source: extensions/net.sf.basedb.reggie/trunk/config/reggie-config.xml @ 5827

<?xml version="1.0" encoding="UTF-8"?>
<reggie>

  <!-- Section for enabling/disabling experimental features -->
  <!-- The list of feature that are considered experimental may change over time -->
  <!-- 0=The feature is disabled, 1=The feature is enabled -->
  <experimental-features>
  </experimental-features>
  
  <!-- Configuration options related to how external samples (RNA or DNA) are handled -->
  <external-samples>
    <!-- Files generated in the secondary analysis can be shared with read permission to -->
    <!-- a group if this is specified here. The prefix attribute is the sample name prefix -->
    <!-- and the value is the group name. This translates to a 'chgrp' command in the secondary -->
    <!-- analysis. Samples with a prefix that is not mapped here are not shared to other groups. -->
    <!--  <groupname prefix="BR">brcalab</groupname> -->
  </external-samples>

  <!-- Settings for the Activity log that is displayed on the Reggie start page -->
  <activity-log>
    <!-- Max number of entries to display in the log (exception: all events within the last two days are always displayed) -->
    <max-entries>35</max-entries>
    <!-- Max age (in days) of entries to display (even if the max number hasn't been reached) -->
    <max-age-in-days>14</max-age-in-days>
    <quote-of-the-day>
      <!-- URL to quote-of-the-day endpoint (optional, set an empty URL to disable this feature) -->
      <url>https://quotes.rest/qod.json</url>
      <!-- Default is 12 hours; do not set to less than 3600 since the external API has a limit -->
      <max-age-in-seconds>43200</max-age-in-seconds>
    </quote-of-the-day>
  </activity-log>

  <!-- Options related to R that is executed on the local server -->
  <rscript>
    <!-- Full or partial path to 'Rscript' executable -->
    <path>Rscript</path>
    <!-- Set the locale to use when running R -->
    <!-- If not set, use whatever locale the operating system provides -->
    <locale>en_US.UTF-8</locale>
    
    <!-- options for the 'geneReport' script -->
    <gene-report>
      <!-- full path to the R script -->
      <path>/path/to/R_RNAseq_scanb_geneReport.R</path>
      <!-- full path to directory with SCAN-B reference data -->
      <!-- default is same directory as the R script -->
      <ref-dir-scanb></ref-dir-scanb>
      <!-- full path to directory with validation reference data -->
      <!-- default is same directory as the R script -->
      <ref-dir-validation></ref-dir-validation>
      <!-- full path to the PDF template -->
      <!-- default is 'template.pdf' in the same directory as the R script -->
      <template></template>
      <!-- file name in BASE for storing the generated report  -->
      <pdf-name>genereport.pdf</pdf-name>
    </gene-report>
    
    <!-- options for the 'pilot report' script -->
    <pilot-report>
      <!-- full path to the R script -->
      <path>/path/to/pilot-report.R</path>
      <!-- full path to directory with reference data -->
      <!-- default is 'referenceData' directory inside -->
      <!-- the same directory as the R script -->
      <ref-dir></ref-dir>
      <!-- full path to directory with source code -->
      <!-- default is 'source' directory inside -->
      <!-- the same directory as the R script -->
      <source-dir></source-dir>
      <!-- full path to the PDF template -->
      <!-- default is 'template.pdf' in the same directory as the R script -->
      <template></template>
      <!-- file name in BASE for storing the generated report  -->
      <pdf-name>pilotreport.pdf</pdf-name>
    </pilot-report>
    
  </rscript>

  <!-- Logotype information for the different sites -->
  <!-- Uncomment as needed and set full path to image file -->
  <!-- Supported file formats: WMF, PNG, JPG (and possible more) -->
  <logos>
    <!-- <region-skåne></region-skåne>  -->
    <!-- <landstinget-kronoberg></landstinget-kronoberg>  -->
    <!-- <uppsala-landsting></uppsala-landsting>  -->
    <!-- <region-halland></region-halland>  -->
    <!-- <landstinget-blekinge></landstinget-blekinge>  -->
    <!-- <jönköpings-län></jönköpings-län>  -->
  </logos>

