Mercurial > repos > iuc > gatk2
annotate print_reads.xml @ 6:35c00763cb5c draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
| author | iuc |
|---|---|
| date | Mon, 04 Jun 2018 05:38:15 -0400 |
| parents | f244b8209eb8 |
| children |
| rev | line source |
|---|---|
| 4 | 1 <tool id="gatk2_print_reads" name="Print Reads" version="@VERSION@.0"> |
| 0 | 2 <description>on BAM files</description> |
| 3 <macros> | |
| 4 <import>gatk2_macros.xml</import> | |
| 5 </macros> | |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
6 <expand macro="requirements" /> |
|
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
7 <expand macro="version_command" /> |
| 0 | 8 <command interpreter="python"> |
| 9 gatk2_wrapper.py | |
| 10 --stdout "${output_log}" | |
| 11 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input" | |
| 12 #if str( $reference_source.input_bam.metadata.bam_index ) != "None": | |
| 13 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index | |
| 14 #end if | |
| 15 -p ' | |
| 16 @JAR_PATH@ | |
| 17 -T "PrintReads" | |
| 18 -o "${output_bam}" | |
| 19 \$GATK2_SITE_OPTIONS | |
| 20 | |
| 21 ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975 | |
| 2 | 22 --num_cpu_threads_per_data_thread \${GALAXY_SLOTS:-6} |
| 0 | 23 |
| 24 #if $reference_source.reference_source_selector != "history": | |
| 25 -R "${reference_source.ref_file.fields.path}" | |
| 26 #end if | |
| 27 #if str($input_recal) != 'None': | |
| 28 --BQSR "${input_recal}" | |
| 29 #end if | |
| 30 --disable_bam_indexing | |
| 31 ' | |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
32 |
| 0 | 33 #include source=$standard_gatk_options# |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
34 |
| 0 | 35 ##start analysis specific options |
| 36 #if $analysis_param_type.analysis_param_type_selector == "advanced": | |
| 37 -p ' | |
| 38 #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set": | |
| 39 --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}" | |
| 40 #end if | |
| 41 #if str( $analysis_param_type.default_platform ) != "default": | |
| 42 --default_platform "${analysis_param_type.default_platform}" | |
| 43 #end if | |
| 44 #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set": | |
| 45 --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}" | |
| 46 #end if | |
| 47 #if str( $analysis_param_type.force_platform ) != "default": | |
| 48 --force_platform "${analysis_param_type.force_platform}" | |
| 49 #end if | |
| 50 ${analysis_param_type.exception_if_no_tile} | |
| 51 #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set": | |
| 52 #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default": | |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
53 --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}" |
| 0 | 54 #end if |
| 55 #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default": | |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
56 --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}" |
| 0 | 57 #end if |
| 58 #end if | |
| 59 ${analysis_param_type.simplify_bam} | |
| 60 --preserve_qscores_less_than "${analysis_param_type.preserve_qscores_less_than}" | |
| 61 --smoothing "${analysis_param_type.smoothing}" | |
| 62 --max_quality_score "${analysis_param_type.max_quality_score}" | |
| 63 --window_size_nqs "${analysis_param_type.window_size_nqs}" | |
| 64 --homopolymer_nback "${analysis_param_type.homopolymer_nback}" | |
| 65 ${analysis_param_type.do_not_write_original_quals} | |
| 66 ' | |
| 67 #end if | |
| 68 </command> | |
| 69 <inputs> | |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
70 <param name="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file" |
| 0 | 71 help="The input covariates table file which enables on-the-fly base quality score recalibration (intended for use with BaseRecalibrator files) (-BQSR,--BQSR)" /> |
| 72 <conditional name="reference_source"> | |
| 73 <expand macro="reference_source_selector_param" /> | |
| 74 <when value="cached"> | |
| 75 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &lt;input_file&gt;"> | |
| 76 <validator type="unspecified_build" /> | |
| 77 <validator type="dataset_metadata_in_data_table" table_name="gatk2_picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select --> | |
| 78 </param> | |
| 79 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;" > | |
| 80 <options from_data_table="gatk2_picard_indexes"> | |
| 81 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> | |
| 82 </options> | |
| 83 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
| 84 </param> | |
| 85 </when> | |
| 86 <when value="history"> | |
| 87 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &lt;input_file&gt;" /> | |
| 88 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;"> | |
| 89 <options> | |
| 90 <filter type="data_meta" key="dbkey" ref="input_bam" /> | |
| 91 </options> | |
| 92 </param> | |
| 93 </when> | |
| 94 </conditional> | |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
95 |
| 0 | 96 <expand macro="gatk_param_type_conditional" /> |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
97 |
| 0 | 98 <conditional name="analysis_param_type"> |
| 99 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> | |
| 100 <option value="basic" selected="True">Basic</option> | |
| 101 <option value="advanced">Advanced</option> | |
| 102 </param> | |
| 103 <when value="basic"> | |
| 104 <!-- Do nothing here --> | |
| 105 </when> | |
| 106 <when value="advanced"> | |
| 107 <conditional name="default_read_group_type"> | |
| 108 <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group"> | |
| 109 <option value="default" selected="True">Don't Set</option> | |
| 110 <option value="set">Set</option> | |
| 111 </param> | |
| 112 <when value="default"> | |
| 113 <!-- do nothing here --> | |
| 114 </when> | |
| 115 <when value="set"> | |
| 116 <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/> | |
| 117 </when> | |
| 118 </conditional> | |
| 119 <param name="default_platform" type="select" label="Set default Platform" help="--default_platform"> | |
| 120 <option value="default" selected="True">Don't Set</option> | |
| 121 <option value="illumina">illumina</option> | |
| 122 <option value="454">454</option> | |
| 123 <option value="solid">solid</option> | |
| 124 </param> | |
| 125 <conditional name="force_read_group_type"> | |
| 126 <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group"> | |
