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

 Package: OncoSimulR

 Type: Package

 Title: Forward Genetic Simulation of Cancer Progression with Epistasis 

-Version: 2.13.1

-Date: 2019-02-07

+Version: 2.13.2

+Date: 2019-03-18

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

 		     email = "rdiaz02@gmail.com"),

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

@@ -18,8 +18,8 @@ Description: Functions for forward population genetic simulation in

     genes (to model mutator phenotypes). Simulations

     use continuous-time models and can include driver and passenger genes

     and modules.  Also included are functions for: simulating random DAGs

-    of the type found in Oncogenetic Tress, Conjunctive Bayesian Networks,

-    and other tumor progression models; plotting and sampling from

+    of the type found in Oncogenetic Trees, Conjunctive Bayesian Networks,

+    and other cancer progression models; plotting and sampling from

     single or multiple realizations of the simulations, including

     single-cell sampling; plotting the parent-child relationships of the

     clones; generating random fitness landscapes (Rough Mount Fuji, House

@@ -1,3 +1,8 @@

+Changes in version 2.13.2 (2019-03-18):

+	- changes in behavior of sample

+	  (see NEWS and https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17494) were

+	  leading to failures of some tests. Using RNGversion in some tests.

+

 Changes in version 2.13.1 (2019-02-07):

 	- bumped to one over the BioC-3.9 version

@@ -141,7 +141,8 @@ allMutatorEffects(epistasis = NULL, noIntGenes = NULL,

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

   }

   In all cases, fitness must be \code{>= 0}. If any possible genotype is

-  missing, its fitness is assumed to be 1.

+  missing, its fitness is assumed to be 0, except for WT (if WT is

+    missing, its fitness is assumed to be 1 ---see examples).

 }

@@ -406,6 +407,19 @@ plotFitnessLandscape(evalAllGenotypes(fe2, order = FALSE))

 plotFitnessLandscape(fe2)

+###### Defaults for missing genotypes

+

+## As a two-column data frame

+

+(m8 <- data.frame(G = c("A, B, C", "B"), F = c(3, 2)))

+evalAllGenotypes(allFitnessEffects(genotFitness = m8), addwt = TRUE)

+

+## As a matrix 

+

+(m9 <- rbind(c(0, 1, 0, 1, 4), c(1, 0, 1, 0, 1.5)))

+evalAllGenotypes(allFitnessEffects(genotFitness = m9), addwt = TRUE)

+

+

 ## Reinitialize the seed

 set.seed(NULL)

 }

@@ -2,6 +2,8 @@ inittime <- Sys.time()

 cat(paste("\n Starting test.Z-all-fitness at", date(), "\n"))

 RNGkind("Mersenne-Twister")

+## in 3.6.0 change in sample: see https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17494

+suppressWarnings(RNGversion("3.5.1"))

 test_that("catches identical gene names in different modules", {

     ## long, because it uses a complex and easy to miss problem

@@ -76,11 +76,14 @@ test_that("all genes must be in geneToModule even if present in fitness", {

 })

-test_that("fitness and mutator effects evaluation of actual values, long example",  {

+test_that("fit. mut. eff. values, long ex",  {

     ## Based on "long example OK" in "test.all-fitness.R"

     ## Fitness and mutator effects are evaluated OK when modules, epist, etc,

     ## are made differently in mutator and fitness and modules even share names 

     RNGkind("Mersenne-Twister")

+    ## in 3.6.0 change in sample: see https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17494

+    suppressWarnings(RNGversion("3.5.1"))

+

     p4 <- data.frame(parent = c(rep("Root", 4), "A", "B", "D", "E", "C", "F"),

                      child = c("A", "B", "D", "E", "C", "C", "F", "F", "G", "G"),

                      s = c(0.01, 0.02, 0.03, 0.04, 0.1, 0.1, 0.2, 0.2, 0.3, 0.3),

@@ -107,6 +107,44 @@ test_that("genotFitness not combined with others", {

 })

+test_that("Missing genotypes defaults: WT 1, others 0", {

+    (m8 <- data.frame(G = c("A, B, C", "B"), F = c(3, 2)))

+    exp_m8 <- data.frame(

+        Genotype = c("WT", "A", "B", "C", "A, B", "A, C",

+                     "B, C", "A, B, C"),

+        Fitness = c(1, 0, 2, rep(0, 4), 3),

+        stringsAsFactors = FALSE)

