@@ -25,3 +25,5 @@ vignettes/*.pdf

 *.knit.md

 .Rproj.user

 inst/doc

+celda.Rproj

+.DS_Store

@@ -9,7 +9,9 @@ Depends:

     R (>= 3.2.2)

 Imports:

     gtools,

-    entropy

+    entropy,

+    RColorBrewer,

+    pheatmap

 Suggests:

 	testthat,

 	knitr,

@@ -20,6 +22,6 @@ VignetteBuilder:

 License: MIT

 Encoding: UTF-8

 LazyData: true

-RoxygenNote: 5.0.1

+RoxygenNote: 6.0.1

 BugReports:

-	https://github.com/definitelysean/celda/issues

\ No newline at end of file

+	https://github.com/definitelysean/celda/issues

@@ -1,9 +1,10 @@

-# Generated by roxygen2: do not edit by hand

-

-export(cCG.calcLLFromVariables)

-export(cCG.generateCells)

-export(celda)

-export(celda_CG)

-export(geneCluster)

-export(generateCells_gene_clustering)

-import(foreach)

+# Generated by roxygen2: do not edit by hand

+

+export(cCG.calcLLFromVariables)

+export(cCG.generateCells)

+export(celda)

+export(celda_CG)

+export(celda_heatmap)

+export(geneCluster)

+export(generateCells_gene_clustering)

+import(foreach)

new file mode 100644

@@ -0,0 +1,42 @@

+##ToDo:  Need to (1)scale the row height accordingly; (2) pick more contradictory color;

+##       (3)Aanotation need to change and; (4)  what else need to do?

+ #' plot the heatmap of the counts data

+ #' @param counts the counts matrix 

+ #' @param K The number of clusters being considered  (Question1)or: Total number of cell populations??

+ #' @param z A numeric vector of cluster assignments

+ #' @param L Total number of transcriptional states

+ #' @param col vector of colors used in heatmap

+ #' @param cluster_gene boolean values determining if genes should be clustered

+ #' @param cluster_cell boolean values determining if cells should be clustered

+ #' @param annotation_gene data frame that specifies the annotations for genes 

+ #' @param annotation_cell data frame that specifies the annotations for cells 

+ #' @example TODO

+ #' @export 

+  celda_heatmap <- function(counts, K, z, L, col="YlOrBr", cluster_gene = TRUE, cluster_cell = FALSE, 

+                            annotation_gene, annotation_cell) {

+    ## Set row name to counts matrix 

+    if(is.null(rownames(counts))){

+      rownames(counts) <- 1:nrow(counts)

+    } 

+    else if(is.null(colnames(counts))) {

+      colnames(counts) <- 1:ncol(counts)

+    }

+    ##-- Set cell annotation    # need to do 

+    #annotaion_cell <- data.frame(pseudoanno = sample(c("Tcell","BCell"), nrow(counts), replace = T))   # ToDo: need to change 

+    ##-- Set gene annotation

+    #annotation_gene <- data.frame(pseudo=sample(1:6,nrow(counts),replace=T))

+    

+    ## Set color 

+    col.pal <- colorRampPalette(RColorBrewer::brewer.pal(n = 9, name =col))(100)  # ToDo: need to be more flexible or fixed to a better color list

+    pheatmap::pheatmap(counts, 

+                       color = col.pal,

+                       cluster_rows = cluster_gene,

+                       cluster_cols = cluster_cell,

+                       annotation_row = annotation_gene,

+                       annotation_col = annotation_cell,

+                       cutree_rows = L,   # Question1: not sure about this

+                       cutree_cols = L,   # Question2: not sure about this either 

+                       fontsize = 6.5,

+                       fontsize_col = 5

+                       )

+  }

\ No newline at end of file

@@ -1,31 +1,30 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/celda_G.R

-\name{calcGibbsProb}

-\alias{calcGibbsProb}

-\title{Calculate Log Likelihood For Single Set of Cluster Assignments (Gene Clustering)}

-\usage{

-calcGibbsProb(ix, r, z, k, a, b, g)

-}

-\arguments{

-\item{ix}{The index in z corresponding to the cell currently being considered during Gibbs sampling}

-

-\item{r}{A numeric count matrix}

-

-\item{z}{A numeric vector of cluster assignments}

-

-\item{k}{The number of clusters being considered}

-

-\item{a}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

-

-\item{b}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

-

-\item{g}{The number of cell states ("topics")}

-}

-\description{

-This function calculates the log-likelihood of a cell's membership to each possible clusters,

-given the cluster assignment for all other cells.

