Mercurial > repos > iuc > bedtools
changeset 2:457b09031d57 draft
Uploaded
| author | iuc |
|---|---|
| date | Tue, 19 May 2015 07:05:36 -0400 |
| parents | 82aac94b06c3 |
| children | 2cd7e321d259 |
| files | genomeCoverageBed.xml macros.xml mapBed.xml mergeBed.xml randomBed.xml test-data/mergedBed_result5.bed test-data/randomBed_result1.bed |
| diffstat | 7 files changed, 78 insertions(+), 101 deletions(-) [+] |
line wrap: on
line diff
--- a/genomeCoverageBed.xml Thu Jan 08 14:25:51 2015 -0500 +++ b/genomeCoverageBed.xml Tue May 19 07:05:36 2015 -0400 @@ -19,14 +19,14 @@ $strand #if str($report.report_select) == "bg": - #if $zero_regions.value: - $zero_regions + #if $report.zero_regions: + $report.zero_regions #else: -bg #end if - #if str($scale): - -scale $scale + #if str($report.scale): + -scale $report.scale #end if #else: #if str($report.max):
--- a/macros.xml Thu Jan 08 14:25:51 2015 -0500 +++ b/macros.xml Tue May 19 07:05:36 2015 -0400 @@ -4,7 +4,6 @@ <requirement type="package" version="2.22">bedtools</requirement> <yield/> </requirements> - <version_command>bedtools --version</version_command> </xml> <token name="@WRAPPER_VERSION@">2.22</token> <xml name="stdio"> @@ -16,6 +15,7 @@ <regex match="Error:" /> <regex match="Exception:" /> </stdio> + <version_command>bedtools --version</version_command> </xml> <xml name="reciprocal"> <param name="reciprocal" type="boolean" checked="false" truevalue="-r" falsevalue="" @@ -45,8 +45,8 @@ </conditional> </xml> <xml name="split"> - <param name="split" type="boolean" checked="false" truevalue="-split" falsevalue="" - label="Treat split/spliced BAM or BED12 entries as distinct BED intervals when computing coverage." + <param name="split" type="boolean" checked="false" truevalue="-split" falsevalue="" + label="Treat split/spliced BAM or BED12 entries as distinct BED intervals when computing coverage." help="If set, the coverage will be calculated based the spliced intervals only. For BAM files, this inspects the CIGAR N operation to infer the blocks for computing coverage. For BED12 files, this inspects the BlockCount, BlockStarts, and BlockEnds fields (i.e., columns 10,11,12). If this option is not set, coverage will be calculated based on the interval's START/END coordinates, and would include introns in the case of RNAseq data. (-split)" /> </xml> <xml name="genome"> @@ -81,14 +81,42 @@ <!-- ToDo column_picker --> <xml name="choose_columns"> <param name="cols" type="text" value="" - label="Specify the column(s) (comma separated) that should be summarized" - help="(-c)"> + label="Specify the column(s) that should be summarized" + help="comma separated (-c)"> <sanitizer invalid_char=""> <valid initial="string.digits"><add value=","/></valid> </sanitizer> </param> </xml> + <xml name="choose_column"> + <param name="col" type="data_column" data_ref="input" label="Specify the column(s) that should be summarized" help="(-c)" /> + </xml> + + <token name="@C_AND_O_ARGUMENT@"> + #set $col = list() + #set $op = list() + #for $item in $c_and_o_argument_repeat: + #silent $col.append( str($item.col) ) + #silent $op.append( str($item.operation) ) + #end for + #if $col: + -c #echo ','.join($col)# + -o #echo ','.join($op)# + #end if + </token> + + <xml name="c_and_o_argument"> + <repeat name="c_and_o_argument_repeat" title="Applying operations to columns from merged intervals" min="0"> + <expand macro="choose_column" /> + <expand macro="choose_operations"> + <expand macro="math_options" /> + <expand macro="additional_math_options" /> + </expand> + </repeat> + </xml> + + <xml name="choose_operations"> <param name="operation" type="select" label="Specify the operation"> <yield />
