Mercurial > repos > peterjc > sample_seqs
diff tools/sample_seqs/sample_seqs.xml @ 0:3a807e5ea6c8 draft
Uploaded v0.0.1
author | peterjc |
---|---|
date | Thu, 27 Mar 2014 09:40:53 -0400 |
parents | |
children | da64f6a9e32b |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/sample_seqs/sample_seqs.xml Thu Mar 27 09:40:53 2014 -0400 @@ -0,0 +1,119 @@ +<tool id="sample_seqs" name="Sub-sample sequences files" version="0.0.1"> + <description>e.g. to reduce coverage</description> + <requirements> + <requirement type="package" version="1.63">biopython</requirement> + <requirement type="python-module">Bio</requirement> + </requirements> + <version_command interpreter="python">sample_seqs.py --version</version_command> + <command interpreter="python"> +#if str($sampling.type) == "everyNth": +sample_seqs.py "$input_file.ext" "$input_file" "$output_file" "${sampling.type}" "${sampling.every_n}" +#elif str($sampling.type) == "percentage": +sample_seqs.py "$input_file.ext" "$input_file" "$output_file" "${sampling.type}" "${sampling.percent}" +#else: +##Should give an error about invalid sampling type: +sample_seqs.py "$input_file.ext" "$input_file" "$output_file" "${sampling.type}" +#end if + </command> + <stdio> + <!-- Anything other than zero is an error --> + <exit_code range="1:" /> + <exit_code range=":-1" /> + </stdio> + <inputs> + <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file" help="FASTA, FASTQ, or SFF format." /> + <conditional name="sampling"> + <param name="type" type="select" label="Sub-sampling approach"> + <option value="everyNth">Take every N-th sequence (e.g. every fifth sequence)</option> + <option value="percentage">Take some percentage of the sequences (e.g. 20% will take every fifth sequence)</option> + <!-- TODO - target coverage etc --> + </param> + <when value="everyNth"> + <param name="every_n" value="5" type="integer" min="2" label="N" help="At least 2, e.g. 5 will take every 5th sequence (taking 20% of the sequences)" /> + </when> + <when value="percentage"> + <param name="percent" value="20.0" type="float" min="0" max="100" label="Percentage" help="Between 0 and 100, e.g. 20% will take every 5th sequence" /> + </when> + </conditional> + </inputs> + <outputs> + <data name="output_file" format="input" metadata_source="input_file" label="${input_file.name} (sub-sampled)"/> + </outputs> + <tests> + <test> + <param name="input_file" value="get_orf_input.Suis_ORF.prot.fasta" /> + <param name="type" value="everyNth" /> + <param name="every_n" value="100" /> + <output name="output_file" file="get_orf_input.Suis_ORF.prot.sample_N100.fasta" /> + </test> + <test> + <param name="input_file" value="ecoli.fastq" /> + <param name="type" value="everyNth" /> + <param name="every_n" value="100" /> + <output name="output_file" file="ecoli.sample_N100.fastq" /> + </test> + <test> + <param name="input_file" value="MID4_GLZRM4E04_rnd30_frclip.sff" ftype="sff" /> + <param name="type" value="everyNth" /> + <param name="every_n" value="5" /> + <output name="output_file" file="MID4_GLZRM4E04_rnd30_frclip.sample_N5.sff" ftype="sff"/> + </test> + <test> + <param name="input_file" value="get_orf_input.Suis_ORF.prot.fasta" /> + <param name="type" value="percentage" /> + <param name="percent" value="1.0" /> + <output name="output_file" file="get_orf_input.Suis_ORF.prot.sample_N100.fasta" /> + </test> + <test> + <param name="input_file" value="ecoli.fastq" /> + <param name="type" value="percentage" /> + <param name="percent" value="1.0" /> + <output name="output_file" file="ecoli.sample_N100.fastq" /> + </test> + <test> + <param name="input_file" value="MID4_GLZRM4E04_rnd30_frclip.sff" ftype="sff" /> + <param name="type" value="percentage" /> + <param name="percent" value="20.0" /> + <output name="output_file" file="MID4_GLZRM4E04_rnd30_frclip.sample_N5.sff" ftype="sff"/> + </test> + </tests> + <help> +**What it does** + +Takes an input file of sequences (typically FASTA or FASTQ, but also +Standard Flowgram Format (SFF) is supported), and returns a new sequence +file sub-sampling from this (in the same format). + +Several sampling modes are supported, all designed to be non-random. This +allows reproducibility, and also works on paired sequence files. Also +note that by sampling uniformly through the file, this avoids any bias +should reads in any part of the file are of lesser quality (e.g. one part +of the slide). + +The simplest mode is to take every N-th sequence, for example taking +every 2nd sequence would sample half the file - while taking every 5th +sequence would take 20% of the file. + + +**Example Usage** + +Suppose you have some Illumina paired end data as files ``R1.fastq`` and +``R2.fastq`` which give an estimated x200 coverage, and you wish to do a +*de novo* assembly with a tool like MIRA which recommends lower coverage. +Taking every 3rd read would reduce the estimated coverage to about x66, +and would preserve the pairing as well. + + +**Citation** + +This tool uses Biopython, so if you use this Galaxy tool in work leading to a +scientific publication please cite the following paper: + +Cock et al (2009). Biopython: freely available Python tools for computational +molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3. +http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878. + +This tool is available to install into other Galaxy Instances via the Galaxy +Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/sample_seqs + </help> +</tool>