diff cnv_sim.xml @ 12:12eb1e77bcfa draft

Uploaded definition file

--- a/cnv_sim.xml	Thu Aug 18 18:41:44 2016 -0400
+++ b/cnv_sim.xml	Wed Sep 07 09:31:48 2016 -0400
@@ -1,22 +1,22 @@
-<tool id="cnvsim" name="Simulate CNV" version="0.9.0">
+<tool id="cnvsim" name="Simulate CNV" version="0.9.2">
     <description>in NGS short reads </description>
     <command interpreter="python" detect_errors="exit_code">
         #if $type.simulation_type=="whole_genome"
-            cnv-sim.py -n $number_of_reads -l $read_length -g $regions_count -a $amplifications -d $deletions -min $minimum -max $maximum genome $reference
+            cnv-sim.py -n $number_of_reads -l $read_length -g $regions_count -a $amplifications_percentage -d $deletions_percentage -cn_min $minimum_copy_number -cn_max $maximum_copy_number -r_min $minimum_region_length -r_max $maximum_region_length genome $reference
         #else
-            cnv-sim.py -n $number_of_reads -l $read_length -g $regions_count -a $amplifications -d $deletions -min $minimum -max $maximum exome $reference $target
+            cnv-sim.py -n $number_of_reads -l $read_length -g $regions_count -a $amplifications_percentage -d $deletions_percentage -cn_min $minimum_copy_number -cn_max $maximum_copy_number -r_min $minimum_region_length -r_max $maximum_region_length exome $reference $target
         #end if
     </command>
     <inputs>
         <conditional name="type">
             <param name="simulation_type" type="select" label="Simulation Type">
-                <option value="whole_genome">CNV Simulation in Whole Genome</option>
-                <option value="whole_exome">CNV Simulation in Exome Regions</option>
+                <option value="whole_genome">CNV Simulation in Whole Genome Sequencing</option>
+                <option value="targeted_exome">CNV Simulation in Targeted Exome Sequencing</option>
             </param>
             <when value="whole_genome">
                 <param format="fasta" name="reference" type="data" label="Reference Genome" help="Reference genome to generate reads from"/>
             </when>
-            <when value="whole_exome">
+            <when value="targeted_exome">
                 <param format="fasta" name="reference" type="data" label="Reference Genome" help="Reference genome to generate reads from"/>
                 <param format="bed" name="target" type="data" label="Target Regions" help="a list of exonic regions"/>
             </when>
@@ -25,31 +25,35 @@
         <param name="read_length" type="integer" value="100" label="Read Length (bp)" help="determines the read length fot the generated FASTQ files"/>
         
         <param name="regions_count" type="integer" value="30" label="Regions Count" help="determines how many randomly-generated regions will show CNVs"/>
-        <param name="amplifications" type="float" value="0.5" label="Percentage of amplifications" help="determines what fraction of the regions will show amplifications (range: 0.0-1.0)"/>
-        <param name="deletions" type="float" value="0.2" label="Percentage of deletions" help="determines what fraction of the regions will show deletions (range: 0.0-1.0)"/>
-        <param name="minimum" type="integer" value="3" label="Variation minimum" help="determines the minumum number of amplifications/deletions introduced in each region"/>
-        <param name="maximum" type="integer" value="10" label="Variation maximum" help="determines the maximum number of amplifications/deletions introduced in each region"/>
+        <param name="minimum_region_length" type="integer" value="1000" label="Minimum Region Length" help="Minimum length of each CNV region"/>
+        <param name="maximum_region_length" type="integer" value="100000" label="Maximum Region Length" help="Minimum length of each CNV region"/>
+        <param name="amplifications_percentage" type="float" value="0.5" label="Percentage of amplifications" help="determines what fraction of the regions will show amplifications (range: 0.0-1.0)"/>
+        <param name="deletions_percentage" type="float" value="0.5" label="Percentage of deletions" help="determines what fraction of the regions will show deletions (range: 0.0-1.0)"/>
+        <param name="minimum_copy_number" type="integer" value="3" label="Variation minimum" help="determines the minumum number of amplifications/deletions introduced in each region"/>
+        <param name="maximum_copy_number" type="integer" value="10" label="Variation maximum" help="determines the maximum number of amplifications/deletions introduced in each region"/>
         
