Mercurial > repos > galaxyp > metaquantome
changeset 4:80ce9ca55697 draft
planemo upload commit d27827cf38d30b9c98923f73bc9cae4ffe41361b
| author | galaxyp |
|---|---|
| date | Fri, 07 Dec 2018 13:43:06 -0500 |
| parents | 28180bbb8fe4 |
| children | 5bc492a15b8b |
| files | macros.xml metaquantome_expand.xml metaquantome_filter.xml metaquantome_stat.xml metaquantome_viz.xml static/images/filtering.png static/images/metaquantome_program_structure.png |
| diffstat | 7 files changed, 163 insertions(+), 49 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Thu Dec 06 08:50:19 2018 -0500 +++ b/macros.xml Fri Dec 07 13:43:06 2018 -0500 @@ -9,9 +9,9 @@ <xml name="ONTOLOGY_ARGS"> <conditional name="ontology_args"> <param name="ontology" type="select" label="Ontology"> - <option value="go">GO Gene Ontology (column named 'go')</option> - <option value="ec">EC Enzyme Commission (column named 'ec')</option> - <option value="cog">COG (column named 'cog')</option> + <option value="go">Gene Ontology (GO terms)</option> + <option value="ec">Enzyme Commission (EC) numbers</option> + <option value="cog">Clusters of Orthologous Groups (COG categories)</option> </param> <when value="go"> <param argument="--slim_down" type="boolean" label="Use slim GO"/> @@ -27,22 +27,22 @@ <xml name="FUNC_FILE"> <param argument="--func_file" type="data" format="tabular" label="Functional file" help="Tabular file with a peptide sequence column and a functional assignment column for GO-term, EC number, or COG."/> - <param argument="--pep_colname_func" type="text" label="Peptide column name" + <param argument="--pep_colname_func" type="text" label="Peptide column name" help="The column name within the function file that corresponds to the peptide sequences"> <validator type="empty_field"/> </param> - <param argument="--func_colname" type="text" label="Functional column name" + <param argument="--func_colname" type="text" label="Functional column name" help="The column name within the function file with the functional terms"> <validator type="empty_field"/> </param> </xml> <xml name="TAX_FILE"> <param argument="--tax_file" type="data" format="tabular" label="Taxonomy assignments file"/> - <param argument="--pep_colname_tax" type="text" label="Peptide column name" + <param argument="--pep_colname_tax" type="text" label="Peptide column name" help="The column name within the taxonomy file that corresponds to the peptide sequences"> <validator type="empty_field"/> </param> - <param argument="--tax_colname" type="text" label="Taxonomy column name"> + <param argument="--tax_colname" type="text" label="Taxonomy column name"> <help> Name of taxonomy column in taxonomy assignments file. The column must be either NCBI taxids (strongly preferred) or taxonomy @@ -53,7 +53,7 @@ </param> </xml> <token name="@MAKE_SAMPS_TSV@"><![CDATA[ - ### make samps config file + ### make samps config file #if $samps_args.samps_src == 'history': cat '$samps_args.samps_file' > samp_file.tab && #else: @@ -81,7 +81,7 @@ <xml name="data_dir"> <conditional name="db_dir"> <param argument="db_loc" type="select" label="Taxonomy and Functional Databases"> - <option value="auto">automatcally load databases</option> + <option value="auto">automatically load databases</option> <!-- bioconda recipe would need to install the databases <option value="pkg">use default metaquantome databases (not current)</option> -->
--- a/metaquantome_expand.xml Thu Dec 06 08:50:19 2018 -0500 +++ b/metaquantome_expand.xml Fri Dec 07 13:43:06 2018 -0500 @@ -1,4 +1,4 @@ -<tool id="metaquantome_expand" name="MetaQuantome Expand" version="@VERSION@.0"> +<tool id="metaquantome_expand" name="metaQuantome: expand" version="@VERSION@.0"> <description>annotated functional or taxonomy terms to include all terms</description> <macros> <import>macros.xml</import> @@ -11,9 +11,9 @@ @EXPAND_PARAMS@ @DB_DIR@ #if $input.input_type == 'nopep': - --nopep --nopep_file='$input.nopep_file' + --nopep --nopep_file='$input.nopep_file' #else: - --int_file='$input.int_file' + --int_file='$input.int_file' --pep_colname_int='$input.pep_colname_int' #end if --outfile='$outfile' @@ -29,7 +29,7 @@ <when value="int"> <param argument="--int_file" type="data" format="tabular" label="intensity data" help=""/> - <param argument="--pep_colname_int" type="text" value="" label="Peptide column name" + <param argument="--pep_colname_int" type="text" value="" label="Peptide column name" help="The column name within the intensity file that corresponds to the peptide sequences"> <validator type="empty_field"/> </param> @@ -47,9 +47,6 @@ </outputs> <tests> <test> - <!