Mercurial > repos > eschen42 > w4mcorcov
changeset 9:06c51af11531 draft
planemo upload for repository https://github.com/HegemanLab/w4mcorcov_galaxy_wrapper/tree/master commit fda7ea61f0a082fd0c28730e471e66c92aaa04d0
| author | eschen42 |
|---|---|
| date | Fri, 10 Aug 2018 11:15:31 -0400 |
| parents | 342570ad880c |
| children | 9a52306991b3 |
| files | w4mcorcov.xml w4mcorcov_lib.R w4mcorcov_salience.R w4mcorcov_wrapper.R |
| diffstat | 4 files changed, 101 insertions(+), 93 deletions(-) [+] |
line wrap: on
line diff
--- a/w4mcorcov.xml Sat Aug 04 17:43:16 2018 -0400 +++ b/w4mcorcov.xml Fri Aug 10 11:15:31 2018 -0400 @@ -1,4 +1,4 @@ -<tool id="w4mcorcov" name="OPLS-DA_Contrasts" version="0.98.12"> +<tool id="w4mcorcov" name="OPLS-DA_Contrasts" version="0.98.13"> <description>OPLS-DA Contrasts of Univariate Results</description> <macros> <xml name="paramPairSigFeatOnly"> @@ -20,8 +20,14 @@ </xml> </macros> <requirements> + <!-- + <requirement type="package" version="3.4.1">r-base</requirement> + <requirement type="package" version="1.1_4">r-batch</requirement> + <requirement type="package" version="1.2.14">bioconductor-ropls</requirement> + --> + <requirement type="package">r-base</requirement> <requirement type="package">r-batch</requirement> - <requirement type="package">bioconductor-ropls</requirement> + <requirement type="package" version="1.10.0">bioconductor-ropls</requirement> </requirements> <command detect_errors="aggressive"><![CDATA[ Rscript '$__tool_directory__/w4mcorcov_wrapper.R' @@ -54,13 +60,12 @@ ]]></command> <inputs> - <param name="dataMatrix_in" type="data" format="tabular" label="Data matrix file" - help="Features x samples (tabular data - decimal: '.'; missing: NA; mode: numerical; separator: tab character)" /> - <param name="sampleMetadata_in" type="data" format="tabular" label="Sample metadata file" - help="Samples x metadata (tabular data - decimal: '.'; missing: NA; mode: character or numerical; separator: tab character)" /> - <param name="variableMetadata_in" type="data" format="tabular" - label="Variable metadata file (ideally from Univariate)" - help="Features x metadata (tabular data - decimal: '.'; missing: NA; mode: character or numerical; separator: tab character)" /> + <param name="dataMatrix_in" format="tabular" label="Data matrix file" type="data" + help="variables ✖ samples" /> + <param name="sampleMetadata_in" format="tabular" label="Sample metadata file" type="data" + help="sample metadata, one row per sample" /> + <param name="variableMetadata_in" format="tabular" label="Variable metadata file (ideally from Univariate)" + type="data" help="variable metadata, one row per variable" /> <param name="facC" type="text" label="Factor of interest" help="REQUIRED - The name of the column of sampleMetadata corresponding to the qualitative variable used to define the contrasts. Except when the 'Univariate Significance-test' is set to 'none', this also must be a portion of the column names in the variableMetadata file."/> @@ -149,7 +154,7 @@ * Wiklund_2008 covariance * Galindo_Prieto_2014 VIP for predictive components, VIP[4,p] * Galindo_Prieto_2014 VIP for orthogonal components, VIP[4,o] - * (When filtering on significance of univariate tests) Significance of test of null hypothesis that there is no difference between the two classes, i.e, the pair-wise test. + * When filtering on significance of univariate tests,significance of test of null hypothesis that there is no difference between the two classes, i.e, the pair-wise test. --> <data name="contrast_corcov" format="tabular" label="${tool.name}_${variableMetadata_in.name}_corcov" /> <!-- @@ -424,7 +429,7 @@ It must be stressed that there may be no *single* definitive computational approach to select features that are reliable biomarkers, especially from a small number of samples or experiments. A few possible choices are: - picking features with maximum loadings along the projection parallel to the predictor (loadp), -- examining extreme values on S-PLOTs (for which covariance is linearly related to loadp), +- examining extreme values on S-PLOTs - examining "variable importance in projection VIP for OPLS-DA" (Galindo-Prieto *et al.* 2014), and - examining a feature's "selectivity ratio" (Rajalahti *et al.*, 2009). @@ -600,15 +605,15 @@ **Input files** - +-------------------------------------------------------------------------------------------------------------------+ - | Download from URL | - +===================================================================================================================+ - | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/input_dataMatrix.tsv | - +-------------------------------------------------------------------------------------------------------------------+ - | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/input_sampleMetadata.tsv | - +-------------------------------------------------------------------------------------------------------------------+ - | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/input_variableMetadata.tsv | - +-------------------------------------------------------------------------------------------------------------------+ + +-----------------------------------------------------------------------------------------------------------------------------------------------+ + | Download from URL | + +===============================================================================================================================================+ + | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/input_dataMatrix.tsv | + +-----------------------------------------------------------------------------------------------------------------------------------------------+ + | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/input_sampleMetadata.tsv | + +-----------------------------------------------------------------------------------------------------------------------------------------------+ + | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/input_variableMetadata.tsv | + +-----------------------------------------------------------------------------------------------------------------------------------------------+ **Example 1:** Include in the analysis only features identified as pair-wise significant in the Univariate test. @@ -627,80 +632,80 @@ +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ | Number of features having extreme loadings | ALL | +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_corcov.tsv | + | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_corcov.tsv | +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_salience.tsv | + | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_salience.tsv | +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_detail.pdf | + | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_detail.pdf | +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ **Example 2:** Include in the analysis only features identified as overall-significant in the Univariate test. Note that this even includes these features in contrasts where they were not determined to be pair-wise significant in the Univariate test. Thus, more features are included than in Example 1. - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Input Parameter or Result | Value | - +============================================+========================================================================================================================================+ - | Factor of interest | k10 | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Univariate Significance-Test | kruskal | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Retain only pairwise-significant features | No | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Levels of interest | ``*`` | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Level-name matching | use wild cards for matching level-names | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Number of features having extreme loadings | 5 | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_corcov_all.tsv | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_salience_all.tsv | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_detail_all.pdf | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Input Parameter or Result | Value | + +============================================+============================================================================================================================================+ + | Factor of interest | k10 | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Univariate Significance-Test | kruskal | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Retain only pairwise-significant features | No | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Levels of interest | ``*`` | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Level-name matching | use wild cards for matching level-names | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Number of features having extreme loadings | 5 | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_corcov_all.tsv | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_salience_all.tsv | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ + | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_detail_all.pdf | + +--------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------+ **Example 3:** Include all features in the analysis without regard to Univariate testing. Univariate testing is not even a pre-requisite to using the tool when 'none' is selected for the test. Thus, more features are included than in Example 2. - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Input Parameter or Result | Value | - +============================================+========================================================================================================================================+ - | Factor of interest | k10 | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Univariate Significance-Test | none | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Levels of interest | k[12],k[3-4] | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Level-name matching | use regular expressions for matching level-names | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Number of features having extreme loadings | 0 | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_corcov_global.tsv | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_salience_global.tsv | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_detail_global.pdf | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Input Parameter or Result | Value | + +============================================+==============================================================================================================================================+ + | Factor of interest | k10 | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Univariate Significance-Test | none | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Levels of interest | k[12],k[3-4] | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Level-name