     </inputs>
     <outputs>
-        <data format="bed" name="cnv_list" from_work_dir="test/CNVList.bed" label="CNV List from ${tool.name} on ${on_string}"/>
-        <data format="fastq" name="control_1" from_work_dir="test/control_1.fastq" label="Control reads 1 from ${tool.name} on ${on_string}"/>
-        <data format="fastq" name="control_2" from_work_dir="test/control_2.fastq" label="Control reads 2 from ${tool.name} on ${on_string}"/>
-        <data format="fastq" name="cnv_1" from_work_dir="test/cnv_1.fastq" label="CNV reads 1 from ${tool.name} on ${on_string}"/>
-        <data format="fastq" name="cnv_2" from_work_dir="test/cnv_2.fastq" label="CNV reads 2 from ${tool.name} on ${on_string}"/>
+        <data format="bed" name="cnv_list" from_work_dir="simulation_output/copynumber.bed" label="CNV List from ${tool.name} on ${on_string}"/>
+        <data format="fastq" name="control_1" from_work_dir="simulation_output/control_1.fastq" label="Control reads 1 from ${tool.name} on ${on_string}"/>
+        <data format="fastq" name="control_2" from_work_dir="simulation_output/control_2.fastq" label="Control reads 2 from ${tool.name} on ${on_string}"/>
+        <data format="fastq" name="cnv_1" from_work_dir="simulation_output/cnv_1.fastq" label="CNV reads 1 from ${tool.name} on ${on_string}"/>
+        <data format="fastq" name="cnv_2" from_work_dir="simulation_output/cnv_2.fastq" label="CNV reads 2 from ${tool.name} on ${on_string}"/>
     </outputs>
     <help><![CDATA[ 
         .. class:: infomark
         '''TIP''' This tool requires *fasta* format.
         ----
         **CNV Simulator**
-        In genomics, Copy Number Variations (CNVs) is a type of structural variation in a genome where sections of the genome are repeated. The number if repetitions (duplications) varies between individuals in the human population.
+        In genomics, Copy Number Variations (CNVs) is a type of structural variation in a genome where sections of the genome are duplicated or deleted. The number of variations (duplications/deletions) varies between individuals in the human population.
 
-        The Copy Number Variation Simulator (CNV Sim) is a tool used to generate a set of artificial DNA fragments for Next Generation Sequencing (NGS) read simulation. When aligned back to the reference genome, the artificial generated reads show variations in the CNV regions. Variations can be either amplifications of deletions.
+        The Copy Number Variation Simulator (CNV-Sim) is a simulation tool that extends the functionality of existing next-generation sequencing read simulators to introduce copy number variations in the generated reads. The resulting reads encompass amplifications as well as deletions according to a predefined list of variant regions.
+
+        CNV-Sim aids testing and benchmarking tools for copy number variation detection and analysis. The tool offers two types of simulation:
 
         CNV-Sim offers two types of simulation:
-        1. CNV simulation in whole genome. CNV-Sim wraps the functionality of ART to introduce variations in the genome.
-        2. CNV simulation in whole exome. CNV-Sim wraps the functionality of Wessim to introduce variations in the targets.
+        1. CNV simulation in whole genome. CNV-Sim utilizes the functionality of ART to introduce variations in the genome.
+        2. CNV simulation in targeted exome. CNV-Sim utilizes the functionality of Wessim to introduce variations in the targets.
 
         Homepage: http://nabavilab.github.io/CNV-Sim/ 
     ]]></help>