Mercurial > repos > brenninc > samtools_flag_filter_1_2
changeset 0:97bb72be07f9 draft default tip
Uploaded first version
| author | brenninc |
|---|---|
| date | Tue, 10 May 2016 03:59:17 -0400 |
| parents | |
| children | |
| files | samtools_flag_filter.xml samtools_macros.xml tool_dependencies.xml |
| diffstat | 3 files changed, 182 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/samtools_flag_filter.xml Tue May 10 03:59:17 2016 -0400 @@ -0,0 +1,104 @@ +<tool id="samtools_flag_filter" name="Samtools flag_filter" version="0.1"> + <description>Use Samtools' view tool to filter alignments based on the flag field.</description> + <macros> + <import>samtools_macros.xml</import> + </macros> + <expand macro="requirements"></expand> + <expand macro="stdio"></expand> + <expand macro="version_command"></expand> + + <command> + <![CDATA[ + samtools sort -@ \${GALAXY_SLOTS:-1} -o temp_bam -O bam -T dataset "${input}" && + samtools view -@ \${GALAXY_SLOTS:-1} + #for $bit in $bits + -${bit.state} ${bit.flag} + #end for + -b -o "${output}" temp_bam + ]]> + </command> + <inputs> + <param name="input" format="bam,sam" label="BAM/SAM dataset to filter by flag" type="data" /> + <repeat name="bits" title="Flag"> + <param name="flag" type="select" label="Type"> + <option value="0x0001">Read is paired 0x0001</option> + <option value="0x0002">Read is mapped in a proper pair 0x0002</option> + <option value="0x0004">The read is unmapped 0x0004</option> + <option value="0x0008">The mate is unmapped 0x0008</option> + <option value="0x0010">Read strand 0x0010</option> + <option value="0x0020">Mate strand 0x0020</option> + <option value="0x0040">Read is the first in a pair 0x0040</option> + <option value="0x0080">Read is the second in a pair 0x0080</option> + <option value="0x0100">The alignment or this read is not primary 0x0100</option> + <option value="0x0200">The read fails platform/vendor quality checks 0x0200</option> + <option value="0x0400">The read is a PCR or optical duplicate 0x0400</option> + </param> + <param name="state" type="select" display="radio" label="Set the states for this flag"> + <option value="f">Keep only alignments with this flag set --f</option> + <option value="F">Remove all alignments with this flag set --F</option> + </param> + </repeat> + + </inputs> + <outputs> + <data format="bam" name="output" label="Filtered by flag from ${on_string}" /> + </outputs> + <tests> + <test> + <param ftype="bam" name="input" value="unfiltered.bam" /> + <param name="bits_0|flag" value="The read is unmapped 0x0004"/> + <param name="bits_0|state" value="f"/> + <output file="f0X0004.bam" ftype="bam" name="output" /> + </test> + <test> + <param ftype="bam" name="input" value="unfiltered.bam" /> + <param name="bits_0|flag" value="The read is unmapped 0x0004"/> + <param name="bits_0|state" value="f"/> + <param name="bits_1|flag" value="The mate is unmapped 0x0008"/> + <param name="bits_1|state" value="f"/> + <output file="f0X0004_plus8.bam" ftype="bam" name="output" /> + </test> + <test> + <param ftype="bam" name="input" value="unfiltered.bam" /> + <param name="bits_0|flag" value="The read is unmapped 0x0004"/> + <param name="bits_0|state" value="f"/> + <param name="bits_1|flag" value="The mate is unmapped 0x0008"/> + <param name="bits_1|state" value="F"/> + <output file="f0X0004_less8.bam" ftype="bam" name="output" /> + </test> + </tests> + <help> +<![CDATA[ +This tool uses Samtools view method and specifically the -f and -F parameters to filter a sam file to remove alignments based on their flag field. + +Alignments can be excluded based on either the presence or absence of that bit in their flag file. + +Multiple check can be carried out in the same pass. + +The flag values used are: + +0x0001: Read is paired + +0x0002: Read is mapped in a proper pair + +0x0004: The read is unmapped + +0x0008: The mate is unmapped + +0x0010: Read strand + +0x0020: Mate strand + +0x0040: Read is the first in a pair + +0x0080: Read is the second in a pair + +0x0100: The alignment or this read is not primary + +0x0200: The read fails platform/vendor quality checks + +0x0400: The read is a PCR or optical duplicate +]]> + </help> + <expand macro="citations"></expand> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/samtools_macros.xml Tue May 10 03:59:17 2016 -0400 @@ -0,0 +1,72 @@ +<?xml version="1.0"?> +<!-- Copied from https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/samtools/samtools_slice_bam --> +<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/tool_dependencies.xml Tue May 10 03:59:17 2016 -0400 @@ -0,0 +1,6 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="samtools" version="1.2"> + <repository changeset_revision="f6ae3ba3f3c1" name="package_samtools_1_2" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency>