@@ -1,8 +1,8 @@

 Package: OncoSimulR

 Type: Package

 Title: Forward Genetic Simulation of Cancer Progresion with Epistasis 

-Version: 2.3.4

-Date: 2016-06-24

+Version: 2.3.5

+Date: 2016-06-25

 Authors@R: c(person("Ramon", "Diaz-Uriarte", role = c("aut", "cre"),

 		     email = "rdiaz02@gmail.com"),

 	      person("Mark", "Taylor", role = "ctb", email = "ningkiling@gmail.com"))

@@ -8,7 +8,8 @@ export("oncoSimulPop", "oncoSimulIndiv", "samplePop",

        "evalGenotypeMut", "evalGenotypeFitAndMut",

        "evalAllGenotypesFitAndMut",

        "rfitness",

-       "plotFitnessLandscape"

+       "plotFitnessLandscape",

+       "to_Magellan"

        )

 S3method(plot, oncosimul)

@@ -24,7 +25,7 @@ S3method(plot, evalAllGenotypesMut)

 import(ggplot2)

 importFrom("ggrepel", geom_text_repel, geom_label_repel)

-

+importFrom("utils", "read.table", "write.table")

 importFrom("stats", "rnorm")

 importFrom("data.table", rbindlist, .rbind.data.table) 

 importFrom(Rcpp, evalCpp)

@@ -54,53 +54,54 @@ plotFitnessLandscape <- function(x, show_labels = TRUE,

     ## get the string representation, etc. And this is for use

     ## with OncoSimul.

-    ## FIXME: passing fitness as a 2 column data frame

-    

-    if( (inherits(x, "genotype_fitness_matrix")) ||

-        ( (is.matrix(x) || is.data.frame(x)) && (ncol(x) > 2) ) ) {

-        ## Why this? We go back and forth twice. We need both things. We

-        ## could construct the afe below by appropriately pasting the

-        ## columns names

-        afe <- evalAllGenotypes(allFitnessEffects(

-            epistasis = from_genotype_fitness(x)),

-            order = FALSE, addwt = TRUE, max = max_num_genotypes)

-        ## Might not be needed with the proper gfm object (so gmf <- x)

-        ## but is needed if arbitrary matrices.

-        gfm <- allGenotypes_to_matrix(afe) 

-    } else if(inherits(x, "fitnessEffects")) {

-        if(!is.null(x$orderEffects) )

-            stop("We cannot yet deal with order effects")

-        afe <- evalAllGenotypes(x,

-                                order = FALSE,

-                                addwt = TRUE, max = max_num_genotypes)

-        gfm <- allGenotypes_to_matrix(afe)

-    } else if( (inherits(x, "evalAllGenotypes")) ||

-               (inherits(x, "evalAllGenotypesMut"))) {

-        if(any(grepl(">", x[, 1], fixed = TRUE)))

-            stop("We cannot deal with order effects yet.")

-        x <- x[, c(1, 2)]

-        if(x[1, "Genotype"] != "WT") {

-            ## Yes, because we expect this present below

-            x <- rbind(data.frame(Genotype = "WT",

-                                  Fitness = 1,

-                                  stringsAsFactors = FALSE),

-                       x)

-        }

-        afe <- x

-        ## in case we pass an evalAllgenotypesfitandmut

-        gfm <- allGenotypes_to_matrix(afe)

-    } else if(is.data.frame(x)) {

-        ## Assume a two-column data frame of genotypes as character

-        ## vectors and fitness

-        if(colnames(x)[2] != "Fitness")

-            stop("We cannot guess what you are passing here") 

-        afe <- evalAllGenotypes(allFitnessEffects(genotFitness = x),

-                                order = FALSE, addwt = TRUE,

-                                max = max_num_genotypes)

-        gfm <- allGenotypes_to_matrix(afe)

-    } else {

-       stop("We cannot guess what you are passing here") 

-    }

+

+    tfm <- to_Fitness_Matrix(x, max_num_genotypes = max_num_genotypes)