| 127 <option value="default" selected="True">Don't Force</option> | |
| 128 <option value="set">Force</option> | |
| 129 </param> | |
| 130 <when value="default"> | |
| 131 <!-- do nothing here --> | |
| 132 </when> | |
| 133 <when value="set"> | |
| 134 <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."/> | |
| 135 </when> | |
| 136 </conditional> | |
| 137 <param name="force_platform" type="select" label="Force Platform" help="--force_platform"> | |
| 138 <option value="default" selected="True">Don't Force</option> | |
| 139 <option value="illumina">illumina</option> | |
| 140 <option value="454">454</option> | |
| 141 <option value="solid">solid</option> | |
| 142 </param> | |
| 143 <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"/> | |
| 144 <conditional name="solid_options_type"> | |
| 145 <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options"> | |
| 146 <option value="default" selected="True">Don't Set</option> | |
| 147 <option value="set">Set</option> | |
| 148 </param> | |
| 149 <when value="default"> | |
| 150 <!-- do nothing here --> | |
| 151 </when> | |
| 152 <when value="set"> | |
| 153 <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;"> | |
| 154 <option value="default" selected="True">Don't set</option> | |
| 155 <option value="DO_NOTHING">DO_NOTHING</option> | |
| 156 <option value="SET_Q_ZERO">SET_Q_ZERO</option> | |
| 157 <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option> | |
| 158 <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option> | |
| 159 </param> | |
| 160 <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;"> | |
| 161 <option value="default" selected="True">Don't set</option> | |
| 162 <option value="THROW_EXCEPTION">THROW_EXCEPTION</option> | |
| 163 <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option> | |
| 164 <option value="PURGE_READ">PURGE_READ</option> | |
| 165 </param> | |
| 166 </when> | |
| 167 </conditional> | |
| 168 <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/> | |
| 169 <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="--window_size_nqs"/> | |
| 170 <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;" /> | |
| 171 <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;"/> | |
| 172 <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &lt;smoothing&gt;"/> | |
| 173 <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &lt;max_quality_score&gt;"/> | |
| 174 <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/> | |
| 175 </when> | |
| 176 </conditional> | |
| 177 </inputs> | |
| 178 <outputs> | |
| 179 <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" /> | |
| 180 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> | |
| 181 </outputs> | |
| 182 <tests> | |
| 183 <test> | |
|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
184 <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" /> |
| 0 | 185 <param name="reference_source_selector" value="history" /> |
| 186 <param name="ref_file" value="phiX.fasta" ftype="fasta" /> | |
| 187 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" /> | |
| 188 <param name="gatk_param_type_selector" value="basic" /> | |
| 189 <param name="analysis_param_type_selector" value="basic" /> | |
| 190 <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" /> | |
| 191 <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" /> | |
| 192 </test> | |
| 193 </tests> | |
| 194 <help> | |
| 195 **What it does** | |
| 196 | |
| 197 This walker is designed to work as the second pass in a two-pass processing step, doing a by-read traversal. For each base in each read this walker calculates various user-specified covariates (such as read group, reported quality score, cycle, and dinuc) Using these values as a key in a large hashmap the walker calculates an empirical base quality score and overwrites the quality score currently in the read. This walker then outputs a new bam file with these updated (recalibrated) reads. Note: This walker expects as input the recalibration table file generated previously by CovariateCounterWalker. Note: This walker is designed to be used in conjunction with CovariateCounterWalker. | |
| 198 | |
| 4 | 199 For more information on base quality score recalibration using the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_readutils_PrintReads.html>`_. |
| 0 | 200 |
| 201 To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gatk/guide/topic?name=best-practices>`_. | |
| 202 | |
| 203 If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gatk/guide/topic?name=faqs>`_. | |
| 204 | |
| 205 ------ | |
| 206 | |
| 207 **Inputs** | |
| 208 | |
| 209 GenomeAnalysisTK: PrintReads accepts an aligned BAM and a recalibration (gatk_report) input files. | |
| 210 | |
| 211 | |
| 212 **Outputs** | |
| 213 | |
| 214 The output is in BAM format. | |
| 215 | |
| 216 | |
| 217 Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. | |
| 218 | |
| 219 ------- | |
| 220 | |
| 221 **Settings**:: | |
| 222 | |
| 223 default_read_group If a read has no read group then default to the provided String. | |
| 224 default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid. | |
| 225 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. | |
| 226 force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid. | |
| 227 window_size_nqs The window size used by MinimumNQSCovariate for its calculation | |
| 228 homopolymer_nback The number of previous bases to look at in HomopolymerCovariate | |
| 229 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 | |
| 230 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) | |
| 231 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) | |
| 232 recal_file Filename for the input covariates table recalibration .gatk_report file | |
| 233 out The output BAM file | |
| 234 bam_compression Compression level to use for writing BAM files | |
| 235 disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files. | |
| 236 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 | |
| 237 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 | |
| 238 smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1 | |
| 239 max_quality_score The integer value at which to cap the quality scores, default=50 | |
| 240 doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read | |
| 241 | |
| 242 @CITATION_SECTION@ | |
| 243 </help> | |
| 4 | 244 <expand macro="citations" /> |
| 0 | 245 </tool> |