Mercurial > repos > bgruening > bedtools_test_bag

changeset 9:893617de95e5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bernhardlutz
date Wed, 18 Jun 2014 14:33:11 -0400
parents d0df760f1d32
children e0214a6e8b81
files annotateBed.xml closestBed.xml getfastaBed.xml shuffleBed.xml slopBed.xml tagBed.xml test-data/0.bed test-data/0_result.bed test-data/1.bed test-data/1_result.bed test-data/2.bed test-data/2_result.bed test-data/3.bed test-data/3_result_1000.bed test-data/annotateBed1.bed test-data/annotateBed2.bed test-data/annotateBed3.bed test-data/annotateBed4.bed test-data/closestBedA.bed test-data/closestBedB.bed test-data/groupbyBed.bed test-data/groupbyinput.bed test-data/mapBedA.bed test-data/mapBedB.bed test-data/shuffleBedA.bed test-data/shuffleBedGenome.genome test-data/t
diffstat 27 files changed, 102 insertions(+), 56 deletions(-) [+]
line wrap: on
line diff
--- a/annotateBed.xml	Wed Jun 18 13:13:51 2014 -0400
+++ b/annotateBed.xml	Wed Jun 18 14:33:11 2014 -0400
@@ -13,7 +13,7 @@
             $bed.input
         #end for
 
-        #if names.names_select == 'yes':
+        #if $names.names_select == 'yes':
         -names
         #for $bed in $names.beds:
             $bed.inputName
--- a/closestBed.xml	Wed Jun 18 13:13:51 2014 -0400
+++ b/closestBed.xml	Wed Jun 18 14:33:11 2014 -0400
@@ -7,7 +7,6 @@
     <expand macro="stdio" />
     <command>
         closestBed
-        $split
         $strand
         $addition
         -t $ties
@@ -20,13 +19,13 @@
         <param format="bed,gff,vcf,gff3" name="inputB" type="data" label="overlap intervals in this BED/VCF/GFF file?"/>
 
         <param name="ties" type="select" label="How ties for closest feature should be handled" help="This occurs when two features in B have exactly the same overlap with a feature in A.">
-            <option value="all" selected="True">all- Report all ties (default)</option>
-            <option value="first">first- Report the first tie that occurred in the B file</option>
-            <option value="last">last- Report the last tie that occurred in the B file</option>
+            <option value="all" selected="True">all - Report all ties (default)</option>
+            <option value="first">first - Report the first tie that occurred in the B file</option>
+            <option value="last">last - Report the last tie that occurred in the B file</option>
         </param>
 
-        <param name="strand" type="boolean" checked="false" truevalue="-s" falsevalue="" label="Force strandedness." help="That is, find the closest feature in B overlaps A on the same strand. By default, this is disabled." />
-        <param name="addition" type="boolean" checked="false" truevalue="-d" falsevalue="" label="In addition to the closest feature in B, report its distance to A as an extra column. The reported distance for overlapping features will be 0." />
+        <param name="strand" type="boolean" checked="false" truevalue="-s" falsevalue="" label="Force strandedness" help="That is, find the closest feature in B overlaps A on the same strand. By default, this is disabled" />
+        <param name="addition" type="boolean" checked="false" truevalue="-d" falsevalue="" label="In addition to the closest feature in B, report its distance to A as an extra column. The reported distance for overlapping features will be 0" />
     </inputs>
     <outputs>
         <data format_source="inputA" name="output" metadata_source="inputA" label="Intersection of ${inputA.name} and ${inputB.name}"/>
--- a/getfastaBed.xml	Wed Jun 18 13:13:51 2014 -0400
+++ b/getfastaBed.xml	Wed Jun 18 14:33:11 2014 -0400
@@ -7,7 +7,6 @@
     <expand macro="stdio" />
     <command>
         bedtools getfasta
-        
         $name
         $tab
         $strand
@@ -17,22 +16,20 @@
         -fo $output
     </command>
     <inputs>
-        <param format="bed,vcf,gff,gff3" name="inputA" type="data" label="BED/VCF/GFF file"/>
-        <param format="fasta" name="fasta" type="data" label="Fasta file"/>
-
+        <param format="bed,vcf,gff,gff3" name="inputA" type="data" label="BED/VCF/GFF file" />
+        <param format="fasta" name="fasta" type="data" label="Fasta file" />
         <param name="name" type="boolean" checked="false" truevalue="-name" falsevalue="" label="Use the “name” column in the BED file for the FASTA headers in the output FASTA file" />
-        <param name="tab" type="boolean" checked="false" truevalue="-tab" falsevalue="" label="Report extract sequences in a tab-delimited format instead of in FASTA format." />
-<param name="strand" type="boolean" checked="false" truevalue="-s" falsevalue="" label="Force strandedness." help="If the feature occupies the antisense strand, the sequence will be reverse complemented." />
-<param name="split" type="boolean" checked="false" truevalue="-split" falsevalue="" label="Given BED12 input, extract and concatenate the sequences from the BED “blocks” (e.g., exons)" />
+        <param name="tab" type="boolean" checked="false" truevalue="-tab" falsevalue="" label="Report extract sequences in a tab-delimited format instead of in FASTA format" />
+        <param name="strand" type="boolean" checked="false" truevalue="-s" falsevalue="" label="Force strandedness" help="If the feature occupies the antisense strand, the sequence will be reverse complemented." />
+        <param name="split" type="boolean" checked="false" truevalue="-split" falsevalue="" label="Given BED12 input, extract and concatenate the sequences from the BED 'blocks' (e.g., exons)" />
     </inputs>
     <outputs>
         <data format="fasta" name="output" />
     </outputs>
     <help>
-
 **What it does**
 