+

+    ## if( (inherits(x, "genotype_fitness_matrix")) ||

+    ##     ( (is.matrix(x) || is.data.frame(x)) && (ncol(x) > 2) ) ) {

+    ##     ## Why this? We go back and forth twice. We need both things. We

+    ##     ## could construct the afe below by appropriately pasting the

+    ##     ## columns names

+    ##     afe <- evalAllGenotypes(allFitnessEffects(

+    ##         epistasis = from_genotype_fitness(x)),

+    ##         order = FALSE, addwt = TRUE, max = max_num_genotypes)

+    ##     ## Might not be needed with the proper gfm object (so gmf <- x)

+    ##     ## but is needed if arbitrary matrices.

+    ##     gfm <- allGenotypes_to_matrix(afe) 

+    ## } else if(inherits(x, "fitnessEffects")) {

+    ##     if(!is.null(x$orderEffects) )

+    ##         stop("We cannot yet deal with order effects")

+    ##     afe <- evalAllGenotypes(x,

+    ##                             order = FALSE,

+    ##                             addwt = TRUE, max = max_num_genotypes)

+    ##     gfm <- allGenotypes_to_matrix(afe)

+    ## } else if( (inherits(x, "evalAllGenotypes")) ||

+    ##            (inherits(x, "evalAllGenotypesMut"))) {

+    ##     if(any(grepl(">", x[, 1], fixed = TRUE)))

+    ##         stop("We cannot deal with order effects yet.")

+    ##     x <- x[, c(1, 2)]

+    ##     if(x[1, "Genotype"] != "WT") {

+    ##         ## Yes, because we expect this present below

+    ##         x <- rbind(data.frame(Genotype = "WT",

+    ##                               Fitness = 1,

+    ##                               stringsAsFactors = FALSE),

+    ##                    x)

+    ##     }

+    ##     afe <- x

+    ##     ## in case we pass an evalAllgenotypesfitandmut

+    ##     gfm <- allGenotypes_to_matrix(afe)

+    ## } else if(is.data.frame(x)) {

+    ##     ## Assume a two-column data frame of genotypes as character

+    ##     ## vectors and fitness

+    ##     if(colnames(x)[2] != "Fitness")

+    ##         stop("We cannot guess what you are passing here") 

+    ##     afe <- evalAllGenotypes(allFitnessEffects(genotFitness = x),

+    ##                             order = FALSE, addwt = TRUE,

+    ##                             max = max_num_genotypes)

+    ##     gfm <- allGenotypes_to_matrix(afe)

+    ## } else {

+    ##    stop("We cannot guess what you are passing here") 

+    ## }

@@ -155,8 +156,8 @@ plotFitnessLandscape <- function(x, show_labels = TRUE,

     ##     }

     ## }

-    mutated <- rowSums(gfm[, -ncol(gfm)])

-    gaj <- genot_to_adj_mat(gfm)

+    mutated <- rowSums(tfm$gfm[, -ncol(tfm$gfm)])

+    gaj <- genot_to_adj_mat(tfm$gfm)

     vv <- which(!is.na(gaj), arr.ind = TRUE)

     ## plot(x = mutated, y = e1$Fitness, ylab = "Fitness",

@@ -172,13 +173,13 @@ plotFitnessLandscape <- function(x, show_labels = TRUE,

     dd <- data.frame(muts = mutated,

-                     fitness = afe$Fitness,

-                     label = afe$Genotype)

+                     fitness = tfm$afe$Fitness,

+                     label = tfm$afe$Genotype)

     cl <- gaj[vv]

     sg <- data.frame(x_from = mutated[vv[, 1]],

-                     y_from = afe$Fitness[vv[, 1]],

+                     y_from = tfm$afe$Fitness[vv[, 1]],

                      x_to = mutated[vv[, 2]],

-                     y_to = afe$Fitness[vv[, 2]],

+                     y_to = tfm$afe$Fitness[vv[, 2]],

                      Change = factor(ifelse(cl == 0, "Neutral",

                                      ifelse(cl > 0, "Gain", "Loss"))))