-}

-\examples{

-TODO 

-}

-

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/celda_G.R

+\name{calcGibbsProb}

+\alias{calcGibbsProb}

+\title{Calculate Log Likelihood For Single Set of Cluster Assignments (Gene Clustering)}

+\usage{

+calcGibbsProb(ix, r, z, k, a, b, g)

+}

+\arguments{

+\item{ix}{The index in z corresponding to the cell currently being considered during Gibbs sampling}

+

+\item{r}{A numeric count matrix}

+

+\item{z}{A numeric vector of cluster assignments}

+

+\item{k}{The number of clusters being considered}

+

+\item{a}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

+

+\item{b}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

+

+\item{g}{The number of cell states ("topics")}

+}

+\description{

+This function calculates the log-likelihood of a cell's membership to each possible clusters,

+given the cluster assignment for all other cells.

+}

+\examples{

+TODO 

+}

@@ -1,31 +1,30 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/celda_G.R

-\name{calcLL_gene_clustering}

-\alias{calcLL_gene_clustering}

-\title{Calculate Log Likelihood For A Set of Gene Clusterings (Gene Clustering)}

-\usage{

-calcLL_gene_clustering(counts, z, k, alpha, beta, gamma)

-}

-\arguments{

-\item{counts}{A numeric count matrix}

-

-\item{z}{A numeric vector of cluster assignments}

-

-\item{k}{The number of clusters being considered}

-

-\item{alpha}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

-

-\item{beta}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

-

-\item{gamma}{The number of cell states ("topics")}

-}

-\description{

-This function calculates the log likelihood of each clustering of genes generated

-over multiple iterations of Gibbs sampling.

-}

-\examples{

-TODO

-}

-\keyword{likelihood}

-\keyword{log}

-

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/celda_G.R

+\name{calcLL_gene_clustering}

+\alias{calcLL_gene_clustering}

+\title{Calculate Log Likelihood For A Set of Gene Clusterings (Gene Clustering)}

+\usage{

+calcLL_gene_clustering(counts, z, k, alpha, beta, gamma)

+}

+\arguments{

+\item{counts}{A numeric count matrix}

+

+\item{z}{A numeric vector of cluster assignments}

+

+\item{k}{The number of clusters being considered}

+

+\item{alpha}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

+

+\item{beta}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

+

+\item{gamma}{The number of cell states ("topics")}

+}

+\description{

+This function calculates the log likelihood of each clustering of genes generated

+over multiple iterations of Gibbs sampling.

+}

+\examples{

+TODO

+}

+\keyword{likelihood}

+\keyword{log}

@@ -1,33 +1,32 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/celda_G.R

-\name{calcLLlite_gene_clustering}

-\alias{calcLLlite_gene_clustering}

-\title{Calculate Log Likelihood For Single Set of Cluster Assignments (Gene Clustering)}

-\usage{

-calcLLlite_gene_clustering(ix, counts, z, k, alpha, beta, gamma)

-}

-\arguments{

-\item{ix}{The index of the cell being assigned a cluster during the current iteration of Gibbs sampling}

-

-\item{counts}{A numeric count matrix}

-

-\item{z}{A numeric vector of cluster assignments}

-

-\item{k}{The number of clusters being considered}

-

-\item{alpha}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

-

-\item{beta}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

-

-\item{gamma}{The number of cell states ("topics")}

-}

-\description{

-This function calculates the log-likelihood of a given set of cluster assigments for the samples

-represented in the provided count matrix.