-- expand('f', sinfo=TTEST_SINFO, int_file=int, pep_colname_int='peptide', pep_colname_func='peptide', - pep_colname_tax='peptide', data_dir=GO_TEST_DIR, outfile=expanded, func_file=func, - func_colname='go', ontology='go') --> <param name="int_file" value="int_ttest.tab" ftype="tabular"/> <param name="pep_colname_int" value="peptide" /> <param name="func_file" value="multiple_func.tab" /> @@ -70,7 +67,59 @@ </test> </tests> <help><![CDATA[ - help +metaQuantome expand +=================== + +The *expand* module is the first step in the metaQuantome analysis workflow, +and can be run to analyze function, taxonomy, or function and taxonomy together. + +See the figure below for an overview of the metaQuantome workflow: + +.. image:: metaquantome_program_structure.png + :width: 100 % + +**metaQuantome workflow**: (A) Outline of metaQuantome program structure, (B) expanding the hierarchy, (C) and the definition of the total term abundance. + + +The following information is required for all 4 analysis modes: + +- experimental design information +- a tab-separated peptide intensity file +- the name of the peptide column in the intensity file + +Function mode +------------- + +In function mode, the following information is required: + +- the ontology being used: Gene Ontology (go), Clusters of Orthologous Groups (COG), or Enzyme Commission (EC) numbers. +- a tab-separated functional annotation file, with a peptide column and a functional annotation column. An entry in the functional annotation column may contain multiple functional annotations separated by a comma. +- the name of the peptide column in the functional annotation file +- the name of the functional annotation column in the functional annotation file + +Taxonomy mode +------------- + +In taxonomy mode, the following information is required: + +- a tab-separated taxonomy annotation file, with a peptide column and a taxonomy annotation column. The taxonomic annotations should be the lowest common ancestor (LCA) for each peptide, preferably given as NCBI taxonomy IDs. +- the name of the peptide column in the taxonomic annotation file +- the name of the taxonomy annotation column in the taxonomy annotation file + +Function-Taxonomy mode +---------------------- + +In the combined mode, all of the above must be provided. In addition, the "target rank" must be provided, which is the desired taxonomic rank at which to summarize the function/taxonomy results. + +Databases +--------- + +Currently, metaQuantome on Galaxy is only set up to use automatically downloaded databases, so your results may change slightly from run to run. In the future, we plan to enable cached databases in Galaxy. + +Questions, Comments, Problems, Kudos +------------------------------------ + +Please file any issues at https://github.com/galaxyproteomics/tools-galaxyp/issues. ]]></help> <expand macro="citations" /> </tool>
--- a/metaquantome_filter.xml Thu Dec 06 08:50:19 2018 -0500 +++ b/metaquantome_filter.xml Fri Dec 07 13:43:06 2018 -0500 @@ -1,4 +1,4 @@ -<tool id="metaquantome_filter" name="MetaQuantome Filter" version="@VERSION@.0"> +<tool id="metaquantome_filter" name="metaQuantome: filter" version="@VERSION@.0"> <description>for quality, redundancy, and sample coverage</description> <macros> <import>macros.xml</import> @@ -9,7 +9,7 @@ metaquantome filter @COMMON_PARAMS@ --expand_file '$expand_file' - --min_peptides $min_peptides + --min_peptides $min_peptides #if $min_pep_nsamp: #set $nsamp = max(int($min_peptides),int($min_pep_nsamp)) --min_pep_nsamp $nsamp @@ -99,7 +99,26 @@ </test> </tests> <help><![CDATA[ - TODO: Fill in help. - ]]></help> +metaQuantome filter +=================== + +The *filter* module is the second step in the metaQuantome analysis workflow. The +purpose of the filter module is to filter expanded terms to those that are +representative and well-supported by the data. + + +The image below illustrates the filtering process. + +.. image:: filtering.png + :width: 100 % + +**Filtering methods**. The circles indicate terms, the grey arrows indicate ‘is a’ relationships, and the blue arrows indicate metaQuantome filtering procedures. (A) Filtering results by number of unique peptides. The numbers inside each term indicate the hypothetical number of peptides giving evidence to each term. (B) Filtering by the number of sample children. The number inside each term indicates the number of children (direct descendants) that term has within the sample. metaQuantome filters out terms that are neither leaves nor meet the user-specified criterion for minimum sample children (here, 2, which is the default). (C) Filtering by the number of samples in which the term was quantified. + + +Questions, Comments, Problems, Kudos +-------------------------------------- + +Please file any issues at https://github.com/galaxyproteomics/tools-galaxyp/issues. + ]]></help> <expand macro="citations" /> </tool>
