Mercurial > repos > ppericard > mixomics_blocksplsda
changeset 4:b0ab97ffc2a1 draft
planemo upload for repository https://github.com/bilille/galaxy-mixomics-blocksplsda commit 0bf5c0745f406f2eca9c708a062c975b1f7ea386
| author | ppericard |
|---|---|
| date | Mon, 09 Mar 2020 11:53:32 -0400 |
| parents | 0a3c83f2197a |
| children | 1ee8d2c20c0a |
| files | circleCor.xml circleCor_wrapper.R computeMatSimilarity.xml matCor_addVar.xml mixomics_blocksplsda.xml mixomics_blocksplsda_script.R mixomics_plotindiv.xml mixomics_plotvar.xml networkVar.xml |
| diffstat | 9 files changed, 146 insertions(+), 79 deletions(-) [+] |
line wrap: on
line diff
--- a/circleCor.xml Fri Oct 25 07:10:59 2019 -0400 +++ b/circleCor.xml Mon Mar 09 11:53:32 2020 -0400 @@ -1,7 +1,7 @@ -<tool id="circleCor" name="circleCor" version="0.2.0" profile="16.04" workflow_compatible="true"> +<tool id="circleCor" name="circleCor" version="0.3.0" profile="16.04" workflow_compatible="true"> - <description></description> - + <description>plots a correlation circle for the datasets whose correlation circles can be superimposed. This correlation circle contains the selected variables of these datasets which are included in a rectangle and the response variables.</description> + <requirements> <requirement type="package">r-base</requirement> <requirement type="package" version="0.4">r-ellipse</requirement> @@ -10,7 +10,7 @@ <!-- <requirement type="package" version="6.8">bioconductor-mixomics</requirement> --> </requirements> - + <stdio> <!-- <exit_code range="1:" level="fatal" /> --> </stdio> @@ -32,16 +32,24 @@ </command> <inputs> - <param name="input_rdata" type="data" format="rdata" label="Input RData file from block.SPLSDA"/> - <param name="blocks_vec_list" type="data" format="tabular" label="List of blocks vector"/> - <param name="select_blocks" type="select" label="Blocks"> + <param name="input_rdata" type="data" format="rdata" + label="Input RData file" + help="output RData from matCor_addVar"/> + <param name="blocks_vec_list" type="data" format="tabular" + label="List of blocks vector." + help="output tsv file from matCor_addVar"/> + <param name="select_blocks" type="select" + label="Blocks" + help="list of the blocks that are to be superimposed"> <options from_dataset="blocks_vec_list"> <column name="value" index="0"/> <filter type="unique_value" column="0"/> <filter type="sort_by" name="sorted_value" column="0"/> </options> </param> - <param name="responses_var_list" type="data" format="tabular" label="List of response variables"/> + <param name="responses_var_list" type="data" format="txt" + label="List of response variables" + help="list of the response variables which will be plotted in the correlation circle"/> <param name="select_responses_var" type="select" display="checkboxes" multiple="true" label="Response variables"> <!-- <param name="select_responses_var" type="select" multiple="true" label="Response variables"> --> <options from_dataset="responses_var_list"> @@ -50,10 +58,14 @@ <filter type="sort_by" name="sorted_value" column="0"/> </options> </param> - <param name="x_min" type="float" value="-1" min="-1" max="1" label="X min" help="" /> - <param name="x_max" type="float" value="1" min="-1" max="1" label="X max" help="" /> - <param name="y_min" type="float" value="-1" min="-1" max="1" label="Y min" help="" /> - <param name="y_max" type="float" value="1" min="-1" max="1" label="Y max" help="" /> + <param name="x_min" type="float" value="-1" min="-1" max="1" + label="X min" help="" /> + <param name="x_max" type="float" value="1" min="-1" max="1" + label="X max" help="" /> + <param name="y_min" type="float" value="-1" min="-1" max="1" + label="Y min" help="" /> + <param name="y_max" type="float" value="1" min="-1" max="1" + label="Y max" help="" /> </inputs> <outputs>
--- a/circleCor_wrapper.R Fri Oct 25 07:10:59 2019 -0400 +++ b/circleCor_wrapper.R Mon Mar 09 11:53:32 2020 -0400 @@ -76,8 +76,11 @@ print(blocks_vector) +# pdf(args$output_pdf, width=12, height=9) +pdf(args$output_pdf) -pdf(args$output_pdf, width=12, height=9) +mar = c(5.1, 4.1, 4.1, 9.1) +par(mar = mar) varSelect = circleCor(liste_dataframe_cor_comp_var_global = liste_dataframe_cor_comp_var_global, liste_vec_indice_blockSelect = liste_vec_indice_blockSelect,
