Mercurial > repos > simon-gladman > phyloseq_nmds
changeset 3:5a2bda9b28c5 draft
New version 1.22.3.2.
author | simon-gladman |
---|---|
date | Mon, 30 Jul 2018 21:06:56 -0400 |
parents | 20adf95eb758 |
children | d06ddf67468f |
files | README.md phyloseq_nmds.xml |
diffstat | 2 files changed, 106 insertions(+), 44 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.md Mon Jul 30 21:06:56 2018 -0400 @@ -0,0 +1,51 @@ +# Phloseq_NMDS + +A Galaxy tool to produce NMDS plots using Phyloseq from either a BIOM1 file or 2 input tables. + +Currently produces the plots embedded in a html file for output with links to a PDF file. + +Requires: + +Phyloseq 1.22.3 +r-getopt 1.20.0 +ghostscript 9.18 + + +### Run phyloseq_nmds.R with three input files +Rscript phyloseq_nmds.R --otu_table=GP_OTU_TABLE.txt --tax_table=GP_TAX_TABLE.txt --meta_table=GP_SAMPLE_TABLE.txt --method="bray" --kingdom=2 --cutoff=5 --category=6 --outdir=/outputdir --htmlfile=test.html + +### Run phyloseq_nmds.R with biom file +Rscript phyloseq_nmds.R --biom=GP.biom --subset=6 --method=NMDS --distance=bray --kingdom=Phylum --cutoff=5 --keep=5 --outdir=/outputdir --htmlfile=biom_out.html + +## Version history: + +**XML Wrapper:** + +Alpha version by Michael Thang of QFAB, Australia. + +1.22.3.1: Simon Gladman Melbourne Bioinformatics + +* Incorporated tests +* Requirements +* Version statement +* Citations + +1.22.3.2: Michael Thang QFAB, Simon Gladman Melbourne Bioinformatics + +* Uses new version of BIOM1 datatype to get metadata +* Output label changed as per user requirements + + +**R Script: phyloseq_nmds.R** + +0.1.0: Michael Thang QFAB + +* Original version + +0.1.1: Michael Thang QFAB + +* Added extra BIOM import functionality so it doesn't solely rely on phyloseq's internal importer. + +0.1.2: Michael Thang QFAB + +* BIOM functionality now requires the column header name in text.
--- a/phyloseq_nmds.xml Fri Jul 20 00:23:53 2018 -0400 +++ b/phyloseq_nmds.xml Mon Jul 30 21:06:56 2018 -0400 @@ -1,5 +1,5 @@ -<tool id="phyloseq_nmds" name="Phyloseq NMDS" version="1.22.3.1" hidden="false"> - <description>Phyloseq NMDS plot</description> +<tool id="phyloseq_nmds" name="Phyloseq Ordination Plot" version="1.22.3.2" hidden="false"> + <description>Ordination Plotting</description> <requirements> <requirement type="package" version="1.22.3">bioconductor-phyloseq</requirement> <requirement type="package" version="1.20.0">r-getopt</requirement> @@ -32,16 +32,14 @@ </command> <inputs> - <conditional name="file_source"> - <param name="file_source_selector" type="select" label="Choose a file type"> + <param name="file_source_selector" type="select" label="Choose an input file type"> <option value="set_biom" selected="True">BIOM File</option> <option value="set_table">TABULAR File</option> </param> <when value="set_biom"> <param format="biom1" name="input" type="data" label="Input File"/> - <!--<param format="tabular" name="META_COLUMN" type="data" label="Column File"/>--> - <param name="subsetColumn" type="select" label="Select a column"> + <param name="subsetColumn" type="select" label="Select variable for ordination"> <options> <filter type="data_meta" ref="input" key="table_column_metadata_headers" /> </options> @@ -51,28 +49,26 @@ <param format="tabular" name="OTU_TABLE" type="data" label="OTU table"/> <param format="tabular" name="TAX_TABLE" type="data" label="Taxonomy table"/> <param format="tabular" name="META_TABLE" type="data" label="Metadata table"/> - <param name="category" type="data_column" data_ref="META_TABLE" use_header_names="True" label="Select a column"/> + <param name="category" type="data_column" data_ref="META_TABLE" use_header_names="True" label="Select