--- a/metaquantome_stat.xml Thu Dec 06 08:50:19 2018 -0500 +++ b/metaquantome_stat.xml Fri Dec 07 13:43:06 2018 -0500 @@ -1,5 +1,5 @@ -<tool id="metaquantome_stat" name="MetaQuantome Stats" version="@VERSION@.0"> - <description>differential functional expression and taxonomic abundance</description> +<tool id="metaquantome_stat" name="metaQuantome: stat" version="@VERSION@.0"> + <description>differential analysis of functional expression and taxonomic abundance</description> <macros> <import>macros.xml</import> </macros> @@ -25,8 +25,8 @@ <option value="ft">Functional-taxonomic interaction analysis</option> </param> <param name="ontology" type="select" label="Ontology"> - <option value="go">Gene Ontology (column named 'go')</option> - <option value="ec">Gene Ontology (column named 'go')</option> + <option value="go">Gene Ontology (GO) terms</option> + <option value="ec">Enzyme Commission (EC) numbers</option> <option value="cog">COG (column named 'cog')</option> </param> <param argument="--parametric" type="select" label="Statistical test to perform"> @@ -47,8 +47,6 @@ <param name="ontology" value="ec" /> <param name="mode" value="f" /> <output name="outfile" value="ec_ttest_tested.tab" ftype="tabular"/> - <!-- stat(expandfile, sinfo=TTEST_SINFO, paired=False, parametric=True, ontology='ec', mode='f', - outfile=tested_file) --> <param name="samps_src" value="build" /> <repeat name="samps"> <param name="group_name" value="s1"/> @@ -61,7 +59,19 @@ </test> </tests> <help><![CDATA[ - help +metaQuantome stat +=================== + +The *stat* module is the third step in the metaQuantome analysis workflow. The purpose +of the *stat* module is to perform differential expression analysis between 2 experimental +conditions. metaQuantome offers paired and unpaired tests, +as well as parametric and non-parametric options. + +Questions, Comments, Problems, Kudos +-------------------------------------- + +Please file any issues at https://github.com/galaxyproteomics/tools-galaxyp/issues. + ]]></help> <expand macro="citations" /> </tool>
--- a/metaquantome_viz.xml Thu Dec 06 08:50:19 2018 -0500 +++ b/metaquantome_viz.xml Fri Dec 07 13:43:06 2018 -0500 @@ -1,10 +1,10 @@ -<tool id="metaquantome_viz" name="MetaQuantome Visualization Plots" version="@VERSION@.0"> - <description>of taxonomic analysis, functional analysis, and function-taxonomy</description> +<tool id="metaquantome_viz" name="metaQuantome: visualize" version="@VERSION@.0"> + <description>taxonomic analysis, functional analysis, and function-taxonomy analysis results</description> <macros> <import>macros.xml</import> <xml name="img_size"> - <param argument="--width" type="float" value="" optional="true" label="Image width in inches"/> - <param argument="--height" type="float" value="" optional="true" label="Image height in inches"/> + <param argument="--width" type="float" value="" optional="true" label="Image width in inches"/> + <param argument="--height" type="float" value="" optional="true" label="Image height in inches"/> </xml> <xml name="common_bar_params"> <param argument="--target_rank" type="text" value="species" label="Taxonomic rank to restrict to in the plot" @@ -25,9 +25,9 @@ <param argument="--barcol" type="integer" value="1" min="1" max="6" label="Color for the bar fill"> <help> The color vector in R is - c("dodgerblue", "darkorange", "yellow2", "red2", "darkviolet", "black"), - so providing a 1 will give the "dodgerblue" color. - These same colors are also used in the heatmap and PCA plot, + c("dodgerblue", "darkorange", "yellow2", "red2", "darkviolet", "black"), + so providing a 1 will give the "dodgerblue" color. + These same colors are also used in the heatmap and PCA plot, so the colors can be tweaked to match. </help> </param> @@ -52,7 +52,6 @@ #end if --barcol=$plot.barcol #elif $plot.plottype == 'volcano': - --meancol='$plot.meancol' --fc_name='$plot.fc_name' #if $plot.textannot: --textannot='$plot.textannot' @@ -91,7 +90,30 @@ #if $plot.height: --height=$plot.height #end if - --img='outfile.png' + --img='outfile.png' && + mkdir '${ wrapped_outfile.files_path }' && + cp outfile.png '${ wrapped_outfile.files_path }' && + ## stylesheet + echo "img { + display: block; + margin-left: auto; + margin-right: auto; + max-width: 75%; + height: auto; + }" > style.css && + cp style.css '${ wrapped_outfile.files_path }' && + echo "<!DOCTYPE html> + <html> + <head> + <link rel=\"stylesheet\" type=\"text/css\" href=\"style.css\"/> + </head> + <body> + <img src=\"outfile.png\"> + <br> + <p>To download the image, right-click and choose \"Save image as...