TCC Bug fix and Extensions

README.md

@@ -1,20 +1,28 @@
 TCC
 ===
 
-R package for tag count comparison
 
+Title
+-----
 
-Differential expression analysis for tag count data with robust normalization strategies
-----------------------------------------------------------------------------------------
+TCC: Differential expression analysis for tag count data with robust normalization strategies
 
-This package provides functions for performing differential expression 
-analysis using differentially expressed gene elimination strategy. 
-A simple unified interface is provided which encapsulates functions 
-to calculate normalization factors and estimate differentially 
-expressed genes defined in edgeR, baySeq, and DESeq packages.   
-The appropriate combination provided by TCC allows a more robust 
-and accurate estimation performed easily than directly using original packages. 
-Functions to produce simulation data under various conditions and to plot the data are also provided.
+Description
+-----------
+
+This package provides a series of functions for performing
+differential expression analysis from RNA-seq count data using robust
+normalization strategy (called DEGES). The basic idea of DEGES is that
+potential differentially expressed genes or transcripts (DEGs) among
+compared samples should be removed before data normalization to obtain
+a well-ranked gene list where true DEGs are top-ranked and non-DEGs are
+bottom ranked. This can be done by performing a multi-step normalization
+strategy (called DEGES for DEG elimination strategy). A major
+characteristic of TCC is to provide the robust normalization methods for
+several kinds of count data (two-group with or without replicates,
+multi-group/multi-factor, and so on) by virtue of the use of combinations
+of functions in other sophisticated packages (especially edgeR, DESeq,
+and baySeq).
 
 Documentation
 -------------
@@ -26,13 +34,14 @@ in addition to the documents included in the software package.
 Development versions
 --------------------
 
-The development version is now on the github repository at https://github.com/tomoakin/TCC
+The development version is now on the github repository
+at https://github.com/kohijiri/huaying.asagao
 
 Releases
 --------
 
-Release of this software is made through CRAN at http://cran.r-project.org/web/packages/TCC/
-
+Release of this software is made through CRAN at
+http://www.bioconductor.org/packages/release/bioc/html/TCC.html
 
 No warranty
 -----------
@@ -53,4 +62,4 @@ A copy of GPL-2 is accompanied in this directory in a file named COPYING.
 Authors
 -------
 
-Sun Jianqiang, Tomoaki Nishiyama, Kentaro Shimizu, and Koji Kadota
+Jianqiang Sun, Tomoaki Nishiyama, Kentaro Shimizu, and Koji Kadota

TCC/DESCRIPTION

@@ -1,19 +1,28 @@
 Package: TCC
 Type: Package
 Title: TCC: Differential expression analysis for tag count data with
-        robust normalization strategies
-Version: 1.0.0
-Date: 2013-01-10
-Author: Sun Jianqiang, Tomoaki Nishiyama, Kentaro Shimizu, and Koji Kadota
-Maintainer: Tomoaki Nishiyama <tomoakin@staff.kanazawa-u.ac.jp>
-Description: This package provides functions for performing differential expression analysis 
- using differentially expressed gene elimination strategy. A simple unified interface is 
- provided which encapsulates functions to calculate normalization factors and estimate 
- differentially expressed genes defined in edgeR, baySeq, and DESeq packages. 
- The appropriate combination provided by TCC allows a more robust and accurate estimation 
- performed easily than directly using original packages.
- Functions to produce simulation data under various conditions and to plot the data are also provided. 
-Depends: R (>= 2.15), edgeR, baySeq, DESeq, ROC, methods
+    robust normalization strategies
+Version: 1.1.99
+Author: Jianqiang Sun, Tomoaki Nishiyama, Kentaro Shimizu, and Koji Kadota
+Maintainer: Jianqiang Sun <wukong@bi.a.u-tokyo.ac.jp>, 
+    Tomoaki Nishiyama <tomoakin@staff.kanazawa-u.ac.jp> 
+Description: This package provides a series of functions for performing
+    differential expression analysis from RNA-seq count data using robust
+    normalization strategy (called DEGES). The basic idea of DEGES is that
+    potential differentially expressed genes or transcripts (DEGs) among
+    compared samples should be removed before data normalization to obtain
+    a well-ranked gene list where true DEGs are top-ranked and non-DEGs are
+    bottom ranked. This can be done by performing a multi-step normalization
+    strategy (called DEGES for DEG elimination strategy). A major
+    characteristic of TCC is to provide the robust normalization methods for
+    several kinds of count data (two-group with or without replicates, 
+    multi-group/multi-factor, and so on) by virtue of the use of combinations
+    of functions in other sophisticated packages (especially edgeR, DESeq, 
+    and baySeq).
+Depends: R (>= 2.15), methods, DESeq, edgeR, baySeq, ROC
+Imports: EBSeq, samr
+Suggests: RUnit, BiocGenerics
+Enhances: snow
+biocViews: HighThroughputSequencing, DifferentialExpression, RNAseq
 License: GPL-2
 Copyright: Authors listed above
-URL: http://www.iu.a.u-tokyo.ac.jp/~kadota/TCC

