Mercurial > repos > jjohnson > gatk2
changeset 18:7533db8dfb5b draft
Update tool_dependencies to GATK v 2.3
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Thu, 20 Dec 2012 11:01:55 -0600 |
| parents | f2b21dc45241 |
| children | d1a88bdaa80a |
| files | README base_recalibrator.xml depth_of_coverage.xml haplotype_caller.xml indel_realigner.xml print_reads.xml realigner_target_creator.xml reduce_reads.xml tool_dependencies.xml unified_genotyper.xml variant_annotator.xml variant_apply_recalibration.xml variant_combine.xml variant_eval.xml variant_filtration.xml variant_recalibrator.xml variant_select.xml variants_validate.xml |
| diffstat | 18 files changed, 101 insertions(+), 38 deletions(-) [+] |
line wrap: on
line diff
--- a/README Thu Nov 15 10:18:55 2012 -0600 +++ b/README Thu Dec 20 11:01:55 2012 -0600 @@ -2,4 +2,18 @@ copied into the tool-data directory. The file tool_data_table_conf.xml must be edited to include references to these two new files. +GATK can be installed via tool_dependencies. +This will install GenomeAnalysisTKLite.jar from ftp://ftp.broadinstitute.org/pub/gsa/GenomeAnalysisTK/ +and create a symbolic link from GenomeAnalysisTK.jar to GenomeAnalysisTKLite.jar +If you have a full licensed copy of GenomeAnalysisTK.jar, change the GenomeAnalysisTK.jar symbolic link +in the installation directory to point to your licensed copy. + +Two environment variables: GATK2_SITE_OPTIONS and GATK2_THREAD_OPTIONS are also set in the tool_dependencies env.sh file. +You can alter the value of those variables for your site. +$ cat tool_dependencies/gatk/2.2/*/gatk2/*/env.sh +GATK2_PATH=/Users/jj/gxt/gxt/tool_dependencies/gatk/2.2/jimmy/gatk2/288cdae6bd9c; export GATK2_PATH +GATK2_SITE_OPTIONS="--phone_home STANDARD"; export GATK2_SITE_OPTIONS +GATK2_THREAD_OPTIONS="--num_threads 4 --num_cpu_threads_per_data_thread 3"; export GATK2_THREAD_OPTIONS + +
--- a/base_recalibrator.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/base_recalibrator.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="0.0.4"> +<tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="0.0.5"> <description>on BAM files</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -15,6 +15,7 @@ -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "BaseRecalibrator" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -90,6 +91,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -417,7 +419,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> - + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/depth_of_coverage.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/depth_of_coverage.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_depth_of_coverage" name="Depth of Coverage" version="0.0.4"> +<tool id="gatk2_depth_of_coverage" name="Depth of Coverage" version="0.0.5"> <description>on BAM files</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -17,6 +17,7 @@ -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "DepthOfCoverage" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home @@ -84,6 +85,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -437,6 +439,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/haplotype_caller.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/haplotype_caller.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_haplotype_caller" name="Haplotype Caller" version="0.0.4"> +<tool id="gatk2_haplotype_caller" name="Haplotype Caller" version="0.0.5"> <description>Call SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -16,6 +16,7 @@ -T "HaplotypeCaller" -o "${output_vcf}" ## \$GATK2_SITE_OPTIONS + ## \$GATK2_THREAD_OPTIONS ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home ##--num_threads 4 ##not supported yet ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -70,6 +71,7 @@ --defaultBaseQualities "${gatk_param_type.default_base_qualities}" --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -417,6 +419,7 @@ </repeat> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/indel_realigner.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/indel_realigner.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_indel_realigner" name="Indel Realigner" version="0.0.4"> +<tool id="gatk2_indel_realigner" name="Indel Realigner" version="0.0.5"> <description>- perform local realignment</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -16,6 +16,7 @@ -T "IndelRealigner" -o "${output_bam}" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home ##--num_threads 4 ##hard coded, for now ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -82,6 +83,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -377,6 +379,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/print_reads.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/print_reads.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_print_reads" name="Print Reads" version="0.0.4"> +<tool id="gatk2_print_reads" name="Print Reads" version="0.0.5"> <description>on BAM files</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -22,7 +22,9 @@ #if $reference_source.reference_source_selector != "history": -R "${reference_source.ref_file.fields.path}" #end if - --BQSR "${input_recal}" + #if str($input_recal) != 'None': + --BQSR "${input_recal}" + #end if --disable_bam_indexing ' ##start standard gatk options @@ -70,6 +72,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -356,6 +359,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/realigner_target_creator.