     ## From http://stackoverflow.com/a/17257422

@@ -17,6 +17,73 @@

 ## Functions that allow passing a matrix or data frame of mappings

 ## genotype -> fitness so this is taken as input in fitnessEffects.

+## and some related functions

+

+

+

+to_Magellan <- function(x, file,

+                        max_num_genotypes = 2000) {

+    if(is.null(file)) {

+        file <- tempfile()

+        cat("\n Using file ", file, "\n")

+    }

+    gfm <- to_Fitness_Matrix(x, max_num_genotypes = max_num_genotypes)$gfm

+    write(rep(2, ncol(gfm) - 1), file = file, ncolumns = ncol(gfm) - 1)

+    write.table(gfm, file = file, append = TRUE,

+                row.names = FALSE, col.names = FALSE, sep = " ")

+}

+

+to_Fitness_Matrix <- function(x, max_num_genotypes) {

+    ## A general converter. Ready to be used by plotFitnessLandscape and

+    ## Magellan exporter.

+    

+    if( (inherits(x, "genotype_fitness_matrix")) ||

+        ( (is.matrix(x) || is.data.frame(x)) && (ncol(x) > 2) ) ) {

+        ## Why this? We go back and forth twice. We need both things. We

+        ## could construct the afe below by appropriately pasting the

+        ## columns names

+        afe <- evalAllGenotypes(allFitnessEffects(

+            epistasis = from_genotype_fitness(x)),

+            order = FALSE, addwt = TRUE, max = max_num_genotypes)

+        ## Might not be needed with the proper gfm object (so gmf <- x)

+        ## but is needed if arbitrary matrices.

+        gfm <- allGenotypes_to_matrix(afe) 

+    } else if(inherits(x, "fitnessEffects")) {

+        if(!is.null(x$orderEffects) )

+            stop("We cannot yet deal with order effects")

+        afe <- evalAllGenotypes(x,

+                                order = FALSE,

+                                addwt = TRUE, max = max_num_genotypes)

+        gfm <- allGenotypes_to_matrix(afe)

+    } else if( (inherits(x, "evalAllGenotypes")) ||

+               (inherits(x, "evalAllGenotypesMut"))) {

+        if(any(grepl(">", x[, 1], fixed = TRUE)))

+            stop("We cannot deal with order effects yet.")

+        x <- x[, c(1, 2)]

+        if(x[1, "Genotype"] != "WT") {

+            ## Yes, because we expect this present below

+            x <- rbind(data.frame(Genotype = "WT",

+                                  Fitness = 1,

+                                  stringsAsFactors = FALSE),

+                       x)

+        }

+        afe <- x

+        ## in case we pass an evalAllgenotypesfitandmut

+        gfm <- allGenotypes_to_matrix(afe)

+    } else if(is.data.frame(x)) {

+        ## Assume a two-column data frame of genotypes as character

+        ## vectors and fitness

+        if(colnames(x)[2] != "Fitness")

+            stop("We cannot guess what you are passing here") 

+        afe <- evalAllGenotypes(allFitnessEffects(genotFitness = x),

+                                order = FALSE, addwt = TRUE,

+                                max = max_num_genotypes)

+        gfm <- allGenotypes_to_matrix(afe)

+    } else {

+        stop("We cannot guess what you are passing here") 

+    }

+    return(list(gfm = gfm, afe = afe))

+}   

 from_genotype_fitness <- function(x) {

@@ -157,20 +224,37 @@ allGenotypes_to_matrix <- function(x) {

 }

+

+magellan_stats <- function(x, max_num_genotypes = 2000,

+                           verbose = FALSE,

+                           fl_statistics = "fl_statistics") {

+    ## if(!is.null(x) && is.null(file))

+    ##     stop("one of object or file name")

+    ## if(is.null(file))

+    fn <- tempfile()

+    fnret <- tempfile()

+    if(verbose)

+        cat("\n Using input file", fn, " and output file ", fnret, "\n")

