diff genSeqErrorModel.xml @ 0:6e75a84e9338 draft

planemo upload commit e96b43f96afce6a7b7dfd4499933aad7d05c955e-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/genSeqErrorModel.xml	Tue May 15 02:39:53 2018 -0400
@@ -0,0 +1,180 @@
+<tool id="genSeqErrorModel"
+      name="genSeqErrorModel"
+      version="1.0.0"
+	  profile="16.04">
+  <description>generates sequence error model for genReads. Creates model file for use in NEAT-genReads</description>
+  <requirements>
+    <requirement type="package" version="1.9.1">numpy</requirement>
+    <requirement type="package">matplotlib</requirement>
+  </requirements>
+  <command detect_errors="exit_code">
+    <![CDATA[
+	#if $lib_type_cond.read1.ext == "fastqsanger.gz":
+	  ln -s $lib_type_cond.read1 read1.fq.gz
+	  #set $read1="read1.fq.gz"
+	  #if $lib_type_cond.lib_type == 'paired':
+	    && ln -s $lib_type_cond.read2 read2.fq.gz
+		#set $read2="read2.fq.gz"
+	  #end if
+	#else
+	  ln -s $lib_type_cond.read1 read1.fq
+	  #set $read1="read1.fq"
+	  #if $lib_type_cond.lib_type == 'paired':
+	    && ln -s $lib_type_cond.read2 read2.fq
+		#set $read2="read2.fq"
+	  #end if
+	#end if
+	&& python2 $__tool_directory__/utilities/genSeqErrorModel.py
+	  -i $read1
+	#if $lib_type_cond.lib_type == 'paired':
+	  -i2 $read2
+	#end if
+	#if $stats.simulations != '':
+	  -s ${stats.simulations}
+	#end if
+	#if $stats.score_offset != '':
+	  -q ${stats.score_offset}
+	#end if
+	#if $stats.max_qualscore != '':
+	  -s ${stats.max_qualscore}
+	#end if
+	#if $stats.process_cond.process == 'max':
+	  -n ${stats.process_cond.max_reads}
+	#end if
+	-o $genSeqErrorModel_modelfile
+	]]>
+  </command>
+  <inputs>
+
+	<conditional name="lib_type_cond">
+	  <param name="lib_type"
+	         type="select"
+			 label="Single-end or paired-end sequencing library?"
+	  >
+		<option value="paired">Paired-end</option>
+	    <option value="single">Single-end</option>
+	  </param>
+	    <when value="paired">
+		<param name="read1"
+			   type="data"
+			   format="fastqsanger,fastqsanger.gz"
+			   label="The first read"
+			   help=""
+		/>
+		<param name="read2"
+			   type="data"
+			   format="fastqsanger,fastqsanger.gz"
+			   label="The second read"
+			   help=""
+		/>
+	    </when>
+		<when value="single">
+			<param name="read1"
+				   type="data"
+				   format="fastqsanger,fastqsanger.gz"
+				   label="The first read"
+				   help=""
+			/>
+	    </when>
+	</conditional>
+
+	<section name="stats"
+			 title="Miscellanous settings"
+			 expanded="false"
+			 help="The settings for the error rates etc. for the model"
+	>
+	  <param name="simulations"
+	         type="integer"
+			 value="1000000"
+			 min="1000"
+			 optional="true"
+			 label="Number of simulation iterations [-s]"
+			 help="Default is 1,000,000"
+	  />
+	  <conditional name="process_cond">
+		  <param name="process" type="select" label="Maximum number of reads to process">
+			  <option value="all">All</option>
+			  <option value="max">Set a maximum number</option>
+		  </param>
+		  <when value="max">
+			  <param name="max_reads"
+					 optional="true"
+					 type="integer"
+					 value="1000000"
+					 min="1"
+					 label="Maximum number of reads to process"
+					 help="Processing all reads is the default [-n]"
+			  />
+		  </when>
+	  </conditional>
+	  
+	  
+	  <param name="score_offset"
+			 optional="true"
+			 type="integer"
+			 label="Quality score offset (Default = 33)"
+			 help="There are different quality score offsets (depends on provider). When in doubt, leave at default (33) which is typical for modern Illumina sequencing runs [-q]"
+	  />
+	  <param name="max_qualscore"
+		 type="integer"
+		 min="1"
+		 optional="true"
+		 label="Maximum quality score (Default = 41)"
+		 help="Setting the maximum quality score may have an effect on the accuracy of the error model [-Q]"
+	  />
+
+	</section>
+
+  </inputs>
+  <outputs>
+	<data format="txt"
+		  name="genSeqErrorModel_modelfile"
+		  label="${os.path.splitext($lib_type_cond.read1.name)[0]}_genSeqErrorModel.p"
+		  metadata_source="in_type.reference">
+	</data>
+  </outputs>
+  <help>
+  </help>
+	<tests>
+		
+		<test>
+			<conditional name="lib_type_cond">
+				<param name="lib_type" value="single"/>
+				<param name="read1" value="chrMT_read1.fq" format="fastqsanger"/>
+			</conditional>
+			<section name="stats">
+				<param name="simulations" value="100000"/>
+			</section>
+			<assert_stdout has_text="saving model..."/>
+		</test>
+
+		<test>
+			<conditional name="lib_type_cond">
+				<param name="lib_type" value="paired"/>
+				<param name="read1" value="chrMT-PE_read1.fq" format="fastqsanger"/>
+				<param name="read2" value="chrMT-PE_read2.fq" format="fastqsanger"/>
+			</conditional>
+			<section name="stats">
+				<param name="simulations" value="100000"/>
+			</section>
+			<assert_stdout has_text="saving model..."/>
+		</test>
+
+		<test>
+			<conditional name="lib_type_cond">
+				<param name="lib_type" value="paired"/>
+				<param name="read1" value="chrMT-PE_read1.fq" format="fastqsanger"/>
+				<param name="read2" value="chrMT-PE_read2.fq" format="fastqsanger"/>
+			</conditional>
+			<section name="stats">
+				<param name="simulations" value="100000"/>
+				<conditional name="process_cond">
+					<param name="process" value="max"/>
+					<param name="max_reads" value="100"/>
+				</conditional>
+			</section>
+			<assert_stdout has_text="saving model..."/>
+		</test>
+
+	</tests>
+</tool>
\ No newline at end of file