Mercurial > repos > idot > fastx_toolkit2
diff fastx_barcode_splitter.xml @ 0:78a7d28f2a15 draft
Uploaded
author | idot |
---|---|
date | Wed, 10 Jul 2013 06:13:48 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fastx_barcode_splitter.xml Wed Jul 10 06:13:48 2013 -0400 @@ -0,0 +1,75 @@ +<tool id="cshl_fastx_barcode_splitter" name="Barcode Splitter"> + <description></description> + <command interpreter="sh">fastx_barcode_splitter_galaxy_wrapper.sh $BARCODE $input "$input.name" "$output.files_path" --mismatches $mismatches --partial $partial $EOL > $output </command> + + <inputs> + <param format="txt" name="BARCODE" type="data" label="Barcodes to use" /> + <param format="fasta,fastq,fastqsanger" name="input" type="data" label="Library to split" /> + + <param name="EOL" type="select" label="Barcodes found at"> + <option value="--bol">Start of sequence (5' end)</option> + <option value="--eol">End of sequence (3' end)</option> + </param> + + <param name="mismatches" type="integer" size="3" value="2" label="Number of allowed mismatches" /> + + <param name="partial" type="integer" size="3" value="0" label="Number of allowed barcodes nucleotide deletions" /> + + </inputs> + + <tests> + <test> + <!-- Split a FASTQ file --> + <param name="BARCODE" value="fastx_barcode_splitter1.txt" /> + <param name="input" value="fastx_barcode_splitter1.fastq" /> + <param name="EOL" value="Start of sequence (5' end)" /> + <param name="mismatches" value="2" /> + <param name="partial" value="0" /> + <output name="output" file="fastx_barcode_splitter1.out" /> + </test> + </tests> + + <outputs> + <data 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 locations. + +**Output Example** + +.. image:: ./static/fastx_icons/barcode_splitter_output_example.png + +------ + +This tool is based on `FASTX-toolkit`__ by Assaf Gordon. + + .. __: http://hannonlab.cshl.edu/fastx_toolkit/ + +</help> +</tool> +<!-- FASTX-barcode-splitter is part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) -->