added Rproj/package

.gitignore

@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata

DESCRIPTION

@@ -0,0 +1,13 @@
+Package: mmRmeta
+Title: What the Package Does (One Line, Title Case)
+Version: 0.0.0.9000
+Authors@R: 
+    person(given = "First",
+           family = "Last",
+           role = c("aut", "cre"),
+           email = "first.last@example.com")
+Description: What the package does (one paragraph).
+License: What license it uses
+Encoding: UTF-8
+LazyData: true
+RoxygenNote: 6.1.1

NAMESPACE

@@ -0,0 +1,6 @@
+# Generated by roxygen2: do not edit by hand
+
+export(make.kruskal.frame)
+importFrom(dplyr,group_by_)
+importFrom(dplyr,summarize)
+importFrom(magrittr,"%>%")

R/add.expression.R

@@ -3,7 +3,7 @@
 #' @param cancer_data A large list created by multimodalR
 #' @param nested_metadata A list of data frames made by >make.nested.metadata<
 #' @param key Character or integer - Column name or index of unique identifier of nested_metadata, default = "case_id"
-#' @importFrom magittr %>%
+#' @importFrom magrittr %>%
 #' @examples
 #' lungMetaExpression <- add.expression(lungXY, lungMetaExpression)
 #' @return Returns the same list but with data franes containing the expression values in a new colummn.

R/count.column.R

@@ -3,7 +3,7 @@
 #' @param df Data frame, in this case meta data of a corresponding gene
 #' @param factor_one Character - first grouping factor, a column name of the data frame
 #' @param factor_two Character - second grouping factor, a column name of the data frame
-#' @importFrom magittr %>%
+#' @importFrom magrittr %>%
 #' @examples
 #' df <- data.frame(case_id = c(1,2,3,4,5,6), group = c("one","one","two","one","two","three"), primary_diagnosis = c("Squamous cell carcinoma, NOS", "Adenocarcinoma, NOS", "Adenocarcinoma with mixed subtypes", "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS"))
 #' diagnosis_counts <- count.column(df, factor_one = "group", factor_two = "primary_diagnosis")

R/counts.per.group.R

@@ -4,7 +4,7 @@
 #' @param list_df Either a list of data frames or a single data frame
 #' @param first_grouping Character - first grouping variable | Default "case_id"
 #' @param second_grouping Character - second grouping variable | Default  "group""
-#' @importFrom magittr %>%
+#' @importFrom magrittr %>%
 #' @importFrom dplyr group_by_ summarize
 #' @examples
 #' Using a Data Frame

R/reorder.column.R

@@ -4,6 +4,7 @@
 #' @param cancer_data A large list created prior by multimodalR.
 #' @param column Character - column name
 #' @param remove Integer - threshold of counts; any factor level with equal or less counts are discarded
+#' @importFrom magrittr %>%
 #' @examples
 #' lungMeta <- reorder.colums(lungMeta, "primary_diagnosis", 10) #keeps factor levels with >= 10 counts.
 #' @return Returns the same large list with changed column names of the expressionmatrix.

R/subset.metadata.R

@@ -5,20 +5,20 @@
 #' @param key character - Unique identifier, default = "case_id"
 #' @param additional_key needs to be added
 #' @param additional_value needs to be added
-#' @importFrom magittr %>%
+#' @importFrom magrittr %>%
 #' @examples
 #' lungMetaData <- subset.metadata(metadata, lungXY)
 #' @return Returns a data table of the metadata for a primary cancer site (organ).
 
 subset.metadata <- function(meta_data, cancer_data, key = "case_id", additional_key = NULL, additional_value = NULL) {
-  if(!is.character(meta_data[[key]]) {
-    meta_data[[key]] <- as.character(meta_data[[key]]) #transform factor to character
+  if(!is.character(meta_data[[key]])) {
+  meta_data[[key]] <- as.character(meta_data[[key]]) #transform factor to character
   }
   correctRows <- numeric()                             #empty vector to be filled later
   caseNames <- names(cancer_data$Expressionmatrix)     #vector of case_id from expressionmatrix
   for (cases in caseNames) {                           #match case_id of the vector with case_id of metadata
-    matchedRow <- grep(cases, meta_data[[key]]
-    correctRows <- c(correctRows, matchedRow)
+  matchedRow <- grep(cases, meta_data[[key]])
+  correctRows <- c(correctRows, matchedRow)
   }
   meta_data <- meta_data[c(correctRows),]              #subset by machted case_id
   if(!is.null(additional_key)) {

