@@ -34,9 +34,9 @@ MTBLS79_DatasetExperiment=function(filtered=FALSE) {

 # internal function to generate corrected data from pmp

 prep_from_pmp = function() {

-    library(pmp)

+    # library(pmp)

     # the pmp SE object

-    SE = MTBLS79

+    SE = pmp::MTBLS79

     # convert to DE

     DE = as.DatasetExperiment(SE)

@@ -117,5 +117,5 @@ prep_from_pmp = function() {

     to_filter=colnames(MTBLS79_corrected)[!to_filter] # names of features to remove

     # write the data

-    usethis::use_data(MTBLS79_corrected,to_filter,internal=TRUE,overwrite=TRUE)

+    #usethis::use_data(MTBLS79_corrected,to_filter,internal=TRUE,overwrite=TRUE)

 }

\ No newline at end of file

@@ -5,9 +5,9 @@

 #' M = filter_by_name(mode='include',dimension='variable',

 #'         names=colnames(D$data)[1:10]) + # first 10 features

 #'     filter_smeta(mode='exclude',levels='QC',

-#'         factor_name='class') + # reduce to two group comparison

-#'     confounders_clsq(factor_name = 'class',

-#'         confounding_factors=c('sample_order','batch'))

+#'         factor_name='Class') + # reduce to two group comparison

+#'     confounders_clsq(factor_name = 'Class',

+#'         confounding_factors=c('run_order','Batch'))

 #' M = model_apply(M,D)

 #' @export confounders_clsq

 confounders_clsq = function(alpha=0.05,mtc='fdr',factor_name,

@@ -169,9 +169,9 @@ setMethod(f="model_apply",

 #' M = filter_by_name(mode='include',dimension='variable',

 #'         names=colnames(D$data)[1:10]) + # first 10 features

 #'     filter_smeta(mode='exclude',levels='QC',

-#'         factor_name='class') + # reduce to two group comparison

-#'     confounders_clsq(factor_name = 'class',

-#'         confounding_factors=c('sample_order','batch'))

+#'         factor_name='Class') + # reduce to two group comparison

+#'     confounders_clsq(factor_name = 'Class',

+#'         confounding_factors=c('run_order','Batch'))

 #' M = model_apply(M,D)

 #' C = C=confounders_lsq_barchart(feature_to_plot=1,threshold=15)

 #' chart_plot(C,M[3])

@@ -251,9 +251,9 @@ setMethod(f="chart_plot",

 #' M = filter_by_name(mode='include',dimension='variable',

 #'         names=colnames(D$data)[1:10]) + # first 10 features

 #'     filter_smeta(mode='exclude',levels='QC',

-#'         factor_name='class') + # reduce to two group comparison

-#'     confounders_clsq(factor_name = 'class',

-#'         confounding_factors=c('sample_order','batch'))

+#'         factor_name='Class') + # reduce to two group comparison

+#'     confounders_clsq(factor_name = 'Class',

+#'         confounding_factors=c('run_order','Batch'))

 #' M = model_apply(M,D)

 #' C = C=confounders_lsq_boxplot(threshold=15)

 #' chart_plot(C,M[3])

@@ -6,8 +6,8 @@

 #' D = D[,1:10]

 #'

 #' # convert to numeric for this example

-#' D$sample_meta$sample_order=as.numeric(D$sample_meta$sample_order)

-#' D$sample_meta$sample_rep=as.numeric(D$sample_meta$sample_rep)

+#' D$sample_meta$sample_order=as.numeric(D$sample_meta$run_order)

+#' D$sample_meta$sample_rep=as.numeric(D$sample_meta$Sample_Rep)

 #'

 #' M = corr_coef(factor_names=c('sample_order','sample_rep'))

 #' M = model_apply(M,D)

@@ -1,7 +1,7 @@

 #' @eval get_description('dratio_filter')

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

-#' M = dratio_filter(threshold=20,qc_label='QC',factor_name='class')

+#' M = dratio_filter(threshold=20,qc_label='QC',factor_name='Class')

 #' M = model_apply(M,D)