--- a/computeMatSimilarity.xml Fri Oct 25 07:10:59 2019 -0400 +++ b/computeMatSimilarity.xml Mon Mar 09 11:53:32 2020 -0400 @@ -1,12 +1,12 @@ -<tool id="computeMatSimilarity" name="computeMatSimilarity" version="0.2.0" profile="16.04" workflow_compatible="true"> +<tool id="computeMatSimilarity" name="computeMatSimilarity" version="0.3.0" profile="16.04" workflow_compatible="true"> - <description></description> - + <description>performs the computation of the similarities. The similarity between two variables is an approximation of the correlation between these two variables.</description> + <requirements> <!-- <requirement type="package" version="6.8">bioconductor-mixomics</requirement> --> <requirement type="package" version="2.0">r-argparse</requirement> </requirements> - + <stdio> <!-- <exit_code range="1:" level="fatal" /> --> </stdio> @@ -21,7 +21,9 @@ </command> <inputs> - <param name="input_rdata" type="data" format="rdata" label="Input RData file from addVariablesResponses"/> + <param name="input_rdata" type="data" format="rdata" + label="Input RData file" + help="output RData file from matCor_addVar"/> </inputs> <outputs>
--- a/matCor_addVar.xml Fri Oct 25 07:10:59 2019 -0400 +++ b/matCor_addVar.xml Mon Mar 09 11:53:32 2020 -0400 @@ -1,12 +1,12 @@ -<tool id="matCor_addVar" name="matCor_addVar" version="0.2.0" profile="16.04" workflow_compatible="true"> +<tool id="matCor_addVar" name="matCor_addVar" version="0.3.0" profile="16.04" workflow_compatible="true"> - <description></description> - + <description>computes all the correlations needed to plot a correlation circle and determines which correlation circles can be superimposed</description> + <requirements> <requirement type="package" version="6.8">bioconductor-mixomics</requirement> <requirement type="package" version="2.0">r-argparse</requirement> </requirements> - + <stdio> <!-- <exit_code range="1:" level="fatal" /> --> </stdio> @@ -24,9 +24,15 @@ </command> <inputs> - <param name="input_rdata" type="data" format="rdata" label="Input RData file from block.SPLSDA"/> - <param name="cutoff_comp" type="float" value="0.8" min="0" max="1" label="" help="" /> - <param name="mat_block_Y" type="data" format="tabular" label="Matrix Block Y" /> + <param name="input_rdata" type="data" format="rdata" + label="Input RData file from block.SPLSDA" + help="This is the RData output file from the block.splsda function." /> + <param name="cutoff_comp" type="float" value="0.8" min="0" max="1" + label="Cutoff comp" + help="[cutoff_comp] Two correlation circles will be superimposed if the correlation of their first and second axis is greater than cutoff_comp in absolute value." /> + <param name="mat_block_Y" type="data" format="tabular" + label="Matrix Block Y" + help="Matrix Block Y in tabular format. This table contains the name of the samples in the first column. The other columns correspond to phenotypes. For each of these other columns, a column determines which sample is associated with this phenotype (value equals to 1) or not (value equals to 0). The name of the samples in Matrix Block Y (transposed), in the sample metadata (transposed) and for all datasets have to be in the same order" /> </inputs> <outputs>
--- a/mixomics_blocksplsda.xml Fri Oct 25 07:10:59 2019 -0400 +++ b/mixomics_blocksplsda.xml Mon Mar 09 11:53:32 2020 -0400 @@ -1,12 +1,12 @@ -<tool id="mixomics_blocksplsda" name="mixOmics block.splsda" version="0.2.0" profile="16.04" workflow_compatible="true"> +<tool id="mixomics_blocksplsda" name="mixOmics block.splsda" version="0.3.0" profile="16.04" workflow_compatible="true"> <description>performs N-integration and feature selection with Projection to Latent Structures models (PLS) with sparse Discriminant Analysis</description> - + <requirements> <requirement type="package" version="6.8">bioconductor-mixomics</requirement> <requirement type="package" version="2.0">r-argparse</requirement> </requirements> - + <!