R/summary.plots.R

@@ -1,6 +1,12 @@
 
 summary.plots <- function(meta_data, file_name = "summary", environment = FALSE, width = 12, height =8, ... ) {
   #first Graph
+  data.summary <- function(x) { #function to calculate median + sd for violin plots
+  mu <- mean(x)
+  sigma1 <- mu-sd(x)
+  sigma2 <- mu+sd(x)
+  return(c(y=mu, ymin=sigma1, ymax=sigma2))
+}
   ### 1. ###################### Boxplots(gender, age) ~ status
   firstGraph <- ggplot(organ_metadata, aes(x = gender, y = age/365)) +
     geom_boxplot(data = organ_metadata, aes(color = status)) +

R/use.prop.test.R

@@ -3,7 +3,10 @@
 #' @param df_count A data frame, made by >count.column<
 #' @param eval_first_column Boolean, should the first column be evaluated as well?
 #' @examples
-#' df <- data.frame(case_id = c(1,2,3,4,5,6), group = c("one","one","two","one","two","three"), primary_diagnosis = c("Squamous cell carcinoma, NOS", "Adenocarcinoma, NOS", "Adenocarcinoma with mixed subtypes", "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS"))
+#' df <- data.frame(case_id = c(1,2,3,4,5,6),
+#'                  group = c("one","one","two","one","two","three"),
+#'                  primary_diagnosis = c("Squamous cell carcinoma, NOS", "Adenocarcinoma, NOS", "Adenocarcinoma with mixed subtypes",
+#'                                        "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS"))
 #' diagnosis_counts <- count.column(df, factor_one = "group", factor_two = "primary_diagnosis")
 #' pValues <- use.prop.test(diagnosis_counts, FALSE)
 #' @return Returns a vector of p.values obtained by the prop.test

example/statistical.test.R

@@ -12,6 +12,17 @@ x1 <- pairwise.wilcox.test(lungMetaExpression[[x[1]]]$expression, g = lungMetaEx
 x2 <- x1 %>% tibble::rownames_to_column('name') %>% filter_all(. , any_vars(. < 0.05))  %>% tibble::column_to_rownames('name')   #filter and keep rownames          
 x3 <- data.frame(t(x2)) %>%  tibble::rownames_to_column('name') %>% filter_all(., any_vars(. < 0.05)) %>% tibble::column_to_rownames('name') #transpose to filter out rows without significant values, cant filter out colums that easy     
 
-wilcox_test(Value ~ factor(Group), data=data[data$Group==1|data$Group==2,], distribution="exact")
+wilcox_test(Value ~ factor(Group), data=data[data$Group==1|data$Group==2,])
+xWil <- wilcox.test(lungMetaExpression[[x[1]]]$expression ~ lungMetaExpression[[x[1]]]$primary_diagnosis == c("Adenocarcinoma, NOS" , "Squamous cell carninoma, NOS"))
+#for every row: do wilcox test if p.value is <0.05 and not the same name ... furthermore try coin::wilcox_test
 
-#for every row: do wilcox test if p.value is <0.05 and not the same name
+rownames(x3)
+
+#what if i subset expression values byy diagnosis factor
+primaryDSpread <- lungMetaExpression$AL671277.1 %>% select(. , c(case_id, primary_diagnosis, expression)) %>% tidyr::spread(., primary_diagnosis, expression)
+wilcox.test(primaryD$`Papillary adenocarcinoma, NOS`, primaryD$`Papillary adenocarcinoma, NOS`)
+primaryD <- lungMetaExpression$AL671277.1 %>% select(. , primary_diagnosis, expression)
+firstTest <- filter(primaryD, primary_diagnosis %in% c("Adenocarcinoma, NOS", "Squamous cell carcinoma, NOS")) #filter if they are named like this
+
+coin::wilcox_test(formula = expression ~ primary_diagnosis, data = firstTest)
+# FUNKTIONIERT