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/realigner_target_creator.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_realigner_target_creator" name="Realigner Target Creator" version="0.0.4"> +<tool id="gatk2_realigner_target_creator" name="Realigner Target Creator" version="0.0.5"> <description>for use in local realignment</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -16,6 +16,7 @@ -T "RealignerTargetCreator" -o "${output_interval}" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home ##--num_threads 4 ##hard coded, for now ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -79,6 +80,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -363,6 +365,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/reduce_reads.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/reduce_reads.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_reduce_reads" name="Reduce Reads" version="0.0.4"> +<tool id="gatk2_reduce_reads" name="Reduce Reads" version="0.0.5"> <description>in BAM files</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -16,6 +16,7 @@ -T "ReduceReads" -o "${output_bam}" ## \$GATK2_SITE_OPTIONS + ## \$GATK2_THREAD_OPTIONS ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home ##--num_threads 4 ##not supported yet ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -72,6 +73,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -363,6 +365,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/tool_dependencies.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/tool_dependencies.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,9 +1,9 @@ <?xml version="1.0"?> <tool_dependency> - <package name="gatk" version="2.2"> + <package name="gatk" version="2.3"> <install version="1.0"> <actions> - <action type="download_by_url">ftp://ftp.broadinstitute.org/pub/gsa/GenomeAnalysisTK/GenomeAnalysisTKLite-2.2-8-g99996f2.tar.bz2</action> + <action type="download_by_url">ftp://ftp.broadinstitute.org/pub/gsa/GenomeAnalysisTK/GenomeAnalysisTKLite-2.3-4-gb8f1308.tar.bz2</action> <action type="move_file"> <source>GenomeAnalysisTKLite.jar</source> <destination>$INSTALL_DIR</destination> @@ -15,7 +15,8 @@ </action> <action type="set_environment"> <environment_variable name="GATK2_PATH" action="set_to">$INSTALL_DIR</environment_variable> - <environment_variable name="GATK2_SITE_OPTIONS" action="set_to">"--num_threads 4 --num_cpu_threads_per_data_thread 3 --phone_home STANDARD"</environment_variable> + <environment_variable name="GATK2_SITE_OPTIONS" action="set_to">"--phone_home STANDARD"</environment_variable> + <environment_variable name="GATK2_THREAD_OPTIONS" action="set_to">"--num_threads 4 --num_cpu_threads_per_data_thread 3"</environment_variable> </action> </actions> </install>
--- a/unified_genotyper.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/unified_genotyper.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_unified_genotyper" name="Unified Genotyper" version="0.0.4"> +<tool id="gatk2_unified_genotyper" name="Unified Genotyper" version="0.0.5"> <description>SNP and indel caller</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -20,6 +20,7 @@ --out "${output_vcf}" --metrics_file "${output_metrics}" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout #if $reference_source.reference_source_selector != "history": @@ -85,6 +86,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -419,6 +421,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional> @@ -458,7 +461,7 @@ <param name="compute_SLOD" type="boolean" truevalue="--computeSLOD" falsevalue="" label="Compute the SLOD" help="--computeSLOD" /> <param name="min_base_quality_score" type="integer" value="17" label="Minimum base quality required to consider a base for calling" help="-mbq,--min_base_quality_score &lt;min_base_quality_score&gt;" /> <param name="max_deletion_fraction" type="float" value="0.05" label="Maximum fraction of reads with deletions spanning this locus for it to be callable" help="to disable, set to < 0 or > 1 (-deletions,--max_deletion_fraction &lt;max_deletion_fraction&gt;)" /> - <param name="max_alternate_alleles" type="integer" value="5" label="Maximum number of alternate alleles to genotype" help="-maxAlleles,--max_alternate_alleles &lt;max_alternate_alleles&gt;" /> + <param name="max_alternate_alleles" type="integer" value="6" label="Maximum number of alternate alleles to genotype" help="-maxAlleles,--max_alternate_alleles &lt;max_alternate_alleles&gt;" /> <param name="min_indel_count_for_genotyping" type="integer" value="5" label="Minimum number of consensus indels required to trigger genotyping run" help="-minIndelCnt,--min_indel_count_for_genotyping &lt;min_indel_count_for_genotyping&gt;" /> <param name="indel_heterozygosity" type="float" value="0.000125" label="Heterozygosity for indel calling" help="1.0/8000==0.000125 (-indelHeterozygosity,--indel_heterozygosity &lt;indel_heterozygosity&gt;)"/> <param name="indelGapContinuationPenalty" type="float" value="10.0" label="Indel gap continuation penalty" help="--indelGapContinuationPenalty" />