-- <stdio> <exit_code range="1:" level="fatal" /> </stdio> --> @@ -47,16 +47,31 @@ <inputs> <repeat name="blocks" title="Blocks"> <param name="block_name" type="text" label="Block name" /> - <param name="keep" type="integer" value="0" min="0" label="Number of variables to select for each component" help="Default is to keep all variables" /> - <param name="data_matrix" type="data" format="tabular" label="Data matrix" help="rows = variables, columns = samples" /> - <param name="variable_metadata" type="data" format="tabular" optional="true" label="Variables metadata" help="rows = variables" /> + <param name="keep" type="integer" value="0" min="0" + label="Number of variables to select for each component" + help="[keep] Estimation of the number of variables in the block correlated with variables from the other blocks and correlated with response variables. If set to 0, all variables will be selected." /> + <param name="data_matrix" type="data" format="tabular" + label="Data matrix" + help="Block data in tabular format (rows = variables, columns = samples). The first column contains the variables names and the first row contains the samples names. Samples names must be in the same order for all blocks and the sample metadata (transposed). The data must not contain missing values." /> + <param name="variable_metadata" type="data" format="tabular" optional="true" + label="Variables metadata [optional]" + help="Variables metadata in tabular format (rows = variables). The first colum contains the variables names. The first row contains the metadata column names. The number of rows in the metadata file must be the same than the number of rows in the block data file, and the variables need to be in the same order. If a metadata file is provided, block.splsda output will be appended as new columns, otherwise a new file will be created." /> </repeat> - <param name="sample_metadata_in" type="data" format="tabular" label="Samples metadata matrix" /> - <param name="sample_description_col" type="integer" value="0" min="0" label="Sample description column number" help="Use the last column by default" /> - <param name="ncomp" type="integer" value="2" min="1" label="Number of components to include in the model" /> - <param name="correlation" type="boolean" truevalue="--correlation" falsevalue="" checked="false" label="Correlation between all blocks"/> + <param name="sample_metadata_in" type="data" format="tabular" + label="Samples metadata" + help="Samples metadata in tabular format (rows = samples). The first column contains the sample names. The first row contains the metadata column names. Samples names must be in the same order (transposed) than all the blocks. One of the column (the last by default) must contain the samples groups for integration." /> + <param name="sample_description_col" type="integer" value="0" min="0" + label="Samples groups column number" + help="Column from the samples metadata file containing samples groups. If set to 0, the last column will be used." /> + <param name="ncomp" type="integer" value="2" min="1" + label="Number of components to include in the model" + help="[ncomp] Number of new variables (components) computed by the data integration." /> + <param name="correlation" type="boolean" truevalue="--correlation" + falsevalue="" checked="false" + label="Correlation between all blocks" + help="[design] If set to Yes, data integration will take into account correlations between all the blocks (design matrix with diagonal coefficients set to 0 and the rest of the coefficients set to 1)." /> <section name="adv" title="Advanced Options" expanded="false"> - <param name="scheme" type="select" label="Scheme"> +<!-- <param name="scheme" type="select" label="Scheme"> <option value="horst" selected="true">horst</option> <option value="factorial" >factorial</option> <option value="centroid" >centroid</option> @@ -66,23 +81,32 @@ <option value="canonical" >canonical</option> <option value="invariant" >invariant</option> <option value="classic" >classic</option> - </param> - <param name="maxiter" type="integer" value="100" min="1" label="Maximum number of iterations" /> - <param name="scale" type="boolean" truevalue="--scale" falsevalue="" checked="true" label="Scale" help="if checked, each block is standardized to zero means and unit variances" /> + </param> --> + <param name="maxiter" type="integer" value="100" min="1" + label="Maximum number of iterations" + help="[max.iter] Maximum number of iterations performed by block.splsda." /> +<!