Mercurial > repos > devteam > samtools_flagstat

changeset 2:0072bf593791 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Tue, 21 Apr 2015 15:56:53 -0400
parents a3dd61e7bec1
children cc61ade70eb8
files macros.xml samtools_flagstat.xml test-data/3unsorted.bam test-data/samtools_flagstat_input1.bam test-data/samtools_flagstat_out1.txt tool_dependencies.xml
diffstat 6 files changed, 106 insertions(+), 26 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Tue Apr 21 15:56:53 2015 -0400
@@ -0,0 +1,70 @@
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="1.2">samtools</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="bibtex">
+                @misc{SAM_def,
+                title={Definition of SAM/BAM format},
+                url = {https://samtools.github.io/hts-specs/SAMv1.pdf},}
+            </citation>
+            <citation type="doi">10.1093/bioinformatics/btp352</citation>
+            <citation type="doi">10.1093/bioinformatics/btr076</citation>
+            <citation type="doi">10.1093/bioinformatics/btr509</citation>
+            <citation type="bibtex">
+                @misc{Danecek_et_al,
+                Author={Danecek, P., Schiffels, S., Durbin, R.},
+                title={Multiallelic calling model in bcftools (-m)},
+                url = {http://samtools.github.io/bcftools/call-m.pdf},}
+            </citation>
+            <citation type="bibtex">
+                @misc{Durbin_VCQC,
+                Author={Durbin, R.},
+                title={Segregation based metric for variant call QC},
+                url = {http://samtools.github.io/bcftools/rd-SegBias.pdf},}
+            </citation>
+            <citation type="bibtex">
+                @misc{Li_SamMath,
+                Author={Li, H.},
+                title={Mathematical Notes on SAMtools Algorithms},
+                url = {http://www.broadinstitute.org/gatk/media/docs/Samtools.pdf},}
+            </citation>
+            <citation type="bibtex">
+                @misc{SamTools_github,
+                title={SAMTools GitHub page},
+                url = {https://github.com/samtools/samtools},}
+            </citation>
+        </citations>
+    </xml>
+    <xml name="version_command">
+        <version_command>samtools --version | head -n 1 | awk '{ print $2 }'</version_command>
+    </xml>
+    <xml name="stdio">
+        <stdio>
+            <exit_code range="1:" level="fatal" description="Error" />
+        </stdio>
+    </xml>
+    <token name="@no-chrom-options@">
+-----
+
+.. class:: warningmark
+
+**No options available? How to re-detect metadata**
+
+If you see a &quot;No options available&quot; within the &quot;**Select references (chromosomes and contigs) you would like to restrict bam to**&quot; drop down, you need to re-detect metadata for the dataset you are trying to process. To do this follow these steps:
+
+1. Click on the **pencil** icon adjacent to the dataset in the history
+2. A new menu will appear in the center pane of the interface
+3. Click **Datatype** tab
+4. Set **New Type** to **BAM**
+5. Click **Save**
+
+The medatada will be re-detected and you will be able to see the list of reference sequences in the &quot;**Select references (chromosomes and contigs) you would like to restrict bam to**&quot; drop-down.
+
+    </token>
+
+</macros>
--- a/samtools_flagstat.xml	Thu Mar 27 15:23:45 2014 -0400
+++ b/samtools_flagstat.xml	Tue Apr 21 15:56:53 2015 -0400
@@ -1,8 +1,11 @@
-<tool id="samtools_flagstat" name="flagstat" version="1.0.1">
-  <requirements>
-    <requirement type="package" version="0.1.19">samtools</requirement>
-  </requirements>
-  <description>provides simple stats on BAM files</description>
+<tool id="samtools_flagstat" name="Flagstat" version="2.0">
+  <description>tabulate descriptive stats for BAM datset</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
+  <expand macro="requirements"></expand>
+  <expand macro="stdio"></expand>
+  <expand macro="version_command"></expand>
   <command>samtools flagstat "$input1" > "$output1"
   </command>
   <inputs>
@@ -13,7 +16,7 @@
   </outputs>
   <tests>
     <test>
-      <param name="input1" value="3unsorted.bam" ftype="bam" />
+      <param name="input1" value="samtools_flagstat_input1.bam" ftype="bam" />
       <output name="output1" file="samtools_flagstat_out1.txt" />
     </test>
   </tests>
@@ -21,17 +24,22 @@
 
 **What it does**
 
-This tool uses the SAMTools_ toolkit to produce simple stats on a BAM file.
-
-.. _SAMTools: http://samtools.sourceforge.net/samtools.shtml
-
-------
+Uses ``samtools flagstat`` command to print descriptive information for a BAM dataset. Here is an example of such information::
 
-**Citation**
-
-For the underlying tool, please cite `Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R; 1000 Genome Project Data Processing Subgroup. The Sequence Alignment/Map format and SAMtools. Bioinformatics. 2009 Aug 15;25(16):2078-9. &lt;http://www.ncbi.nlm.nih.gov/pubmed/19505943&gt;`_
-
-If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
-
+  200 + 0 in total (QC-passed reads + QC-failed reads)  
+  0 + 0 secondary
+  0 + 0 supplementary
+  0 + 0 duplicates
+  25 + 0 mapped (12.50%:nan%)
+  200 + 0 paired in sequencing
+  100 + 0 read1
+  100 + 0 read2
+  0 + 0 properly paired (0.00%:nan%)
+  0 + 0 with itself and mate mapped
+  25 + 0 singletons (12.50%:nan%)
+  0 + 0 with mate mapped to a different chr
+  0 + 0 with mate mapped to a different chr (mapQ>=5)
+  
   </help>
+  <expand macro="citations"></expand>
 </tool>
Binary file test-data/3unsorted.bam has changed
Binary file test-data/samtools_flagstat_input1.bam has changed
--- a/test-data/samtools_flagstat_out1.txt	Thu Mar 27 15:23:45 2014 -0400
+++ b/test-data/samtools_flagstat_out1.txt	Tue Apr 21 15:56:53 2015 -0400
@@ -1,11 +1,13 @@
-10 + 0 in total (QC-passed reads + QC-failed reads)
+200 + 0 in total (QC-passed reads + QC-failed reads)
+0 + 0 secondary
+0 + 0 supplementary
 0 + 0 duplicates
-10 + 0 mapped (100.00%:nan%)
-0 + 0 paired in sequencing
-0 + 0 read1
-0 + 0 read2
-0 + 0 properly paired (nan%:nan%)
+25 + 0 mapped (12.50%:nan%)
+200 + 0 paired in sequencing
+100 + 0 read1
+100 + 0 read2
+0 + 0 properly paired (0.00%:nan%)
 0 + 0 with itself and mate mapped
-0 + 0 singletons (nan%:nan%)
+25 + 0 singletons (12.50%:nan%)
 0 + 0 with mate mapped to a different chr
 0 + 0 with mate mapped to a different chr (mapQ>=5)
--- a/tool_dependencies.xml	Thu Mar 27 15:23:45 2014 -0400
+++ b/tool_dependencies.xml	Tue Apr 21 15:56:53 2015 -0400
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <tool_dependency>
-    <package name="samtools" version="0.1.19">
-        <repository changeset_revision="1ef76f8d8e52" name="package_samtools_0_1_19" owner="devteam" toolshed="http://toolshed.g2.bx.psu.edu" />
+    <package name="samtools" version="1.2">
+        <repository changeset_revision="6eea04363026" name="package_samtools_1_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
     </package>
 </tool_dependency>