+    to_Magellan(x, fn, max_num_genotypes = max_num_genotypes)

+    call_M <- system(paste(fl_statistics, fn, "-s", "-o", fnret))

+    return(read.table(fnret, skip = 1, header = TRUE)[-1])

+}

+

+

 ##

-## Example of Bozic issues

-m1 <- cbind(c(0, 1), c(1, 0), c(2, 3))

+## ## Example of Bozic issues

+## m1 <- cbind(c(0, 1), c(1, 0), c(2, 3))

-m2 <- cbind(c(1, 1), c(1, 0), c(2, 3))

+## m2 <- cbind(c(1, 1), c(1, 0), c(2, 3))

-m3 <- data.frame(G = c("A, B", "A"), F = c(1, 2))

+## m3 <- data.frame(G = c("A, B", "A"), F = c(1, 2))

-m4 <- data.frame(G = c("A, B", "A", "WT", "B"), F = c(3, 2, 1, 4))

+## m4 <- data.frame(G = c("A, B", "A", "WT", "B"), F = c(3, 2, 1, 4))

-m5 <- data.frame(G = c("A, B", "A", "WT", "B"), F = c(3, 2, 1, 0))

+## m5 <- data.frame(G = c("A, B", "A", "WT", "B"), F = c(3, 2, 1, 0))

-m6 <- data.frame(G = c("A, B", "A", "WT", "B"), F = c(3, 2.5, 2, 0))

+## m6 <- data.frame(G = c("A, B", "A", "WT", "B"), F = c(3, 2.5, 2, 0))

@@ -1,18 +1,21 @@

+Changes in version 2.3.5 (2016-06-25):

+	- to_Magellan.

+

 Changes in version 2.3.4 (2016-06-24):

 	- Failing some tests in Win 32-bits

 Changes in version 2.3.3 (2016-06-23):

 	- Vignette improvements and typo fixes.

-	- rfitness

-	- Plot of fitness landscapes

-	- Specify fitness by giving genotype-> fitness mapping

-	- Tests showing same gene in epist./DAG/order

-	- Clarified internal C++ unique/sorted in genotypes

-	- Checks initMutant correct and bug initMutant mutable pos

+	- rfitness: generate fitness landscapes.

+	- Plot of fitness landscapes.

+	- Specify fitness by giving genotype-> fitness mapping.

+	- Tests showing same gene in epist./DAG/order.

+	- Clarified internal C++ unique/sorted in genotypes.

+	- Checks initMutant correct and bug initMutant mutable pos.

 	- samplePop: sample at arbitrary sizes.

 	- plot.oncosimulpop using auto for color.

 	- Mutator phenotype and gene-specific mutation rates.

-	- Bug fixed: to_update set at 2 when mutating to pre-existing;

+	- Bug fixed: to_update set at 2 when mutating to pre-existing.

 	- Lots and lots of new tests.

 Changes in version 2.2.0 (for BioC 3.3):

@@ -389,9 +389,9 @@ evalAllGenotypes(fem6, addwt = TRUE, order = FALSE)

 ## Plotting a fitness landscape

 fe2 <- allFitnessEffects(noIntGenes =

-                         c(a1 = 0.1, a2 = 0.2,

-                           b1 = 0.01, b2 = 0.3, b3 = 0.2,

-                           c1 = 0.3, c2 = -0.2))

+                         c(a1 = 0.1, 

+                           b1 = 0.01,

+                           c1 = 0.3))

 plot(evalAllGenotypes(fe2, order = FALSE))

@@ -109,7 +109,7 @@ Ramon Diaz-Uriarte

 \references{

   MAGELLAN web site: \url{http://wwwabi.snv.jussieu.fr/public/Magellan/}

-  Brouillet, S. et al. (2015). MAGELLAN: a tool to explore small fitness landscapes. \emph{bioRxiv\/}, \bold{31583}. \url{http://doi.org/10.1101/031583}

+  Brouillet, S. et al. (2015). MAGELLAN: a tool to explore small fitness landscapes. \emph{bioRxiv}, \bold{31583}. \url{http://doi.org/10.1101/031583}

 }

@@ -118,18 +118,17 @@ Ramon Diaz-Uriarte

   I have copied most of the ideas (and colors, and labels) of this plot

   from MAGELLAN (\url{http://wwwabi.snv.jussieu.fr/public/Magellan/})

-  but MAGELLAN has other functionality that is not provided here (e.g.,

+  but MAGELLAN has other functionality that is not provided here such as

   epistasis stats for the landscape, and several visual manipulation

-  options).