-- <param name="scale" type="boolean" truevalue="-\-scale" falsevalue="" checked="true" + label="Scale" + help="if checked, each block is standardized to zero means and unit variances" /> <param name="init" type="select" label="Init"> <option value="svd" selected="true">svd</option> <option value="svd.single" >svd.single</option> </param> - <param name="tol" type="float" value="1e-06" min="0" label="Convergence stopping value (tol)" /> - <param name="nearzerovar" type="boolean" truevalue="--nearzerovar" falsevalue="" checked="false" label="Should be set to TRUE in particular for data with many zero values" /> + <param name="tol" type="float" value="1e-06" min="0" + label="Convergence stopping value" + help="[tol]" /> + <param name="nearzerovar" type="boolean" truevalue="-\-nearzerovar" falsevalue="" checked="false" + label="Should be set to TRUE in particular for data with many zero values" /> --> </section> </inputs> <outputs> <data name="rdata_out" format="rdata" label="${tool.name}_output.rdata" /> - <data name="sample_metadata_out" format="tabular" label="${tool.name}_${sample_metadata_in.name}" /> + <data name="sample_metadata_out" format="tabular" + label="${tool.name}_${sample_metadata_in.name}" /> <collection name="blocks_output" type="list" label="${tool.name}_blocks_output"> - <discover_datasets pattern="(?P<designation>.+)\.tsv" directory="outdir" format="tabular" /> + <discover_datasets pattern="(?P<designation>.+)\.tsv" + directory="outdir" format="tabular" /> </collection> </outputs>
--- a/mixomics_blocksplsda_script.R Fri Oct 25 07:10:59 2019 -0400 +++ b/mixomics_blocksplsda_script.R Mon Mar 09 11:53:32 2020 -0400 @@ -141,18 +141,18 @@ ################### mixomics_result <- block.splsda(X = list_X, - Y = Y, - ncomp = args$ncomp, - keepX = keepX, - design = design, - scheme = args$scheme, - mode = args$mode, - scale = args$scale, - init = args$init, - tol = args$tol, - max.iter = args$maxiter, - near.zero.var = args$nearzerovar, - all.outputs = TRUE) + Y = Y, + ncomp = args$ncomp, + keepX = keepX, + design = design, + scheme = args$scheme, + mode = args$mode, + scale = args$scale, + init = args$init, + tol = args$tol, + max.iter = args$maxiter, + near.zero.var = args$nearzerovar, + all.outputs = TRUE) print("Block.splsda object:") print(mixomics_result)
--- a/mixomics_plotindiv.xml Fri Oct 25 07:10:59 2019 -0400 +++ b/mixomics_plotindiv.xml Mon Mar 09 11:53:32 2020 -0400 @@ -1,12 +1,12 @@ -<tool id="mixomics_plotindiv" name="mixOmics plotIndiv" version="0.2.0" profile="16.04" workflow_compatible="true"> +<tool id="mixomics_plotindiv" name="mixOmics plotIndiv" version="0.3.0" profile="16.04" workflow_compatible="true"> <description>provides scatter plots for individuals (experimental units) representation in (sparse)(I)PCA,(regularized)CCA, (sparse)PLS(DA) and (sparse)(R)GCCA(DA)</description> - + <requirements> <requirement type="package" version="6.8">bioconductor-mixomics</requirement> <requirement type="package" version="2.0">r-argparse</requirement> </requirements> - + <stdio> <!-- <exit_code range="1:" level="fatal" /> --> </stdio> @@ -23,10 +23,14 @@ </command> <inputs> - <param name="input_rdata" type="data" format="rdata" label="Input RData file from (sparse)(I)PCA, (regularized)CCA, (sparse)PLS(DA) or (sparse)(R)GCCA(DA)"/> + <param name="input_rdata" type="data" format="rdata" + label="Input RData file from (sparse)(I)PCA, (regularized)CCA, (sparse)PLS(DA) or (sparse)(R)GCCA(DA)" + help="This is the RData output file from the block.splsda function." /> <section name="adv" title="Advanced Options" expanded="false"> - <param name="legend" type="boolean" checked="true" truevalue="--legend" falsevalue="" label="Plot legend"/> - <param name="ellipse" type="boolean" checked="true" truevalue="--ellipse" falsevalue="" label="Plot ellipse plots"/> + <param name="legend" type="boolean" checked="true" truevalue="--legend" falsevalue="" + label="Plot legend" /> + <param name="ellipse" type="boolean" checked="true" truevalue="--ellipse" falsevalue="" + label="Plot ellipse plots" /> </section> </inputs>