 #' @export dratio_filter

 dratio_filter = function(threshold=20, qc_label='QC', factor_name, ...) {

@@ -206,7 +206,7 @@ setMethod(f="chart_plot",

 #' @eval get_description('mv_boxplot')

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

-#' C = mv_boxplot(factor_name='class')

+#' C = mv_boxplot(factor_name='Class')

 #' chart_plot(C,D)

 #'

 #' @import struct

@@ -342,7 +342,7 @@ setMethod(f="chart_plot",

 #' @eval get_description('DatasetExperiment_dist')

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

-#' C = DatasetExperiment_dist(factor_name='class')

+#' C = DatasetExperiment_dist(factor_name='Class')

 #' chart_plot(C,D)

 #' @import struct

 #' @export DatasetExperiment_dist

@@ -420,7 +420,7 @@ setMethod(f="chart_plot",

 #' @eval get_description('DatasetExperiment_boxplot')

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

-#' C = DatasetExperiment_boxplot(factor_name='class',number=10,per_class=FALSE)

+#' C = DatasetExperiment_boxplot(factor_name='Class',number=10,per_class=FALSE)

 #' chart_plot(C,D)

 #' @return struct object

 #' @export DatasetExperiment_boxplot

@@ -533,7 +533,7 @@ setMethod(f="chart_plot",

 #' @examples

 #' D1=MTBLS79_DatasetExperiment(filtered=FALSE)

 #' D2=MTBLS79_DatasetExperiment(filtered=TRUE)

-#' C = compare_dist(factor_name='class')

+#' C = compare_dist(factor_name='Class')

 #' chart_plot(C,D1,D2)

 #' @import struct

 #' @export compare_dist

@@ -2,10 +2,10 @@

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

 #' C = feature_profile_array(

-#'     run_order='sample_order',

+#'     run_order='run_order',

 #'     qc_label='QC',

-#'     qc_column='class',

-#'     colour_by='class',

+#'     qc_column='Class',

+#'     colour_by='Class',

 #'     feature_to_plot=1:3,

 #'     nrow=1,

 #'     log=TRUE)

@@ -1,10 +1,10 @@

 #' @eval get_description('feature_profile')

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

-#' C = feature_profile(run_order='sample_order',

+#' C = feature_profile(run_order='run_order',

 #'     qc_label='QC',

-#'     qc_column='class',

-#'     colour_by='class',

+#'     qc_column='Class',

+#'     colour_by='Class',

 #'     feature_to_plot=1)

 #' chart_plot(C,D)

 #' @export feature_profile

@@ -1,7 +1,7 @@

 #' @eval get_description('filter_na_count')

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

-#' M = filter_na_count(threshold=3,factor_name='class')

+#' M = filter_na_count(threshold=3,factor_name='Class')

 #' M = model_apply(M,D)

 #' @export filter_na_count

 filter_na_count = function(threshold,factor_name,...) {

@@ -9,7 +9,7 @@

 #' pred=as.data.frame(pred)

 #'

 #' # apply method

-#' M = fisher_exact(alpha=0.05,mtc='fdr',factor_name='class',factor_pred=pred)

+#' M = fisher_exact(alpha=0.05,mtc='fdr',factor_name='Class',factor_pred=pred)

 #' M=model_apply(M,D)

 #' @import struct

 #' @import stats

@@ -1,7 +1,7 @@

 #' @eval get_description('fold_change')

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

-#' M = fold_change(factor_name='class')

+#' M = fold_change(factor_name='Class')

 #' M = model_apply(M,D)

 #' @import stats

 #' @export fold_change

@@ -2,8 +2,8 @@

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

 #' D=D[,1:10,drop=FALSE]

-#' M = filter_smeta(mode='exclude',levels='QC',factor_name='class') +

-#'     fold_change_int(factor_name=c('class','batch'))

+#' M = filter_smeta(mode='exclude',levels='QC',factor_name='Class') +

+#'     fold_change_int(factor_name=c('Class','Batch'))

 #' M = model_apply(M,D)

 #' @export fold_change_int

 fold_change_int = function(

@@ -4,20 +4,20 @@

 #' D = MTBLS79_DatasetExperiment(filtered=TRUE)