-

-  In addition to cosmetic differences, an important difference between

-  this plot and those of MAGELLAN is \bold{how sinks/peaks of more than

-  one genotype are dealt with}. This plot will correctly show as sinks

-  or peaks sets of one or more genotypes that are of identical fitness

-  (and separated by a Haming distance of one). So a sink or a peak might

-  actually be made of more than one genotype. MAGELLAN, as far as I can

-  tell, cannot do this: peaks and sinks are always made of a single

-  isolated genotype.

+  options.

+

+  In addition to the above differences, another difference between this

+  plot and those of MAGELLAN is \bold{how sinks/peaks of more than one

+  genotype are dealt with}. This plot will show as sinks or peaks sets

+  of one or more genotypes that are of identical fitness (and separated

+  by a Haming distance of one). So a sink or a peak might actually be

+  made of more than one genotype. In MAGELLAN, as far as I can tell,

+  peaks and sinks are always made of a single isolated genotype.

   Does this matter? In most realistic cases where not two genotypes can

   have exactly the same fittnes it does not. In some cases, though, it

new file mode 100644

@@ -0,0 +1,107 @@

+\name{to_Magellan}

+\alias{to_Magellan}

+

+\title{ Create output for MAGELLAN.  }

+

+\description{ Create a fitness landscape in a format that is understood

+  by MAGELLAN \url{http://wwwabi.snv.jussieu.fr/public/Magellan/}. 

+

+}

+

+\usage{

+to_Magellan(x, file,

+            max_num_genotypes = 2000)

+}

+

+\arguments{

+  

+  \item{x}{ One of the following:

+    \itemize{

+

+      \item A matrix (or data frame) with g + 1 columns. Each of the

+      first g columns contains a 1 or a 0 indicating that the gene of

+      that column is mutated or not. Column g+ 1 contains the fitness

+      values. This is, for instance, the output you will get from

+      \code{\link{rfitness}}.

+

+      \item A two column data frame. The second column is fitness, and

+      the first column are genotypes, given as a character vector. For

+      instance, a row "A, B" would mean the genotype with both A and B

+      mutated.

+      

+      \item The output from a call to

+      \code{\link{evalAllGenotypes}}. Make sure you use \code{order =

+	FALSE} in that call.

+      

+      \item The output from a call to

+      \code{\link{evalAllGenotypesMut}}. Make sure you use \code{order =

+	FALSE}.

+      

+      \item The output from a call to \code{\link{allFitnessEffects}}

+      (with no order effects in the specification).

+      

+    }

+    

+    The first two are the same as the format for the \code{genotFitness}

+    component in \code{\link{allFitnessEffects}}.  }

+  

+  \item{file}{The name of the output file. If NULL, a name will be

+  created using \code{\link{tempfile}}.}

+

+  \item{max_num_genotypes}{Maximum allowed number of genotypes. For some

+  types of input, we make a call to \code{\link{evalAllGenotypes}}, and

+  use this as the maximum.}

+

+}

+

+\value{

+

+  A file is written to disk. You can then plot and/or show summary

+  statistics using MAGELLAN.

+}

+

+\note{

+  If you try to pass a fitness specification with order effects you will

+  receive an error, since that cannot be plotted with MAGELLAN.