-bedtools getfasta will extract the sequence defined by the coordinates in a BED interval and create a new FASTA entry in the output file for each extracted sequence. By default, the FASTA header for each extracted sequence will be formatted as follows: “<chrom>:<start>-<end>”.
+bedtools getfasta will extract the sequence defined by the coordinates in a BED interval and create a new FASTA entry in the output file for each extracted sequence. By default, the FASTA header for each extracted sequence will be formatted as follows: “&lt;chrom>:&lt;start>-&lt;end>”.
 
 .. image:: $PATH_TO_IMAGES/getfasta-glyph.png
 
--- a/shuffleBed.xml	Wed Jun 18 13:13:51 2014 -0400
+++ b/shuffleBed.xml	Wed Jun 18 14:33:11 2014 -0400
@@ -30,8 +30,7 @@
     </command>
     <inputs>
         <param format="bed,vcf,gff,gff3" name="inputA" type="data" label="BED/VCF/GFF file"/>
-         <param name="bedpe" type="boolean" label="The file is in BEDPE format" selected="False" truevalue="-bedpe" falsevalue="" />
-            </when>
+        <param name="bedpe" type="boolean" label="The file is in BEDPE format" selected="False" truevalue="-bedpe" falsevalue="" />
         <expand macro="genome" />
         <param name="chrom" type="boolean" label="Keep features in the input file on the same chromosome. Solely permute their location on the chromosome. By default, both the chromosome and position are randomly chosen" selected="False" truevalue="-chrom" falsevalue="" />
         <param name="intervals" type="integer" value="1000000" label="The number of intervals to generate." />
@@ -40,6 +39,7 @@
             <param name="choose" type="boolean" label="Choose a BED file of coordinates in which features from -i should not be placed?" selected="False" truevalue="True" falsevalue="False" />
             <when value="True">
                 <param name="excl" type="data" format="bed" label="Choose File" />
+            </when>
         </conditional>
         <conditional name="incl">
             <param name="choose" type="boolean" label="Choose a BED file of coordinates in which features from -i should be placed.?" selected="False" truevalue="True" falsevalue="False" />
--- a/slopBed.xml	Wed Jun 18 13:13:51 2014 -0400
+++ b/slopBed.xml	Wed Jun 18 14:33:11 2014 -0400
@@ -38,7 +38,7 @@
 
 **What it does**
 
-bedtools slop will increase the size of each feature in a feature file by a user-defined number of bases. While something like this could be done with an awk '{OFS="\t" print $1,$2-<slop>,$3+<slop>}', bedtools slop will restrict the resizing to the size of the chromosome (i.e. no start &lt; 0 and no end > chromosome size).
+bedtools slop will increase the size of each feature in a feature file by a user-defined number of bases. While something like this could be done with an awk '{OFS="\t" print $1,$2-&lt;slop>,$3+&lt;slop>}', bedtools slop will restrict the resizing to the size of the chromosome (i.e. no start &lt; 0 and no end > chromosome size).
 .. image:: $PATH_TO_IMAGES/slop-glyph.png
 