TCC/NAMESPACE

@@ -2,25 +2,33 @@ import(ROC)
 import(DESeq)
 import(baySeq)
 import(edgeR)
+import(EBSeq)
+import(samr)
 
-# Export TCC class.
 exportClasses(
     "TCC" 
 )
 
-# Export the public methods in TCC package.
 export(
+  show,
+  names,
+  length,
+  "[",
+  TCC,
   calcAUCValue,
   calcNormFactors,
   do_TbT,
   estimateDE,
   exactTestafterTbT,
   filterLowCountGenes,
-  generateSimulationData,
+  simulateReadCounts,
   getNormalizedData,
   getResult,
   MAplot,
   NBsample,
   plotFCPseudocolor,
-  plot.TCC
+  plot.TCC,
+  WAD,
+  ROKU
 )
+

TCC/NEWS

@@ -0,0 +1,43 @@
+CHANGES IN VERSION 1.2.0
+------------------------
+
+NEW FEATURES
+
+    o This package was released as a Bioconductor package (previously CRAN).
+    o WAD method for identifying DEGs was added.
+    o ROKU method for identifying tissue-specific genes was added.
+    o 'increment' argument of 'calcNormFactor' function was added.
+
+
+SIGNIFICANT USER-VISIBLE CHANGES
+
+    o 'replicates' field of TCC class was deleted.
+
+
+
+
+CHANGES IN VERSION 1.1.3
+------------------------
+
+SIGNIFICANT USER-VISIBLE CHANGES
+
+    o 'generateSimulationData' function was renamed to 'simulateReadCount'.
+
+    o 'names' field of TCC class was changed to 'gene_id'.
+
+    o 'hypoData' was reduced to a smaller data set.
+
+    o 'hypoData_mg' was created. This is the simulation dataset which consists
+    of 1,000 genes and 9 samples.
+
+
+
+
+CHANGES IN VERSION 1.0.0
+------------------------
+
+SIGNIFICANT USER-VISIBLE CHANGES
+
+    o 'TCC' class was implemented as a R5 reference class. Wrapper functions
+    with functional programming semantics were proviede.
+