variable for ordination"/> </when> </conditional> - <param name="plot_type" type="select" label="Type of Plot" help="NMDS plot by type (e.g., OTU, SAMPLE)"> - <option value="1">OTU</option> - <option value="2">SAMPLE</option> + <param name="ord_method" type="select" display="radio" label="Select Ordination method"> + <option value="NMDS" selected="true">NMDS(Non-metric Multidimensional Scalling)</option> + <option value="DCA">DCA (Detrended Correspondence Analysis)</option> + <option value="CCA">CCA (Constrained Correspondence Analysis)</option> + <option value="RDA">RDA (Redundancy Analysis)</option> + <option value="DPCoA">DPCoA (Double Principle Coordinate Analysis)</option> + <option value="MDS">MDS (Multidimensional Scaling)</option> + <option value="PCoA">PCoA (Principal Coordinate Analysis)</option> </param> - <param name="ord_method" type="select" display="radio" label="Select NMDS method"> - <option value="NMDS" selected="true">NMDS</option> - <option value="DCA">DCA</option> - <option value="CCA">CCA</option> - <option value="RDA">RDA</option> - <option value="DPCoA">DPCoA</option> - <option value="MDS">MDS</option> - <option value="PCoA">PCoA</option> + <param name="distance" type="select" display="radio" label="Select Distance method"> + <option value="bray" selected="true">bray (Bray-Curtis distance)</option> + <option value="gower">gower (Gower's distance)</option> + <option value="jsd">jds (Jensen-Shannon Divergence)</option> + <option value="unifrac">unifrac (unweighted UniFrac distance)</option> + <option value="wunifrac">wunifrac (weighted-UniFrac distance)</option> </param> - <param name="distance" type="select" display="radio" label="Select a distance for NMDS"> - <option value="bray" selected="true">bray</option> - <option value="gower">gower</option> - <option value="unifrac">unifrac</option> - </param> - <param name="kingdom_field" type="select" display="radio" label="Select a taxonomy rank"> + <param name="kingdom_field" type="select" display="radio" label="Select a taxonomic rank for the analysis"> <option value="Kingdom">Kingdom</option> <option value="Phylum" selected="true">Phylum</option> <option value="Class">Class</option> @@ -81,30 +77,34 @@ <option value="Genus">Genus</option> <option value="Species">Species</option> </param> - <param name="nsample" size="10" type="float" value="0.5" label="Number of samples to keep" help="The percentage of sample number to keep for analysis (e.g., 0.5 is equivalent to half of the samples to keep for analysis)"/> - <param name="cutoff" size="10" type="integer" value="5" label="Cutoff value for filtering OTU table" help="Remove OTUs that do not appear more than 5 times"/> - <param name="keep" size="10" type="integer" value="5" label="Number of most abundant phyla" help="provide the number of most abundancet phyla to display"/> + <param name="plot_type" type="select" label="Type of Plot" help="Ordination plot type (Plot OTUs, Plot SAMPLE, Biplot graphic, Split plot graphic)"> + <option value="1">OTU</option> + <option value="2">SAMPLE</option> + </param> + <param name="nsample" size="10" type="float" value="0.5" label="Specify the number of samples to discard" help="i.e. remove OTUs from the analysis that do not appear more than X times in more than Y% of the samples (where 1.0 = 100%)"/> + <param name="cutoff" size="10" type="integer" value="5" label="specify value of X" help="Remove OTUs that do not appear more than X times (e.g., 5 times)"/> + <param name="keep" size="10" type="integer" value="5" label="Number of the most abundant taxonomic rank units to keep" help="e.g. Phyla, Class and etc"/> </inputs> <outputs> - <data format="html" name="htmlfile" label="${tool.name}.html"/> + <data format="html" name="htmlfile" label="${tool.name} - ${ord_method.value_label}_${distance.value_label}.html"/> </outputs> <tests> - <test> <!