Merge pull request #93 from jasenfinch/devel

v0.15.2

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: metabolyseR
 Title: Methods for Pre-Treatment, Data Mining and Correlation Analyses of Metabolomics Data
-Version: 0.15.1
+Version: 0.15.2
 Authors@R: person("Jasen", "Finch", email = "jsf9@aber.ac.uk", role = c("aut", "cre"))
 Description: A tool kit for pre-treatment, modelling, feature selection and correlation analyses of metabolomics data.
 URL: https://jasenfinch.github.io/metabolyseR/

NEWS.md

@@ -1,3 +1,9 @@
+# metabolyseR 0.15.2
+
+* Added the argument `refactor` to the method [`transformTICnorm()`](https://jasenfinch.github.io/metabolyseR/reference/transform.html) to enable the feature intensities of total ion count (TIC) normalised data to be refactored back to a range consistent with the original data by multiplying the normalised values by the median TIC.
+
+* Removed the permutation cap when the `perm` argument of [`randomForest()`](https://jasenfinch.github.io/metabolyseR/reference/randomForest.html) is less than the total number of permutations possible.
+
 # metabolyseR 0.15.1
 
 * The class occupancy methods now throw a helpful error message if no features are available on which to compute class occupancy.

R/randomForest-permute.R

@@ -1,4 +1,3 @@
-nPerm <- function(n,k){choose(n,k) * factorial(k)}
 
 #' @importFrom stats runif
 
@@ -35,10 +34,6 @@ permutations <- function(x,cls,rf,n,type){
     i <- factor(i)
   }
 
-  if (nPerm(length(i),length(unique(i))) < n) {
-    n <- nPerm(length(i),length(unique(i)))
-  }
-
   permutation_results <- future_map(1:n,
                                     ~permute(x = x,
                                              cls = cls,

R/transform.R

@@ -3,6 +3,7 @@
 #' @description Methods for data scaling, transformation and normalisation.
 #' @param d S4 object of class `AnalysisData` 
 #' @param add value to add prior to transformation
+#' @param refactor TRUE/FALSE. Re-factor the normalised intensity values to a range consistent with the raw values by multiplying by the median sample TIC.
 #' @return An S4 object of class `AnalysisData` containing the transformed data.
 #' @details 
 #' Prior to downstream analyses, metabolomics data often require transformation to fulfil the assumptions of a particular statistical/data mining technique.
@@ -237,19 +238,28 @@ setMethod('transformSQRT',signature = 'AnalysisData',
 #' @rdname transform
 #' @export
 
-setGeneric("transformTICnorm", function(d)
+setGeneric("transformTICnorm", function(d,refactor = TRUE)
   standardGeneric("transformTICnorm"))
 
 #' @rdname transform
 
 setMethod('transformTICnorm',signature = 'AnalysisData',
-          function(d){
-            dat(d) <- d %>% 
-              dat() %>%
-              base::split(seq_len(nrow(.))) %>%
-              map(~{. / sum(.)}) %>%
-              bind_rows() %>%
+          function(d, refactor = TRUE){
+
+            raw_data <- dat(d)
+
+            tics <- rowSums(raw_data)
+
+            normalised_data <- raw_data %>% 
+              {. / tics}
+
+            if (refactor){
+              normalised_data <- normalised_data * median(tics)
+            }
+
+            dat(d) <- normalised_data %>% 
               as_tibble()
+
             return(d)
           }
 )

vignettes/quick_start.Rmd

@@ -70,7 +70,8 @@ A total ion count normalisation will also be applied.
 ```{r pre_treat}
 d <- d %>%
   occupancyMaximum(cls = 'day', occupancy = 2/3) %>%
-  transformTICnorm()
+  transformTICnorm() %>% 
+  transformLog10()
 ```
 
 ```{r pre_treat_result}