+    

+    o_m8 <- evalAllGenotypes(allFitnessEffects(genotFitness = m8),

+                     addwt = TRUE)

+    ## as exp_m8 does not have the evalAllGenotypes attribute

+    expect_equivalent(o_m8, exp_m8)

+

+    

+

+    (m9 <- rbind(

+         c(0, 1, 1, 0, 2),

+         c(1, 1, 0, 0, 4),

+         c(1, 0, 1, 0, 1.5)

+     ))

+    

+    exp_m9 <- data.frame(

+        Genotype = c("WT", "A", "B", "C", "D",

+                     "A, B", "A, C", "A, D", 

+                     "B, C", "B, D", "C, D",

+                     "A, B, C", "A, B, D", "A, C, D", "B, C, D",

+                     "A, B, C, D"),

+        Fitness = c(1, rep(0, 4),

+                    4, 1.5, 0, 2,

+                    rep(0, 7)),

+        stringsAsFactors = FALSE)

+

+    o_m9 <- evalAllGenotypes(allFitnessEffects(genotFitness = m9), addwt = TRUE)

+

+    expect_equivalent(o_m9, exp_m9)

+    

+})

+

 cat(paste("\n Ending genotFitness at", date(), "\n"))

 cat(paste("  Took ", round(difftime(Sys.time(), inittime, units = "secs"), 2), "\n\n"))

 rm(inittime)

@@ -3598,12 +3598,12 @@ And you can plot the fitness landscape:

 plotFitnessLandscape(evalAllGenotypes(fem4))

 ``` 

-

 To specify the mapping you can also use 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. And you do not even need to specify all the

-genotypes (we will assume that the missing genotypes have fitness 1):

+genotypes: the missing genotypes are assigned a fitness 0 ---except

+for the WT genotype which, if missing, is assigned a fitness of 1:

 ```{r}

 m6 <- cbind(c(1, 1), c(1, 0), c(2, 3))

@@ -3726,7 +3726,7 @@ we use.

 <!-- % As we will see in the examples (e.g., see sections \@ref(e2), \@ref(e3), -->

 <!-- % \@ref(exlong)) OncoSimulR makes it simple to be explicit about the mapping -->

-<!-- % of specific genotypes, while also using the ``how this specific effects -->

+<!-- % of specific genotypes, while also using the "how this specific effects -->

 <!-- % modifies previous effects" logic, leading to a flexible -->

 <!-- % specification. This also means that in many cases the same fitness -->

 <!-- % effects can be specified in several different ways. -->

@@ -4203,7 +4203,7 @@ all.equal(gcbn2[56, "Fitness"], 1.03 * 1.04 * 1.2 * 0.10)

 ``` 

 where "g" is taken as if its dependencies are satisfied (as "c",

-``d", and "e" are present) even when the dependencies of "c" are not

+"d", and "e" are present) even when the dependencies of "c" are not

 satisfied (and that is why the term for "c" is 0.9).

@@ -4277,7 +4277,7 @@ gxor1 <- evalAllGenotypes(xor1, order = FALSE)

 Whenever "c" is present with both "a" and "b", the fitness component

 for "c" will be $(1 - 0.1)$. Similarly for "g" (if more than one of

-``d", "e", or "c" is present, it will show as $(1 - 0.05)$). For example:

+"d", "e", or "c" is present, it will show as $(1 - 0.05)$). For example:

 ```{r}

 gxor1[c(22, 41), ] 

@@ -4895,7 +4895,7 @@ But we can also use a specification where we do not use the "-". That

 requires a different numerical value of the interaction, because now, as

 we are rewriting the interaction term as genotype "A is mutant, B is

 mutant" the double mutant will incorporate the effects of "A mutant",

-``B mutant" and "both A and B mutants". We can define a new $s_2$ that

+"B mutant" and "both A and B mutants". We can define a new $s_2$ that

 satisfies $(1 + s_{ab}) = (1 + s_a) (1 + s_b) (1 + s_2)$ so

 $(1 + s_2) = (1 + s_{ab})/((1 + s_a) (1 + s_b))$ and therefore specify as:

@@ -4977,7 +4977,7 @@ evalAllGenotypes(E3A, order = FALSE, addwt = FALSE)

 We needed to pass the $s_{ac}$ coefficient explicitly, even if it that

 term was just the product. We can try to avoid using the "-", however

 (but we will need to do other calculations). For simplicity, I use capital

-``S" in what follows where the letters differ from the previous

+"S" in what follows where the letters differ from the previous

 specification:

@@ -5100,7 +5100,7 @@ depicted above (several genes in module A, for example) actually is one of

 interaction: the members of "A" are combined using an "OR" operator

 (i.e., the fitness consequences of having one or more genes of A mutated

 are the same), not just simply multiplying their fitness; similarly for

-``B". This is why no interaction genes also mean no modules allowed.

