@@ -2,7 +2,7 @@ Package: omada

 Type: Package

 Title: Machine learning tools for automated transcriptome 

     clustering analysis

-Version: 1.5.0

+Version: 1.5.1

 Authors@R: person("Sokratis", "Kariotis", role = c("aut", "cre"),

                         email = "[email protected]",

                         comment = c(ORCID = "0000-0001-9993-6017"))

@@ -42,7 +42,7 @@ Suggests:

     testthat

 License: GPL-3

 Encoding: UTF-8

-RoxygenNote: 7.2.0

+RoxygenNote: 7.2.1

 VignetteBuilder: knitr

 biocViews: Software, Clustering, RNASeq, GeneExpression

 LazyData: true

@@ -26,6 +26,7 @@ S3method(get_partition_agreement_scores,clusterAnalysis)

 S3method(get_partition_agreement_scores,methodSelection)

 S3method(get_sample_memberships,clusterAnalysis)

 S3method(get_signature_feature_coefs,clusterAnalysis)

+S3method(get_top_coefficients,geneSignature)

 S3method(get_vote_frequencies_k,clusterVoting)

 S3method(plot_average_stabilities,featureSelection)

 S3method(plot_cluster_voting,clusterAnalysis)

@@ -33,7 +34,7 @@ S3method(plot_feature_selection,clusterAnalysis)

 S3method(plot_partition_agreement,clusterAnalysis)

 S3method(plot_partition_agreement,methodSelection)

 S3method(plot_signature_feature,clusterAnalysis)

-S3method(plot_top30percent_coefficients,geneSignature)

+S3method(plot_top_coefficients,geneSignature)

 S3method(plot_vote_frequencies,clusterVoting)

 export(clusterVoting)

 export(clusteringMethodSelection)

@@ -66,6 +67,7 @@ export(get_optimal_stability_score)

 export(get_partition_agreement_scores)

 export(get_sample_memberships)

 export(get_signature_feature_coefs)

+export(get_top_coefficients)

 export(get_vote_frequencies_k)

 export(omada)

 export(optimalClustering)

@@ -75,7 +77,7 @@ export(plot_cluster_voting)

 export(plot_feature_selection)

 export(plot_partition_agreement)

 export(plot_signature_feature)

-export(plot_top30percent_coefficients)

+export(plot_top_coefficients)

 export(plot_vote_frequencies)

 import(ggplot2)

 importFrom(clValid,clusters)

deleted file mode 100644

@@ -1,118 +0,0 @@

-#' Generating the feature/gene signature per cluster

-#'

-#' @param data A dataframe, where columns are features and rows are data points.

-#'

-#' @param memberships A dataframe with column "id" (same samples ids as above)

-#' and column "membership" containing the cluster membership of each sample.

-#' The memberships must be strings

-#'

-#' @return An object of class "geneSignature" containing a list of LASSO

-#' (regression analysis) coefficients of each gene and a plot of the highest

-#' 30% of coefficients per cluster.

-#'

-#' @export

-#'

-#' @examples

-#' geneSignatures(toy_genes, toy_gene_memberships)

-#'

-#' @import ggplot2

-#' @importFrom dplyr across filter %>% left_join

-

-

-geneSignatures <- function(data, memberships) {

-

-    # utils::globalVariables("where", add=FALSE)

-

-    data <- as.data.frame(data)

-    rnames <- row.names(data)

-    data$id <- rnames

-

-    # if(!("id" %in% colnames(data)))

-    # {

-    #     id <- paste0("s", 1:dim(data)[1])

-    #     data <- cbind(id,data)

-    # }

-

-    # Composite data

-    data <- left_join(memberships, data)

-    data$id <- NULL

-    row.names(data) <- rnames

-

-    # Cluster names

-    clusters <- unique(memberships$membership)

-

-    # Running cross-validation Lasso to find optimal lambda value

-    data.matrix <- as.matrix(data[,2:dim(data)[2]])

-    cv_model <- glmnet::cv.glmnet(data.matrix(data.matrix), data$membership,

-                                  family = "multinomial", alpha = 1)

-

-    # Optimal lambda value (minimizing test MSE)

-    optimal_lambda <- cv_model$lambda.min

-

-    # Running optimal lasso model

-    optimal_lasso <- glmnet::glmnet(data.matrix(data.matrix), data$membership,

-                            family = "multinomial",

-                            alpha = 1, lambda = optimal_lambda)

-

-    # Extract coefficients for minimized test MSE)

-    Coefficients <- stats::coef(optimal_lasso, s = "min")

-

-    # Formatting coefficient dataframe per cluster

-    ns <- names(Coefficients)

-    ni <- 1

-    coef.dataset <- data.frame(matrix(ncol= 0, nrow=dim(data)[2]-1))

-

-    for(i in Coefficients) {

-        temp <- as.data.frame(as.matrix(i)) %>% `colnames<-`(ns[ni])

-        temp$Cluster <- ns[ni]

-        temp <- temp[-1,]

-        temp$Cluster <- NULL

-        coef.dataset <- cbind(coef.dataset, temp)

-        ni <- ni + 1

-    }

-

-    # Calculating mean coefficient per feature across clusters

-    coef.dataset <- filter(coef.dataset,

-                           rowSums(abs(across(where(is.numeric))))!=0)