  <remote-hosts>
    <!-- one or more hosts entries. Each entry should match an -->
    <!-- entry in the opengrid-config.xml. The 'ID' of an Open Grid cluster -->
    <!-- is a combination of the username, address and port: user@host:port -->
    <!-- A comma-separated list is allowed -->
    <!-- Note that the default port number (22) must be included in the ID  -->
    <!-- even if it is not specified in the opengrid-config.xml file. -->
  
    <host 
      id="user@address:port in opengrid-config.xml (one or more separated by comma)"
      >
      
      <!-- full path to the location where HiSeq/NextSeq data is stored (required) -->
      <run-archive>/casa2/run_archive</run-archive>
      <!-- Alternate paths in search order in case data is not found in the primary -->
      <!-- run archive. Add more entries as needed, but it is important that they -->
      <!-- are numbered in strictly increasing order from '2' and up. -->
      <run-archive-2></run-archive-2>
      
      <!-- Full path to the location where data files should be archived (required) -->
      <!-- The path should include the name of the project -->
      <project-archive>/casa4/project_archive/scanb</project-archive>
      <!-- Full path to the location where external data files should be archive (optional) -->
      <!-- If not specified, the 'project-archive' path is used -->
      <external-archive></external-archive>
      
      <!-- Full path to the root location where reference genomes are located -->
      <!-- Do not include name of project -->
      <reference-folder>/reference</reference-folder>
      
      <!-- Information about programs used by reggie -->
      <!-- Unless otherwise noted, all paths must be the same on all nodes -->
      <programs>
        <java>
          <!-- full path to java binary to use (1.8 is required by GATK!) -->
          <path>/usr/local/packages/jre/8.0_144/bin/java</path>
        </java>
        <pipeline-scripts>
          <!-- folder where the pipeline scripts are located (required). -->
          <path>/home/scanb/lorry-pipeline/pipeline-2.16</path>
        </pipeline-scripts>
        <picard>
          <!-- full path to the directory with Picard jar files (required) -->
          <path>/usr/local/packages/picard-tools/2.20.8</path>
        </picard>
        <genseq>
          <!-- full path to the genseq_check_illumina_dir.pl script (required) -->
          <path>/usr/local/packages/genseq_tools/v0.01/genseq_check_illumina_dir.pl</path>
        </genseq>
        <trimmomatic>
          <!-- full path to the JAR file with the Trimmomatic program (required) -->
          <path>/usr/local/packages/trimmomatic/0.32/trimmomatic-0.32.jar</path>
          <!-- full path to the file with Illumina adapter information -->
          <adapter-file>/usr/local/packages/trimmomatic/0.32/adapters/TruSeq3-PE-2.fa</adapter-file>
        </trimmomatic>
        <bowtie2>
          <!-- full or partial path to bowtie2 (required) -->
          <path>/usr/local/packages/bowtie/2.2.4/bin/bowtie2</path>
        </bowtie2>
        <tophat>
          <!-- full or partial path to tophat (required) -->
          <path>/usr/local/packages/tophat/2.0.12/bin/tophat</path>
        </tophat>
        <hisat>
          <!-- full or partial path to hisat (required) -->
          <path>/usr/local/packages/hisat/2.1.0/bin/hisat2</path>
        </hisat>
        <samtools>
          <!-- full or partial path to samtools (required) -->
          <path>/usr/local/packages/samtools/1.4/samtools</path>
        </samtools>
        <bedtools>
          <!-- full or partial path to bedtools (required) -->
          <path>/usr/local/packages/bedtools/2.26.0/bin/bedtools</path>
        </bedtools>
        <cufflinks>
          <!-- full or partial path to cufflinks (required) -->
          <path>/usr/local/packages/cufflinks/2.2.1/bin/cufflinks</path>
        </cufflinks>
        <stringtie>
          <!-- full or partial path to stringtie (required) -->
          <path>/usr/local/packages/stringtie/1.3.3b/bin/stringtie</path>
        </stringtie>
        <gatk>
          <!-- full path to GenomeAnalysisToolkit JAR file (required) -->
          <path>/usr/local/packages/GenomeAnalysisTK/3.8/GenomeAnalysisTK.jar</path>
        </gatk>
        <mosdepth>
          <!-- full or partial path to mosdepth (required) -->
          <path>/usr/local/packages/mosdepth/0.2.6/bin/mosdepth</path>
        </mosdepth>
        <vardict>
          <!-- path to the directory where VarDict is installed -->
          <!-- NOTE! not including the 'bin/VarDict' part since -->
          <!-- that will be added automatically -->
          <path>/usr/local/packages/vardict/1.6.0</path>
        </vardict>
        <vcfanno>
          <!-- full or partial path to vcfanno (required) -->
          <path>/usr/local/packages/vcfanno/0.3.2/bin/vcfanno</path>
        </vcfanno>
        <snpeff>
          <!-- full path to the snpEff.jar file (required) -->
          <path>/usr/local/packages/snpeff/4.3s/snpEff.jar</path>
        </snpeff>
        <snpsift>
          <!-- full path to the SnpSift.jar file (required) -->
          <path>/usr/local/packages/snpeff/4.3s/SnpSift.jar</path>
        </snpsift>
      </programs>
      
