Mercurial > repos > jeremie > pindel_test

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/pindel.xml	Wed Jul 02 04:40:40 2014 -0400
@@ -0,0 +1,153 @@
+<tool id="pindel" name="pindel" version="">
+	<description></description>
+	<parallelism method="basic"></parallelism>
+
+	<command interpreter="python">
+		pindel.py
+		<!-- required -->
+		-r $inputReferenceFile
+		-b $inputBamFile
+		-s $insertSize
+		-o $outputVcfFile
+		-n $sampleTag
+		<!-- optional -->
+	#if $breakdancer.checking == "yes":
+		-input1 $breakdancer.input1
+	#end if
+		--number_of_threads $number_of_threads
+		--window_size $window_size
+		--sequencing_error_rate $sequencing_error_rate
+		--sensitivity $sensitivity
+	#if $reportInversions:
+		--report_inversions
+	#end if
+	#if $reportDuplications:
+		--report_duplications
+	#end if
+	#if $reportLongInsertions:
+		--report_long_insertions
+	#end if
+	#if $reportBreakpoints:
+		--report_breakpoints
+	#end if
+	</command>
+
+	<inputs>
+		<!-- required -->
+		<param format="fasta" name="inputReferenceFile" type="data" label="reference file" help="" />
+		<param format="bam" name="inputBamFile" type="data" label="bam file" help="" />
+		<param name="insertSize" type="integer" label="insert size of the reads" value="500" />
+		<param name="sampleTag" type="text" label="tag for this sample" value="sample" />
+
+		<!-- optional -->
+		<param name="number_of_threads" type="integer" label="the number of threads Pindel will use" value="4" />
+
+		<param name="window_size" type="integer" value="5" label="for saving RAM, divides the reference in bins of X million bases and only analyzes the reads that belong in the current bin, (default 5 (=5 million))" />
+
+		<param name="sequencing_error_rate" type="float" value="0.01" />
+
+		<param name="sensitivity" type="float" value="0.95" label="sensitivity"
+ help="Pindel only reports reads if they can be fit around an event within a certain number of mismatches. If the fraction of sequencing errors is 0.01, (so we'd expect a total error rate of 0.011 since on average 1 in 1000 bases is a SNP) and pindel calls a deletion, but there are 4 mismatched bases in the new fit of the pindel read (100 bases) to the reference genome, Pindel would calculate that with an error rate of 0.01 (=0.011 including SNPs) the chance that there are 0, 1 or 2 mismatched bases in the reference genome is 90%. Setting -E to .90 (=90%) will thereforethrow away all reads with 3 or more mismatches, even though that means that you throw away 1 in 10 valid reads. Increasing this parameter to say 0.99 will increase the sensitivity of pindel though you may get more false positives, decreasing the parameter ensures you only get very good matches but pindel may not find as many events. (default 0.95)" />
+
+		<!-- <param name="maximum_allowed_mismatch_rate" type="float" value="0.02" label="maximum allowed mismatch rate" help="Only reads with more than this fraction of mismatches than the reference genome will be considered as harboring potential SVs." />
+
+		<param name="NM" type="integer" value="2" label="NM" help="the minimum number of edit distance between reads and reference genome (default 2). reads at least NM edit distance (>= NM) will be realigned" /> -->
+
+		<param name="reportInversions" type="boolean" label="report inversions" checked="true"/>
+		<param name="reportDuplications" type="boolean" label="report duplications" checked="true"/>
+		<param name="reportLongInsertions" type="boolean" label="report long insertions" checked="true"/>
+		<param name="reportBreakpoints" type="boolean" label="report breakpoints" checked="true"/>
+
+
+<!-- 		<conditional name="report_close_mapped_reads">
+			<param name="checking" type="select" label="report reads of which only one end (the one closest to the mapped read of the paired-end read) could be mapped.">
+				<option value="yes">Yes</option>
+				<option value="no" selected="True">No</option>
+			</param>
+			<when value="yes" />
+			<when value="no" />
+		</conditional>
+
+		<conditional name="report_only_close_mapped_reads">
+			<param name="checking" type="select" label="do not search for SVs, only report reads of which only one end (the one closest to the mapped read of the paired-end read) could be mapped (the output file can then be used as an input file for another run of pindel, which may save size if you need to transfer files). (default false)">