-    coef.dataset$means <- rowMeans(coef.dataset)

-    coef.dataset <- coef.dataset[with(coef.dataset, order(abs(means),

-                                                          decreasing = TRUE)),]

-    coef.dataset$features <- rownames(coef.dataset)

-    coef.dataset$means <- NULL #addition

-

-    # retain top 30%

-    coef.dataset <- coef.dataset[seq_len(round(dim(coef.dataset)[1]*0.3,

-                                               digits = 0)),]

-    coef.data.melt <- reshape::melt(coef.dataset)

-

-    coef.30perc <- ggplot2::ggplot(data = coef.data.melt,

-                                   aes(x = features, y = value,

-                                                     fill = variable)) +

-        geom_bar(stat = "identity") +

-        theme(axis.title.x=element_blank(),

-              axis.text.x = element_text(angle=45, vjust = 1, hjust = 1,

-                                         size = 12),

-              plot.title = element_text(hjust = 0.5),

-              axis.title.y = element_text(size = 15),

-              legend.position = "none") +

-        geom_hline(yintercept=0, linetype="dashed", color = "red") +

-        labs(title = "Coefficients") +

-        facet_grid(variable~.)

-

-    geneSignature <-

-        function(coefficient.dataset = coef.dataset,

-                 top30percent.coefficients = coef.30perc){

-

-            gs <- list(coefficient.dataset = coefficient.dataset,

-                       top30percent.coefficients = top30percent.coefficients)

-

-            ## Set the name for the class

-            class(gs) <- "geneSignature"

-

-            return(gs)

-        }

-

-    gene.signature <- geneSignature()

-

-    return(gene.signature)

-}

deleted file mode 100644

@@ -1,12 +0,0 @@

-#' Plot of the highest 30 percentage of coefficients per cluster

-#'

-#' @param object An object of class "geneSignature"

-#' @return A plot of the highest 30 percentage of coefficients per cluster

-#' @export

-get_top30percent_coefficients <- function(object) {

-    UseMethod("get_top30percent_coefficients")

-}

-#' @export

-get_top30percent_coefficients.geneSignature <- function(object) {

-    object$top30percent.coefficients

-}

@@ -86,7 +86,7 @@ omada <- function(data, method.upper.k = 5) {

     # data$id <- rownames(data)

     gene.signature.results <- geneSignatures(data, memberships)

     gs.matrix <- get_coefficient_dataset(gene.signature.results)

-    gs.plot <- plot_top30percent_coefficients(gene.signature.results)

+    gs.plot <- plot_top_coefficients(gene.signature.results)

     clusterAnalysis <- function(partition.agreement.scores=pa.df,

                                 partition.agreement.plot=pa.plot,

deleted file mode 100644

@@ -1,16 +0,0 @@

-#' Plot of the highest 30 percentage of coefficients per cluster

-#'

-#' @param object An object of class "geneSignature"

-#' @return A plot of the highest 30 percentage of coefficients per cluster

-#' @export

-#'

-#' @examples

-#' gs.object <- geneSignatures(toy_genes, toy_gene_memberships)

-#' plot_top30percent_coefficients(gs.object)

-plot_top30percent_coefficients <- function(object) {

-    UseMethod("plot_top30percent_coefficients")

-}

-#' @export

-plot_top30percent_coefficients.geneSignature <- function(object) {

-    object$top30percent.coefficients

-}

@@ -1,5 +1,5 @@

 % Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/gene_singatures.R

+% Please edit documentation in R/gene_signatures.R

 \name{geneSignatures}

 \alias{geneSignatures}

 \title{Generating the feature/gene signature per cluster}

deleted file mode 100644

@@ -1,17 +0,0 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/get_top30percent_coefficients.R

-\name{get_top30percent_coefficients}

-\alias{get_top30percent_coefficients}

-\title{Plot of the highest 30 percentage of coefficients per cluster}

-\usage{

-get_top30percent_coefficients(object)

-}

-\arguments{

-\item{object}{An object of class "geneSignature"}

-}

-\value{

-A plot of the highest 30 percentage of coefficients per cluster

-}

-\description{

-Plot of the highest 30 percentage of coefficients per cluster

-}

deleted file mode 100644

@@ -1,21 +0,0 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/plot_top30percent_coefficients.R

-\name{plot_top30percent_coefficients}

-\alias{plot_top30percent_coefficients}

-\title{Plot of the highest 30 percentage of coefficients per cluster}

-\usage{

-plot_top30percent_coefficients(object)

-}

-\arguments{

-\item{object}{An object of class "geneSignature"}

-}

-\value{

-A plot of the highest 30 percentage of coefficients per cluster

-}

-\description{

-Plot of the highest 30 percentage of coefficients per cluster

-}

-\examples{

-gs.object <- geneSignatures(toy_genes, toy_gene_memberships)

-plot_top30percent_coefficients(gs.object)

-}

@@ -165,6 +165,6 @@ signature.results <- geneSignatures(toy_genes, toy_gene_memberships)

 signature.dataframe <- get_coefficient_dataset(signature.results)

 # Plot results

-plot_top30percent_coefficients(signature.results)

+plot_top_coefficients(signature.results)

 ```