      <!-- priority values that are selectable in the web interface -->
      <!-- allowed range is -1023 to 1024 -->
      <!-- NOTE! positive values require special permissions on the cluster -->
      <priorities>
        <!-- <priority name="high" value="500" /> -->
        <priority name="normal" value="0" default="true" />
        <priority name="low" value="-500" />
      </priorities>
      
      <!-- settings for the demuxing step (RNAseq) -->
      <demux>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting requests 4 slots -->
        <parallel-environment>smp 4-4</parallel-environment>
        <!-- Number of open files to set with 'ulimit -n' command -->
        <!-- if not specified, the default on the server is used -->
        <ulimit></ulimit>
        <!-- amount of memory to give to Picard (default is 50g)-->
        <picard-memory>50g</picard-memory>
        <!-- static options for the picard ExtractIlluminaBarcodes step -->
        <extract-options>-QUIET true -VERBOSITY WARNING</extract-options>
        <!-- static options for the picard IlluminaBasecallsToFastq step -->
        <fastq-options>-INCLUDE_NON_PF_READS false -MAX_READS_IN_RAM_PER_TILE 5000000 -QUIET true -VERBOSITY WARNING</fastq-options>
        <!-- number of tiles to process when debugging (default=2 (HiSeq), 16 (NextSeq)) -->
        <debug-tile-limit-hiseq>2</debug-tile-limit-hiseq>
        <debug-tile-limit-nextseq>16</debug-tile-limit-nextseq>
        <!-- static options for Bowtie when used for estimating fragment size -->
        <bowtie-options>-q --fr -k 1 --phred33 --local --no-hd --no-unal -t -u 100000</bowtie-options>
        <!-- the smallest number of fragments that must have been used in the fragment -->
        <!-- size estimation, or we will set FragmentSizeAvg and FragmentSizeStdev to -1 -->
        <bowtie-fragment-count-limit>20000</bowtie-fragment-count-limit>
        <!-- static options for Trimmomatic -->
        <trimmomatic-options>
          <!-- The first step should ONLY filter Illumina adapters-->
          <step-1>ILLUMINACLIP:${AdapterFile}:2:30:12:1:true MINLEN:20</step-1>
          <!-- The second step is for all other filters -->
          <step-2>MAXINFO:40:0.9 MINLEN:20</step-2>
        </trimmomatic-options>
        <!-- static options for gzip compression with pigz (default=-5) -->
        <!-- NOTE! Number of threads (-p) is set automatically and should not be included here -->
        <pigz-options>-5</pigz-options>
      </demux>
  