-}

-\examples{

-TODO

-}

-\keyword{likelihood}

-\keyword{log}

-

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/celda_G.R

+\name{calcLLlite_gene_clustering}

+\alias{calcLLlite_gene_clustering}

+\title{Calculate Log Likelihood For Single Set of Cluster Assignments (Gene Clustering)}

+\usage{

+calcLLlite_gene_clustering(ix, counts, z, k, alpha, beta, gamma)

+}

+\arguments{

+\item{ix}{The index of the cell being assigned a cluster during the current iteration of Gibbs sampling}

+

+\item{counts}{A numeric count matrix}

+

+\item{z}{A numeric vector of cluster assignments}

+

+\item{k}{The number of clusters being considered}

+

+\item{alpha}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

+

+\item{beta}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

+

+\item{gamma}{The number of cell states ("topics")}

+}

+\description{

+This function calculates the log-likelihood of a given set of cluster assigments for the samples

+represented in the provided count matrix.

+}

+\examples{

+TODO

+}

+\keyword{likelihood}

+\keyword{log}

new file mode 100644

@@ -0,0 +1,31 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/celda_heatmap.R

+\name{celda_heatmap}

+\alias{celda_heatmap}

+\title{plot the heatmap of the counts data}

+\usage{

+celda_heatmap(counts, K, z, L, col = "YlOrBr", cluster_gene = TRUE,

+  cluster_cell = FALSE, annotation_gene, annotation_cell)

+}

+\arguments{

+\item{counts}{the counts matrix}

+

+\item{K}{The number of clusters being considered  (Question1)or: Total number of cell populations??}

+

+\item{z}{A numeric vector of cluster assignments}

+

+\item{L}{Total number of transcriptional states}

+

+\item{col}{vector of colors used in heatmap}

+

+\item{cluster_gene}{boolean values determining if genes should be clustered}

+

+\item{cluster_cell}{boolean values determining if cells should be clustered}

+

+\item{annotation_gene}{data frame that specifies the annotations for genes}

+

+\item{annotation_cell}{data frame that specifies the annotations for cells}

+}

+\description{

+plot the heatmap of the counts data

+}

@@ -1,45 +1,44 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/celda_G.R

-\name{geneCluster}

-\alias{geneCluster}

-\title{Cluster Genes from Single Cell Sequencing Data}

-\usage{

-geneCluster(counts, k, a = 1, b = 1, g = 1, max.iter = 25,

-  min.cell = 5, seed = 12345, best = TRUE, kick = TRUE,

-  converge = 1e-05)

-}

-\arguments{

-\item{counts}{A numeric count matrix}

-

-\item{k}{The number of clusters to generate}

-

-\item{a}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

-

-\item{b}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

-

-\item{g}{Number of cell states ("topics")}

-

-\item{max.iter}{Maximum iterations of Gibbs sampling to perform. Defaults to 25.}

-

-\item{min.cell}{Desired minimum number of cells per cluster}

-

-\item{seed}{Parameter to set.seed() for random number generation}

-

-\item{best}{Whether to return the cluster assignment with the highest log-likelihood. Defaults to TRUE. Returns last generated cluster assignment when FALSE.}

-

-\item{kick}{Whether to randomize cluster assignments when a cluster has fewer than min.cell cells assigned to it during Gibbs sampling. (TODO param currently unused?)}

-

-\item{converge}{Threshold at which to consider the Markov chain converged}

-}

-\description{

-geneCluster provides cluster assignments for all genes in a provided single-cell 

-sequencing count matrix, using the celda Bayesian hierarchical model.

-}

-\examples{

-TODO

-}

-\keyword{LDA}

-\keyword{clustering}

-\keyword{gene}

-\keyword{gibbs}

-

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/celda_G.R

+\name{geneCluster}

+\alias{geneCluster}

+\title{Cluster Genes from Single Cell Sequencing Data}

+\usage{

+geneCluster(counts, k, a = 1, b = 1, g = 1, max.iter = 25,

+  min.cell = 5, seed = 12345, best = TRUE, kick = TRUE,

+  converge = 1e-05)

+}

+\arguments{

+\item{counts}{A numeric count matrix}

+

+\item{k}{The number of clusters to generate}

+

+\item{a}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

+

+\item{b}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

+

+\item{g}{Number of cell states ("topics")}

+

+\item{max.iter}{Maximum iterations of Gibbs sampling to perform. Defaults to 25.}