--- a/variant_annotator.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variant_annotator.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_variant_annotator" name="Variant Annotator" version="0.0.4"> +<tool id="gatk2_variant_annotator" name="Variant Annotator" version="0.0.5"> <description></description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py @@ -19,6 +19,7 @@ ##--list -T "VariantAnnotator" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -117,6 +118,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -444,6 +446,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/variant_apply_recalibration.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variant_apply_recalibration.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_variant_apply_recalibration" name="Apply Variant Recalibration" version="0.0.4"> +<tool id="gatk2_variant_apply_recalibration" name="Apply Variant Recalibration" version="0.0.5"> <description></description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py --max_jvm_heap_fraction "1" @@ -13,6 +13,7 @@ -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "ApplyRecalibration" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home #if $reference_source.reference_source_selector != "history": @@ -68,6 +69,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -334,6 +336,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/variant_combine.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variant_combine.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_variant_combine" name="Combine Variants" version="0.0.4"> +<tool id="gatk2_variant_combine" name="Combine Variants" version="0.0.5"> <description></description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py --max_jvm_heap_fraction "1" @@ -19,6 +19,7 @@ -T "CombineVariants" --out "${output_variants}" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -74,6 +75,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -354,6 +356,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/variant_eval.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variant_eval.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_variant_eval" name="Eval Variants" version="0.0.4"> +<tool id="gatk2_variant_eval" name="Eval Variants" version="0.0.5"> <description></description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py #from binascii import hexlify @@ -15,6 +15,7 @@ -T "VariantEval" --out "${output_report}" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -82,6 +83,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -410,6 +412,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/variant_filtration.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variant_filtration.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_variant_filtration" name="Variant Filtration" version="0.0.4"> +<tool id="gatk2_variant_filtration" name="Variant Filtration" version="0.0.5"> <description>on VCF files</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py #from binascii import hexlify @@ -12,6 +12,7 @@ -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "VariantFiltration" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home -o "${output_vcf}" @@ -78,6 +79,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -363,6 +365,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/variant_recalibrator.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variant_recalibrator.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_variant_recalibrator" name="Variant Recalibrator" version="0.0.4"> +<tool id="gatk2_variant_recalibrator" name="Variant Recalibrator" version="0.0.5"> <description></description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py --max_jvm_heap_fraction "1" @@ -13,6 +13,7 @@ -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "VariantRecalibrator" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file"##ET no phone home ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -86,6 +87,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -589,6 +591,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/variant_select.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variant_select.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_variant_select" name="Select Variants" version="0.0.4"> +<tool id="gatk2_variant_select" name="Select Variants" version="0.0.5"> <description>from VCF files</description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py #from binascii import hexlify @@ -12,6 +12,7 @@ -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "SelectVariants" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home -o "${output_vcf}" @@ -138,6 +139,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -408,6 +410,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>
--- a/variants_validate.xml Thu Nov 15 10:18:55 2012 -0600 +++ b/variants_validate.xml Thu Dec 20 11:01:55 2012 -0600 @@ -1,7 +1,7 @@ -<tool id="gatk2_validate_variants" name="Validate Variants" version="0.0.4"> +<tool id="gatk2_validate_variants" name="Validate Variants" version="0.0.5"> <description></description> <requirements> - <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py --max_jvm_heap_fraction "1" @@ -12,6 +12,7 @@ -T "ValidateVariants" \$GATK2_SITE_OPTIONS + \$GATK2_THREAD_OPTIONS ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home ##--num_threads 4 ##hard coded, for now ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout @@ -71,6 +72,7 @@ --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -334,6 +336,7 @@ <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> + <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional>