Mercurial > repos > jjohnson > gatk2
changeset 14:d73c92a7b0ea draft
Remove unneeded params
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Thu, 08 Nov 2012 13:09:56 -0600 |
| parents | da03516b528c |
| children | 35c6289faeff |
| files | haplotype_caller.xml reduce_reads.xml |
| diffstat | 2 files changed, 45 insertions(+), 206 deletions(-) [+] |
line wrap: on
line diff
--- a/haplotype_caller.xml Thu Nov 08 11:50:01 2012 -0600 +++ b/haplotype_caller.xml Thu Nov 08 13:09:56 2012 -0600 @@ -25,7 +25,6 @@ #if str($input_recal) != 'None': --BQSR "${input_recal}" #end if - --disable_bam_indexing ' ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": @@ -71,7 +70,6 @@ --defaultBaseQualities "${gatk_param_type.default_base_qualities}" --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.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): @@ -406,92 +404,10 @@ </conditional> </repeat> - <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"/> </when> </conditional> - - <conditional name="analysis_param_type"> - <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> - <option value="basic" selected="True">Basic</option> - <option value="advanced">Advanced</option> - </param> - <when value="basic"> - <!-- Do nothing here --> - </when> - <when value="advanced"> - - <conditional name="default_read_group_type"> - <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group"> - <option value="default" selected="True">Don't Set</option> - <option value="set">Set</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/> - </when> - </conditional> - <param name="default_platform" type="select" label="Set default Platform" help="--default_platform"> - <option value="default" selected="True">Don't Set</option> - <option value="illumina">illumina</option> - <option value="454">454</option> - <option value="solid">solid</option> - </param> - <conditional name="force_read_group_type"> - <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group"> - <option value="default" selected="True">Don't Force</option> - <option value="set">Force</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="force_read_group" type="text" value="Unknown" label="If provided, the read group ID of EVERY read will be forced to be the provided String."/> - </when> - </conditional> - <param name="force_platform" type="select" label="Force Platform" help="--force_platform"> - <option value="default" selected="True">Don't Force</option> - <option value="illumina">illumina</option> - <option value="454">454</option> - <option value="solid">solid</option> - </param> - <param name="exception_if_no_tile" type="boolean" checked="False" truevalue="--exception_if_no_tile" falsevalue="" label="Throw an exception when no tile can be found" help="--exception_if_no_tile"/> - <conditional name="solid_options_type"> - <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options"> - <option value="default" selected="True">Don't Set</option> - <option value="set">Set</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="solid_recal_mode" type="select" label="How should we recalibrate solid bases in which the reference was inserted" help="-sMode,--solid_recal_mode &lt;solid_recal_mode&gt;"> - <option value="default" selected="True">Don't set</option> - <option value="DO_NOTHING">DO_NOTHING</option> - <option value="SET_Q_ZERO">SET_Q_ZERO</option> - <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option> - <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option> - </param> - <param name="solid_nocall_strategy" type="select" label="Behavior of the recalibrator when it encounters no calls" help="-solid_nocall_strategy,--solid_nocall_strategy &lt;solid_nocall_strategy&gt;"> - <option value="default" selected="True">Don't set</option> - <option value="THROW_EXCEPTION">THROW_EXCEPTION</option> - <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option> - <option value="PURGE_READ">PURGE_READ</option> - </param> - </when> - </conditional> - <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/> - <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="--window_size_nqs"/> - <param name="homopolymer_nback" type="integer" value="7" label="Number of previous bases to look at in HomopolymerCovariate" help="-nback,--homopolymer_nback &lt;homopolymer_nback&gt;" /> - <param name="preserve_qscores_less_than" type="integer" value="5" label="Bases with quality scores less than this threshold won't be recalibrated" help="-pQ,--preserve_qscores_less_than &lt;preserve_qscores_less_than&gt;"/> - <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &lt;smoothing&gt;"/> - <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &lt;max_quality_score&gt;"/> - <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/> - </when> - </conditional> <conditional name="analysis_param_type"> <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> @@ -578,8 +494,8 @@ <help> **What it does** -HaplotypeCaller -Call SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region. +**HaplotypeCaller** +calls SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region. Haplotypes are evaluated using an affine gap penalty Pair HMM. For more information on using read based compression in the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_haplotypecaller_HaplotypeCaller.html>`_. @@ -592,7 +508,7 @@ **Inputs** -GenomeAnalysisTK: PrintReads accepts an aligned BAM files. +GenomeAnalysisTK: PrintReads accepts aligned BAM files. **Outputs** @@ -606,26 +522,6 @@ **Settings**:: - default_read_group If a read has no read group then default to the provided String. - default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid. - force_read_group If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group. - force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid. - window_size_nqs The window size used by MinimumNQSCovariate for its calculation - homopolymer_nback The number of previous bases to look at in HomopolymerCovariate - exception_if_no_tile If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1 - solid_recal_mode How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS) - solid_nocall_strategy Defines the behavior of the recalibrator when it encounters no calls in the color space. Options = THROW_EXCEPTION, LEAVE_READ_UNRECALIBRATED, or PURGE_READ (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ) - recal_file Filename for the input covariates table recalibration .csv file - out The output BAM file - bam_compression Compression level to use for writing BAM files - disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files. - simplifyBAM If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier - preserve_qscores_less_than Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below < 5, since base callers use these values to indicate random or bad bases - smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1 - max_quality_score The integer value at which to cap the quality scores, default=50 - doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read - -*HaplotypeCaller specific arguments*:: activeRegionIn Use this interval list file as the active regions to process activeRegionOut Output the active region to this interval list file alleles The set of alleles at which to genotype when --genotyping_mode is GENOTYPE_GIVEN_ALLELES
--- a/reduce_reads.xml Thu Nov 08 11:50:01 2012 -0600 +++ b/reduce_reads.xml Thu Nov 08 13:09:56 2012 -0600 @@ -367,87 +367,6 @@ </when> </conditional> - - <conditional name="analysis_param_type"> - <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> - <option value="basic" selected="True">Basic</option> - <option value="advanced">Advanced</option> - </param> - <when value="basic"> - <!-- Do nothing here --> - </when> - <when value="advanced"> - <conditional name="default_read_group_type"> - <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group"> - <option value="default" selected="True">Don't Set</option> - <option value="set">Set</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/> - </when> - </conditional> - <param name="default_platform" type="select" label="Set default Platform" help="--default_platform"> - <option value="default" selected="True">Don't Set</option> - <option value="illumina">illumina</option> - <option value="454">454</option> - <option value="solid">solid</option> - </param> - <conditional name="force_read_group_type"> - <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group"> - <option value="default" selected="True">Don't Force</option> - <option value="set">Force</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="force_read_group" type="text" value="Unknown" label="If provided, the read group ID of EVERY read will be forced to be the provided String."/> - </when> - </conditional> - <param name="force_platform" type="select" label="Force Platform" help="--force_platform"> - <option value="default" selected="True">Don't Force</option> - <option value="illumina">illumina</option> - <option value="454">454</option> - <option value="solid">solid</option> - </param> - <param name="exception_if_no_tile" type="boolean" checked="False" truevalue="--exception_if_no_tile" falsevalue="" label="Throw an exception when no tile can be found" help="--exception_if_no_tile"/> - <conditional name="solid_options_type"> - <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options"> - <option value="default" selected="True">Don't Set</option> - <option value="set">Set</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="solid_recal_mode" type="select" label="How should we recalibrate solid bases in which the reference was inserted" help="-sMode,--solid_recal_mode &lt;solid_recal_mode&gt;"> - <option value="default" selected="True">Don't set</option> - <option value="DO_NOTHING">DO_NOTHING</option> - <option value="SET_Q_ZERO">SET_Q_ZERO</option> - <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option> - <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option> - </param> - <param name="solid_nocall_strategy" type="select" label="Behavior of the recalibrator when it encounters no calls" help="-solid_nocall_strategy,--solid_nocall_strategy &lt;solid_nocall_strategy&gt;"> - <option value="default" selected="True">Don't set</option> - <option value="THROW_EXCEPTION">THROW_EXCEPTION</option> - <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option> - <option value="PURGE_READ">PURGE_READ</option> - </param> - </when> - </conditional> - <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/> - <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="--window_size_nqs"/> - <param name="homopolymer_nback" type="integer" value="7" label="Number of previous bases to look at in HomopolymerCovariate" help="-nback,--homopolymer_nback &lt;homopolymer_nback&gt;" /> - <param name="preserve_qscores_less_than" type="integer" value="5" label="Bases with quality scores less than this threshold won't be recalibrated" help="-pQ,--preserve_qscores_less_than &lt;preserve_qscores_less_than&gt;"/> - <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &lt;smoothing&gt;"/> - <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &lt;max_quality_score&gt;"/> - <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/> - </when> - </conditional> - <conditional name="analysis_param_type"> <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> <option value="basic" selected="True">Basic</option> @@ -533,24 +452,48 @@ **Settings**:: - default_read_group If a read has no read group then default to the provided String. - default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid. - force_read_group If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group. - force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid. - window_size_nqs The window size used by MinimumNQSCovariate for its calculation - homopolymer_nback The number of previous bases to look at in HomopolymerCovariate - exception_if_no_tile If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1 - solid_recal_mode How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS) - solid_nocall_strategy Defines the behavior of the recalibrator when it encounters no calls in the color space. Options = THROW_EXCEPTION, LEAVE_READ_UNRECALIBRATED, or PURGE_READ (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ) - recal_file Filename for the input covariates table recalibration .csv file - out The output BAM file - bam_compression Compression level to use for writing BAM files - disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files. - simplifyBAM If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier - preserve_qscores_less_than Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below < 5, since base callers use these values to indicate random or bad bases - smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1 - max_quality_score The integer value at which to cap the quality scores, default=50 - doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read + + --allow_polyploid_reduction / -polyploid ( boolean with default value false ) + Allow the experimental polyploid-based reduction capabilities of this tool + + --context_size / -cs ( int with default value 10 ) + The number of bases to keep around mismatches (potential variation) + + --dont_compress_read_names / -nocmp_names ( boolean with default value false ) + Do not compress read names. By default, ReduceReads will compress read names to numbers and guarantee uniqueness and reads with similar name will still have similar compressed names. Note: If you scatter/gather there is no guarantee that read name uniqueness will be maintained -- in this case we recommend not compressing. + + --dont_hardclip_low_qual_tails / -noclip_tail ( boolean with default value false ) + Do not hard clip the low quality tails of the reads. This option overrides the argument of minimum tail quality. + + --dont_simplify_reads / -nosimplify ( boolean with default value false ) + Do not simplify read (strip away all extra information of the read -- anything other than bases, quals and read group). + + --dont_use_softclipped_bases / -no_soft ( boolean with default value false ) + Do not use high quality soft-clipped bases. By default, ReduceReads will hard clip away any low quality soft clipped base left by the aligner and use the high quality soft clipped bases in it's traversal algorithm to identify variant regions. The minimum quality for soft clipped bases is the same as the minimum base quality to consider (minqual) + + --downsample_coverage / -ds ( int with default value 250 ) + Downsamples the coverage of a variable region approximately (guarantees the minimum to be equal to this). A value of 0 turns downsampling off. + + --hard_clip_to_interval / -clip_int ( boolean with default value false ) + Optionally hard clip all incoming reads to the desired intervals. The hard clips will happen exactly at the interval border. + + -mindel / --minimum_del_proportion_to_trigger_variant ( double with default value 0.05 ) + Minimum proportion of indels in a site to trigger a variant region. Anything below this will be considered consensus. + + --minimum_mapping_quality / -minmap ( int with default value 20 ) + The minimum mapping quality to be considered for the consensus synthetic read. Reads that have mapping quality below this threshold will not be counted towards consensus, but are still counted towards variable regions. + + --minimum_tail_qualities / -mintail ( byte with default value 2 ) + Reads have notoriously low quality bases on the tails (left and right). Consecutive bases with quality lower than this threshold will be hard clipped off before entering the reduce reads algorithm. + + -minqual / --minimum_base_quality_to_consider ( byte with default value 20 ) + The minimum base quality to be considered for the consensus synthetic read. Reads that have base quality below this threshold will not be counted towards consensus, but are still counted towards variable regions. + + -minvar / --minimum_alt_proportion_to_trigger_variant ( double with default value 0.05 ) + Minimum proportion of mismatches in a site to trigger a variant region. Anything below this will be considered consensus. + + -noclip_ad / --dont_hardclip_adaptor_sequences ( boolean with default value false ) + Do not hard clip adaptor sequences. Note: You don't have to turn this on for reads that are not mate paired. The program will behave correctly in those cases. ------