected="true">Defaults</option>
				<option value="other">History</option>
			</param>	
			<when value="default">
				<param name="gtf" type="select"  label="GTF File --gtf" help="GTF file containing gene ID co-ordinates">
					<options from_data_table="pycrac_gtf"/>
				</param>

				<conditional name="annotate">
				<param name="annotations" type="select"  label="Select annotation">
					<option value="all" selected="true">All</option>
					<option value="manual">Enter in text box</option>
					<option value="auto">Scan pyGetGTFSources file</option>
				</param>	
				<when value="all">
					<param name="annotation" type="hidden" format="txt" size="10" value="all"/>
				</when>
				<when value="manual">
					<param name="annotation" type="text" format="txt" size="100" value="protein_coding" label="Select which annotation to focus search on --annotation" help="To find a list of available annotations please use pyGetGTFSources tool">
						<validator type="empty_field" message="Please enter a value"/>			
					</param>
				</when>
				<when value="auto">
					<param format="tabular" name="gtf_annotation" type="data" label="GTF annotation File (pyGetGTFSources output)" help="Tabular file containing unique list of annotations/sources in selected GTF file. Refer to pyGetGTFSources"/>	
						<conditional name="scan">
						<param name="annotations" type="select"  label="Scan this file for annotations" help="Choose the correct GTF file then choose GO">
							<option value="wait" selected="true">Waiting</option>
							<option value="scanning">Go</option>
						</param>	
						<when value="wait">
						</when>
						<when value="scanning">
						<param name="annotation" type="select" multiple="false" label="Select which annotation to focus search on --annotation">
							  <options from_dataset="gtf_annotation">
							    <column name="name" index="0"/>
							    <column name="value" index="0"/>
							  </options>
						</param>      
						</when>
						</conditional>
				</when>
				</conditional>		
			</when>
			<when value="other">
				<param format="gtf" name="gtf" type="data" label="GTF File --gtf" help="GTF file containing gene ID co-ordinates"/>
				<conditional name="annotate">
				<param name="annotations" type="select"  label="Select annotation">
					<option value="all" selected="true">All</option>
					<option value="manual">Enter in text box</option>
					<option value="auto">Scan selected file</option>
				</param>	
				<when value="all">
					<param name="annotation" type="hidden" format="txt" size="10" value="all"/>
				</when>
				<when value="manual">
					<param name="annotation" type="text" format="txt" size="100" value="protein_coding" label="Select which annotation to focus search on --annotation" help="To find a list of available annotations please use pyGetGTFSources tool">
						<validator type="empty_field" message="Please enter a value"/>			
					</param>
				</when>
				<when value="auto">
					<param name="annotation" type="select" multiple="false" label="Select which annotation to focus search on --annotation">
						  <options from_dataset="gtf">
						    <column name="name" index="1"/>
						    <column name="value" index="1"/>
						    <filter type="unique_value" name="unique" column="1"/>
						  </options>
					</param>      
				</when>
				</conditional>
			</when>
		</conditional>
		<conditional name="addOpt">
		  <param name="options" type="select"  label="Standard options">
		    <option value="default" selected="true">Default</option>
		    <option value="edit">Edit</option>
		  </param>
		  <when value="edit">
		    <param format="integer" name="kmin" type="integer" label="Minimum k-mer Length --k_min " value="4" size="6" help="Set the minimal k-mer length">
		      <validator type="in_range" min="1" message="Please enter a value >= 1"/>
		    </param>
		    <param format="integer" name="kmax" type="integer" label="Maximum k-mer Length --k_min " value="8" size="6" help="Set the minimal k-mer length">
		      <validator type="in_range" min="0" message="Please enter a value >= 0"/>
		    </param>
		    <param format="integer" name="numberofkmers" type="integer" label="Maximum number of k-mers in output file --numberofkmers" value="1000" size="6" help="Set the maximum number of k-mers in output">
		      <validator type="in_range" min="0" message="Please enter a value >= 0"/>
		    </param>
		    <param format="integer" name="range" type="integer" label="Range --range" value="0" size="5" help="Manually set the length of the 5' and 3' UTRs 0>50000">
		      <validator type="in_range" min="0" max="50000" message="Please enter a value between 0 and 50000"/>
		    </param>
		    <param format="integer" name="overlap" type="integer" label="Overlap --overlap" value="1" size="5" help="Sets the number of nucleotides a read has to overlap with a gene before it is considered a hit. ">
		      <validator type="in_range" min="1" message="Please enter a positive integer"/>
		    </param>
		  </when>
		  <when value="default">
		  </when>
		</conditional>
                <param name="label" type="text" format="txt" size="30" value="pyMotif" label="Enter output file label -o" />
	</inputs>

	<outputs>
		<data format="tabular" name="zscores" label="${label.value}_k-mer_Z_scores.txt"/>
		<data format="tabular" name="count" label="${label.value}_data_k-mers_count.txt"/>
		<data format="gtf" name="features" label="${label.value}_top_k-mers_in_features.gtf"/>
                <data format="tabular" name="random" label="${label.value}_random_k-mers_count.txt"/>
	</outputs>
	<help>

.. class:: infomark

**pyMotif**

pyMotif is part of the pyCRAC_ package. Looks for enriched sequence motifs in high-throughput sequencing data. Produces a GTF type output file 
with coordinates and Z-scores for enriched motifs. The GTF file can be visualised in genome browsers.
   
.. _pyCRAC: http://sandergranneman.bio.ed.ac.uk/Granneman_Lab/pyCRAC_software.html
        
------

**Parameter list**

File input options::

    -f intervals.gtf, --input_file=intervals.gtf
                        Provide the path to an interval gtf file. By default
                        it expects data from the standard input.
    -o OUTPUT_FILE, --output_file=OUTPUT_FILE
                        Use this flag to override the standard file names. Do
                        NOT add an extension.
    --gtf=annotation_file.gtf
                        type the path to the gtf annotation file that you want
                        to use
    --tab=tab_file.tab  
                        type the path to the tab file that contains the
                        genomic reference sequence

pyMotif specific options::

    --k_min=4           
                        this option allows you to set the shortest k-mer
                        length. Default = 4.
    --k_max=6           
                        this option allows you to set the longest k-mer
                        length. Default = 8.
    -n 100, --numberofkmers=100
                        choose the maximum number of enriched k-mer sequences
                        you want to have reported in output files. Default =
                        1000

pyCRAC common options::

    -a protein_coding, --annotation=protein_coding
                        select which annotation (i.e. protein_coding, ncRNA,
                        sRNA, rRNA,snoRNA,snRNA, depending on the source of
                        your GTF file) you would like to focus your search on.
                        Default = all annotations
    -r 100, --range=100
                        allows you to add regions flanking the genomic
                        feature. If you set '-r 50' or '--range=50', then the
                        program will add 50 nucleotides to each feature on
                        each side regardless of whether the GTF file has genes
                        with annotated UTRs.
    --overlap=1         
                        sets the number of nucleotides a motif has to overlap
                        with a genomic feature before it is considered a hit.
                        Default =  1 nucleotide




	</help>
</tool>