Mercurial > repos > iuc > rna_starsolo

changeset 20:45795f582ae9 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/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 2b3fa63863a366beef057c7f75ccbcaf0c280151
author iuc
date Tue, 27 Aug 2024 14:11:53 +0000
parents 42ce70172b72
children
files macros.xml rg_rnaStarSolo.xml test-data/filtered3.vcf test-data/filtered4.bam test-data/rnastar_test.log test-data/rnastar_test_splicejunctions_wasp.bed
diffstat 6 files changed, 497 insertions(+), 105 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Wed Feb 14 09:04:09 2024 +0000
+++ b/macros.xml	Tue Aug 27 14:11:53 2024 +0000
@@ -5,7 +5,7 @@
     the index versions in sync, but you should manually update @IDX_VERSION_SUFFIX@ -->
     <!-- STAR version to be used -->
     <token name="@TOOL_VERSION@">2.7.11a</token>
-    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@VERSION_SUFFIX@">1</token>
     <token name="@PROFILE@">21.01</token>
     <!-- STAR index version compatible with this version of STAR
     This is the STAR version that introduced the index structure expected
@@ -17,16 +17,14 @@
     <token name="@IDX_VERSION@">2.7.4a</token>
     <token name="@IDX_VERSION_SUFFIX@">2</token>
     <token name="@IDX_DATA_TABLE@">rnastar_index2x_versioned</token>
-
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">star</requirement>
             <requirement type="package" version="1.18">samtools</requirement>
             <requirement type="package" version="1.13">gzip</requirement>
-            <yield />
+            <yield/>
         </requirements>
     </xml>
-
     <xml name="edam">
         <edam_topics>
             <edam_topic>topic_3170</edam_topic>
@@ -36,20 +34,16 @@
             <edam_operation>operation_0292</edam_operation>
         </edam_operations>
     </xml>
-
     <xml name="index_selection" token_with_gene_model="0">
-        <param argument="--genomeDir" type="select"
-        label="Select reference genome"
-        help="If your genome of interest is not listed, contact the Galaxy team">
+        <param argument="--genomeDir" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
             <options from_data_table="@IDX_DATA_TABLE@">
-                <filter type="static_value" column="4" value="@WITH_GENE_MODEL@" />
-                <filter type="static_value" column="5" value="@IDX_VERSION@" />
-                <filter type="sort_by" column="2" />
-                <validator type="no_options" message="No indexes are available for the selected input dataset" />
+                <filter type="static_value" column="4" value="@WITH_GENE_MODEL@"/>
+                <filter type="static_value" column="5" value="@IDX_VERSION@"/>
+                <filter type="sort_by" column="2"/>
+                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
             </options>
         </param>
     </xml>
-
     <token name="@FASTQ_GZ_OPTION@">
         --readFilesCommand zcat
     </token>
@@ -59,9 +53,9 @@
         </citations>
     </xml>
     <xml name="SJDBOPTIONS">
-         <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/>
-         <param argument="--sjdbGTFfeatureExon" type="text" value="exon" label="Elements to use from the gene model to use for splice junctions" help="By default and for almost all cases: 'exon', referring to finding junctions at the RNA splice sites. This can optionally be changed to allow splicing at other levels, such as 'gene', 'transcript', 'CDS'."/>
-         <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/>
+        <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/>
+        <param argument="--sjdbGTFfeatureExon" type="text" value="exon" label="Elements to use from the gene model to use for splice junctions" help="By default and for almost all cases: 'exon', referring to finding junctions at the RNA splice sites. This can optionally be changed to allow splicing at other levels, such as 'gene', 'transcript', 'CDS'."/>
+        <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/>
     </xml>
     <xml name="dbKeyActions">
         <actions>
@@ -80,7 +74,7 @@
             </when>
             <when value="history">
                 <action type="metadata" name="dbkey">
-                    <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
+                    <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey"/>
                 </action>
             </when>
         </conditional>
@@ -135,7 +129,7 @@
         &&
     #end if
     ]]></token>
-    <token name="@REFGENOMEHANDLING@" ><![CDATA[
+    <token name="@REFGENOMEHANDLING@"><![CDATA[
     --runThreadN \${GALAXY_SLOTS:-4}
     --genomeLoad NoSharedMemory
     --genomeDir
@@ -154,7 +148,7 @@
         #end if
     #end if
     ]]></token>
-    <token name="@READSHANDLING@" ><![CDATA[
+    <token name="@READSHANDLING@"><![CDATA[
     ## Check that the input pairs are of the same type
     ## otherwise STARsolo will run for a long time and then error out.
     ## We consume either repeats of two inputs R1 + R2
@@ -183,59 +177,57 @@
         @FASTQ_GZ_OPTION@
     #end if
     ]]></token>
-    <token name="@LIMITS@" ><![CDATA[
+    <token name="@LIMITS@"><![CDATA[
         --limitOutSJoneRead $getVar('algo.params.junction_limits.limitOutSJoneRead', $getVar('solo.junction_limits.limitOutSJoneRead', 1000))
         --limitOutSJcollapsed $getVar('algo.params.junction_limits.limitOutSJcollapsed', $getVar('solo.junction_limits.limitOutSJcollapsed', 1000000))
         --limitSjdbInsertNsj $getVar('algo.params.junction_limits.limitSjdbInsertNsj', $getVar('solo.junction_limits.limitSjdbInsertNsj', 1000000))
     ]]></token>
     <xml name="ref_selection">
-        <param argument="--genomeFastaFiles" type="data" format="fasta,fasta.gz" label="Select a reference genome" />
-          <param argument="--genomeSAindexNbases" type="integer" min="2" max="16" value="14" label="Length of the SA pre-indexing string" help="Typically between 10 and 15. Longer strings will use much more memory, but allow faster searches. For small genomes, the parameter --genomeSAindexNbases must be scaled down to min(14, log2(GenomeLength)/2 - 1)"/>
+        <param argument="--genomeFastaFiles" type="data" format="fasta,fasta.gz" label="Select a reference genome"/>
+        <param argument="--genomeSAindexNbases" type="integer" min="2" max="16" value="14" label="Length of the SA pre-indexing string" help="Typically between 10 and 15. Longer strings will use much more memory, but allow faster searches. For small genomes, the parameter --genomeSAindexNbases must be scaled down to min(14, log2(GenomeLength)/2 - 1)"/>
     </xml>
-    <xml name="stdio" >
+    <xml name="stdio">
         <stdio>
             <regex match="FATAL error" source="both" level="fatal"/>
             <regex match="EXITING: FATAL INPUT ERROR:" source="both" level="fatal"/>
             <regex match="EXITING: fatal error trying to allocate genome arrays, exception thrown: std::bad_alloc" source="both" level="fatal"/>
             <regex match="\[sam_read1\] missing header\? Abort!" source="both" level="fatal"/>
-            <yield />
+            <yield/>
         </stdio>
     </xml>
     <xml name="input_selection">
-        <conditional name="input_types" >
-            <param name="use" type="select" label="Input Type" >
-                <option value="repeat" >Separate barcode and cDNA reads</option>
-                <option value="list_paired" >Paired collection of barcode and cDNA reads</option>
+        <conditional name="input_types">
+            <param name="use" type="select" label="Input Type">
+                <option value="repeat">Separate barcode and cDNA reads</option>
+                <option value="list_paired">Paired collection of barcode and cDNA reads</option>
             </param>
             <when value="repeat">
-                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data"  multiple="true"
-                label="RNA-Seq FASTQ/FASTA file, Barcode reads" />
-                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data"  multiple="true"
-                label="RNA-Seq FASTQ/FASTA file, cDNA reads"/>
+                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" multiple="true" label="RNA-Seq FASTQ/FASTA file, Barcode reads"/>
+                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" multiple="true" label="RNA-Seq FASTQ/FASTA file, cDNA reads"/>
             </when>
             <when value="list_paired">
-                <param name="input_collection" collection_type="paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="Collection of Pairs" />
+                <param name="input_collection" collection_type="paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="Collection of Pairs"/>
             </when>
         </conditional>
     </xml>
     <xml name="input_selection_smart_seq">
-        <conditional name="input_types_smart_seq" >
-            <param name="use" type="select" label="Input Type" >
-                <option value="list_single_end" >Single-end FASTQ collection</option>
-                <option value="list_paired_end" >Paired FASTQ collection</option>
+        <conditional name="input_types_smart_seq">
+            <param name="use" type="select" label="Input Type">
+                <option value="list_single_end">Single-end FASTQ collection</option>
+                <option value="list_paired_end">Paired FASTQ collection</option>
             </param>
             <when value="list_single_end">
-                <param name="single_end_collection" collection_type="list" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of single-end FASTQ files" />
+                <param name="single_end_collection" collection_type="list" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of single-end FASTQ files"/>
             </when>
             <when value="list_paired_end">
-                <param name="paired_end_collection" collection_type="list:paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of paired-end FASTQ files" />
+                <param name="paired_end_collection" collection_type="list:paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of paired-end FASTQ files"/>
             </when>
         </conditional>
     </xml>
     <xml name="umidedup_options">
         <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other (1MM_All)</option>
-        <option value="1MM_Directional_UMItools" >Directional method from the UMI-tool</option>
-        <option value="1MM_Directional" >Directional with stringent UMI deduplication</option>
+        <option value="1MM_Directional_UMItools">Directional method from the UMI-tool</option>
+        <option value="1MM_Directional">Directional with stringent UMI deduplication</option>
     </xml>
     <xml name="anchor_types">
         <option value="0">Read start</option>
@@ -244,16 +236,16 @@
         <option value="3">Adapter end</option>
     </xml>
     <xml name="cb_match_wl_common">
-        <option value="Exact" >Exact</option>
-        <option value="1MM" >Single match (1MM)</option>
+        <option value="Exact">Exact</option>
+        <option value="1MM">Single match (1MM)</option>
     </xml>
     <xml name="cb_match_wl_cellranger">
-        <option value="1MM_multi" selected="true" >Multiple matches (CellRanger 2, 1MM_multi)</option>
-        <option value="1MM_multi_pseudocounts" >Multiple matches (CellRanger 3, 1MM_multi_pseudocounts)</option>