      <!-- settings for the demuxing step (MIPs) -->
      <demux-mips>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting requests 8-16 slots -->
        <parallel-environment>smp 8-16</parallel-environment>
        <!-- amount of memory to give to Picard (default is 50g)-->
        <picard-memory>50g</picard-memory>
        <!-- static options for the picard ExtractIlluminaBarcodes step -->
        <extract-options>-MINIMUM_BASE_QUALITY 0 -MINIMUM_QUALITY 2 -MAX_MISMATCHES 2 -MIN_MISMATCH_DELTA 2 -MAX_NO_CALLS 2 -QUIET true -VERBOSITY WARNING</extract-options>
        <!-- static options for the picard IlluminaBasecallsToFastq step -->
        <fastq-options>-INCLUDE_NON_PF_READS false -APPLY_EAMSS_FILTER false -MINIMUM_QUALITY 2 -MAX_READS_IN_RAM_PER_TILE 5000000 -QUIET true -VERBOSITY WARNING</fastq-options>
        <!-- static options to put into the "Read group" files -->
        <readgroup-options>PL=ILLUMINA CN=BRCAlab</readgroup-options>
        <!-- number of tiles to process when debugging (default=2 (HiSeq), 16 (NextSeq)) -->
        <debug-tile-limit-hiseq>2</debug-tile-limit-hiseq>
        <debug-tile-limit-nextseq>16</debug-tile-limit-nextseq>
        <!-- static options for gzip compression with pigz (default=-5) -->
        <!-- NOTE! Number of threads (-p) is set automatically and should not be included here -->
        <pigz-options>-5</pigz-options>
      </demux-mips>
  
      <mask>
        <!-- relative path from <reference-folder> to the reference genome used for masking -->
        <!-- This is the -x option used for bowtie -->
        <reference-name>scanb/ribo_phix_repeats_filter/ribo_phix_repeats_filter</reference-name>
        
        <!-- static options for bowtie -->
        <bowtie-options>-q --fr -k 1 --phred33 -t --local</bowtie-options>
        
        <!-- max number of sequences to align when running in debug mode (default=2 millions)-->
        <debug-max-align>2000000</debug-max-align>
      </mask>
  
      <align>
        <!-- relative path from <reference-folder> to the reference genome used for alignment -->
        <!-- TODO selectable in GUI? saved as annotation? -->
        <reference-gidx>hg38/hg38.analysisSet/hg38.analysisSet</reference-gidx>
        <reference-tidx>hg38/UCSC_hg38_knownGenes_22sep2014/knownGenes.vs.hg38.analysisSet</reference-tidx>
        
        <!-- static options for tophat -->
        <tophat-options>--library-type fr-firststrand --keep-fasta-order --no-coverage-search --max-insertion-length 20 --max-deletion-length 20 --read-gap-length 20 --read-edit-dist 22</tophat-options>
        <!-- adjustment values for the 'mate-inner-dist' and 'mate-std-dev' -->
        <!-- parameters to tophat. The specified values are added to those -->
        <!-- calculated by bowtie -->
        <adjust-mate-inner-dist>13</adjust-mate-inner-dist>
        <adjust-mate-std-dev>10</adjust-mate-std-dev>
        
        <!-- static options for the picard MarkDuplicates step -->
        <mark-duplicates-options>-REMOVE_DUPLICATES false -ASSUME_SORTED true -MAX_FILE_HANDLES_FOR_READ_ENDS_MAP 2000 -QUIET true -VERBOSITY WARNING</mark-duplicates-options>
      </align>
      
      <!-- settings for aligning with Hisat -->
      <align-hisat>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting use up to 16 slots on hosts with at least 8 slots available -->
        <parallel-environment>smp 8-16</parallel-environment>
        
