Mercurial > repos > brenninc > tagdust_2_31
diff macros.xml @ 0:40c86e14b674 draft
Uploaded first version of tagdust
author | brenninc |
---|---|
date | Mon, 09 May 2016 04:08:01 -0400 |
parents | |
children | da90c37031bb |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon May 09 04:08:01 2016 -0400 @@ -0,0 +1,179 @@ +<?xml version="1.0"?> +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="2.31">tagdust</requirement> + </requirements> + </xml> + <xml name="version_command"> + <version_command>tagdust --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="@cat-archiecture@"> + echo using architecture ; + cat $architecture.fields.path ; + echo ; + </token> + <token name="@tagdust-call-minus-files@"> + mkdir output ; + tagdust -t\${GALAXY_SLOTS:-4} -o output/data + -arch $architecture.fields.path + #if $reference_source.reference_source_selector=='history': + -ref $reference_source.ref_file + #end if + #if $reference_source.reference_source_selector=='cached': + -ref $reference_source.ref_path.fields.path + #end if + </token> + <token name="@ls_and_barcode@"> + echo files in output folder ; + ls -al output ; + #if $include.barcode_files=="yes" + #if $architecture.fields.barcode=="yes" + cd output ; + ls *_BC_* > $barcode_files + #else + echo Selected architecture not expected to generate any barcode files > $barcode_files ; + echo To avoid this output set Choose to find the barcode files to No >> $barcode_files ; + #end if + #else + #if $architecture.fields.barcode=="yes" + echo ; + echo Tagdust not included in output at users request! ; + echo To get then set Choose to find the barcode files to Yes and run the tool again ; + #end if + #end if + </token> + <xml name="architecture"> + <param name="architecture" type="select" label="Using architecture"> + <options from_data_table="tagdust_architecture"/> + <validator type="no_options" message="No architecture found"/> + <!--filter name="barcode" value="yes" column="3"/--> + </param> + </xml> + <xml name="reference_source"> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference fasta (If any)"> + <option value="none" selected="true">Do not include a reference fasta</option> + <option value="cached">Locally cached</option> + <option value="history">History</option> + </param> + <when value="none"/> + <when value="cached"> + <param name="ref_path" type="select" label="Using reference fasta"> + <options from_data_table="all_fasta"/> + <validator type="no_options" message="A built-in reference fasta is not available for the build associated with the selected input file"/> + </param> + </when> + <when value="history"> + <param name="ref_file" type="data" format="fasta" label="Using reference file" /> + </when> + </conditional> + </xml> + <xml name="include_barcode_file"> + <conditional name="include"> + <param name="barcode_files" type="select" label="Choose to find the barcode files (If any)"> + <option value="yes" selected="true">Yes. Look for possible barcode separated files.</option> + <option value="no" >No. Ignores all barcode files even if these are generated.</option> + </param> + <when value="yes"/> + <when value="no"/> + </conditional> + </xml> + <xml name="output_barcode"> + <data format="txt" name="barcode_files" label="Tagdust barcoded reads."> + <discover_datasets pattern="data_BC_(?P<designation>.+)\.fq" ext="fastq" directory="output" visible="true" /> + <filter>(include['barcode_files']=='yes')</filter> + </data> + </xml> + <token name="@tool-documentation@"> +<![CDATA[ + +Note: Output from Architecture with could have a Barcode HMM building block choose to find the barcode files. +....If no barcode files are found this will simply be empty. +....You may have refresh the history for all barcode files to show. + +Please contact the admin to add an architecture / HMM building blocks. +(There is Data Manager that they can use) + +]]> + </token> + <token name="@tagdust-documentation@"> +<![CDATA[ +==== + +Taken from The TagDust2 Manual http://tagdust.sourceforge.net (part of Version 2_31 download) + +Raw sequences produced by next generation sequencing (NGS) machines can contain adapter, linker, +barcode and fingerprint sequences. TagDust2 is a program to extract and correctly label the sequences +to be mapped in downstream pipelines. +TagDust allows users to specify the expected architecture of a read and converts it into a hidden +Markov model. The latter can assign sequences to a particular barcode (or index) even in the presence +of sequencing errors. Sequences not matching the architecture (primer dimers, contaminants etc.) are +automatically discarded + +TagDust requires an input file containing sequences and a user defined HMM architecture used to ex- +tract the reads. The architecture is composed of a selection of pre-defined building blocks representing +indices, barcodes, spacers and other sequences one might encounter in the raw output of a sequenced +sample. + +HMM Building Blocks + +TagDust comes with a set of pre-defined HMM building blocks. Each includes a silent state at the +beginning and end used to link blocks together. Each block is specified by a unique letter following +by a colon and some information about the sequence. + +Read +Segment modeling the read. +Code: R:N + +Optional +Segment modeling an optional single or short stretch of nucleotides. +Code: O:N + +G addition +Segment modeling the occasional addition of guanines to the reads. +(89.3% chance of a single G , 19.5% chance of 2 Gs..). +Code: G:G + +Barcode or Index +Segment modeling a set of barcode sequences. For each sequence a separate HMM is created. The +barcode sequences must be given as a comma separated list. A null model of the same length as the +barcode is automatically added and initialized to the background nucleotide frequencies. +Code: B:GTA,AAC + +Fingerprint or Unique Molecular Identifier - UMI +Segment modeling a fingerprint (or unique molecular identifiers). Insertions and deletions are by +default not allowed within a fingerprint segment. +Code: F:NNN + +Spacer +Segment modeling a pre-defined sequence. +Code: S:GTA + +Partial +This segment is used to model sequences that may only be partially present at the 5‘ or 3‘ end of +the read. The transition probabilities (orange and blue) are set automatically based on the length +distribution of exactly matching adapters. +Code: P:CCTTAA +]]> + </token> + <xml name="citations"> + <citations> + <citation type="bibtex"> + @misc{ + TagDust, + author = {Timo Lassmann}, + title = {TagDust on sourceforge}, + url = {http://tagdust.sourceforge.net/} + } + </citation> + <citation type="doi">10.1093/bioinformatics/btp527</citation> + <citation type="doi">10.1186/s12859-015-0454-y</citation> + </citations> + </xml> +</macros>