-        <option value="1MM_multi_Nbase_pseudocounts" >Multimatching to WL is allowed for CBs with N-bases (CellRanger 3, 1MM_multi_Nbase_pseudocounts)</option>
+        <option value="1MM_multi" selected="true">Multiple matches (CellRanger 2, 1MM_multi)</option>
+        <option value="1MM_multi_pseudocounts">Multiple matches (CellRanger 3, 1MM_multi_pseudocounts)</option>
+        <option value="1MM_multi_Nbase_pseudocounts">Multimatching to WL is allowed for CBs with N-bases (CellRanger 3, 1MM_multi_Nbase_pseudocounts)</option>
     </xml>
     <xml name="solo_adapter_params">
-        <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes." >
+        <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes.">
             <sanitizer>
                 <valid initial="string.digits">
                     <add value="-"/>
@@ -265,11 +257,11 @@
                 </valid>
             </sanitizer>
         </param>
-        <param argument="--soloAdapterMismatchesNmax" type="integer" min="1" value="1" label="Maximum number of mismatches allowed in adapter sequence" />
-        <param argument="--clipAdapterType" type="select" >
-            <option value="Hamming" selected="true" >Adapter clipping based on Hamming distance</option>
-            <option value="CellRanger4" >5p and 3p adapter clipping similar to CellRanger4</option>
-            <option value="None" >No adapter clipping</option>
+        <param argument="--soloAdapterMismatchesNmax" type="integer" min="1" value="1" label="Maximum number of mismatches allowed in adapter sequence"/>
+        <param argument="--clipAdapterType" type="select">
+            <option value="Hamming" selected="true">Adapter clipping based on Hamming distance</option>
+            <option value="CellRanger4">5p and 3p adapter clipping similar to CellRanger4</option>
+            <option value="None">No adapter clipping</option>
         </param>
     </xml>
     <xml name="common_SAM_attributes">
@@ -284,14 +276,14 @@
     </xml>
     <xml name="limits">
         <section name="junction_limits" title="Junction Limits" expanded="false">
-            <param argument="--limitOutSJoneRead" type="integer" min="1" value="1000" label="Maximum number of junctions for one read (including all multimappers)" />
-            <param argument="--limitOutSJcollapsed" type="integer" min="1" value="1000000" label="Maximum number of collapsed junctions" />
-            <param argument="--limitSjdbInsertNsj" type="integer" min="0" value="1000000" label="Maximum number of inserts to be inserted into the genome on the fly." />
+            <param argument="--limitOutSJoneRead" type="integer" min="1" value="1000" label="Maximum number of junctions for one read (including all multimappers)"/>
+            <param argument="--limitOutSJcollapsed" type="integer" min="1" value="1000000" label="Maximum number of collapsed junctions"/>
+            <param argument="--limitSjdbInsertNsj" type="integer" min="0" value="1000000" label="Maximum number of inserts to be inserted into the genome on the fly."/>
         </section>
     </xml>
     <xml name="outCountActions">
         <actions>
-            <action name="column_names" type="metadata" default="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand" />
+            <action name="column_names" type="metadata" default="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand"/>
             <expand macro="dbKeyAction"/>
         </actions>
     </xml>
@@ -304,7 +296,7 @@
             </param>
             <when value="None">
                 <!-- This is necessary for the filtering of output -->
-                <param name="outWigStrand" type="hidden" value="false" />
+                <param name="outWigStrand" type="hidden" value="false"/>
             </when>
             <when value="bedGraph">
                 <expand macro="outWigParams"/>
@@ -352,73 +344,92 @@
     <xml name="outWigOutputs">
         <data format="bedgraph" name="signal_unique_str1" label="${tool.name} on ${on_string}: Coverage Uniquely mapped strand 1" from_work_dir="Signal.Unique.str1.out">
             <filter>outWig['outWigType'] != "None"</filter>
-            <expand macro="dbKeyActions" />
+            <expand macro="dbKeyActions"/>
             <change_format>
-                <when input="outWig.outWigType" value="wiggle" format="wig" />
+                <when input="outWig.outWigType" value="wiggle" format="wig"/>
             </change_format>
         </data>
         <data format="bedgraph" name="signal_uniquemultiple_str1" label="${tool.name} on ${on_string}: Coverage Uniquely + Multiple mapped strand 1" from_work_dir="Signal.UniqueMultiple.str1.out">
             <filter>outWig['outWigType'] != "None"</filter>
-            <expand macro="dbKeyActions" />
+            <expand macro="dbKeyActions"/>
             <change_format>
-                <when input="outWig.outWigType" value="wiggle" format="wig" />
+                <when input="outWig.outWigType" value="wiggle" format="wig"/>
             </change_format>
         </data>
         <data format="bedgraph" name="signal_unique_str2" label="${tool.name} on ${on_string}: Coverage Uniquely mapped strand 2" from_work_dir="Signal.Unique.str2.out">
             <filter>outWig['outWigType'] != "None" and outWig['outWigStrand']</filter>
-            <expand macro="dbKeyActions" />
+            <expand macro="dbKeyActions"/>
             <change_format>
-                <when input="outWig.outWigType" value="wiggle" format="wig" />
+                <when input="outWig.outWigType" value="wiggle" format="wig"/>
             </change_format>
         </data>
         <data format="bedgraph" name="signal_uniquemultiple_str2" label="${tool.name} on ${on_string}: Coverage Uniquely + Multiple mapped strand 2" from_work_dir="Signal.UniqueMultiple.str2.out">
             <filter>outWig['outWigType'] != "None" and outWig['outWigStrand']</filter>
-            <expand macro="dbKeyActions" />
+            <expand macro="dbKeyActions"/>
             <change_format>
-                <when input="outWig.outWigType" value="wiggle" format="wig" />
+                <when input="outWig.outWigType" value="wiggle" format="wig"/>
             </change_format>
         </data>
     </xml>
     <xml name="quantMode">
         <conditional name="quantmode_output">
-            <param argument="--quantMode" type="select"
-            label="Per gene/transcript output"
-            help="STAR can provide analysis results not only with respect to the reference genome, but also with respect to genes and transcripts described by a gene model. Note: This functionality requires either the selection above of a cached index with a gene model, or a gene model provided alongside the index/reference genome in GTF or GFF3 format!">
+            <param argument="--quantMode" type="select" label="Per gene/transcript output" help="STAR can provide analysis results not only with respect to the reference genome, but also with respect to genes and transcripts described by a gene model. Note: This functionality requires either the selection above of a cached index with a gene model, or a gene model provided alongside the index/reference genome in GTF or GFF3 format!">
                 <option value="-">No per gene or transcript output</option>
                 <option value="GeneCounts">Per gene read counts (GeneCounts)</option>
                 <option value="TranscriptomeSAM">Transcript-based BAM output (TranscriptomeSAM)</option>
                 <option value="TranscriptomeSAM GeneCounts">Both per gene read counts and transcript-based BAM output (TranscriptomeSAM GeneCounts)</option>
             </param>
-            <when value="-" />
-            <when value="GeneCounts" />
+            <when value="-"/>
+            <when value="GeneCounts"/>
             <when value="TranscriptomeSAM">
-                <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend"
-                label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?"
-                help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled." />
+                <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend" label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?" help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled."/>
             </when>
             <when value="TranscriptomeSAM GeneCounts">
-                <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend"
-                label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?"
-                help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled." />
+                <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend" label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?" help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled."/>
             </when>
         </conditional>
     </xml>
     <xml name="quantModeNoGTF">
         <conditional name="quantmode_output">
-            <param argument="--quantMode" type="select"
-            label="Per gene/transcript output">
+            <param argument="--quantMode" type="select" label="Per gene/transcript output">
                 <option value="-">No per gene or transcript output as no GTF was provided</option>
             </param>
-            <when value="-" />
+            <when value="-"/>
         </conditional>
     </xml>
     <xml name="outSAMmapqUnique">
         <!-- MAPQ 255 is the default in STAR (coming from tophat behaviour and compatibility for Cufflinks) but it is a problematic value
         - according to SAM/BAM specs it means "undefined".
         - Using 255 as the max mapq causes problem with modern downstream tools like mutect2: https://sites.duke.edu/workblog/2021/08/18/star-rnaseq-gatk-mutect2/ and 60 has become an inofficial replacement for 255. -->
-        <param argument="--outSAMmapqUnique" type="integer" value="60" min="0" max="255"
-        label="MAPQ value for unique mappers"
-        help="STAR bases the mapping quality scores of alignment records in its BAM output on the number of alternative mappings for the read. If a read maps to multiple locations on the reference genome, the following MAPQ scoring scheme is
-used: >=5 mappings => MAPQ=0; 3-4 mappings => MAPQ=1; 2 mappings => MAPQ=3. This setting lets you control the MAPQ used for reads mapped to a single location. Set to 255 for compatibility with Cufflink (default in STAR) but keep to 60 for modern downstream tools like mutect2." />
+        <param argument="--outSAMmapqUnique" type="integer" value="60" min="0" max="255" label="MAPQ value for unique mappers" help="STAR bases the mapping quality scores of alignment records in its BAM output on the number of alternative mappings for the read. If a read maps to multiple locations on the reference genome, the following MAPQ scoring scheme is used: &gt;=5 mappings =&gt; MAPQ=0; 3-4 mappings =&gt; MAPQ=1; 2 mappings =&gt; MAPQ=3. This setting lets you control the MAPQ used for reads mapped to a single location. Set to 255 for compatibility with Cufflink (default in STAR) but keep to 60 for modern downstream tools like mutect2."/>
+    </xml>
+    <xml name="wasp">
+        <!--
+            This is re-implementation of the original WASP algorithm by Bryce van de Geijn, Graham McVicker,
+            Yoav Gilad and Jonathan K Pritchard. Please cite the original WASP paper: Nature Methods 12,
+            1061–1063 (2015) https://www.nature.com/articles/nmeth.3582. WASP filtering is activated
+            with "waspOutputMode SAMtag".
