Mercurial > repos > devteam > samtools_idxstats
changeset 0:87398ae795c7 draft
Uploaded
| author | devteam |
|---|---|
| date | Tue, 21 Apr 2015 16:00:31 -0400 |
| parents | |
| children | 88b8c2916784 |
| files | macros.xml samtools_idxstats.xml test-data/phiX.bam test-data/samtools_idxstats_out.tabular tool_dependencies.xml |
| diffstat | 5 files changed, 150 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Tue Apr 21 16:00:31 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 $2 }'</version_command> + </xml> + <xml name="stdio"> + <stdio> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> + </xml> + <token name="@no-chrom-options@"> +----- + +.. class:: warningmark + +**No options available? How to re-detect metadata** + +If you see a "No options available" within the "**Select references (chromosomes and contigs) you would like to restrict bam to**" drop down, you need to re-detect metadata for the dataset you are trying to process. To do this follow these steps: + +1. Click on the **pencil** icon adjacent to the dataset in the history +2. A new menu will appear in the center pane of the interface +3. Click **Datatype** tab +4. Set **New Type** to **BAM** +5. Click **Save** + +The medatada will be re-detected and you will be able to see the list of reference sequences in the "**Select references (chromosomes and contigs) you would like to restrict bam to**" drop-down. + + </token> + +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/samtools_idxstats.xml Tue Apr 21 16:00:31 2015 -0400 @@ -0,0 +1,72 @@ +<tool id="samtools_idxstats" name="IdxStats" version="2.0"> + <description>tabulate mapping statistics for BAM dataset</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"></expand> + <expand macro="stdio"></expand> + <expand macro="version_command"></expand> + <command><![CDATA[ +if [ ! -f "${input}.bai" ] ; then + ln -s "${input}" input.bam ; + samtools sort -o sorted.bam -O bam -T sts "${input}" ; + samtools index sorted.bam ; + samtools idxstats sorted.bam > "${output}" ; +else + samtools idxstats "${input}" > "${output}" ; +fi]]> + </command> + <inputs> + <param name="input" type="data" format="bam" label="BAM file" /> + </inputs> + <outputs> + <data format="tabular" name="output" label="${tool.name} on ${on_string}" /> + </outputs> + <tests> + <test> + <param name="input" value="phiX.bam" ftype="bam" /> + <output name="output" file="samtools_idxstats_out.tabular" compare="diff" ftype="tabular" /> + </test> + </tests> + <help> +<![CDATA[ +**What it does** + +Runs the ``samtools idxstats`` command. It retrieves and prints stats in the index file. + +Input is a sorted and indexed BAM file, the output is tabular with +four columns (one row per reference sequence plus a final line for +unmapped reads):: + + Column Description + ------ ----------------------------- + 1 Reference sequence identifier + 2 Reference sequence length + 3 Number of mapped reads + 4 Number of placed but unmapped reads + (typically unmapped partners of mapped reads) + +------ + +**Example** output from a *de novo* assembly:: + + contig_1 170035 98397 0 + contig_2 403835 199564 0 + contig_3 553102 288189 0 + ... ... ... ... + contig_603 653 50 0 + contig_604 214 6 0 + \* 0 0 50320 + + +In this example there were 604 contigs, each with one line in the output table, +plus the final row (labelled with an asterisk) representing 50320 unmapped reads. +In this BAM file, the final column was otherwise zero. + +------ + +Peter J.A. Cock (2013), `Galaxy wrapper <https://github.com/peterjc/pico_galaxy/tree/master/tools/samtools_idxstats>`_ for the samtools idxstats command +]]> + </help> + <expand macro="citations"></expand> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_idxstats_out.tabular Tue Apr 21 16:00:31 2015 -0400 @@ -0,0 +1,2 @@ +phiX174 5386 972 18 +* 0 0 10
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Tue Apr 21 16:00:31 2015 -0400 @@ -0,0 +1,6 @@ +<?xml version="1.0"?> +<tool_dependency> + <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>