+}

+

+\author{

+Ramon Diaz-Uriarte

+}

+

+\references{

+  MAGELLAN web site: \url{http://wwwabi.snv.jussieu.fr/public/Magellan/}

+

+  Brouillet, S. et al. (2015). MAGELLAN: a tool to explore small fitness landscapes. \emph{bioRxiv}, \bold{31583}. \url{http://doi.org/10.1101/031583}

+

+}

+

+

+

+\seealso{

+  \code{\link{allFitnessEffects}},

+  \code{\link{evalAllGenotypes}},

+  \code{\link{allFitnessEffects}},

+  \code{\link{rfitness}}

+}

+\examples{

+

+## Generate random fitness for four-genes genotype

+## and export landscape.

+

+r1 <- rfitness(4)

+to_Magellan(r1, NULL)

+

+## Specify fitness using a DAG and export it

+cs <-  data.frame(parent = c(rep("Root", 3), "a", "d", "c"),

+                      child = c("a", "b", "d", "e", "c", "f"),

+                      s = 0.1,

+                      sh = -0.9,

+                      typeDep = "MN")

+

+to_Magellan(allFitnessEffects(cs), NULL)

+

+}

+

+\keyword{ manip }

+

@@ -2586,8 +2586,9 @@ maxima and get an idea of how the fitness landscape looks.

 In \Rfunction{plotFitnessLandscape} I have blatantly and shamelessly

 copied most of the looks of the plots of MAGELLAN

 (\url{http://wwwabi.snv.jussieu.fr/public/Magellan/},

-\cite{brouillet_magellan:_2015}), a nice web-based tool for fitness

-landscape plotting and analysis.

+\cite{brouillet_magellan:_2015}), a very nice web-based tool for fitness

+landscape plotting and analysis (MAGELLAN provide some other extra

+functionality and epistasis statistics not provided here).

 As an example, let us show the previous example of Weissman et al. we saw

 in \ref{weissmanex}:

@@ -2612,17 +2613,17 @@ wb <- allFitnessEffects(

 @ 

 \clearpage

-<<>>=

-plotFitnessLandscape(wb, use_ggrepel = TRUE) ## ggrepel to avoid overlap 

-                                             ## of labels

-

+<<fig.width=6.5, fig.height=6>>=

+plotFitnessLandscape(wb, use_ggrepel = TRUE) 

 @ 

+We have set \texttt{use\_ggrepel = TRUE} to avoid overlap of labels.

+

 \clearpage

 For some types of objects, directly invoking \Rfunction{plot} will give

 you the fitness plot

-<<>>=

+<<fig.width=6.5, fig.height=6>>=

 (ewb <- evalAllGenotypes(wb, order = FALSE))

 plot(ewb, use_ggrepel = TRUE) 

@@ -2711,7 +2712,7 @@ And if you compare the tabular output of \Rfunction{evalAllGenotypes} you can

 see that the values of fitness reproduces the fitness landscape that they

 show in their Figure 1. We can also use our plot for fitness landscapes:

-<<>>=

+<<fig.width=6, fig.height=6>>=

 plot(b1, use_ggrepel = TRUE)

 @ 

@@ -1,15 +1,15 @@

 \usepackage[%

-		shash={3486983},

-		lhash={348698385e2f09528be7eb816768bd8ec06b7e70},

+		shash={a8daef6},

+		lhash={a8daef6cae6f3c218599ea59264b950e95040f54},

 		authname={Ramon Diaz-Uriarte},

 		authemail={rdiaz02@users.noreply.github.com},

-		authsdate={2016-06-23},

-		authidate={2016-06-23 19:01:20 +0200},

-		authudate={1466701280},

+		authsdate={2016-06-24},

+		authidate={2016-06-24 10:14:31 +0200},

+		authudate={1466756071},

 		commname={Ramon Diaz-Uriarte},

 		commemail={rdiaz02@users.noreply.github.com},

-		commsdate={2016-06-23},

-		commidate={2016-06-23 19:01:20 +0200},

-		commudate={1466701280},

+		commsdate={2016-06-24},

+		commidate={2016-06-24 10:14:31 +0200},

+		commudate={1466756071},

 		refnames={ (HEAD, origin/master, origin/HEAD)}

 	]{gitsetinfo}

\ No newline at end of file