+            -->
+        <conditional name="wasp_conditional">
+            <param argument="--waspOutputMode" type="select" label="Actiavte WASP filtering">
+                <help><![CDATA[This is a reimplementation of the original WASP algorithm by Bryce van de Geijn, Graham McVicker,
+                    Yoav Gilad and Jonathan K Pritchard. https://doi.org/10.1038/nmeth.3582. This option will add the vW tag to the SAM output. vW:i:1 means
+                    alignment passed WASP filtering, and all other values mean it did not:<br/>
+                    - vW:i:2 = multi-mapping read<br/>
+                    - vW:i:3 = variant base in the read is N (non-ACGT)<br/>
+                    - vW:i:4 = remapped read did not map <br/>
+                    - vW:i:5 = remapped read multi-maps <br/>
+                    - vW:i:6 = remapped read maps to a different locus <br/>
+                    - vW:i:7 = read overlaps too many variants <br/>
+                    ]]>
+                </help>
+                <option value="" selected="true">No WASP filtering</option>
+                <option value="wasp_mode">Activate WASP filtering</option>
+            </param>
+            <when value="wasp_mode">
+                <param argument="--varVCFfile" type="data" format="vcf" label="VCF file with personal variants" help="Each variant is expected to have a genotype with two alleles. The VCF file needs to have the 10th column with genotype recorded as 0/1, 1/0, 1/1 (or | instead of /)"/>
+            </when>
+            <when value=""/>
+        </conditional>
     </xml>
 </macros>
--- a/rg_rnaStarSolo.xml	Wed Feb 14 09:04:09 2024 +0000
+++ b/rg_rnaStarSolo.xml	Tue Aug 27 14:11:53 2024 +0000
@@ -94,6 +94,11 @@
     --soloCBwhitelist None
     #end if
 
+    #if $solo.wasp_conditional.waspOutputMode == "wasp_mode":
+        --waspOutputMode SAMtag
+        --varVCFfile '$solo.wasp_conditional.varVCFfile'
+    #end if
+
     --soloStrand $solo.soloStrand
     --soloFeatures $solo.soloFeatures
     --soloUMIdedup $sc.umidedup.soloUMIdedup
@@ -355,6 +360,7 @@
                 <option value="GeneFull_Ex50pAS" >Full: Count all reads overlapping genes' exons and introns: prioritize 50% overlap with exons. Do not count reads with 100% exonic overlap in the antisense direction.</option>
                 <option value="Gene Velocyto">Velocyto: calculate spliced, unspliced, and ambiguous counts per cell per gene similar to the velocyto tool</option>
             </param>
+            <expand macro="wasp"/>
             <conditional name="filter" >
                 <param name="filter_type" type="select" label="Cell filtering type and parameters" >
                     <option value="cellranger2" selected="true" >Simple filtering of CellRanger v2</option>
@@ -515,6 +521,10 @@
                 <param name="soloStrand" value="Forward" />
                 <param name="soloFeatures" value="Gene" />
                 <param name="quantModeGene" value="true" />
+                <conditional name="wasp_conditional">
+                    <param name="waspOutputMode" value="wasp_mode"/>
+                    <param name="varVCFfile" value="filtered3.vcf" ftype="vcf" />
+                </conditional>
             </section>
             <output name="output_barcodes" >
                 <assert_contents>
@@ -544,7 +554,7 @@
                     <has_line_matching expression="\s+yesUMIs\s+8" />
                 </assert_contents>
             </output>
-            <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" />
+            <output name="output_BAM" value="filtered4.bam" ftype="bam" lines_diff="6"/>
             <output name="reads_per_gene" >
                 <assert_contents>
                     <has_line_matching expression="ENSG00000279493\s+0\s+0\s+0" />
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtered3.vcf	Tue Aug 27 14:11:53 2024 +0000
@@ -0,0 +1,175 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##bcftoolsVersion=1.15.1+htslib-1.15.1
+##bcftoolsCommand=mpileup -f filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa filtered3.bam
+##reference=file://filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa
+##contig=<ID=21,length=697740>
+##ALT=<ID=*,Description="Represents allele(s) other than observed.">
+##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL.">
+##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of raw reads supporting an indel">
+##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of raw reads supporting an indel">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth">
+##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)",Version="3">
+##INFO=<ID=RPBZ,Number=1,Type=Float,Description="Mann-Whitney U-z test of Read Position Bias (closer to 0 is better)">
+##INFO=<ID=MQBZ,Number=1,Type=Float,Description="Mann-Whitney U-z test of Mapping Quality Bias (closer to 0 is better)">
+##INFO=<ID=BQBZ,Number=1,Type=Float,Description="Mann-Whitney U-z test of Base Quality Bias (closer to 0 is better)">
+##INFO=<ID=MQSBZ,Number=1,Type=Float,Description="Mann-Whitney U-z test of Mapping Quality vs Strand Bias (closer to 0 is better)">
+##INFO=<ID=SCBZ,Number=1,Type=Float,Description="Mann-Whitney U-z test of Soft-Clip Length Bias (closer to 0 is better)">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric.">
+##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward , ref-reverse, alt-forward and alt-reverse bases">
+##INFO=<ID=MQ,Number=1,Type=Integer,Description="Average mapping quality">
+##bcftools_callVersion=1.15.1+htslib-1.15.1
+##bcftools_callCommand=call -mv -Ob -o filtered3.bcf; Date=Tue Aug 27 14:09:53 2024
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	filtered3.bam
+21	13871	.	G	A	8.19139	.	DP=16;VDB=0.163924;SGB=-0.651104;RPBZ=-1.26304;MQBZ=1.7272;BQBZ=1;SCBZ=-0.447396;FS=0;MQ0F=0.0625;AC=1;AN=2;DP4=8,0,8,0;MQ=9	GT:PL	0/1:38,0,6
+21	13918	.	A	G	8.05611	.	DP=9;VDB=0.12166;SGB=-0.616816;RPBZ=1.03713;MQBZ=-0.154303;BQBZ=0;SCBZ=0.707107;FS=0;MQ0F=0.111111;AC=1;AN=2;DP4=3,0,6,0;MQ=14	GT:PL	0/1:40,0,15
+21	13924	.	G	A	27.0767	.	DP=11;VDB=0.0108096;SGB=-0.651104;RPBZ=-0.261911;MQBZ=0.968246;BQBZ=-0.745356;SCBZ=-0.931695;FS=0;MQ0F=0.0909091;AC=2;AN=2;DP4=2,0,8,0;MQ=14	GT:PL	1/1:54,3,0
+21	13928	.	G	C	34.42	.	DP=11;VDB=0.0257451;SGB=-0.670168;FS=0;MQ0F=0.0909091;AC=2;AN=2;DP4=0,0,10,0;MQ=14	GT:PL	1/1:64,24,0