 #'

 #' # normalise, impute and scale then remove QCs

-#' P = pqn_norm(qc_label='QC',factor_name='class') +

+#' P = pqn_norm(qc_label='QC',factor_name='Class') +

 #'     knn_impute(neighbours=5) +

-#'     glog_transform(qc_label='QC',factor_name='class') +

-#'     filter_smeta(mode='exclude',levels='QC',factor_name='class')

+#'     glog_transform(qc_label='QC',factor_name='Class') +

+#'     filter_smeta(mode='exclude',levels='QC',factor_name='Class')

 #' P = model_apply(P,D)

 #' D = predicted(P)

 #'

 #' # forward selection using a PLSDA model

-#' M = forward_selection_by_rank(factor_name='class',

+#' M = forward_selection_by_rank(factor_name='Class',

 #'                              min_no_vars=2,

 #'                              max_no_vars=11,

 #'                              variable_rank=1:2063) *

 #'     (mean_centre() + PLSDA(number_components=1,

-#'                            factor_name='class'))

+#'                            factor_name='Class'))

 #' M = run(M,D,balanced_accuracy())

 #'

 #' @export forward_selection_by_rank

@@ -260,20 +260,20 @@ eval_loess=function(x,X,Y,k=10,p=0.66)

 #' D = MTBLS79_DatasetExperiment(filtered=TRUE)

 #'

 #' # normalise, impute and scale then remove QCs

-#' P = pqn_norm(qc_label='QC',factor_name='class') +

+#' P = pqn_norm(qc_label='QC',factor_name='Class') +

 #'     knn_impute(neighbours=5) +

-#'     glog_transform(qc_label='QC',factor_name='class') +

-#'     filter_smeta(mode='exclude',levels='QC',factor_name='class')

+#'     glog_transform(qc_label='QC',factor_name='Class') +

+#'     filter_smeta(mode='exclude',levels='QC',factor_name='Class')

 #' P = model_apply(P,D)

 #' D = predicted(P)

 #'

 #' # forward selection using a PLSDA model

-#' M = forward_selection_by_rank(factor_name='class',

+#' M = forward_selection_by_rank(factor_name='Class',

 #'                              min_no_vars=2,

 #'                              max_no_vars=11,

 #'                              variable_rank=1:2063) *

 #'     (mean_centre() + PLSDA(number_components=1,

-#'                            factor_name='class'))

+#'                            factor_name='Class'))

 #' M = run(M,D,balanced_accuracy())

 #'

 #' # chart

@@ -3,10 +3,10 @@

 #' @examples

 #' D = MTBLS79_DatasetExperiment()

 #' # some preprocessing

-#' M = pqn_norm(qc_label='QC',factor_name='class') +

+#' M = pqn_norm(qc_label='QC',factor_name='Class') +

 #'     knn_impute() +

-#'     glog_transform(qc_label='QC',factor_name='class') +

-#'     filter_smeta(factor_name='class',levels='QC',mode='exclude')

+#'     glog_transform(qc_label='QC',factor_name='Class') +

+#'     filter_smeta(factor_name='Class',levels='QC',mode='exclude')

 #' M=model_apply(M,D)

 #' D=predicted(M)

 #'

@@ -15,8 +15,8 @@

 #'

 #' # optmise number of components for PLS model

 #' I = grid_search_1d(param_to_optimise='number_components',search_values=1:5,

-#'         model_index=2,factor_name='class') *

-#'         (mean_centre()+PLSDA(factor_name='class'))

+#'         model_index=2,factor_name='Class') *

+#'         (mean_centre()+PLSDA(factor_name='Class'))

 #' I = run(I,D,balanced_accuracy())

 #'

 grid_search_1d = function(param_to_optimise,search_values,model_index,factor_name,max_min='min',...) {

@@ -1,7 +1,7 @@

 #' @eval get_description('rsd_filter')

 #' @export rsd_filter

 #' @examples

-#' M = rsd_filter(factor_name='class')

+#' M = rsd_filter(factor_name='Class')

