# HG changeset patch # User eschen42 # Date 1571926883 14400 # Node ID c18040b6e8b92b724905aba9358d09b83e9e881c # Parent 38f509903a0b6d3400977a5152443183cb1f144b "planemo upload for repository https://github.com/HegemanLab/w4mclassfilter_galaxy_wrapper/tree/master commit 1a5dd14c3697516bc55950bd6e46c978af7c19cf" diff -r 38f509903a0b -r c18040b6e8b9 w4mclassfilter.xml --- a/w4mclassfilter.xml Tue Oct 01 16:57:58 2019 -0400 +++ b/w4mclassfilter.xml Thu Oct 24 10:21:23 2019 -0400 @@ -1,10 +1,10 @@ - + Filter W4m data by values or metadata r-base r-batch - w4mclassfilter + w4mclassfilter + help="data matrix, with sample names in first row and feature names in first column" /> + help="sample metadata, with one row per sample" /> + help="variable metadata, with one row per feature" /> + help="name of the column in sample metadata that has the values to be tested against the 'Names of sample-classes' input parameter"> @@ -42,7 +44,7 @@ + help="comma-separated names (or regular expressions to match names) of sample-classes to filter in or out (Leave empty to match no names.)"> @@ -69,17 +71,17 @@ + help="'wild-cards' - use '*' and '?' to match class names;    'regular-expressions' - use regular expressions to match class names"> + help="'filter-out' - exclude only the named sample-classes;    'filter-in' - include only the named sample-classes"> + help="comma-separated filters, each specified as 'variableMetadataColumnName:min:max' (leave empty for no filtering, as described in help below.)"> @@ -91,17 +93,37 @@ + help="'none' - do not transform data;    'log2' - log base 2 of data;    'log10' - log base 10 of data;    in all cases, negative and missing values are imputed to zero"> + help="'zero' - replace missing values with zero;    'center' - replace missing values with feature-median;    'none' - perform no imputation"> + + + + + + + + + + + + + + + + + + @@ -552,7 +574,7 @@ **Tool updates** -See the **NEWS** section at the bottom of this page +See https://github.com/HegemanLab/w4mclassfilter_galaxy_wrapper#news --------------------------------------------------- @@ -599,7 +621,8 @@ - Samples that are missing from either sampleMetadata or dataMatrix are eliminated. - Features that are missing from either variableMetadata or dataMatrix are eliminated. - Features and samples that have zero variance are eliminated. -- Samples and features are sorted alphabetically in rows and columns of dataMatrix and in rows of variableMetadata and sampleMetadata. +- Samples and features have consistent order in `variableMetadata`, `sampleMetadata`, and `dataMatrix`. + (The column for sorting `variableMetadata` or `sampleMetadata` may be specified.) - The names of the first columns of variableMetadata and sampleMetadata are set respectively to "variableMetadata" and "sampleMetadata". - If desired, the values in the dataMatrix may be log-transformed. - If desired, each missing value in dataMatrix is replaced with zero or the median value observed for the corresponding feature. @@ -638,7 +661,7 @@ ---------- Data matrix file - | variable x sample **dataMatrix** (tabular separated values) file of the numeric data matrix, with . as decimal, and NA for missing values; the table must not contain metadata apart from row and column names; the row and column names must be identical, respectively, to the rownames of the sample metadata file and variable metadata file + | feature x sample **dataMatrix** (tabular separated values) file of the numeric data matrix, with period-character ('.') as decimal, and 'NA' for missing values; the table must not contain metadata apart from the required row and column names; the row and column names must be identical (with regard to both content or order) to the respective rownames of the sample metadata file and variable metadata file | Sample metadata file @@ -683,6 +706,13 @@ | '``center``' - For each feature, negative and missing values are imputed to the median of other values. | +Column that specifies order for samples (default = 'sampleMetadata') + | name of the column in **sampleMetadata** that is used to sort samples; only letters, digits, periods, and underscores are permitted. + | + +Column that specifies order for features (default = 'variableMetadata') + | name of the column in **variableMetadata** that is used to sort features; only letters, digits, periods, and underscores are permitted. + | ------------ Output files @@ -833,6 +863,10 @@ +---------------------------------------------+-------------------------------+ | Missing-value imputation | center | +---------------------------------------------+-------------------------------+ +| Sample-sort column | sampleMetadata | ++---------------------------------------------+-------------------------------+ +| Feature-sort column | variableMetadata | ++---------------------------------------------+-------------------------------+ **Expected outputs** @@ -872,6 +906,10 @@ +---------------------------------------------+-----------------------------------+ | Missing-value imputation | zero | +---------------------------------------------+-----------------------------------+ +| Sample-sort column | sampleMetadata | ++---------------------------------------------+-----------------------------------+ +| Feature-sort column | variableMetadata | ++---------------------------------------------+-----------------------------------+ **Expected outputs** diff -r 38f509903a0b -r c18040b6e8b9 w4mclassfilter_wrapper.R --- a/w4mclassfilter_wrapper.R Tue Oct 01 16:57:58 2019 -0400 +++ b/w4mclassfilter_wrapper.R Thu Oct 24 10:21:23 2019 -0400 @@ -104,6 +104,9 @@ classnameColumn <- as.character(argVc["classnameColumn"]) samplenameColumn <- as.character(argVc["samplenameColumn"]) +order_smpl <- as.character(argVc["order_smpl"]) +order_vrbl <- as.character(argVc["order_vrbl"]) + variable_range_filter <- as.character(argVc["variable_range_filter"]) variable_range_filter <- strsplit(x = variable_range_filter, split = ",", fixed = TRUE)[[1]] @@ -160,6 +163,8 @@ , include = inclusive , class_column = classnameColumn , samplename_column = samplenameColumn +, order_vrbl = order_vrbl +, order_smpl = order_smpl , variable_range_filter = variable_range_filter , failure_action = my_print , data_imputation = my_transformation_and_imputation