+21	13962	.	A	G	3.21856	.	DP=13;VDB=0.00595258;SGB=-0.616816;RPBZ=2.14581;MQBZ=0.245201;BQBZ=-0.113961;SCBZ=-1.73888;FS=0;MQ0F=0.0769231;AC=1;AN=2;DP4=7,0,6,0;MQ=12	GT:PL	0/1:33,0,34
+21	15349	.	G	C	3.74242	.	DP=33;VDB=3.28209e-07;SGB=-0.689466;RPBZ=-1.0584;MQBZ=1.31911;MQSBZ=-1.01601;BQBZ=-1.40181;SCBZ=0.601646;FS=0;MQ0F=0.0606061;AC=1;AN=2;DP4=1,15,1,15;MQ=13	GT:PL	0/1:34,0,49
+21	15425	.	T	C	15.3182	.	DP=21;VDB=0.739317;SGB=-0.686358;RPBZ=-1.79168;MQBZ=0.125524;BQBZ=1.41022;SCBZ=0.514874;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,7,0,14;MQ=12	GT:PL	0/1:47,0,9
+21	15431	.	G	A	6.81655	.	DP=18;VDB=0.777008;SGB=-0.683931;RPBZ=-0.93741;MQBZ=-1.01859;BQBZ=1.61245;SCBZ=-1.53815;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,5,0,13;MQ=10	GT:PL	0/1:38,0,11
+21	19605	.	A	G	7.20516	.	DP=9;VDB=0.534935;SGB=-0.590765;RPBZ=0.489898;MQBZ=0.169031;MQSBZ=-0.534522;BQBZ=0.33541;SCBZ=-0.873128;FS=0;MQ0F=0;AC=1;AN=2;DP4=1,3,0,5;MQ=16	GT:PL	0/1:39,0,26
+21	19637	.	A	G	12.9958	.	DP=5;VDB=0.360777;SGB=-0.556411;RPBZ=-0.707107;MQBZ=-0.5;MQSBZ=-0.5;BQBZ=-0.5;SCBZ=0.5;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,1,1,3;MQ=16	GT:PL	0/1:43,0,5
+21	19654	.	C	T	4.85359	.	DP=4;VDB=0.18;SGB=-0.453602;RPBZ=-1.54919;MQBZ=1.63299;MQSBZ=-0.942809;BQBZ=0;SCBZ=1;FS=0;MQ0F=0.25;AC=2;AN=2;DP4=0,2,1,1;MQ=10	GT:PL	1/1:30,2,0
+21	19742	.	T	C	7.30814	.	DP=2;VDB=0.36;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	19744	.	A	G	7.30814	.	DP=2;VDB=0.32;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	19811	.	T	C	8.50643	.	DP=10;VDB=0.0411825;SGB=-0.616816;RPBZ=-0.427699;MQBZ=1.71761;BQBZ=0;SCBZ=-0.731925;FS=0;MQ0F=0.2;AC=1;AN=2;DP4=4,0,6,0;MQ=10	GT:PL	0/1:38,0,5
+21	19866	.	A	C	37.4152	.	DP=6;VDB=0.168702;SGB=-0.616816;FS=0;MQ0F=0.166667;AC=2;AN=2;DP4=0,0,6,0;MQ=16	GT:PL	1/1:67,18,0
+21	19881	.	T	C	19.4636	.	DP=4;VDB=0.784982;SGB=-0.556411;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,4,0;MQ=15	GT:PL	1/1:49,12,0
+21	20703	.	A	G	6.0118	.	DP=15;VDB=0.000802463;SGB=-0.680642;RPBZ=1.37489;MQBZ=-0.787761;BQBZ=2;SCBZ=0;FS=0;MQ0F=0.133333;AC=1;AN=2;DP4=3,0,12,0;MQ=11	GT:PL	0/1:33,0,2
+21	20716	.	A	G	21.9575	.	DP=21;VDB=0.0812721;SGB=-0.69168;RPBZ=1.56004;MQBZ=-0.254328;BQBZ=-0.470162;SCBZ=-0.806322;FS=0;MQ0F=0.0952381;AC=2;AN=2;DP4=2,0,19,0;MQ=8	GT:PL	1/1:49,30,0
+21	27426	.	G	C	14.5766	.	DP=6;VDB=0.0411825;SGB=-0.616816;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,6;MQ=14	GT:PL	1/1:46,17,2
+21	27432	.	G	T	18.4764	.	DP=6;VDB=0.0389458;SGB=-0.616816;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,6;MQ=14	GT:PL	1/1:48,18,0
+21	27882	.	A	G	4.4843	.	DP=17;VDB=0.696154;SGB=-0.680642;RPBZ=-1.21295;MQBZ=-0.0564227;MQSBZ=0.983359;BQBZ=-0.645497;SCBZ=-2.26608;FS=0;MQ0F=0.0588235;AC=1;AN=2;DP4=4,1,12,0;MQ=10	GT:PL	0/1:34,0,8
+21	27933	.	A	G	21.3683	.	DP=25;VDB=0.347065;SGB=-0.686358;RPBZ=0.848872;MQBZ=0.0622633;MQSBZ=0.7886;BQBZ=0.428896;SCBZ=-1.60703;FS=0;MQ0F=0.04;AC=1;AN=2;DP4=11,0,13,1;MQ=12	GT:PL	0/1:54,0,33
+21	27958	.	T	C	12.0816	.	DP=10;VDB=0.316575;SGB=-0.651104;RPBZ=0.783349;MQBZ=-0.75;BQBZ=-0.5;SCBZ=0.5;FS=0;MQ0F=0;AC=1;AN=2;DP4=2,0,8,0;MQ=16	GT:PL	0/1:44,0,10
+21	27990	.	T	C	17.3194	.	DP=4;VDB=0.309755;SGB=-0.511536;RPBZ=1.34164;MQBZ=1.73205;BQBZ=-0.57735;SCBZ=0.942809;FS=0;MQ0F=0;AC=2;AN=2;DP4=1,0,3,0;MQ=15	GT:PL	1/1:44,5,0
+21	28137	.	G	C	19.4636	.	DP=4;VDB=0.131345;SGB=-0.556411;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,4,0;MQ=15	GT:PL	1/1:49,12,0
+21	29792	.	C	T	7.27325	.	DP=7;VDB=0.0221621;SGB=-0.556411;RPBZ=0.180021;MQBZ=0.440959;MQSBZ=0;BQBZ=0;SCBZ=2.2014;FS=0;MQ0F=0;AC=1;AN=2;DP4=3,0,1,3;MQ=14	GT:PL	0/1:39,0,20
+21	29810	.	G	A	77.4149	.	DP=24;VDB=1.25119e-06;SGB=-0.692717;MQSBZ=0.524975;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,20,3;MQ=12	GT:PL	1/1:107,69,0
+21	29842	.	C	T	21.1507	.	DP=47;VDB=0.0659263;SGB=-0.691153;RPBZ=0.0328523;MQBZ=0.41088;MQSBZ=0.598526;BQBZ=0.787839;SCBZ=2.34163;FS=0;MQ0F=0.0212766;AC=1;AN=2;DP4=26,3,15,3;MQ=13	GT:PL	0/1:54,0,56
+21	29908	.	T	C	42.9541	.	DP=16;VDB=0.00415584;SGB=-0.683931;RPBZ=0.373337;MQBZ=-0.829774;MQSBZ=0.203566;BQBZ=-0.407039;SCBZ=0.517769;FS=0;MQ0F=0.0625;AC=2;AN=2;DP4=1,0,11,2;MQ=12	GT:PL	1/1:70,19,0
+21	29919	.	A	G	19.2592	.	DP=6;VDB=0.0414745;SGB=-0.590765;RPBZ=1.48522;MQBZ=0.933257;MQSBZ=-0.311086;BQBZ=-0.948683;SCBZ=0.447214;FS=0;MQ0F=0.166667;AC=2;AN=2;DP4=1,0,4,1;MQ=10	GT:PL	1/1:46,10,0
+21	30209	.	G	A	7.30814	.	DP=2;VDB=0.1;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,0;MQ=20	GT:PL	1/1:36,6,0
+21	30213	.	G	A	7.30814	.	DP=2;VDB=0.1;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,0;MQ=20	GT:PL	1/1:36,6,0
+21	35166	.	G	A	8.08613	.	DP=32;VDB=0.000100416;SGB=-0.692067;RPBZ=2.35842;MQBZ=0.0865916;BQBZ=0.324617;SCBZ=1.38514;FS=0;MQ0F=0.0625;AC=1;AN=2;DP4=0,12,0,20;MQ=11	GT:PL	0/1:40,0,33
+21	35229	.	G	C	24.4377	.	DP=19;VDB=0.220127;SGB=-0.69168;MQSBZ=0.682959;FS=0;MQ0F=0.105263;AC=2;AN=2;DP4=0,0,1,18;MQ=8	GT:PL	1/1:54,48,0
+21	35243	.	A	C	38.9535	.	DP=19;VDB=0.18357;SGB=-0.690438;RPBZ=1.33076;MQBZ=0.500703;MQSBZ=0.884764;BQBZ=-0.342997;SCBZ=0.85812;FS=0;MQ0F=0.105263;AC=2;AN=2;DP4=0,2,1,16;MQ=10	GT:PL	1/1:66,27,0
+21	35301	.	C	T	3.22451	.	DP=4;VDB=0.0681597;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,3;MQ=14	GT:PL	1/1:30,9,0
+21	36052	.	C	A	21.4492	.	DP=13;VDB=0.0262535;SGB=-0.680642;MQSBZ=-1.68732;FS=0;MQ0F=0.0769231;AC=2;AN=2;DP4=0,0,11,1;MQ=9	GT:PL	1/1:51,33,0
+21	36053	.	A	G	5.97965	.	DP=13;VDB=0.0258627;SGB=-0.676189;RPBZ=-1.01567;MQBZ=-1.07375;MQSBZ=-1.68732;BQBZ=-0.445362;SCBZ=-1.21854;FS=0;MQ0F=0.0769231;AC=2;AN=2;DP4=1,0,10,1;MQ=9	GT:PL	1/1:32,13,0
+21	37577	.	A	G	6.30333	.	DP=5;VDB=0.0452455;SGB=-0.556411;RPBZ=1.11803;MQBZ=0.372678;MQSBZ=-0.372678;BQBZ=-0.5;SCBZ=1.11803;FS=0;MQ0F=0.2;AC=2;AN=2;DP4=0,1,4,0;MQ=9	GT:PL	1/1:32,8,0
+21	37653	.	A	G	44.4192	.	DP=13;VDB=0.00955183;SGB=-0.683931;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,13,0;MQ=13	GT:PL	1/1:74,36,0
+21	37658	.	G	C	36.4192	.	DP=15;VDB=0.0373922;SGB=-0.688148;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,15,0;MQ=11	GT:PL	1/1:66,42,0
+21	37661	.	A	G	5.7493	.	DP=16;VDB=0.126837;SGB=-0.636426;RPBZ=0.741504;MQBZ=0.722806;BQBZ=0.311046;SCBZ=-0.452414;FS=0;MQ0F=0;AC=1;AN=2;DP4=9,0,7,0;MQ=12	GT:PL	0/1:37,0,29