+				<option value="yes">Yes</option>
+				<option value="no" selected="True">No</option>
+			</param>
+			<when value="yes" />
+			<when value="no" />
+		</conditional>
+
+		<conditional name="report_interchromosomal_events">
+			<param name="checking" type="select" label="search for interchromosomal events. Note: will require the computer to have at least 4 GB of memory">
+				<option value="yes">Yes</option>
+				<option value="no" selected="True">No</option>
+			</param>
+			<when value="yes" />
+			<when value="no" />
+		</conditional> -
+
+		<conditional name="IndelCorrection">
+			<param name="checking" type="select" label="search for consensus indels to corret contigs (default false)">
+				<option value="yes">Yes</option>
+				<option value="no" selected="True">No</option>
+			</param>
+			<when value="yes" />
+			<when value="no" />
+		</conditional>
+
+		<conditional name="NormalSamples">
+			<param name="checking" type="select" label="Turn on germline filtering, less sensistive and you may miss somatic calls (default false)">
+				<option value="yes">Yes</option>
+				<option value="no" selected="True">No</option>
+			</param>
+			<when value="yes" />
+			<when value="no" />
+		</conditional>
+		-->
+
+		<conditional name="breakdancer">
+			<param name="checking" type="select" label="use calls from an other method?">
+				<option value="yes">Yes</option>
+				<option value="no" selected="True">No</option>
+			</param>
+			<when value="yes">
+				<param name="input1" type="data" format="tabular" label="variant call file" help="Pindel is able to use calls from other SV methods such as BreakDancer to further increase sensitivity and specificity. BreakDancer result or calls from any methods must in the format: ChrA LocA stringA ChrB LocB stringB other" />
+			</when>
+
+			<when value="no" />
+		</conditional>
+
+		<!-- <param name="additional_mismatch" type="integer" value="1" label="additional mismatch" help="Pindel will only map part of a read to the reference genome if there are no other candidate positions with no more than the specified number of mismatches position. The bigger the value, the more accurate but less sensitive. (minimum value 1, default value 1)" />
+
+		<param name="min_perfect_match_around_BP" type="integer" value="3" label="min perfect match around BP" help="at the point where the read is split into two, there should at least be this number of perfectly matching bases between read and reference (default value 3)" />
+
+		<param name="min_inversion_size" type="integer" value="50" label="min inversion size" help="only report inversions greater than this number of bases (default 50)" />
+
+		<param name="min_num_matched_bases" type="integer" value="30" label="min num matched bases" help="only consider reads as evidence if they map with more than X bases to the reference. (default 30)" />
+
+		<param name="balance_cutoff" type="integer" value="0" label="balance cutoff" help="the number of bases of a SV above which a more stringent filter is applied which demands that both sides of the SV are mapped with sufficiently long strings of bases (default 0)" />
+
+		<param name="anchor_quality" type="integer" value="0" label="anchor quality" help="the minimal mapping quality of the reads Pindel uses as anchor If you only need high confident calls, set to 30 or higher(default 0)" />
+
+		<param name="minimum_support_for_event" type="integer" value="3" label="minimum support for event" help="Pindel only calls events which have this number or more supporting reads (default 3)" />
+
+		<param name="input_SV_Calls_for_assembly" type="text" value="" label="input SV Calls for assembly" help="A filename of a list of SV calls for assembling breakpoints
+			Types: DEL, INS, DUP, INV, CTX and ITX
+			File format: Type chrA posA Confidence_Range_A chrB posB
+		   Confidence_Range_B
+			Example: DEL chr1 10000 50 chr2 20000 100" />
+
+		<param name="genotyping" type="boolean" truevalue="true" falsevalue="false" checked="no" label="genotyping" help="gentype variants if -i is also used." /> -->
+	</inputs>
+
+	<outputs>
+		<data format="vcf" name="outputVcfFile" label="vcf pindel"/>
+	</outputs>
+
+	<help>
+	</help>
+
+	<tests>
+	</tests>
+
+</tool>
\ No newline at end of file