--- a/mapBed.xml Thu Jan 08 14:25:51 2015 -0500 +++ b/mapBed.xml Tue May 19 07:05:36 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="bedtools_map" name="MapBed" version="@WRAPPER_VERSION@.0"> +<tool id="bedtools_map" name="MapBed" version="@WRAPPER_VERSION@.1"> <description></description> <macros> <import>macros.xml</import> @@ -11,8 +11,7 @@ -a "${inputA}" -b "${inputB}" $strand - -o $operation - -c "${cols}" + @C_AND_O_ARGUMENT@ -f $overlap $reciprocal $split @@ -26,16 +25,12 @@ <inputs> <param format="bam,bed,vcf,gff,gff3" name="inputA" type="data" label="File A (BAM/BED/VCF/GFF)" /> <param format="bam,bed,gff,vcf,gff3" name="inputB" type="data" label="File B (BAM/BED/VCF/GFF)" /> - <expand macro="choose_columns" /> <expand macro="overlap" /> <param name="reciprocal" type="boolean" checked="false" truevalue="-r" falsevalue="" label="Require reciprocal overlap" help="If set, the overlap between the BAM alignment and the BED interval must affect the above fraction of both the alignment and the BED interval. (-r)" /> <expand macro="strand2" /> - <expand macro="choose_operations"> - <expand macro="math_options" /> - <expand macro="additional_math_options" /> - </expand> + <expand macro="c_and_o_argument" /> <expand macro="split" /> <expand macro="print_header" /> <conditional name="genome"> @@ -53,30 +48,38 @@ <test> <param name="inputA" value="mapBed1.bed" ftype="bed" /> <param name="inputB" value="mapBed2.bed" ftype="bed" /> - <param name="cols" value="5" /> - <param name="operation" value="mean" /> + <repeat name="c_and_o_argument_repeat"> + <param name="cols" value="5" /> + <param name="operation" value="mean" /> + </repeat> <output name="output" file="mapBed_result1.bed" ftype="bed" /> </test> <test> <param name="inputA" value="mapBed1.bed" ftype="bed" /> <param name="inputB" value="mapBed2.bed" ftype="bed" /> - <param name="cols" value="5" /> - <param name="operation" value="collapse" /> + <repeat name="c_and_o_argument_repeat"> + <param name="col" value="5" /> + <param name="operation" value="collapse" /> + </repeat> <output name="output" file="mapBed_result2.bed" ftype="bed" /> </test> <test> <param name="inputA" value="mapBed1.bed" ftype="bed" /> <param name="inputB" value="mapBed2.bed" ftype="bed" /> - <param name="cols" value="5" /> - <param name="operation" value="collapse" /> + <repeat name="c_and_o_argument_repeat"> + <param name="cols" value="5" /> + <param name="operation" value="collapse" /> + </repeat> <param name="strand" value="-S" /> <output name="output" file="mapBed_result3.bed" ftype="bed" /> </test> <test> <param name="inputA" value="mapBed1.bed" ftype="bed" /> <param name="inputB" value="mapBed2.bed" ftype="bed" /> - <param name="cols" value="5" /> - <param name="operation" value="collapse" /> + <repeat name="c_and_o_argument_repeat"> + <param name="cols" value="5" /> + <param name="operation" value="collapse" /> + </repeat> <param name="strand" value="-s" /> <output name="output" file="mapBed_result4.bed" ftype="bed" /> </test>
--- a/mergeBed.xml Thu Jan 08 14:25:51 2015 -0500 +++ b/mergeBed.xml Tue May 19 07:05:36 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="bedtools_mergebed" name="Merge BED files" version="@WRAPPER_VERSION@.0"> +<tool id="bedtools_mergebed" name="Merge BED files" version="@WRAPPER_VERSION@.1"> <description>(mergeBed)</description> <macros> <import>macros.xml</import> @@ -12,6 +12,7 @@ $strand -d $distance $header + @C_AND_O_ARGUMENT@ > "${output}" ]]> </command> @@ -27,11 +28,7 @@ label="Maximum distance between features allowed for features to be merged" help="That is, overlapping and/or book-ended features are merged. (-d)"/> <expand macro="print_header" /> - <expand macro="choose_columns" /> - <expand macro="choose_operations"> - <expand macro="math_options" /> - <expand macro="additional_math_options" /> - </expand> + <expand macro="c_and_o_argument" /> </inputs> <outputs> <data format="bed" name="output" metadata_source="input" label="Merged ${input.name}"/> @@ -56,6 +53,15 @@ <param name="distance" value="1000" /> <output name="output" file="mergedBed_result4.bed" ftype="bed" /> </test> + <test> + <param name="input" value="mergedBed4.bed" ftype="bed" /> + <param name="distance" value="1000" /> + <repeat name="c_and_o_argument_repeat"> + <param name="col" value="1"/> + <param name="operation" value="count"/> + </repeat> + <output name="output" file="mergedBed_result5.bed" ftype="bed" /> + </test> </tests> <help> <![CDATA[ @@ -92,7 +98,7 @@ ========================================================================== -*-s* Enforcing "strandedness" +*-s* Enforcing "strandedness" ========================================================================== The ``-s`` option will only merge intervals that are overlapping/bookended *and* are on the same strand. @@ -112,26 +118,6 @@ ========================================================================== -*-n* Reporting the number of features that were merged -========================================================================== -The -n option will report the number of features that were combined from the -original file in order to make the newly merged feature. If a feature in the -original file was not merged with any other features, a "1" is reported. - -:: - - $ cat A.bed - chr1 100 200 - chr1 180 250 - chr1 250 500 - chr1 501 1000 - - $ bedtools merge -i A.bed -n - chr1 100 500 3 - chr1 501 1000 1 - - -========================================================================== *-d* Controlling how close two features must be in order to merge ========================================================================== By default, only overlapping or book-ended features are combined into a new @@ -154,48 +140,6 @@ chr1 100 200 1000 -============================================================= -*-nms* Reporting the names of the features that were merged -============================================================= -Occasionally, one might like to know that names of the features that were -merged into a new feature. The ``-nms`` option will add an extra column to the -``merge`` output which lists (separated by semicolons) the names of the -merged features. - -:: - - $ cat A.bed - chr1 100 200 A1 - chr1 150 300 A2 - chr1 250 500 A3 - - $ bedtools merge -i A.bed -nms - chr1 100 500 A1,A2,A3 - - -=============================================================== -*-scores* Reporting the scores of the features that were merged -=============================================================== -Similarly, we might like to know that scores of the features that were -merged into a new feature. Enter the ``-scores`` option. One can specify -how the scores from each overlapping interval should be reported. - -:: - - $ cat A.bed - chr1 100 200 A1 1 - chr1 150 300 A2 2 - chr1 250 500 A3 3 - - $ bedtools merge -i A.bed -scores mean - chr1 100 500 2 - - $ bedtools merge -i A.bed -scores max - chr1 100 500 3 - - $ bedtools merge -i A.bed -scores collapse - chr1 100 500 1,2,3 - @REFERENCES@ ]]> </help>
--- a/randomBed.xml Thu Jan 08 14:25:51 2015 -0500 +++ b/randomBed.xml Tue May 19 07:05:36 2015 -0400 @@ -11,7 +11,7 @@ -g $genome -l $length -n $intervals - #if $seed.seed_choose: + #if str($seed.seed_choose) == "True": -seed $seed.seed #end if > "$output" @@ -29,11 +29,15 @@ <tests> <test> <param name="genome" value="mm9_chr1.len" /> - <param name="seed_choose" value="True" /> - <param name="seed" value="1" /> + <param name="seed_choose" value="False" /> <param name="length" value="5" /> <param name="intervals" value="3" /> - <output name="output" file="randomBed_result1.bed" ftype="bed" /> + <output name="output"> + <assert_contents> + <has_text_matching expression="chr1" /> + <has_n_columns n="6" /> + </assert_contents> + </output> </test> </tests> <help>