+21	37706	.	C	G	6.82671	.	DP=12;VDB=0.0572236;SGB=-0.680642;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,12,0;MQ=11	GT:PL	1/1:50,39,15
+21	37778	.	A	G	8.13869	.	DP=3;VDB=0.0560361;SGB=-0.511536;FS=0;MQ0F=0.333333;AC=2;AN=2;DP4=0,0,3,0;MQ=13	GT:PL	1/1:37,9,0
+21	38899	.	G	A	5.61693	.	DP=3;VDB=0.26;SGB=-0.453602;RPBZ=-1.22474;MQBZ=1.41421;BQBZ=-0.707107;SCBZ=0.707107;FS=0;MQ0F=0.333333;AC=2;AN=2;DP4=0,1,0,2;MQ=13	GT:PL	1/1:31,3,0
+21	38910	.	A	G	8.13869	.	DP=3;VDB=0.185719;SGB=-0.511536;FS=0;MQ0F=0.333333;AC=2;AN=2;DP4=0,0,0,3;MQ=13	GT:PL	1/1:37,9,0
+21	38941	.	T	C	35.0072	.	DP=10;VDB=0.49524;SGB=-0.651104;RPBZ=1.1786;MQBZ=0.968246;BQBZ=1.30437;SCBZ=-0.963794;FS=0;MQ0F=0.1;AC=2;AN=2;DP4=0,2,0,8;MQ=14	GT:PL	1/1:62,11,0
+21	45996	.	A	G	10.5539	.	DP=7;VDB=0.0452455;SGB=-0.556411;RPBZ=-0.178377;MQBZ=1.1547;BQBZ=1.1547;SCBZ=-0.540062;FS=0;MQ0F=0;AC=1;AN=2;DP4=3,0,4,0;MQ=17	GT:PL	0/1:43,0,20
+21	46012	.	G	A	17.1077	.	DP=9;VDB=0.00467508;SGB=-0.636426;RPBZ=-0.29277;MQBZ=-0.808122;BQBZ=1.87083;SCBZ=-0.46291;FS=0;MQ0F=0;AC=1;AN=2;DP4=2,0,7,0;MQ=15	GT:PL	0/1:46,0,3
+21	46016	.	A	G	21.2626	.	DP=10;VDB=0.0987508;SGB=-0.651104;RPBZ=-0.783349;MQBZ=1.125;BQBZ=-0.5;SCBZ=-0.140242;FS=0;MQ0F=0;AC=2;AN=2;DP4=2,0,8,0;MQ=16	GT:PL	1/1:48,1,0
+21	46027	.	A	G	15.309	.	DP=20;VDB=0.0607471;SGB=-0.676189;RPBZ=-0.152119;MQBZ=1.12615;BQBZ=-0.549946;SCBZ=-2.65745;FS=0;MQ0F=0.05;AC=1;AN=2;DP4=9,0,11,0;MQ=12	GT:PL	0/1:48,0,26
+21	46130	.	A	G	10.7632	.	DP=13;VDB=0.0760875;SGB=-0.651104;RPBZ=0.659639;MQBZ=-0.401112;MQSBZ=0.741063;BQBZ=-0.790569;SCBZ=1.16775;FS=0;MQ0F=0.0769231;AC=1;AN=2;DP4=5,0,5,3;MQ=11	GT:PL	0/1:43,0,24
+21	46817	.	A	G	5.74887	.	DP=17;VDB=0.342281;SGB=-0.662043;RPBZ=0.289385;MQBZ=-0.487798;BQBZ=0;SCBZ=0.129433;FS=0;MQ0F=0.176471;AC=1;AN=2;DP4=0,8,0,9;MQ=12	GT:PL	0/1:37,0,37
+21	46824	.	A	G	5.74887	.	DP=17;VDB=0.00667786;SGB=-0.662043;RPBZ=0.723909;MQBZ=-0.704597;BQBZ=0;SCBZ=0.905028;FS=0;MQ0F=0.176471;AC=1;AN=2;DP4=0,8,0,9;MQ=12	GT:PL	0/1:37,0,37
+21	46827	.	C	T	5.03467	.	DP=16;VDB=0.00487534;SGB=-0.636426;RPBZ=-0.26541;MQBZ=0.612938;BQBZ=0;SCBZ=-1.04295;FS=0;MQ0F=0.1875;AC=1;AN=2;DP4=0,9,0,7;MQ=13	GT:PL	0/1:36,0,38
+21	46868	.	G	A	19.4636	.	DP=5;VDB=0.857144;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,3;MQ=20	GT:PL	1/1:49,9,0
+21	50245	.	T	A	27.4222	.	DP=8;VDB=0.163924;SGB=-0.651104;FS=0;MQ0F=0.25;AC=2;AN=2;DP4=0,0,8,0;MQ=12	GT:PL	1/1:57,24,0
+21	50266	.	A	G	27.2551	.	DP=6;VDB=0.110342;SGB=-0.590765;RPBZ=0.29277;MQBZ=1.41421;BQBZ=-0.447214;SCBZ=0;FS=0;MQ0F=0.333333;AC=2;AN=2;DP4=1,0,5,0;MQ=13	GT:PL	1/1:54,10,0
+21	50269	.	G	C	4.15607	.	DP=6;VDB=0.0433485;SGB=-0.511536;RPBZ=1.96396;MQBZ=1.58114;BQBZ=1;SCBZ=0;FS=0;MQ0F=0.333333;AC=1;AN=2;DP4=3,0,3,0;MQ=13	GT:PL	0/1:34,0,10
+21	50270	.	C	G	9.02432	.	DP=7;VDB=0.084975;SGB=-0.636426;FS=0;MQ0F=0.285714;AC=2;AN=2;DP4=0,0,7,0;MQ=11	GT:PL	1/1:46,20,8
+21	50661	.	G	A	7.30814	.	DP=2;VDB=0.1;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,0;MQ=20	GT:PL	1/1:36,6,0
+21	50704	.	A	C	8.13869	.	DP=3;VDB=0.364077;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,3,0;MQ=14	GT:PL	1/1:37,9,0
+21	51204	.	C	G	15.5259	.	DP=36;VDB=0.000362184;SGB=-0.69168;RPBZ=-0.625851;MQBZ=0.0864411;MQSBZ=1.20664;BQBZ=0;SCBZ=0;FS=0;MQ0F=0.0277778;AC=1;AN=2;DP4=1,14,0,19;MQ=14	GT:PL	0/1:48,0,47
+21	51287	.	T	C	11.9325	.	DP=32;VDB=0.0211251;SGB=-0.692831;RPBZ=0.217737;MQBZ=-1.188;MQSBZ=-0.25502;BQBZ=-1.37823;SCBZ=-2.27742;FS=0;MQ0F=0;AC=1;AN=2;DP4=1,7,1,23;MQ=11	GT:PL	0/1:43,0,8
+21	51868	.	A	T	35.0172	.	DP=22;VDB=0.00829484;SGB=-0.692067;RPBZ=0.685829;MQBZ=-0.196214;MQSBZ=-1.35401;BQBZ=2.06216;SCBZ=-1.9261;FS=0;MQ0F=0;AC=2;AN=2;DP4=2,0,19,1;MQ=12	GT:PL	1/1:62,28,0
+21	51917	.	C	T	10.873	.	DP=22;VDB=0.0282545;SGB=-0.689466;RPBZ=-1.10613;MQBZ=0.957427;BQBZ=-1.11155;SCBZ=1.50667;FS=0;MQ0F=0;AC=2;AN=2;DP4=6,0,16,0;MQ=10	GT:PL	1/1:38,0,1
+21	52178	.	T	C	6.00737	.	DP=13;VDB=0.0909239;SGB=-0.662043;RPBZ=-1.15887;MQBZ=-0.165087;BQBZ=2.20794;SCBZ=0.882823;FS=0;MQ0F=0.0769231;AC=1;AN=2;DP4=4,0,9,0;MQ=10	GT:PL	0/1:33,0,2
+21	52221	.	G	A	11.7419	.	DP=5;VDB=0.409395;SGB=-0.590765;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,5,0;MQ=16	GT:PL	1/1:50,18,9
+21	52329	.	G	A	6.32811	.	DP=4;VDB=0.529687;SGB=-0.511536;RPBZ=-1.34164;MQBZ=1.41421;BQBZ=0;SCBZ=-1.73205;FS=0;MQ0F=0.25;AC=2;AN=2;DP4=1,0,3,0;MQ=10	GT:PL	1/1:32,5,0
+21	60392	.	T	C	3.64636	.	DP=9;VDB=0.314313;SGB=-0.556411;RPBZ=-0.734847;MQBZ=-1.11803;MQSBZ=-0.353553;BQBZ=0;SCBZ=-1.34164;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,5,1,3;MQ=18	GT:PL	0/1:34,0,48
+21	60396	.	G	A	6.50182	.	DP=9;VDB=0.372756;SGB=-0.556411;RPBZ=0;MQBZ=0.894427;MQSBZ=-0.353553;BQBZ=-1.11803;SCBZ=0.33541;FS=0;MQ0F=0;AC=1;AN=2;DP4=1,4,0,4;MQ=18	GT:PL	0/1:38,0,48
+21	60419	.	A	G	3.72363	.	DP=9;VDB=0.0645318;SGB=-0.556411;RPBZ=1.85262;MQBZ=0;MQSBZ=-0.53033;BQBZ=0;SCBZ=-1.34164;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,5,1,3;MQ=16	GT:PL	0/1:34,0,40
+21	60770	.	A	C	47.3472	.	DP=18;VDB=0.662143;SGB=-0.690438;RPBZ=1.44635;MQBZ=1.73462;MQSBZ=1.15641;BQBZ=-0.352941;SCBZ=-1.73506;FS=0;MQ0F=0.0555556;AC=2;AN=2;DP4=0,1,1,16;MQ=14	GT:PL	1/1:74,33,0
+21	60813	.	T	C	8.10157	.	DP=15;VDB=0.0663569;SGB=-0.651104;RPBZ=0.290097;MQBZ=0.395285;BQBZ=-0.935414;SCBZ=-1.56492;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,7,0,8;MQ=12	GT:PL	0/1:40,0,31
+21	60850	.	T	C	8.13869	.	DP=3;VDB=0.756524;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,3;MQ=13	GT:PL	1/1:37,9,0
+21	62454	.	A	T	25.9268	.	DP=11;VDB=0.115319;SGB=-0.670168;RPBZ=-0.948683;MQBZ=-0.737028;BQBZ=-0.316228;SCBZ=0.471405;FS=0;MQ0F=0.181818;AC=2;AN=2;DP4=1,0,10,0;MQ=12	GT:PL	1/1:53,10,0
+21	62491	.	T	C	11.4795	.	DP=16;VDB=0.266813;SGB=-0.676189;RPBZ=1.81528;MQBZ=0.524802;BQBZ=0.492366;SCBZ=0.183211;FS=0;MQ0F=0;AC=1;AN=2;DP4=5,0,11,0;MQ=13	GT:PL	0/1:44,0,19
+21	62492	.	G	A	13.4162	.	DP=15;VDB=0.289496;SGB=-0.651104;RPBZ=1.79699;MQBZ=1.59476;BQBZ=-0.935414;SCBZ=0.122597;FS=0;MQ0F=0;AC=1;AN=2;DP4=7,0,8,0;MQ=13	GT:PL	0/1:46,0,23
+21	62535	.	T	C	12.5601	.	DP=11;VDB=0.173752;SGB=-0.636426;RPBZ=-1.13648;MQBZ=-1.12122;BQBZ=0;SCBZ=-0.38503;FS=0;MQ0F=0;AC=1;AN=2;DP4=4,0,7,0;MQ=16	GT:PL	0/1:45,0,33
+21	62935	.	A	G	6.45586	.	DP=36;VDB=0.00893984;SGB=-0.692831;RPBZ=-0.553846;MQBZ=-0.407841;MQSBZ=-1.67857;BQBZ=0.5073;SCBZ=1.00855;FS=0;MQ0F=0.0833333;AC=1;AN=2;DP4=12,0,23,1;MQ=9	GT:PL	0/1:38,0,15
+21	62981	.	T	G	8.13869	.	DP=3;VDB=0.0349627;SGB=-0.511536;FS=0;MQ0F=0.333333;AC=2;AN=2;DP4=0,0,3,0;MQ=13	GT:PL	1/1:37,9,0