 .. class:: warningmark
--- a/tagBed.xml	Wed Jun 18 13:13:51 2014 -0400
+++ b/tagBed.xml	Wed Jun 18 14:33:11 2014 -0400
@@ -35,7 +35,6 @@
             <option value="-labels -intervals">Intervals</option>
         </param>
     </inputs>
-    </inputs>
 
     <outputs>
         <data format="bed" name="output" label="" />
--- a/test-data/0.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/0.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,4 +1,4 @@
-chr1  100  200
-chr1  180  250
-chr1  250  500
-chr1  501  1000
+chr1	100	200
+chr1	180	250
+chr1	250	500
+chr1	501	1000
--- a/test-data/0_result.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/0_result.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,2 +1,2 @@
-chr1  100  500
-chr1  501  1000
+chr1	100	500
+chr1	501	1000
--- a/test-data/1.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/1.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,4 +1,4 @@
-chr1  100  200   a1  1 +
-chr1  180  250   a2  2 +
-chr1  250  500   a3  3 -
-chr1  501  1000  a4  4 +
+chr1	100	200	a1	1	+
+chr1	180	250	a2	2	+
+chr1	250	500	a3	3	-
+chr1	501	1000	a4	4	+
--- a/test-data/1_result.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/1_result.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,3 +1,3 @@
-chr1  100  250    +
-chr1  501  1000   +
-chr1  250  500    -
+chr1	100	250	+
+chr1	501	1000	+
+chr1	250	500	-
--- a/test-data/2.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/2.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,4 +1,4 @@
-chr1  100  200
-chr1  180  250
-chr1  250  500
-chr1  501  1000
+chr1	100	200
+chr1	180	250
+chr1	250	500
+chr1	501	1000
--- a/test-data/2_result.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/2_result.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,2 +1,2 @@
-chr1  100  500  3
-chr1  501  1000 1
+chr1	100	500	3
+chr1	501	1000	1
--- a/test-data/3.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/3.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,2 +1,2 @@
-chr1  100  200
-chr1  501  1000
+chr1	100	200
+chr1	501	1000
--- a/test-data/3_result_1000.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/3_result_1000.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,1 +1,1 @@
-chr1  100  200  1000
+chr1	100	200	1000
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/annotateBed1.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,4 @@
+chr1	100	200	nasty	1	-
+chr2	500	1000	ugly	2	+
+chr3	1000	5000	big	3	-
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/annotateBed2.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,3 @@
+chr1	150	200	geneA	1	+
+chr1	175	250	geneB	2	+
+chr3	0	10000	geneC	3	-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/annotateBed3.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,3 @@
+chr1	0	10000	cons1	1	+
+chr2	700	10000	cons2	2	-
+chr3	4000	10000	cons3	3	+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/annotateBed4.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,4 @@
+chr1	0	120	known1	-
+chr1	150	160	known2	-
+chr2	0	10000	known3	+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/closestBedA.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,1 @@
+chr1	100	200
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/closestBedB.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,2 @@
+chr1	500	1000
+chr1	1300	2000
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/groupbyBed.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,14 @@
+chr21	9719758	9729320	variant1	chr21	9719768	9721892	ALR/Alpha	1004	+
+chr21	9719758	9729320	variant1	chr21	9721905	9725582	ALR/Alpha	1010	+
+chr21	9719758	9729320	variant1	chr21	9725582	9725977	L1PA3	3288	+
+chr21	9719758	9729320	variant1	chr21	9726021	9729309	ALR/Alpha	1051	+
