diff tools/annotation_profiler/annotation_profiler.xml @ 0:9071e359b9a3

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/annotation_profiler/annotation_profiler.xml	Fri Mar 09 19:37:19 2012 -0500
@@ -0,0 +1,136 @@
+<tool id="Annotation_Profiler_0" name="Profile Annotations" version="1.0.0">
+  <description>for a set of genomic intervals</description>
+  <command interpreter="python">annotation_profiler_for_interval.py -i $input1 -c ${input1.metadata.chromCol} -s ${input1.metadata.startCol} -e ${input1.metadata.endCol} -o $out_file1 $keep_empty -p ${GALAXY_DATA_INDEX_DIR}/annotation_profiler/$dbkey $summary -b 3 -t $table_names</command>
+  <inputs>
+    <param format="interval" name="input1" type="data" label="Choose Intervals">
+      <validator type="dataset_metadata_in_file" filename="annotation_profiler_valid_builds.txt" metadata_name="dbkey" metadata_column="0" message="Profiling is not currently available for this species."/>
+    </param>
+    <param name="keep_empty" type="select" label="Keep Region/Table Pairs with 0 Coverage">
+      <option value="-k">Keep</option>
+      <option value="" selected="true">Discard</option>
+    </param>
+    <param name="summary" type="select" label="Output per Region/Summary">
+      <option value="-S">Summary</option>
+      <option value="" selected="true">Per Region</option>
+    </param>
+    <param name="table_names" type="drill_down" display="checkbox" hierarchy="recurse" multiple="true" label="Choose Tables to Use" help="Selecting no tables will result in using all tables." from_file="annotation_profiler_options.xml"/>
+   </inputs>
+   <outputs>
+     <data format="input" name="out_file1">
+       <change_format>
+         <when input="summary" value="-S" format="tabular" />
+       </change_format>
+     </data>
+   </outputs>
+   <tests>
+     <test>
+       <param name="input1" value="4.bed" dbkey="hg18"/>
+       <param name="keep_empty" value=""/>
+       <param name="summary" value=""/>
+       <param name="table_names" value="acembly,affyGnf1h,knownAlt,knownGene,mrna,multiz17way,multiz28way,refGene,snp126"/>
+       <output name="out_file1" file="annotation_profiler_1.out" />
+     </test>
+     <test>
+       <param name="input1" value="3.bed" dbkey="hg18"/>
+       <param name="keep_empty" value=""/>
+       <param name="summary" value="Summary"/>
+       <param name="table_names" value="acembly,affyGnf1h,knownAlt,knownGene,mrna,multiz17way,multiz28way,refGene,snp126"/>
+       <output name="out_file1" file="annotation_profiler_2.out" />
+     </test>
+   </tests>
+   <help>
+**What it does**
+
+Takes an input set of intervals and for each interval determines the base coverage of the interval by a set of features (tables) available from UCSC. Genomic regions from the input feature data have been merged by overlap / direct adjacency (e.g. a table having ranges of: 1-10, 6-12, 12-20 and 25-28 results in two merged ranges of: 1-20 and 25-28).
+
+By default, this tool will check the coverage of your intervals against all available features; you may, however, choose to select only those tables that you want to include. Selecting a section heading will effectively cause all of its children to be selected.
+
+You may alternatively choose to receive a summary across all of the intervals that you provide.
+
+-----
+
+**Example**
+
+Using the interval below and selecting several tables::
+
+ chr1 4558 14764 uc001aab.1 0 -
+
+results in::
+
+ chr1 4558 14764 uc001aab.1 0 - snp126Exceptions 151 142
+ chr1 4558 14764 uc001aab.1 0 - genomicSuperDups 10206 1
+ chr1 4558 14764 uc001aab.1 0 - chainOryLat1 3718 1
+ chr1 4558 14764 uc001aab.1 0 - multiz28way 10206 1
+ chr1 4558 14764 uc001aab.1 0 - affyHuEx1 3553 32
+ chr1 4558 14764 uc001aab.1 0 - netXenTro2 3050 1
+ chr1 4558 14764 uc001aab.1 0 - intronEst 10206 1
+ chr1 4558 14764 uc001aab.1 0 - xenoMrna 10203 1
+ chr1 4558 14764 uc001aab.1 0 - ctgPos 10206 1
+ chr1 4558 14764 uc001aab.1 0 - clonePos 10206 1
+ chr1 4558 14764 uc001aab.1 0 - chainStrPur2Link 1323 29
+ chr1 4558 14764 uc001aab.1 0 - affyTxnPhase3HeLaNuclear 9011 8
+ chr1 4558 14764 uc001aab.1 0 - snp126orthoPanTro2RheMac2 61 58
+ chr1 4558 14764 uc001aab.1 0 - snp126 205 192
+ chr1 4558 14764 uc001aab.1 0 - chainEquCab1 10206 1
+ chr1 4558 14764 uc001aab.1 0 - netGalGal3 3686 1
+ chr1 4558 14764 uc001aab.1 0 - phastCons28wayPlacMammal 10172 3
+
+Where::
+
+ The first added column is the table name.