-- Test #1: Test BIOM format input --> - <!-- Equivalent command (replace + with double dash): Rscript phyloseq_nmds.R +biom=test-data/GP.biom +subset=6 +method=NMDS - +distance=bray +kingdom=Phylum +cutoff=5 +keep=5 +outdir=outputdir +htmlfile=biom_out.html --> + <test> <!-- Test #1: Test BIOM format input --> + <!-- Equivalent command (replace + with double dash): Rscript phyloseq_nmds.R +biom=test-data/GP.biom +subset=6 +method=NMDS + +distance=bray +kingdom=Phylum +cutoff=5 +keep=5 +outdir=outputdir +htmlfile=biom_out.html --> <conditional name="file_source"> <param name="file_source_selector" value="set_biom"/> - <param name="input" value="GP.biom" format="biom1"/> + <param name="input" value="GP.biom" /> <param name="subsetColumn" value="Primer" /> </conditional> <output name="htmlfile" ftype="html" file="biom_out.html" /> </test> - <test><!-- Test #2: Test TABULAR format inputs --> - <!-- Equivalent command (replace + with double dash): Rscript phyloseq_nmds.R +otu_table=test-data/GP_OTU_TABLE.txt - +tax_table=test-data/GP_TAX_TABLE.txt +meta_table=test-data/GP_SAMPLE_TABLE.txt - +method="bray" +kingdom=Phylum +cutoff=5 + keep=5 +category=6 +outdir=outputdir +htmlfile=test.html --> + <test> <!-- Test #2: Test TABULAR format inputs --> + <!-- Equivalent command (replace + with double dash): Rscript phyloseq_nmds.R +otu_table=test-data/GP_OTU_TABLE.txt + +tax_table=test-data/GP_TAX_TABLE.txt +meta_table=test-data/GP_SAMPLE_TABLE.txt + +method="bray" +kingdom=Phylum +cutoff=5 + keep=5 +category=6 +outdir=outputdir +htmlfile=test.html --> <conditional name="file_source"> <param name="file_source_selector" value="set_table" /> <param name="OTU_TABLE" value="GP_OTU_TABLE.txt" /> @@ -126,17 +126,28 @@ **Input** -- **Choose a file type** - BIOM File or TABULAR file -- **Select a column** - This column is used to extract unique value from the column of interest for NMDS plot +- **Choose an input file type** - BIOM File or TABULAR file +- **Select variable for ordination** - This column is used to extract unique value from the column of interest for ordination plot - **OTU TABLE** - this is a OTU matrix - **Taxonomy TABLE** - this is a TAX matrix - **Metadata TABLE** - this is a metadata file of the experiment design -- **Select NMDS method** - select a method for NMDS plot -- **Select a distance for NMDS** - select a distance option for NMDS plot -- **Select a taxonomy rank** - select a taxonomy for NMDS plot -- **Number of samples to keep** - Number of samples to keep for analysis -- **Cutoff value for filtering OTU table** - this cutoff value is used to fitler OTU table -- **Number of most abundant phyla** - a number of most abundant phyla to be display in NMDS plot +- **Select Ordination method** - select ordination method +- **Select Distance method** - select distance method for ordination plot +- **Select a taxonomic rank for the analysis** - select a taxonomy for NMDS plot +- **Specify the number of samples to discard** - Y% of samples to discard (where 1.0 = 100%) +- **specify value of X** - Remove OTUs that do not appear more than X times (e.g., 5 times) +- **Number of the most abundant taxonomic rank units** - taxonomic rank units (e.g. Phyla, Class etc) to keep + +----- + +========= +Resources +========= + +**Wrapper Authors** + +QFAB Bioinformatics (support@qfab.org) +Melbourne Bioinformatics </help> <citations> <citation type="doi">10.18129/B9.bioc.phyloseq</citation>