\"</p> + </body> + </html>" > wrapped_outfile.html && + cat wrapped_outfile.html ]]></command> <inputs> <expand macro="common_params"/> @@ -110,29 +132,25 @@ <expand macro="img_size"/> </when> <when value="volcano"> - <param argument="--meancol" type="text" label="Mean intensity column name" - help="Mean intensity column name for desired experimental condition"> - <validator type="empty_field"/> - </param> <param argument="--fc_name" type="text" label="Name of the fold change column in the stat dataframe"> <validator type="empty_field"/> </param> - <param argument="--textannot" type="text" optional="true" label="Name of the annotation column" + <param argument="--textannot" type="text" optional="true" label="Name of the annotation column" help="Provides text annoatation for the plot. Optional, if missing, no text will be plotted."/> - <param argument="--flip_fc" type="boolean" truevalue="--flip_fc" falsevalue="" checked="false" + <param argument="--flip_fc" type="boolean" truevalue="--flip_fc" falsevalue="" checked="false" label="Flip the fold change (i.e., multiply log fold change by -1)"/> - <param argument="--gosplit" type="boolean" truevalue="--gosplit" falsevalue="" checked="false" - label="Make one plot for each of BiologicalProcess, CellularComponent, and MolecularFunction"/> + <param argument="--gosplit" type="boolean" truevalue="--gosplit" falsevalue="" checked="false" + label="Make one plot for each of BiologicalProcess, CellularComponent, and MolecularFunction GO term categories."/> <expand macro="img_size"/> </when> <when value="heatmap"> - <param argument="--filter_to_sig" type="boolean" truevalue="--filter_to_sig" falsevalue="" checked="false" + <param argument="--filter_to_sig" type="boolean" truevalue="--filter_to_sig" falsevalue="" checked="false" label="Only plot significant term" help="Necessitates use of results from `test`"/> <param argument="--alpha" type="float" value="0.05" min="0.0" max="1.0" label="If filter_to_sig, the q-value significance level"/> <expand macro="img_size"/> </when> <when value="pca"> - <param argument="--calculate_sep" type="boolean" truevalue="--calculate_sep" falsevalue="" checked="false" + <param argument="--calculate_sep" type="boolean" truevalue="--calculate_sep" falsevalue="" checked="false" label="Calculate separation between groups and include in title"/> <expand macro="img_size"/> </when> @@ -157,11 +175,12 @@ <when value="name"> <param argument="--name" type="text" label="Taxonomic or functional term name"> <help> + Case-sensitive. Should be either a common taxonomic name ("Streptococcus") or functional term ("carbohydrate metabolic process"). </help> </param> </when> </conditional> - <param argument="--target_onto" type="select" optional="true" label="Restrict to GO category"> + <param argument="--target_onto" type="select" optional="false" label="GO category to restrict to"> <option value="bp">Biological Process</option> <option value="mf">Molecular Function</option> <option value="cc">Cellular Component</option> @@ -172,6 +191,7 @@ </inputs> <outputs> <data format="png" name="outfile" label="${tool.name} on ${on_string} ${plot.plottype}" from_work_dir="outfile.png"/> + <data format="html" name="wrapped_outfile" label="${tool.name} on ${on_string} ${plot.plottype}" from_work_dir="wrapped_outfile.html"/> </outputs> <tests> <test> @@ -190,7 +210,23 @@ </test> </tests> <help><![CDATA[ - TODO: Fill in help. +metaQuantome viz +=================== + +The *viz* module is the final step in the metaQuantome analysis workflow. +The available visualizations are: + +- bar plot +- volcano plot +- heatmap +- PCA plot + +Please consult the manuscript for full details on each of these plots. + +Questions, Comments, Problems, Kudos +-------------------------------------- + +Please file any issues at https://github.com/galaxyproteomics/tools-galaxyp/issues. ]]></help> <expand macro="citations" /> </tool>