Mercurial > repos > lparsons > fastx_barcode_splitter_enhanced
diff fastx_barcode_splitter.xml @ 0:84bbf4fd24c3 draft
Initial toolshed version with support for separate index reads and automatic loading of results into Galaxy history.
author | lparsons |
---|---|
date | Fri, 08 Nov 2013 09:53:39 -0500 |
parents | |
children | b7b3d008e2d3 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fastx_barcode_splitter.xml Fri Nov 08 09:53:39 2013 -0500 @@ -0,0 +1,92 @@ +<tool id="cshl_princeton_fastx_barcode_splitter" version="1.1" name="Barcode Splitter" force_history_refresh="True"> + <description></description> + <command interpreter="bash"> + fastx_barcode_splitter_galaxy_wrapper.sh $BARCODE $input "primary_$output.id" "$__new_file_path__" $input.extension --mismatches $mismatches --partial $partial + #if $refBarcodeLocation.barcodeLocation == "idxfile": + --idxfile $refBarcodeLocation.idxfile + #else: + $refBarcodeLocation.EOL + #end if + > $output + </command> + + <inputs> + <param format="txt" version="1.1" name="BARCODE" type="data" label="Barcodes to use" /> + <param format="fasta,fastqsanger,fastqsolexa,fastqillumina" version="1.1" name="input" type="data" label="Library to split" /> + + <conditional name="refBarcodeLocation"> + <param version="1.1" name="barcodeLocation" type="select" label="Barcodes found at"> + <option value="bol">Start of sequence (5' end)</option> + <option value="eol">End of sequence (3' end)</option> + <option value="idxfile">Separate index file</option> + </param> + <when value="bol"> + <param version="1.1" name="EOL" type="hidden" value="--bol" /> + </when> + <when value="eol"> + <param version="1.1" name="EOL" type="hidden" value="--eol" /> + </when> + <when value="idxfile"> + <param version="1.1" name="idxfile" type="data" format="fasta,fastq,fastqsanger" label="Select index read file" /> + </when> + </conditional> + + <param version="1.1" name="mismatches" type="integer" size="3" value="0" label="Number of allowed mismatches" /> + + <param version="1.1" name="partial" type="integer" size="3" value="0" label="Number of allowed barcodes nucleotide deletions" /> + + </inputs> + + <tests> + <test> + <!-- Split a FASTQ file --> + <param version="1.1" name="BARCODE" value="fastx_barcode_splitter1.txt" /> + <param version="1.1" name="input" value="fastx_barcode_splitter1.fastq" ftype="fastqsolexa" /> + <param version="1.1" name="EOL" value="Start of sequence (5' end)" /> + <param version="1.1" name="mismatches" value="2" /> + <param version="1.1" name="partial" value="0" /> + <output version="1.1" name="output" file="fastx_barcode_splitter1.out" /> + </test> + </tests> + + <outputs> + <data version="1.1" format="html" name="output" /> + </outputs> +<help> + +**What it does** + +This tool splits a FASTQ or FASTA file into several files, using barcodes as the split criteria. + +-------- + +**Barcode file Format** + +Barcode files are simple text files. +Each line should contain an identifier (descriptive name for the barcode), and the barcode itself (A/C/G/T), separated by a TAB character. +Example:: + + #This line is a comment (starts with a 'number' sign) + BC1 GATCT + BC2 ATCGT + BC3 GTGAT + BC4 TGTCT + +For each barcode, a new FASTQ file will be created (with the barcode's identifier as part of the file name). +Sequences matching the barcode will be stored in the appropriate file. + +One additional FASTQ file will be created (the 'unmatched' file), where sequences not matching any barcode will be stored. + +The output of this tool is an HTML file, displaying the split counts and the file names. +In addition, each fastq file produced will be loaded into the galaxy history automatically. + + +------ + +This tool is based on `FASTX-toolkit`__ by Assaf Gordon. + + .. __: http://hannonlab.cshl.edu/fastx_toolkit/ + +</help> +<!-- FASTX-barcode-splitter is part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) --> +</tool>