+21	62984	.	A	G	6.32811	.	DP=4;VDB=0.0349627;SGB=-0.511536;RPBZ=1.34164;MQBZ=0.471405;BQBZ=0;SCBZ=-1.73205;FS=0;MQ0F=0.25;AC=2;AN=2;DP4=1,0,3,0;MQ=10	GT:PL	1/1:32,5,0
+21	63080	.	T	G	26.4242	.	DP=5;VDB=0.197286;SGB=-0.590765;MQSBZ=0.790569;FS=0;MQ0F=0.2;AC=2;AN=2;DP4=0,0,4,1;MQ=12	GT:PL	1/1:56,15,0
+21	70129	.	A	G	7.30814	.	DP=2;VDB=0.28;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	70231	.	C	T	7.30814	.	DP=3;VDB=0.06;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	70232	.	G	A	5.61693	.	DP=3;VDB=0.06;SGB=-0.453602;RPBZ=1.22474;MQBZ=1.41421;BQBZ=1.41421;SCBZ=0;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,1,0,2;MQ=13	GT:PL	1/1:31,3,0
+21	74439	.	A	G	19.4636	.	DP=3;VDB=0.336489;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,3,0;MQ=20	GT:PL	1/1:49,9,0
+21	74453	.	T	A	8.13869	.	DP=3;VDB=0.345596;SGB=-0.511536;FS=0;MQ0F=0.333333;AC=2;AN=2;DP4=0,0,3,0;MQ=13	GT:PL	1/1:37,9,0
+21	75748	.	G	A	31.8678	.	DP=11;VDB=0.382624;SGB=-0.670168;RPBZ=0.948683;MQBZ=-0.74162;MQSBZ=1.85405;BQBZ=-0.469042;SCBZ=0.469042;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,1,1,9;MQ=13	GT:PL	1/1:59,13,0
+21	75756	.	A	G	31.2817	.	DP=9;VDB=0.77747;SGB=-0.651104;RPBZ=0;MQBZ=1.41421;BQBZ=-0.353553;SCBZ=-2.12132;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,1,0,8;MQ=14	GT:PL	1/1:58,15,0
+21	75806	.	A	G	3.73811	.	DP=13;VDB=0.0760875;SGB=-0.651104;RPBZ=-0.659639;MQBZ=-0.802225;BQBZ=1.26491;SCBZ=0.0775791;FS=0;MQ0F=0.0769231;AC=1;AN=2;DP4=0,5,0,8;MQ=11	GT:PL	0/1:34,0,22
+21	75821	.	T	C	16.3508	.	DP=11;VDB=0.00114085;SGB=-0.670168;RPBZ=-0.953025;MQBZ=0.335888;BQBZ=-0.469042;SCBZ=1.00509;FS=0;MQ0F=0.0909091;AC=2;AN=2;DP4=0,1,0,10;MQ=10	GT:PL	1/1:43,20,0
+21	81337	.	C	T	5.00423	.	DP=11;VDB=0.0224626;SGB=-0.590765;RPBZ=-1.27802;MQBZ=0;BQBZ=0;SCBZ=-1.74801;FS=0;MQ0F=0;AC=1;AN=2;DP4=6,0,5,0;MQ=16	GT:PL	0/1:36,0,45
+21	81342	.	C	G	19.0687	.	DP=11;VDB=0.00262538;SGB=-0.670168;RPBZ=0.633898;MQBZ=-0.469042;BQBZ=-0.316228;SCBZ=-1.63299;FS=0;MQ0F=0;AC=2;AN=2;DP4=1,0,10,0;MQ=16	GT:PL	1/1:58,17,12
+21	81349	.	C	T	3.77891	.	DP=12;VDB=0.0525422;SGB=-0.590765;RPBZ=-0.893198;MQBZ=1.37017;BQBZ=0.845154;SCBZ=-1.60357;FS=0;MQ0F=0.0833333;AC=1;AN=2;DP4=7,0,5,0;MQ=12	GT:PL	0/1:34,0,26
+21	81441	.	A	C	28.4205	.	DP=6;VDB=0.072067;SGB=-0.616816;FS=0;MQ0F=0.166667;AC=2;AN=2;DP4=0,0,6,0;MQ=13	GT:PL	1/1:58,18,0
+21	81447	.	G	A	19.4636	.	DP=3;VDB=0.0506481;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,3,0;MQ=20	GT:PL	1/1:49,9,0
+21	88097	.	G	T	43.0532	.	DP=15;VDB=0.441271;SGB=-0.683931;RPBZ=-0.511815;MQBZ=0.0969111;MQSBZ=0.792406;BQBZ=1.21626;SCBZ=1.46152;FS=0;MQ0F=0.0666667;AC=2;AN=2;DP4=2,0,12,1;MQ=12	GT:PL	1/1:70,19,0
+21	88111	.	A	G	23.2308	.	DP=7;VDB=0.530999;SGB=-0.616816;RPBZ=0;MQBZ=-0.62361;MQSBZ=0.62361;BQBZ=-0.408248;SCBZ=-0.264575;FS=0;MQ0F=0;AC=2;AN=2;DP4=1,0,5,1;MQ=14	GT:PL	1/1:50,1,0
+21	88160	.	C	G	6.76147	.	DP=11;VDB=0.0298868;SGB=-0.670168;RPBZ=0.316949;MQBZ=0.520088;MQSBZ=0.866814;BQBZ=-0.316228;SCBZ=0.469042;FS=0;MQ0F=0.181818;AC=2;AN=2;DP4=1,0,9,1;MQ=11	GT:PL	1/1:48,24,16
+21	88202	.	A	G	7.26048	.	DP=4;VDB=0.732596;SGB=-0.511536;RPBZ=-1.34164;MQBZ=0;BQBZ=0;SCBZ=0.57735;FS=0;MQ0F=0;AC=1;AN=2;DP4=1,0,3,0;MQ=20	GT:PL	0/1:38,0,8
+21	91562	.	A	G	6.32811	.	DP=4;VDB=0.309755;SGB=-0.511536;RPBZ=-1.34164;MQBZ=1;BQBZ=0;SCBZ=0;FS=0;MQ0F=0;AC=2;AN=2;DP4=1,0,3,0;MQ=11	GT:PL	1/1:32,5,0
+21	97579	.	T	C	7.30814	.	DP=2;VDB=0.84;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	98696	.	C	T	3.22451	.	DP=5;VDB=0.588406;SGB=-0.590765;FS=0;MQ0F=0.2;AC=2;AN=2;DP4=0,0,5,0;MQ=8	GT:PL	1/1:30,15,0
+21	115868	.	A	G	26.4242	.	DP=8;VDB=0.151;SGB=-0.651104;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,8,0;MQ=11	GT:PL	1/1:56,24,0
+21	117459	.	C	T	24.4299	.	DP=5;VDB=0.226768;SGB=-0.590765;MQSBZ=1.58114;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,1,4;MQ=12	GT:PL	1/1:54,15,0
+21	117482	.	A	C	5.48067	.	DP=13;VDB=0.835187;SGB=-0.680642;RPBZ=-0.267999;MQBZ=-0.887625;MQSBZ=1.62731;BQBZ=-0.288675;SCBZ=0.288675;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,1,1,11;MQ=11	GT:PL	1/1:40,12,9
+21	117530	.	T	A	26.3052	.	DP=14;VDB=0.0614523;SGB=-0.683931;RPBZ=0.869199;MQBZ=1.18176;BQBZ=1.72091;SCBZ=-1.87083;FS=0;MQ0F=0.0714286;AC=2;AN=2;DP4=0,1,0,13;MQ=9	GT:PL	1/1:53,31,0
+21	117551	.	G	C	7.30814	.	DP=7;VDB=0.0175011;SGB=-0.636426;FS=0;MQ0F=0.142857;AC=2;AN=2;DP4=0,0,0,7;MQ=6	GT:PL	1/1:36,21,0
+21	126011	.	C	T	5.61693	.	DP=3;VDB=0.66;SGB=-0.453602;RPBZ=1.22474;MQBZ=1.41421;BQBZ=0;SCBZ=0;FS=0;MQ0F=0;AC=2;AN=2;DP4=1,0,2,0;MQ=14	GT:PL	1/1:31,3,0
+21	136979	.	G	A	8.13869	.	DP=3;VDB=0.0941127;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,3,0;MQ=14	GT:PL	1/1:37,9,0
+21	136988	.	A	G	8.13869	.	DP=3;VDB=0.0941127;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,3,0;MQ=14	GT:PL	1/1:37,9,0
+21	137088	.	T	C	5.61693	.	DP=3;VDB=0.02;SGB=-0.453602;RPBZ=-1.22474;MQBZ=1.41421;BQBZ=0;SCBZ=0;FS=0;MQ0F=0;AC=2;AN=2;DP4=1,0,2,0;MQ=14	GT:PL	1/1:31,3,0
+21	137113	.	G	A	7.30814	.	DP=2;VDB=0.02;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,0;MQ=20	GT:PL	1/1:36,6,0
+21	138443	.	T	G	12.6566	.	DP=6;VDB=0.000959055;SGB=-0.616816;MQSBZ=1.20605;FS=0;MQ0F=0.166667;AC=2;AN=2;DP4=0,0,5,1;MQ=7	GT:PL	1/1:42,18,0
+21	139664	.	A	G	12.3697	.	DP=11;VDB=0.025915;SGB=-0.616816;RPBZ=-0.0914953;MQBZ=1.27265;MQSBZ=-0.734763;BQBZ=0;SCBZ=-1.62481;FS=0;MQ0F=0.0909091;AC=1;AN=2;DP4=1,4,0,6;MQ=13	GT:PL	0/1:45,0,18
+21	143593	.	C	T	9.88514	.	DP=3;VDB=0.392388;SGB=-0.511536;MQSBZ=-1.41421;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,1;MQ=13	GT:PL	1/1:39,9,0
+21	152544	.	T	C	10.3436	.	DP=9;VDB=0.0196075;SGB=-0.590765;RPBZ=-0.996546;MQBZ=1.36931;BQBZ=0.33541;SCBZ=0.894427;FS=0;MQ0F=0;AC=2;AN=2;DP4=4,0,5,0;MQ=11	GT:PL	1/1:37,3,0
+21	152547	.	A	G	8.54666	.	DP=8;VDB=0.00477428;SGB=-0.636426;RPBZ=0.223607;MQBZ=-0.774597;BQBZ=-0.377964;SCBZ=0.377964;FS=0;MQ0F=0;AC=2;AN=2;DP4=1,0,7,0;MQ=12	GT:PL	1/1:35,4,0
+21	221789	.	T	C	19.4636	.	DP=5;VDB=0.300397;SGB=-0.590765;FS=0;MQ0F=0.2;AC=2;AN=2;DP4=0,0,5,0;MQ=12	GT:PL	1/1:49,15,0
+21	221824	.	A	G	17.2912	.	DP=5;VDB=0.446842;SGB=-0.556411;RPBZ=0;MQBZ=0.790569;BQBZ=0;SCBZ=0;FS=0;MQ0F=0.2;AC=2;AN=2;DP4=1,0,4,0;MQ=12	GT:PL	1/1:44,8,0
+21	236291	.	A	G	3.21958	.	DP=7;VDB=0.535497;SGB=-0.556411;RPBZ=0.707107;MQBZ=-0.866025;BQBZ=0;SCBZ=-0.585142;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,3,0,4;MQ=17	GT:PL	0/1:33,0,31