        <!-- relative path from <reference-folder> to the reference genome used for alignment -->
        <reference-tidx>hg38/hg38.analysisSet_gencode27_snp150/genome_snp_tran</reference-tidx>
        
        <!-- static options for hisat -->
        <hisat-options>-q --fr --phred33 -t --dta --dta-cufflink --new-summary --no-unal --non-deterministic --novel-splicesite-outfile aligned/splicesites.tsv --rna-strandness RF --summary-file aligned/summary.txt --rg PL:Illumina --rg CN:SCANB-prim</hisat-options>
        
        <!-- static options for the picard MarkDuplicates step -->
        <mark-duplicates-options>-REMOVE_DUPLICATES false -ASSUME_SORTED true -MAX_FILE_HANDLES_FOR_READ_ENDS_MAP 2000 -QUIET true -VERBOSITY WARNING</mark-duplicates-options>
        
        <!-- relative path from <reference-folder> to FASTA file used as reference for the alignment  -->
        <haplotypecaller-ref>hg38/hg38.analysisSet_gencode27_snp150/hg38.analysisSet_gencodeid.fa</haplotypecaller-ref>
        
        <!-- relative path from <reference-folder> to VCF file with SNP that we should look for -->
        <haplotypecaller-dbsnp>scanb/genotyping-213-snp_feb2018.vcf</haplotypecaller-dbsnp>
        
        <!-- static options for the HaplotypeCaller step -->
        <haplotypecaller-options>-stand_call_conf 20 --filter_reads_with_N_cigar --annotation AlleleBalance --no_cmdline_in_header</haplotypecaller-options>
      </align-hisat>
      
      <!-- settings for aligning MIPs sequencing -->
      <align-mips>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting use up to 16 slots on hosts with at least 8 slots available -->
        <parallel-environment>smp 8-16</parallel-environment>
        
        <!-- Options for Trimmomatic -->
        <trimmomatic>
          <!-- Optional path to Trimmomatic, if not specified the default in the 'programs' section is used -->
          <path>/usr/local/packages/trimmomatic/0.39/trimmomatic.jar</path>
          <!-- The first step should filter Illumina adapters-->
          <step-1>ILLUMINACLIP:adapter.fa:3:12:7:1:true MINLEN:30</step-1>
          <!-- The second step is for all other filters -->
          <step-2>MAXINFO:30:0.25 MINLEN:30</step-2>
        </trimmomatic>
        
      </align-mips>
      
      <mbaf>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting use up to 16 slots on hosts with at least 8 slots available -->
        <parallel-environment>smp 8-16</parallel-environment>
        
        <!-- relative path from <reference-folder> to FASTA file used as reference for the alignment  -->
        <!-- this should probably be the same as in <align-hisat>/<haplotypecaller-ref> -->
        <haplotypecaller-ref>hg38/hg38.analysisSet_gencode27_snp150/hg38.analysisSet_gencodeid.fa</haplotypecaller-ref>
        
        <!-- relative path from <reference-folder> to VCF file with SNP:s that we should look for -->
        <haplotypecaller-dbsnp>scanb/genotyping-mbaf-snp_oct2018.vcf</haplotypecaller-dbsnp>
        
        <!-- static options for the HaplotypeCaller step -->
        <haplotypecaller-options>-stand_call_conf 20 --filter_reads_with_N_cigar --no_cmdline_in_header</haplotypecaller-options>
      </mbaf>
      
      <!-- settings for variant calling -->
      <variant-call>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting use up to 16 slots on hosts with at least 8 slots available -->
        <parallel-environment>smp 8-16</parallel-environment>

        <!-- relative path from <reference-folder> to FASTA file used as reference for the alignment  -->
        <!-- this should probably be the same as in <align-hisat>/<haplotypecaller-ref> -->
        <genome-fasta>hg38/hg38.analysisSet_gencode27_snp150/hg38.analysisSet_gencodeid.fa</genome-fasta>
        