 #'

 rsd_filter = function(rsd_threshold=20,qc_label='QC',factor_name,...) {

     out=struct::new_struct('rsd_filter',

@@ -1,7 +1,7 @@

 #' @eval get_description('ttest')

 #' @export ttest

 #' @examples

-#' M = ttest(factor_name='class')

+#' M = ttest(factor_name='Class')

 #'

 ttest = function(

     alpha=0.05,

@@ -2,7 +2,7 @@

 #' @return struct object

 #' @export wilcox_test

 #' @examples

-#' M = wilcox_test(factor_name='class')

+#' M = wilcox_test(factor_name='Class')

 #'

 wilcox_test = function(alpha=0.05,mtc='fdr',factor_names,paired=FALSE,paired_factor=character(0),...) {

     out=struct::new_struct('wilcox_test',

@@ -33,6 +33,6 @@ A boxplot to visualise the distribution of values within a subset of features.

 }

 \examples{

 D = MTBLS79_DatasetExperiment()

-C = DatasetExperiment_boxplot(factor_name='class',number=10,per_class=FALSE)

+C = DatasetExperiment_boxplot(factor_name='Class',number=10,per_class=FALSE)

 chart_plot(C,D)

 }

@@ -21,6 +21,6 @@ A histogram to visualise the distribution of values within features.

 }

 \examples{

 D = MTBLS79_DatasetExperiment()

-C = DatasetExperiment_dist(factor_name='class')

+C = DatasetExperiment_dist(factor_name='Class')

 chart_plot(C,D)

 }

@@ -20,6 +20,6 @@ Histograms and boxplots computed across samples and features are used to visuall

 \examples{

 D1=MTBLS79_DatasetExperiment(filtered=FALSE)

 D2=MTBLS79_DatasetExperiment(filtered=TRUE)

-C = compare_dist(factor_name='class')

+C = compare_dist(factor_name='Class')

 chart_plot(C,D1,D2)

 }

@@ -37,8 +37,8 @@ D = MTBLS79_DatasetExperiment()

 M = filter_by_name(mode='include',dimension='variable',

         names=colnames(D$data)[1:10]) + # first 10 features

     filter_smeta(mode='exclude',levels='QC',

-        factor_name='class') + # reduce to two group comparison

-    confounders_clsq(factor_name = 'class',

-        confounding_factors=c('sample_order','batch'))

+        factor_name='Class') + # reduce to two group comparison

+    confounders_clsq(factor_name = 'Class',

+        confounding_factors=c('run_order','Batch'))

 M = model_apply(M,D)

 }

@@ -24,9 +24,9 @@ D = MTBLS79_DatasetExperiment()

 M = filter_by_name(mode='include',dimension='variable',

         names=colnames(D$data)[1:10]) + # first 10 features

     filter_smeta(mode='exclude',levels='QC',

-        factor_name='class') + # reduce to two group comparison

-    confounders_clsq(factor_name = 'class',

-        confounding_factors=c('sample_order','batch'))

+        factor_name='Class') + # reduce to two group comparison

+    confounders_clsq(factor_name = 'Class',

+        confounding_factors=c('run_order','Batch'))

 M = model_apply(M,D)

 C = C=confounders_lsq_barchart(feature_to_plot=1,threshold=15)

 chart_plot(C,M[3])

@@ -22,9 +22,9 @@ D = MTBLS79_DatasetExperiment()

 M = filter_by_name(mode='include',dimension='variable',

         names=colnames(D$data)[1:10]) + # first 10 features

     filter_smeta(mode='exclude',levels='QC',

-        factor_name='class') + # reduce to two group comparison

-    confounders_clsq(factor_name = 'class',

-        confounding_factors=c('sample_order','batch'))

+        factor_name='Class') + # reduce to two group comparison

+    confounders_clsq(factor_name = 'Class',

+        confounding_factors=c('run_order','Batch'))

 M = model_apply(M,D)

 C = C=confounders_lsq_boxplot(threshold=15)

 chart_plot(C,M[3])

@@ -33,8 +33,8 @@ D = MTBLS79_DatasetExperiment(filtered=TRUE)

 D = D[,1:10]