+21	236294	.	C	T	4.32521	.	DP=6;VDB=0.176409;SGB=-0.556411;RPBZ=1.38873;MQBZ=-0.707107;BQBZ=0;SCBZ=0.491869;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,2,0,4;MQ=16	GT:PL	0/1:35,0,19
+21	236295	.	A	G	4.32521	.	DP=6;VDB=0.522837;SGB=-0.556411;RPBZ=0;MQBZ=-0.707107;BQBZ=0;SCBZ=-1.47561;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,2,0,4;MQ=16	GT:PL	0/1:35,0,19
+21	236320	.	G	A	3.20067	.	DP=8;VDB=0.220638;SGB=-0.556411;RPBZ=1.76777;MQBZ=0;BQBZ=-0.866025;SCBZ=0.866025;FS=0;MQ0F=0;AC=1;AN=2;DP4=0,3,0,4;MQ=14	GT:PL	0/1:33,0,20
+21	236327	.	A	G	6.77159	.	DP=6;VDB=0.673544;SGB=-0.590765;RPBZ=-0.29277;MQBZ=-0.69282;BQBZ=-0.447214;SCBZ=0.69282;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,1,0,5;MQ=14	GT:PL	1/1:34,0,2
+21	236359	.	A	T	8.99921	.	DP=4;VDB=0.160409;SGB=-0.556411;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,4;MQ=11	GT:PL	1/1:38,12,0
+21	248947	.	T	C	4.85359	.	DP=4;VDB=0.38;SGB=-0.453602;RPBZ=-0.774597;MQBZ=1.73205;MQSBZ=-1;BQBZ=0;SCBZ=1;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,2,1,1;MQ=11	GT:PL	1/1:30,2,0
+21	248966	.	G	A	12.6566	.	DP=4;VDB=0.112085;SGB=-0.556411;MQSBZ=-1;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,1,3;MQ=11	GT:PL	1/1:42,12,0
+21	251560	.	C	T	11.7172	.	DP=3;VDB=0.137328;SGB=-0.511536;MQSBZ=0.707107;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,1;MQ=14	GT:PL	1/1:41,9,0
+21	289446	.	T	C	49.4146	.	DP=22;VDB=1.4824e-07;SGB=-0.692562;FS=0;MQ0F=0.0454545;AC=2;AN=2;DP4=0,0,22,0;MQ=12	GT:PL	1/1:79,66,0
+21	289481	.	T	C	3.73429	.	DP=48;VDB=0.22406;SGB=-0.692976;RPBZ=0.341551;MQBZ=-1.11595;BQBZ=-1.2128;SCBZ=-1.70538;FS=0;MQ0F=0.0208333;AC=1;AN=2;DP4=22,0,26,0;MQ=11	GT:PL	0/1:34,0,44
+21	289488	.	T	C	6.50824	.	DP=50;VDB=0.518994;SGB=-0.693021;RPBZ=0.545171;MQBZ=-1.485;BQBZ=2.489;SCBZ=-1.74235;FS=0;MQ0F=0.04;AC=1;AN=2;DP4=23,0,27,0;MQ=11	GT:PL	0/1:38,0,40
+21	289520	.	A	C	21.7432	.	DP=41;VDB=4.57336e-05;SGB=-0.69312;RPBZ=-0.393988;MQBZ=0.311388;BQBZ=2.69313;SCBZ=1.10119;FS=0;MQ0F=0.0243902;AC=2;AN=2;DP4=9,0,32,0;MQ=10	GT:PL	1/1:49,21,0
+21	289647	.	G	A	3.22451	.	DP=3;VDB=0.873285;SGB=-0.511536;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,3,0;MQ=14	GT:PL	1/1:30,9,0
+21	339923	.	C	T	7.30814	.	DP=2;VDB=0.56;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,0;MQ=20	GT:PL	1/1:36,6,0
+21	355659	.	C	T	6.32811	.	DP=4;VDB=0.868052;SGB=-0.511536;RPBZ=-1.34164;MQBZ=1;BQBZ=0;SCBZ=0;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,1,0,3;MQ=11	GT:PL	1/1:32,5,0
+21	553515	.	C	G	7.30814	.	DP=2;VDB=0.68;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,2,0;MQ=20	GT:PL	1/1:36,6,0
+21	602273	.	A	C	6.32811	.	DP=4;VDB=0.131948;SGB=-0.511536;RPBZ=-1.34164;MQBZ=1;BQBZ=-0.57735;SCBZ=-1.73205;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,1,0,3;MQ=11	GT:PL	1/1:32,5,0
+21	682407	.	G	T	7.30814	.	DP=2;VDB=0.56;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	682421	.	T	G	7.30814	.	DP=2;VDB=0.56;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	682423	.	C	G	7.30814	.	DP=2;VDB=0.56;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	682426	.	G	A	7.30814	.	DP=2;VDB=0.56;SGB=-0.453602;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,2;MQ=20	GT:PL	1/1:36,6,0
+21	682568	.	A	G	8.13869	.	DP=5;VDB=0.133161;SGB=-0.590765;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,0,5;MQ=9	GT:PL	1/1:37,15,0
+21	694476	.	C	G	18.4764	.	DP=6;VDB=0.0341101;SGB=-0.616816;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,6,0;MQ=11	GT:PL	1/1:48,18,0
+21	694482	.	T	C	19.4636	.	DP=4;VDB=0.131345;SGB=-0.556411;FS=0;MQ0F=0;AC=2;AN=2;DP4=0,0,4,0;MQ=15	GT:PL	1/1:49,12,0
Binary file test-data/filtered4.bam has changed
--- a/test-data/rnastar_test.log	Wed Feb 14 09:04:09 2024 +0000
+++ b/test-data/rnastar_test.log	Tue Aug 27 14:11:53 2024 +0000
@@ -3,32 +3,35 @@
                                     Finished on |	.*
        Mapping speed, Million of reads per hour |	.*
 
-                          Number of input reads |	100
-                      Average input read length |	75
+                          Number of input reads |	15447
+                      Average input read length |	119
                                     UNIQUE READS:
-                   Uniquely mapped reads number |	99
-                        Uniquely mapped reads % |	99.00%
-                          Average mapped length |	74.65
-                       Number of splices: Total |	52
+                   Uniquely mapped reads number |	150
+                        Uniquely mapped reads % |	0.97%
+                          Average mapped length |	105.11
+                       Number of splices: Total |	131
             Number of splices: Annotated (sjdb) |	0
-                       Number of splices: GT/AG |	52
-                       Number of splices: GC/AG |	0
-                       Number of splices: AT/AC |	0
-               Number of splices: Non-canonical |	0
-                      Mismatch rate per base, % |	2.00%
-                         Deletion rate per base |	0.00%
-                        Deletion average length |	0.00
-                        Insertion rate per base |	0.00%
-                       Insertion average length |	0.00
+                       Number of splices: GT/AG |	100
+                       Number of splices: GC/AG |	6
+                       Number of splices: AT/AC |	1
+               Number of splices: Non-canonical |	24
+                      Mismatch rate per base, % |	6.68%
+                         Deletion rate per base |	0.04%
+                        Deletion average length |	1.17
+                        Insertion rate per base |	0.04%
+                       Insertion average length |	1.50
                              MULTI-MAPPING READS:
-        Number of reads mapped to multiple loci |	1
-             % of reads mapped to multiple loci |	1.00%
-        Number of reads mapped to too many loci |	0
-             % of reads mapped to too many loci |	0.00%
+        Number of reads mapped to multiple loci |	451
+             % of reads mapped to multiple loci |	2.92%
+        Number of reads mapped to too many loci |	58
+             % of reads mapped to too many loci |	0.38%
                                   UNMAPPED READS:
+  Number of reads unmapped: too many mismatches |	0