+chr21	9729310	9757478	variant2	chr21	9729320	9729809	L1PA3	3897	-
+chr21	9729310	9757478	variant2	chr21	9729809	9730866	L1P1	8367	+
+chr21	9729310	9757478	variant2	chr21	9730866	9734026	ALR/Alpha	1036	-
+chr21	9729310	9757478	variant2	chr21	9734037	9757471	ALR/Alpha	1182	-
+chr21	9795588	9796685	variant3	chr21	9795589	9795713	(GAATG)n	308	+
+chr21	9795588	9796685	variant3	chr21	9795736	9795894	(GAATG)n	683	+
+chr21	9795588	9796685	variant3	chr21	9795911	9796007	(GAATG)n	345	+
+chr21	9795588	9796685	variant3	chr21	9796028	9796187	(GAATG)n	756	+
+chr21	9795588	9796685	variant3	chr21	9796202	9796615	(GAATG)n	891	+
+chr21	9795588	9796685	variant3	chr21	9796637	9796824	(GAATG)n	621	+
--- a/test-data/groupbyinput.bed	Wed Jun 18 13:13:51 2014 -0400
+++ b/test-data/groupbyinput.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -1,14 +1,14 @@
-chr21  9719758 9729320 variant1   chr21  9719768 9721892 ALR/Alpha   1004  +
-chr21  9719758 9729320 variant1   chr21  9721905 9725582 ALR/Alpha   1010  +
-chr21  9719758 9729320 variant1   chr21  9725582 9725977 L1PA3       3288  +
-chr21  9719758 9729320 variant1   chr21  9726021 9729309 ALR/Alpha   1051  +
-chr21  9729310 9757478 variant2   chr21  9729320 9729809 L1PA3       3897  -
-chr21  9729310 9757478 variant2   chr21  9729809 9730866 L1P1        8367  +
-chr21  9729310 9757478 variant2   chr21  9730866 9734026 ALR/Alpha   1036  -
-chr21  9729310 9757478 variant2   chr21  9734037 9757471 ALR/Alpha   1182  -
-chr21  9795588 9796685 variant3   chr21  9795589 9795713 (GAATG)n    308   +
-chr21  9795588 9796685 variant3   chr21  9795736 9795894 (GAATG)n    683   +
-chr21  9795588 9796685 variant3   chr21  9795911 9796007 (GAATG)n    345   +
-chr21  9795588 9796685 variant3   chr21  9796028 9796187 (GAATG)n    756   +
-chr21  9795588 9796685 variant3   chr21  9796202 9796615 (GAATG)n    891   +
-chr21  9795588 9796685 variant3   chr21  9796637 9796824 (GAATG)n    621   +
+chr21	9719758	9729320	variant1	chr21	9719768	9721892	ALR/Alpha	1004	+
+chr21	9719758	9729320	variant1	chr21	9721905	9725582	ALR/Alpha	1010	+
+chr21	9719758	9729320	variant1	chr21	9725582	9725977	L1PA3	3288	+
+chr21	9719758	9729320	variant1	chr21	9726021	9729309	ALR/Alpha	1051	+
+chr21	9729310	9757478	variant2	chr21	9729320	9729809	L1PA3	3897	-
+chr21	9729310	9757478	variant2	chr21	9729809	9730866	L1P1	8367	+
+chr21	9729310	9757478	variant2	chr21	9730866	9734026	ALR/Alpha	1036	-
+chr21	9729310	9757478	variant2	chr21	9734037	9757471	ALR/Alpha	1182	-
+chr21	9795588	9796685	variant3	chr21	9795589	9795713	(GAATG)n	308	+
+chr21	9795588	9796685	variant3	chr21	9795736	9795894	(GAATG)n	683	+
+chr21	9795588	9796685	variant3	chr21	9795911	9796007	(GAATG)n	345	+
+chr21	9795588	9796685	variant3	chr21	9796028	9796187	(GAATG)n	756	+
+chr21	9795588	9796685	variant3	chr21	9796202	9796615	(GAATG)n	891	+
+chr21	9795588	9796685	variant3	chr21	9796637	9796824	(GAATG)n	621	+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mapBedA.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,4 @@
+chr1	10	20	a1	1	+
+chr1	50	60	a2	2	-
+chr1	80	90	a3	3	-
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mapBedB.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,5 @@
+chr1	12	14	b1	2	+
+chr1	13	15	b2	5	-
+chr1	16	18	b3	5	+
+chr1	82	85	b4	2	-
+chr1	85	87	b5	3	+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/shuffleBedA.bed	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,2 @@
+chr1	0	100	a1	1	+
+chr1	0	1000	a2	2	-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/shuffleBedGenome.genome	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,5 @@
+chr1	10000
+chr2	8000
+chr3	5000
+chr4	2000
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/t	Wed Jun 18 14:33:11 2014 -0400
@@ -0,0 +1,4 @@
+chr1 100	200	nasty 1	-
+chr2 500	1000	ugly	2	+
+chr3 1000 5000	big	3	-
+