TCC/R/ROKU.R

@@ -0,0 +1,123 @@
+.outval <- function(y, upper.limit) {
+    if (all(is.na(y)))
+        y <- rep(0, length = length(y))
+    z <- y[!is.na(y)]
+
+    N <- length(z)
+    fN <- floor(N * upper.limit) + 1
+
+    z.sorted <- sort(z)
+    z.ordered <- order(z)
+
+    df <- matrix(c(rep(1:fN, times = c(fN:1)), j = sequence(fN:1)),
+                 ncol = 2, byrow = FALSE)
+    n <- N - df[, 2] - df[, 1] + 2
+    s <- N - n
+    f <- rep(0, length = N)
+
+    if (sd(z) != 0) {
+        ssd <- apply(df, 1, function(d, w = z.sorted, N = N) {
+           return(sd(w[d[1]:(N + 1 - d[2])]))
+        }, z.sorted, N)
+        u <- n * log(ssd * sqrt((n - 1) / n)) + 
+             sqrt(2) * s * lfactorial(n) / n
+        min.u <- min(u)
+        d <- t(df[u == min.u, ])[1:2]
+        if (d[1] > 1)
+            f[z.ordered[1:(d[1] - 1)]] <- -1
+        if (d[2] > 1)
+            f[z.ordered[(N + 1 - d[2] + 1):N]] <- 1
+    } 
+    return(replace(y, !is.na(y), f))
+}
+
+
+.tbw <- function(y) {
+    y <- y[!is.na(y)]
+    y.m <- median(y)
+    y.u <- (y - y.m) / (5 * median(abs(y - y.m)) + 1e-04)
+    y.w <- rep(0, length(y))
+    y.i <- abs(y.u) <= 1
+    y.w[y.i] <- ((1 - y.u^2)^2)[y.i]
+    y.b <- sum(y.w * y) / sum(y.w)
+}
+
+.entvalmod <- function(y) {
+    y <- y[!is.na(y)]
+    l <- length(y)
+    y <- y[y != 0]
+    if (is.na(sd(y))) {
+        return (0)
+    } else if (sum(y) <= 0 || sd(y) == 0) {
+        return (log2(l))
+    } else {
+        y.m <- median(y)
+        y.u <- (y - y.m) / (5 * median(abs(y - y.m)) + 1e-04)
+        y.w <- rep(0, length(y))
+        y.i <- abs(y.u) <= 1
+        y.w[y.i] <- ((1 - y.u^2)^2)[y.i]
+        y.b <- sum(y.w * y) / sum(y.w)
+        p <- abs(y - y.b)
+        p <- p / sum(p)
+        e <- - sum(p * log2(p))
+        if (is.na(e))
+            e <- 0
+        return (e)
+    }
+}
+
+.entval <- function(y) {
+    y <- y[!is.na(y)]
+    l <- length(y)
+    y <- y[y != 0]
+    if (is.na(sd(y))) {
+        return (0)
+    } else if (sum(y) <= 0 || sd(y) == 0) {
+        return (log2(l))
+    } else {
+        p <- y / sum(y)
+        e <- - sum(p * log2(p))
+        if (is.na(e))
+            e <- 0
+        return (e)
+    }
+}
+
+ROKU <- function(data, upper.limit = 0.25, sort = FALSE) {
+    rs <- NULL
+    if (is.vector(data)) {
+        data <- t(matrix(data))
+    } else {
+        data <- as.matrix(data)
+    }
+    rs$outliers <- t(apply(t(scale(t(data))), 1,
+                          function (y, upper.limit = upper.limit) {
+                          .outval(y, upper.limit = upper.limit)
+                     }, upper.limit))
+    rs$H <- apply(data, 1, .entval)
+    rs$modH <- apply(data, 1, .entvalmod)
+    rs$rank <- rank(rs$modH)
+    rs$Tbw <- apply(data, 1, .tbw)
+    if (!is.null(colnames(data))) {
+        l <- colnames(data)
+    } else {
+        l <- paste("tissue", 1:ncol(data), sep = "_")
+    }
+    if (!is.null(rownames(data))) {
+        r <- rownames(data)
+    } else {
+        r <- 1:nrow(data)
+    }
+    colnames(rs$outliers) <- l
+    rownames(rs$outliers) <- r
+    if (sort) {
+        reindex <- order(rs$rank)
+        rs$outliers <- rs$outliers[reindex, ]
+        rs$H <- rs$H[reindex]
+        rs$modH <- rs$modH[reindex]
+        rs$rank <- rs$rank[reindex]
+        rs$Tbw <- rs$Tbw[reindex]
+    }
+    return (rs)
+}
+