        % of reads unmapped: too many mismatches |	0.00%
-                 % of reads unmapped: too short |	0.00%
-                     % of reads unmapped: other |	0.00%
+            Number of reads unmapped: too short |	7912
+                 % of reads unmapped: too short |	51.22%
+                Number of reads unmapped: other |	6876
+                     % of reads unmapped: other |	44.51%
                                   CHIMERIC READS:
                        Number of chimeric reads |	0
                             % of chimeric reads |	0.00%
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/rnastar_test_splicejunctions_wasp.bed	Tue Aug 27 14:11:53 2024 +0000
@@ -0,0 +1,193 @@
+21	13873	52149	1	1	0	0	1	12
+21	13882	20712	2	2	0	0	3	28
+21	13882	29808	2	2	0	0	1	28
+21	13882	35980	2	2	0	0	1	26
+21	13882	50180	2	2	0	0	1	19
+21	13887	27728	1	1	0	0	1	21
+21	13887	35985	1	1	0	0	1	15
+21	13887	51866	1	1	0	0	4	40
+21	13887	62408	1	1	0	0	2	24
+21	13887	88031	1	1	0	0	2	40
+21	13887	152470	1	1	0	2	2	40
+21	13894	50193	1	1	0	0	1	24
+21	13907	27883	2	2	0	0	2	45
+21	13976	19932	2	2	0	0	4	41
+21	13976	88119	2	2	0	0	2	33
+21	13976	108267	2	2	0	0	2	33
+21	13991	30873	2	2	0	0	1	18
+21	13991	52131	2	2	0	0	1	18
+21	15394	46773	1	1	0	0	1	39
+21	18885	50205	2	4	0	0	1	35
+21	18949	28120	1	1	0	0	1	26
+21	18953	27816	2	2	0	0	1	16
+21	18953	37719	2	2	0	1	0	34
+21	19001	46120	2	2	0	0	1	17
+21	19001	52299	2	2	0	0	1	17
+21	19001	63039	2	2	0	0	1	17
+21	19533	60698	2	2	0	1	0	44
+21	19658	51267	1	1	0	0	1	45
+21	19737	28120	1	1	0	0	1	16
+21	19826	51848	1	1	0	1	1	36
+21	19830	37617	1	1	0	0	2	12
+21	19842	20715	1	1	0	0	1	23
+21	19842	51866	1	1	0	1	0	22
+21	19842	62903	1	1	0	0	1	18
+21	19842	88031	1	1	0	0	2	37
+21	20671	27816	2	2	0	0	1	20
+21	20671	52116	2	2	0	0	2	25
+21	20671	62856	2	2	0	0	3	23
+21	20704	30891	1	1	0	0	3	38
+21	20704	37617	1	1	0	0	2	12
+21	20704	52149	1	1	0	0	5	22
+21	20704	120492	1	1	0	0	2	38
+21	20765	51916	2	2	0	0	1	14
+21	20819	30873	2	2	0	0	1	18
+21	20819	52131	2	2	0	0	1	18
+21	25471	61751	2	2	0	0	1	12
+21	26064	51210	2	2	0	0	1	13
+21	27406	35153	1	1	0	0	1	28
+21	27406	51199	1	1	0	1	0	26
+21	27494	38948	2	2	0	0	1	33
+21	27494	46813	2	2	0	1	1	44
+21	27494	75795	2	2	0	0	1	39
+21	27684	52116	2	2	0	0	1	16
+21	27713	51848	1	1	0	0	1	40
+21	27846	29795	1	1	0	1	0	16
+21	27859	29808	2	2	0	0	1	20
+21	27864	35985	1	1	0	0	1	24
+21	27864	45984	1	1	0	0	1	24
+21	27864	51866	1	1	0	1	1	32
+21	27864	62408	1	1	0	0	2	41
+21	27864	74425	1	1	0	0	1	24
+21	27864	88031	1	1	0	1	1	36
+21	27935	30198	1	1	0	0	1	33
+21	27935	62479	1	1	0	0	1	27
+21	27951	88119	2	2	0	0	2	31
+21	28186	46133	1	1	0	0	2	18
+21	28186	63052	1	1	0	1	1	25
+21	29614	31023	1	1	0	0	1	12
+21	29614	63020	1	1	0	0	2	24
+21	29901	37719	2	2	0	1	6	28
+21	29901	88119	2	2	0	0	5	36
+21	29901	91677	2	2	0	0	3	24
+21	29901	108267	2	2	0	0	5	36
+21	29916	30873	2	2	0	0	1	18
+21	29916	52131	2	2	0	0	1	18
+21	29949	52299	2	2	0	0	2	18
+21	30122	62898	2	2	0	0	1	19
+21	30127	37629	1	1	0	0	1	24
+21	30127	51866	1	1	0	0	2	15
+21	30127	88031	1	1	0	1	4	28
+21	30901	62898	2	2	0	0	1	31
+21	30906	51866	1	1	0	0	1	36
+21	30906	62408	1	1	0	0	1	14
+21	35204	75757	1	1	0	1	0	43
+21	35246	51292	1	1	0	0	1	33
+21	35288	38995	1	1	0	0	1	22
+21	35986	45984	1	1	0	0	2	17
+21	35986	88031	1	1	0	0	3	32
+21	35994	50193	1	1	0	0	2	25
+21	35994	51874	1	1	0	0	3	24
+21	35994	74433	1	1	0	0	2	23
+21	36035	51916	2	2	0	0	1	14
+21	36066	37411	1	1	0	0	1	37
+21	36074	46072	2	4	0	0	1	33
+21	37630	51866	1	1	0	0	1	37
+21	37630	62903	1	1	0	0	3	12
+21	37630	81353	1	1	0	0	1	44
+21	37679	51916	2	2	0	0	1	14
+21	38899	46764	1	1	0	0	1	20
+21	38954	51292	1	1	0	0	1	43
+21	38981	75826	1	1	0	0	1	34
+21	38996	60894	1	1	0	0	1	22
+21	45985	88031	1	1	0	0	1	38
+21	46057	62479	1	1	0	0	1	14
+21	46065	143522	1	1	0	0	2	45
+21	46069	88115	1	1	0	1	2	41
+21	46073	88119	2	2	0	0	1	29
+21	46814	70282	2	2	0	0	1	32
+21	46870	51210	2	2	0	1	0	21
+21	50168	62885	1	1	0	0	1	18
+21	50168	81335	1	1	0	0	1	34
+21	50244	137072	2	2	0	0	2	35
+21	50274	88119	2	2	0	0	1	39
+21	50274	91677	2	2	0	0	1	13
+21	50658	51848	1	1	0	1	0	42
+21	51216	75722	2	2	0	0	2	21
+21	51280	56626	2	2	0	0	1	19
+21	51288	75795	2	2	0	0	1	22
+21	51288	149429	2	2	0	0	2	41
+21	51293	60852	1	1	0	1	1	29
+21	51293	117556	1	1	0	0	2	44
+21	51302	60411	2	2	0	0	1	33
+21	51302	60861	2	2	0	0	2	42
+21	51320	75826	1	1	0	0	1	34
+21	51849	62390	1	1	0	0	1	37
+21	51849	62885	1	1	0	1	0	18
+21	51853	52149	1	1	0	0	1	12
+21	51899	52192	1	1	0	0	1	22
+21	51899	120538	1	1	0	1	4	32
+21	51955	206521	2	2	0	1	2	27
+21	52117	62856	2	2	0	0	3	18
+21	52162	62903	1	1	0	1	0	14
+21	52162	81353	1	1	0	0	1	44
+21	52162	88031	1	1	0	1	5	44
+21	52162	98665	1	1	0	0	1	36
+21	52162	152470	1	1	0	0	3	44
+21	52162	289491	1	1	0	1	10	36
+21	52182	62923	2	4	0	0	1	13
+21	52252	62856	2	2	0	1	0	21
+21	52252	88119	2	2	0	0	1	30
+21	52329	63068	1	1	0	0	1	28
+21	57410	60698	2	2	0	0	1	29
+21	57410	75645	2	2	0	0	2	38
+21	57475	60763	2	2	0	0	1	36
+21	60286	60730	2	4	0	1	0	40
+21	60390	60840	2	2	0	0	1	24
+21	60699	75645	2	2	0	0	2	27
+21	62480	98737	1	1	0	0	2	12
+21	62496	108267	2	2	0	0	1	43
+21	62544	63039	2	2	0	0	2	40
+21	62557	63052	1	1	0	0	1	15
+21	62890	120492	1	1	0	0	2	42
+21	62899	81348	2	2	0	0	1	24
+21	62899	108178	2	2	0	0	2	20
+21	62904	88031	1	1	0	1	4	44
+21	62936	120538	1	1	0	0	4	38
+21	62976	80498	1	1	0	1	0	24
+21	62976	137268	1	1	0	0	2	33
+21	63053	81502	1	1	0	0	1	32
+21	63053	88180	1	1	0	0	1	43
+21	70140	75651	2	2	0	0	1	31
+21	70283	75795	2	2	0	0	1	15
+21	70283	149429	2	2	0	2	1	45
+21	74506	143522	1	1	0	0	3	45
+21	74510	88115	1	1	0	0	2	35
+21	75799	117556	1	1	0	1	0	37
+21	75818	117576	2	2	0	0	1	15
+21	76355	87984	2	2	0	0	1	16
+21	76378	91540	1	1	0	0	1	24
+21	81349	115881	2	2	0	0	1	37
+21	81354	115886	1	1	0	0	1	33
+21	81438	88115	1	1	0	0	1	36
+21	88064	120538	1	1	0	1	5	32
+21	88120	91677	2	2	0	0	1	26
+21	91565	115886	1	1	0	0	2	33
+21	91597	120538	1	1	0	0	1	25
+21	98666	143455	1	1	0	1	0	18
+21	98750	138516	1	1	0	0	1	14
+21	108179	115881	2	2	0	0	1	38
+21	108223	152509	2	2	0	0	1	25
+21	112412	138384	2	2	0	0	1	16
+21	115887	152470	1	1	0	0	1	22
+21	115919	120538	1	1	0	0	7	43
+21	126053	137131	1	1	0	0	1	26
+21	131927	138384	2	2	0	0	1	21
+21	136828	136968	2	2	0	0	2	26
+21	137014	289491	1	1	0	0	6	25
+21	137087	137268	1	1	0	0	1	14
+21	137346	138586	1	1	0	0	1	19
+21	138427	152465	2	2	0	1	6	40
+21	138432	152470	1	1	0	0	2	31
+21	138513	143522	1	1	0	0	2	45
+21	682607	689282	2	2	0	1	0	36