 # convert to numeric for this example

-D$sample_meta$sample_order=as.numeric(D$sample_meta$sample_order)

-D$sample_meta$sample_rep=as.numeric(D$sample_meta$sample_rep)

+D$sample_meta$sample_order=as.numeric(D$sample_meta$run_order)

+D$sample_meta$sample_rep=as.numeric(D$sample_meta$Sample_Rep)

 M = corr_coef(factor_names=c('sample_order','sample_rep'))

 M = model_apply(M,D)

@@ -23,7 +23,7 @@ The dispersion ratio (d-ratio) compares the standard deviation (or non-parametri

 }

 \examples{

 D = MTBLS79_DatasetExperiment()

-M = dratio_filter(threshold=20,qc_label='QC',factor_name='class')

+M = dratio_filter(threshold=20,qc_label='QC',factor_name='Class')

 M = model_apply(M,D)

 }

 \references{

@@ -37,10 +37,10 @@ A plot visualising the change in intensity of a feature with a continuous variab

 }

 \examples{

 D = MTBLS79_DatasetExperiment()

-C = feature_profile(run_order='sample_order',

+C = feature_profile(run_order='run_order',

     qc_label='QC',

-    qc_column='class',

-    colour_by='class',

+    qc_column='Class',

+    colour_by='Class',

     feature_to_plot=1)

 chart_plot(C,D)

 }

@@ -41,10 +41,10 @@ A plot visualising the change in intensity of a feature with a continuous variab

 \examples{

 D = MTBLS79_DatasetExperiment()

 C = feature_profile_array(

-    run_order='sample_order',

+    run_order='run_order',

     qc_label='QC',

-    qc_column='class',

-    colour_by='class',

+    qc_column='Class',

+    colour_by='Class',

     feature_to_plot=1:3,

     nrow=1,

     log=TRUE)

@@ -21,6 +21,6 @@ The number of measured values is counted for each feature, and any feature with

 }

 \examples{

 D = MTBLS79_DatasetExperiment()

-M = filter_na_count(threshold=3,factor_name='class')

+M = filter_na_count(threshold=3,factor_name='Class')

 M = model_apply(M,D)

 }

@@ -33,6 +33,6 @@ pred=lapply(pred,factor,levels=c(TRUE,FALSE))

 pred=as.data.frame(pred)

 # apply method

-M = fisher_exact(alpha=0.05,mtc='fdr',factor_name='class',factor_pred=pred)

+M = fisher_exact(alpha=0.05,mtc='fdr',factor_name='Class',factor_pred=pred)

 M=model_apply(M,D)

 }

@@ -40,7 +40,7 @@ Fold change is the relative change in mean (or non-parametric equivalent) intens

 }

 \examples{

 D = MTBLS79_DatasetExperiment()

-M = fold_change(factor_name='class')

+M = fold_change(factor_name='Class')

 M = model_apply(M,D)

 }

 \references{

@@ -35,8 +35,8 @@ For more than one factor the fold change calculation is extended to include all

 \examples{

 D = MTBLS79_DatasetExperiment()

 D=D[,1:10,drop=FALSE]

-M = filter_smeta(mode='exclude',levels='QC',factor_name='class') +

-    fold_change_int(factor_name=c('class','batch'))

+M = filter_smeta(mode='exclude',levels='QC',factor_name='Class') +

+    fold_change_int(factor_name=c('Class','Batch'))

 M = model_apply(M,D)

 }

 \references{

@@ -37,20 +37,20 @@ A model is trained and performance metric computed by including increasing numbe

 D = MTBLS79_DatasetExperiment(filtered=TRUE)

 # normalise, impute and scale then remove QCs

-P = pqn_norm(qc_label='QC',factor_name='class') +

+P = pqn_norm(qc_label='QC',factor_name='Class') +

     knn_impute(neighbours=5) +

-    glog_transform(qc_label='QC',factor_name='class') +

-    filter_smeta(mode='exclude',levels='QC',factor_name='class')

+    glog_transform(qc_label='QC',factor_name='Class') +

+    filter_smeta(mode='exclude',levels='QC',factor_name='Class')