+

+\item{min.cell}{Desired minimum number of cells per cluster}

+

+\item{seed}{Parameter to set.seed() for random number generation}

+

+\item{best}{Whether to return the cluster assignment with the highest log-likelihood. Defaults to TRUE. Returns last generated cluster assignment when FALSE.}

+

+\item{kick}{Whether to randomize cluster assignments when a cluster has fewer than min.cell cells assigned to it during Gibbs sampling. (TODO param currently unused?)}

+

+\item{converge}{Threshold at which to consider the Markov chain converged}

+}

+\description{

+geneCluster provides cluster assignments for all genes in a provided single-cell 

+sequencing count matrix, using the celda Bayesian hierarchical model.

+}

+\examples{

+TODO

+}

+\keyword{LDA}

+\keyword{clustering}

+\keyword{gene}

+\keyword{gibbs}

@@ -1,32 +1,31 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/celda_G.R

-\name{generateCells_gene_clustering}

-\alias{generateCells_gene_clustering}

-\title{Generate Count Data}

-\usage{

-generateCells_gene_clustering(C = 100, N.Range = c(500, 5000), G = 1000,

-  k = 5, a = 1, b = 1, g = 1, seed = 12345)

-}

-\arguments{

-\item{C}{The number of cells}

-

-\item{N.Range}{The range of counts each gene should have}

-

-\item{G}{The number of genes for which to simulate counts}

-

-\item{a}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

-

-\item{b}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

-

-\item{g}{The number of cell states ("topics")' @param k The number of gene clusters to simulate from}

-

-\item{seed}{Parameter to set.seed() for random number generation}

-}

-\description{

-Generate a simulated count matrix, based off a generative distribution whose 

-parameters can be provided by the user.

-}

-\examples{

-TODO

-}

-

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/celda_G.R

+\name{generateCells_gene_clustering}

+\alias{generateCells_gene_clustering}

+\title{Generate Count Data}

+\usage{

+generateCells_gene_clustering(C = 100, N.Range = c(500, 5000), G = 1000,

+  k = 5, a = 1, b = 1, g = 1, seed = 12345)

+}

+\arguments{

+\item{C}{The number of cells}

+

+\item{N.Range}{The range of counts each gene should have}

+

+\item{G}{The number of genes for which to simulate counts}

+

+\item{a}{Vector of non-zero concentration parameters for sample <-> cluster assignment Dirichlet distribution}

+

+\item{b}{Vector of non-zero concentration parameters for cluster <-> gene assignment Dirichlet distribution}

+

+\item{g}{The number of cell states ("topics")' @param k The number of gene clusters to simulate from}

+

+\item{seed}{Parameter to set.seed() for random number generation}

+}

+\description{

+Generate a simulated count matrix, based off a generative distribution whose 

+parameters can be provided by the user.

+}

+\examples{

+TODO

+}

@@ -1,24 +1,23 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/celda_G.R

-\name{sample.ll}

-\alias{sample.ll}

-\title{Sample log-likelihood probabilities}

-\usage{

-sample.ll(ll.probs)

-}

-\arguments{

-\item{counts}{A numeric count matrix}

-}

-\value{

-A single integer in 1:k corresponding to a cluster assignment

-}

-\description{

-Given a set of log-likelihoods for cluster membership, return a single cluster assignment.

-}

-\examples{

-TODO

-}

-\keyword{likelihood}

-\keyword{log}

-\keyword{sample}

-

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/celda_G.R

+\name{sample.ll}

+\alias{sample.ll}

+\title{Sample log-likelihood probabilities}

+\usage{

+sample.ll(ll.probs)

+}

+\arguments{

+\item{counts}{A numeric count matrix}

+}

+\value{

+A single integer in 1:k corresponding to a cluster assignment

+}

+\description{

+Given a set of log-likelihoods for cluster membership, return a single cluster assignment.

+}

+\examples{

+TODO

+}

+\keyword{likelihood}

+\keyword{log}

+\keyword{sample}