matching | use regular expressions for matching level-names | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Number of features having extreme loadings | 0 | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_corcov_global.tsv | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_salience_global.tsv | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_detail_global.pdf | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ **Example 4:** Analysis of a two-level factor (including all features). This suppresses the contrasts of "each factor vs. the aggregate of all the others". - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Input Parameter or Result | Value | - +============================================+========================================================================================================================================+ - | Factor of interest | lohi | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Univariate Significance-Test | none | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Levels of interest | low,high | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Level-name matching | use regular expressions for matching level-names | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Number of features having extreme loadings | 3 | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_corcov_lohi.tsv | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_salience_lohi.tsv | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ - | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/test-data/expected_contrast_detail_lohi.pdf | - +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Input Parameter or Result | Value | + +============================================+==============================================================================================================================================+ + | Factor of interest | lohi | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Univariate Significance-Test | none | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Levels of interest | low,high | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Level-name matching | use regular expressions for matching level-names | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Number of features having extreme loadings | 3 | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Output primary table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_corcov_lohi.tsv | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Output salience table | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_salience_lohi.tsv | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ + | Output figures PDF | https://raw.githubusercontent.com/HegemanLab/w4mcorcov_galaxy_wrapper/master/tools/w4mcorcov/test-data/expected_contrast_detail_lohi.pdf | + +--------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------+ Trademarks
--- a/w4mcorcov_lib.R Sat Aug 04 17:43:16 2018 -0400 +++ b/w4mcorcov_lib.R Fri Aug 10 11:15:31 2018 -0400 @@ -1,3 +1,12 @@ suppressMessages(library(batch)) # suppressMessages(library(foreach)) suppressMessages(library(ropls)) +suppressMessages(library(methods)) + +# cat("Installed packages:",stderr()) +# write.table((installed.packages(.Library, priority = "high"))[, c(1,3:5)], stderr()) +# cat("Loaded packages:",stderr()) +# write(.packages(), stderr()) + +print(sessionInfo()) +
--- a/w4mcorcov_salience.R Sat Aug 04 17:43:16 2018 -0400 +++ b/w4mcorcov_salience.R Fri Aug 10 11:15:31 2018 -0400 @@ -61,8 +61,8 @@ ) rcvOfFeatureBySampleClassLevel[is.nan(rcvOfFeatureBySampleClassLevel)] <- max(9999,max(rcvOfFeatureBySampleClassLevel, na.rm = TRUE)) - # "For each feature, 'select max(median_feature_intensity) from feature'." - maxApplyMedianOfFeatureBySampleClassLevel <- sapply( + # "For each feature, 'select max(max_feature_intensity) from feature'." + maxApplyMaxOfFeatureBySampleClassLevel <- sapply( X = 1:n_features , FUN = function(i) { match( @@ -84,19 +84,19 @@ # the feature name feature = features # the name (or factor-level) of the class-level with the highest median intensity for the feature - , max_level = medianOfFeatureBySampleClassLevel[maxApplyMedianOfFeatureBySampleClassLevel,1] + , max_level = medianOfFeatureBySampleClassLevel[maxApplyMaxOfFeatureBySampleClassLevel,1] # the median intensity for the feature and the level max_level , max_median = sapply( X = 1:n_features , FUN = function(i) { - maxOfFeatureBySampleClassLevel[maxApplyMedianOfFeatureBySampleClassLevel[i], 1 + i] + maxOfFeatureBySampleClassLevel[maxApplyMaxOfFeatureBySampleClassLevel[i], 1 + i] } ) # the coefficient of variation (expressed as a proportion) for the intensity for the feature and the level max_level , max_rcv = sapply( X = 1:n_features , FUN = function(i) { - rcvOfFeatureBySampleClassLevel[maxApplyMedianOfFeatureBySampleClassLevel[i], i] + rcvOfFeatureBySampleClassLevel[maxApplyMaxOfFeatureBySampleClassLevel[i], i] } ) # the mean of the medians of intensity for all class-levels for the feature
--- a/w4mcorcov_wrapper.R Sat Aug 04 17:43:16 2018 -0400 +++ b/w4mcorcov_wrapper.R Fri Aug 10 11:15:31 2018 -0400 @@ -55,12 +55,6 @@ source(paste(script.dir, "w4mcorcov_salience.R", sep="/")) source(paste(script.dir, "w4mcorcov_calc.R", sep="/")) source(paste(script.dir, "w4mcorcov_output.R", sep="/")) -#source("w4mcorcov_lib.R") -#source("w4mcorcov_util.R") -#source("w4mcorcov_input.R") -#source("w4mcorcov_salience.R") -#source("w4mcorcov_calc.R") -#source("w4mcorcov_output.R") ## log file ##---------