        <!-- Full path to base directory with databases and other stuff needed by the pipeline -->
        <!-- This value can be used in other options as ${BaseDir} -->
        <base-dir>${ReferenceDir}/scanb/rnaseqvarcall-feb2020</base-dir>
        
        <!-- static options for 'mosdepth' for regular and debug modes (optional) -->
        <mosdepth-options></mosdepth-options>
        <mosdepth-options-debug>-c chr6</mosdepth-options-debug>
        
        <!-- the required depth for a base to be callable for variants (optional, default=5) -->
        <min-depth>5</min-depth>
        
        <!-- static options for VarDict (required) -->
        <vardict-options>-f 0.02 -c 1 -S 2 -E 3 -g 4 -Q 20 -r 2 -q 20 --nosv</vardict-options>
        
        <!-- static options for var2vcf_valid.pl (required) -->
        <var2vcf-options>-A -f 0.02</var2vcf-options>
        
        <!--static options for vcfanno command line (required) -->
        <!-- See https://github.com/brentp/vcfanno for more information -->
        <vcfanno-options>-p 8 -lua ${BaseDir}/vcfanno.lua -base-path ${BaseDir} ${BaseDir}/allDbs.toml</vcfanno-options>
        
        <!-- static options for the snpEff command (required) -->
        <snpeff-options>-configOption data.dir=${BaseDir}/snpEff_v4_3_hg38/data -noLog -noStats -canon hg38</snpeff-options>

        <!-- static options for the SnpSift command (required) -->
        <snpsift-options>-s ${BaseDir}/rna_chr_set.txt -s ${BaseDir}/intogen-BRCA-genes-list_patch.txt -e ${BaseDir}/filter_expression.txt</snpsift-options>
        
        <!-- path to the COSMIC mutation signature data -->
        <mutation-signature>${BaseDir}/COSMIC_Cancer_signatures_probabilities.RData</mutation-signature>
      </variant-call>
      
      <cufflinks>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting use between 8 and 16 slots on hosts with at least 8 slots available -->
        <parallel-environment>smp 8-16</parallel-environment>
  
        <!-- relative path from <reference-folder> to the reference genome used by cufflinks -->
        <reference-gidx>hg38/hg38.analysisSet/hg38.analysisSet.fa</reference-gidx>
        <reference-gtf>hg38/UCSC_hg38_knownGenes_22sep2014.gtf</reference-gtf>
        
        <!-- static options for cufflinks -->
        <options>--multi-read-correct --library-type fr-firststrand --total-hits-norm --max-bundle-frags 10000000 --no-update-check --quiet</options>
        
        <!-- if the aligned sequences item has more reads than this limit (when running in debug mode) -->
        <!-- the accepted_hits.bam will be  limited to chr1 before running cufflinks -->
        <debug-max-aligned>2000000</debug-max-aligned>
        
        <!-- path to a file containing pairs of tracking_id values -->
        <!-- *.fpkm_tracking files are searched and values from the -->
        <!-- second column are replaced with values in the first column -->
        <!-- If no mapping file is specified, no replacement is done -->
        <tracking-id-map>hg38/UCSC_hg38_knownGenes_22sep2014_duplicate_transcript_id.txt</tracking-id-map>
      </cufflinks>
      
      <stringtie>
        <!-- parallel environment option to the queue system -->
        <!-- the default setting use between 8 and 16 slots on hosts with at least 8 slots available -->
        <parallel-environment>smp 8-16</parallel-environment>
        
        <!-- relative path from <reference-folder> to the reference genome used by stringtie -->
        <reference-gtf>hg38/hg38.analysisSet_gencode27_snp150/gencode.v27.primary_assembly.annotation_subset_transcripttype_proteincoding.gtf</reference-gtf>

        <!-- static options for stringtie -->
        <options>--rf -B -e</options>

      </stringtie>
    </host>
  
    
  </remote-hosts>

</reggie>