+ The second added column is the number of bases covered by the table.
+ The third added column is the number of regions from the table that is covered by the interval.
+
+Alternatively, requesting a summary, using the intervals below and selecting several tables::
+
+ chr1 4558 14764 uc001aab.1 0 -
+ chr1 4558 19346 uc001aac.1 0 -
+
+results in::
+
+ #tableName tableSize tableRegionCount allIntervalCount allIntervalSize allCoverage allTableRegionsOverlaped allIntervalsOverlapingTable nrIntervalCount nrIntervalSize nrCoverage nrTableRegionsOverlaped nrIntervalsOverlapingTable
+ snp126Exceptions 133601 92469 2 24994 388 359 2 1 14788 237 217 1
+ genomicSuperDups 12268847 657 2 24994 24994 2 2 1 14788 14788 1 1
+ chainOryLat1 70337730 2542 2 24994 7436 2 2 1 14788 3718 1 1
+ affyHuEx1 15703901 112274 2 24994 7846 70 2 1 14788 4293 38 1
+ netXenTro2 111440392 1877 2 24994 6100 2 2 1 14788 3050 1 1
+ snp126orthoPanTro2RheMac2 700436 690674 2 24994 124 118 2 1 14788 63 60 1
+ intronEst 135796064 2332 2 24994 24994 2 2 1 14788 14788 1 1
+ xenoMrna 129031327 1586 2 24994 20406 2 2 1 14788 10203 1 1
+ snp126 956976 838091 2 24994 498 461 2 1 14788 293 269 1
+ clonePos 224999719 39 2 24994 24994 2 2 1 14788 14788 1 1
+ chainStrPur2Link 7948016 119841 2 24994 2646 58 2 1 14788 1323 29 1
+ affyTxnPhase3HeLaNuclear 136797870 140244 2 24994 22601 17 2 1 14788 13590 9 1
+ multiz28way 225928588 38 2 24994 24994 2 2 1 14788 14788 1 1
+ ctgPos 224999719 39 2 24994 24994 2 2 1 14788 14788 1 1
+ chainEquCab1 246306414 141 2 24994 24994 2 2 1 14788 14788 1 1
+ netGalGal3 203351973 461 2 24994 7372 2 2 1 14788 3686 1 1
+ phastCons28wayPlacMammal 221017670 22803 2 24994 24926 6 2 1 14788 14754 3 1
+
+Where::
+ 
+ tableName is the name of the table
+ tableChromosomeCoverage is the number of positions existing in the table for only the chromosomes that were referenced by the interval file
+ tableChromosomeCount is the number of regions existing in the table for only the chromosomes that were referenced by the interval file
+ tableRegionCoverage is the number of positions existing in the table between the minimal and maximal bounding regions that were referenced by the interval file
+ tableRegionCount is the number of regions existing in the table between the minimal and maximal bounding regions that were referenced by the interval file
+ 
+ allIntervalCount is the number of provided intervals
+ allIntervalSize is the sum of the lengths of the provided interval file
+ allCoverage is the sum of the coverage for each provided interval
+ allTableRegionsOverlapped is the sum of the number of regions of the table (non-unique) that were overlapped for each interval
+ allIntervalsOverlappingTable is the number of provided intervals which overlap the table
+ 
+ nrIntervalCount is the number of non-redundant intervals
+ nrIntervalSize is the sum of the lengths of non-redundant intervals
+ nrCoverage is the sum of the coverage of non-redundant intervals
+ nrTableRegionsOverlapped is the number of regions of the table (unique) that were overlapped by the non-redundant intervals
+ nrIntervalsOverlappingTable is the number of non-redundant intervals which overlap the table
+ 
+
+.. class:: infomark
+
+**TIP:** non-redundant (nr) refers to the set of intervals that remains after the intervals provided have been merged to resolve overlaps
+
+  </help>
+</tool>