 P = model_apply(P,D)

 D = predicted(P)

 # forward selection using a PLSDA model

-M = forward_selection_by_rank(factor_name='class',

+M = forward_selection_by_rank(factor_name='Class',

                              min_no_vars=2,

                              max_no_vars=11,

                              variable_rank=1:2063) *

     (mean_centre() + PLSDA(number_components=1,

-                           factor_name='class'))

+                           factor_name='Class'))

 M = run(M,D,balanced_accuracy())

 }

@@ -20,20 +20,20 @@ A line plot for forward selection. The computed model performance metric is plot

 D = MTBLS79_DatasetExperiment(filtered=TRUE)

 # normalise, impute and scale then remove QCs

-P = pqn_norm(qc_label='QC',factor_name='class') +

+P = pqn_norm(qc_label='QC',factor_name='Class') +

     knn_impute(neighbours=5) +

-    glog_transform(qc_label='QC',factor_name='class') +

-    filter_smeta(mode='exclude',levels='QC',factor_name='class')

+    glog_transform(qc_label='QC',factor_name='Class') +

+    filter_smeta(mode='exclude',levels='QC',factor_name='Class')

 P = model_apply(P,D)

 D = predicted(P)

 # forward selection using a PLSDA model

-M = forward_selection_by_rank(factor_name='class',

+M = forward_selection_by_rank(factor_name='Class',

                              min_no_vars=2,

                              max_no_vars=11,

                              variable_rank=1:2063) *

     (mean_centre() + PLSDA(number_components=1,

-                           factor_name='class'))

+                           factor_name='Class'))

 M = run(M,D,balanced_accuracy())

 # chart

@@ -35,10 +35,10 @@ A one dimensional grid search calculates a performance metric for a model at eve

 \examples{

 D = MTBLS79_DatasetExperiment()

 # some preprocessing

-M = pqn_norm(qc_label='QC',factor_name='class') +

+M = pqn_norm(qc_label='QC',factor_name='Class') +

     knn_impute() +

-    glog_transform(qc_label='QC',factor_name='class') +

-    filter_smeta(factor_name='class',levels='QC',mode='exclude')

+    glog_transform(qc_label='QC',factor_name='Class') +

+    filter_smeta(factor_name='Class',levels='QC',mode='exclude')

 M=model_apply(M,D)

 D=predicted(M)

@@ -47,8 +47,8 @@ D=D[,1:10]

 # optmise number of components for PLS model

 I = grid_search_1d(param_to_optimise='number_components',search_values=1:5,

-        model_index=2,factor_name='class') *

-        (mean_centre()+PLSDA(factor_name='class'))

+        model_index=2,factor_name='Class') *

+        (mean_centre()+PLSDA(factor_name='Class'))

 I = run(I,D,balanced_accuracy())

 }

@@ -31,7 +31,7 @@ Boxplots of the number of missing values per sample/feature.

 }

 \examples{

 D = MTBLS79_DatasetExperiment()

-C = mv_boxplot(factor_name='class')

+C = mv_boxplot(factor_name='Class')

 chart_plot(C,D)

 }

@@ -25,7 +25,7 @@ An RSD filter calculates the relative standard deviation (the ratio of the stand

 This object makes use of functionality from the following packages:\itemize{\item{\code{pmp}}}

 }

 \examples{

-M = rsd_filter(factor_name='class')

+M = rsd_filter(factor_name='Class')

 }

 \references{

@@ -36,6 +36,6 @@ A  \code{ttest} object.

 A t-test compares the means of two factor levels. Multiple-test corrected p-values are used to indicate the significance of the computed difference for all features.

 }

 \examples{

-M = ttest(factor_name='class')

+M = ttest(factor_name='Class')

 }

@@ -35,6 +35,6 @@ struct object

 A Mann-Whitney-Wilcoxon signed rank test compares ,the ranks of values in two groups. It is the non-parametric equivalent of a t-test. Multiple test corrected p-values are computed as indicators of significance for each variable/feature.

 }

 \examples{

-M = wilcox_test(factor_name='class')

+M = wilcox_test(factor_name='Class')

 }