--- a/mixomics_plotvar.xml Fri Oct 25 07:10:59 2019 -0400 +++ b/mixomics_plotvar.xml Mon Mar 09 11:53:32 2020 -0400 @@ -1,12 +1,12 @@ -<tool id="mixomics_plotvar" name="mixOmics plotVar" version="0.2.0" profile="16.04" workflow_compatible="true"> +<tool id="mixomics_plotvar" name="mixOmics plotVar" version="0.3.0" profile="16.04" workflow_compatible="true"> <description>provides variables representation for (regularized) CCA, (sparse) PLS regression, PCA and (sparse) Regularized generalised CCA</description> - + <requirements> <requirement type="package" version="6.8">bioconductor-mixomics</requirement> <requirement type="package" version="2.0">r-argparse</requirement> </requirements> - + <stdio> <!-- <exit_code range="1:" level="fatal" /> --> </stdio> @@ -23,10 +23,15 @@ </command> <inputs> - <param name="input_rdata" type="data" format="rdata" label="Input RData file from (sparse)(I)PCA, (regularized)CCA, (sparse)PLS(DA) or (sparse)(R)GCCA(DA)"/> + <param name="input_rdata" type="data" format="rdata" + label="Input RData file from (sparse)(I)PCA, (regularized)CCA, (sparse)PLS(DA) or (sparse)(R)GCCA(DA)" + help="This is the RData output file from the block.splsda function." /> <section name="adv" title="Advanced Options" expanded="false"> - <param name="legend" type="boolean" checked="true" truevalue="--legend" falsevalue="" label="Plot legend"/> - <param name="cutoff" type="float" value="0" min="0" max="1" label="Cut-off" /> + <param name="legend" type="boolean" checked="true" truevalue="--legend" falsevalue="" + label="Plot legend" /> + <param name="cutoff" type="float" value="0" min="0" max="1" + label="Cut-off" + help="Only selected variables whose correlation with the first or second axis is greater than Cut-off in absolute value will be plotted." /> </section> </inputs>
--- a/networkVar.xml Fri Oct 25 07:10:59 2019 -0400 +++ b/networkVar.xml Mon Mar 09 11:53:32 2020 -0400 @@ -1,13 +1,13 @@ -<tool id="networkVar" name="networkVar" version="0.2.0" profile="16.04" workflow_compatible="true"> +<tool id="networkVar" name="networkVar" version="0.3.0" profile="16.04" workflow_compatible="true"> - <description></description> - + <description>creates a network between selected variables of datasets and the response variables. In the network, the similarity between two variables is associated with the link between these two variables.</description> + <requirements> <requirement type="package" version="6.8">bioconductor-mixomics</requirement> <requirement type="package" version="1.2">r-igraph</requirement> <requirement type="package" version="2.0">r-argparse</requirement> </requirements> - + <stdio> <!-- <exit_code range="1:" level="fatal" /> --> </stdio> @@ -23,7 +23,7 @@ #if str($var_of_interest_file) !='': --interest_var_file ${var_of_interest_file} #end if - + --responses_var ${select_responses_var} --output_graph ${output_graph} @@ -31,15 +31,26 @@ </command> <inputs> - <param name="mat_similarity_rdata" type="data" format="rdata" label="Input RData file from computeMatSimilarity"/> - <param name="block_splsda_rdata" type="data" format="rdata" label="Input RData file from block.SPLSDA"/> - <param name="var_list_file" type="data" format="tabular" label="Variables list file" /> - + <param name="mat_similarity_rdata" type="data" format="rdata" + label="Input computeMatSimilarity RData file" + help="output RData file from computeMatSimilarity"/> + <param name="block_splsda_rdata" type="data" format="rdata" + label="Input block.SPLSDA RData file" + help="output Rdata file from block.SPLSDA"/> + <param name="var_list_file" type="data" format="tabular" + label="Variables list file" + help="output tabular file from circleCor"/> + <!-- Fichier avec noms de gènes/variables, donné par l'utilisateur --> - <param name="var_of_interest_file" type="data" format="tabular" optional="true" label="Variables of interest (Optional)" /> + <param name="var_of_interest_file" type="data" format="tabular" optional="true" + label="Variables of interest (Optional)" + help="these variables have to belong to datasets that can be superimposed"/> - <param name="responses_var_list" type="data" format="tabular" label="List of response variables"/> - <param name="select_responses_var" type="select" display="checkboxes" multiple="true" label="Response variables"> + <param name="responses_var_list" type="data" format="txt" + label="List of response variables" + help="list of the response variables that will be in the network"/> + <param name="select_responses_var" type="select" display="checkboxes" multiple="true" + label="Response variables"> <!-- <param name="select_responses_var" type="select" multiple="true" label="Response variables"> --> <options from_dataset="responses_var_list"> <column name="value" index="0"/>