+"B". This is why no interaction genes also mean no modules allowed.

 So how do you get what you want in this case?  Enter the names of

 the modules in the `epistasis` component but have no term for ":"

@@ -5298,7 +5298,7 @@ evalAllGenotypes(sv, order = FALSE, addwt = TRUE, model = "Bozic")

 ```

 What gives here? The simulation code would alert you of this (see section

-\@ref(ex-0-death)) in this particular case because there are ``-1",

+\@ref(ex-0-death)) in this particular case because there are "-1",

 which might indicate that this is not what you want. The problem is that

 you probably want the Death rate to be infinity (the birth rate was 0, so

 no clone viability, when we used birth rates ---section \@ref(noviab)).

@@ -6516,14 +6516,16 @@ you need to decide:

 ## Can I start the simulation from a specific mutant? {#initmut}

-You bet. <!-- In v.1 you can only give the initial mutant as one with a single -->

-<!-- mutated gene. --> In version 2 you can specify the genotype for the

+You bet. In version 2 you can specify the genotype for the

 initial mutant with the same flexibility as in `evalGenotype`. Here we show

 a couple of examples (we use the representation of the parent-child

 relationships ---discussed in section \@ref(phylog)--- of the clones so that

 you can see which clones appear, and from which, and check that we are not

 making mistakes).

+<!-- In v.1 you can only give the initial mutant as one with a single -->

+<!-- mutated gene. -->

+

 <!-- %% o3init <- allFitnessEffects(orderEffects = c( -->

 <!-- %%                             "M > D > F" = 0.99, -->

 <!-- %%                             "D > M > F" = 0.2, -->

@@ -6660,7 +6662,7 @@ drivers, whichever comes first (if any of these happen before

 In the `onlyCancer = TRUE` case, what happens if we reach

 `finalTime` (or the population size becomes zero) before any of the

-``reach cancer" conditions have been fulfilled?  The simulation will be

+"reach cancer" conditions have been fulfilled?  The simulation will be

 repeated again, within the following limits:

@@ -6932,7 +6934,7 @@ example, suppose we have a five loci genotype and suppose that you want to

 stop the simulations only if genotypes "A", "B, E", or "A, B, C, D, E"

 reach fixation. You do not want to stop it if, say, genotype "A, B, E"

 reaches fixation. To specify genotypes, you prepend the genotype

-combinations with a ``_,'', and that tells OncoSimulR that you want

+combinations with a "_,", and that tells OncoSimulR that you want

 fixation of **genotypes**, not just gene combinations.

 An example of the differences between the mechanisms can be seen from

@@ -7039,7 +7041,7 @@ fixation. These must be successive sampling periods without interruptions

 (i.e., a single period when the condition is not fulfilled will set the

 counter to 0). This can help to exclude short, transitional, local maxima

 that are quickly replaced by other genotypes. (The default is 50, but this

-is probably too small for ``real life'' usage).

+is probably too small for "real life" usage).

 `fixation_min_size`: you might only want to consider fixation to have

 happened if a minimal size has been reached (this can help weed out local

@@ -7701,7 +7703,7 @@ streamgraph(lb1, Genotype, Y, Time, scale = "continuous",

 <!-- %% \verb= %>% =, the pipe operator. Something like  -->

 <!-- %% \begin{verbatim} -->

 <!-- %% streamgraph(lb1, Genotype, Y, Time, scale = "continuous",   -->

-<!-- %%            offset = "zero") \%>\%                                                                                                                                sg_legend(show=TRUE, label=``Genotype: ")  -->

+<!-- %%            offset = "zero") \%>\%                                                                                                                                sg_legend(show=TRUE, label="Genotype: ")  -->

 <!-- %% \end{verbatim} -->

 <!-- %% but it gives me problems with knitr, etc). -->

@@ -8312,7 +8314,7 @@ par(op)

 ## Parent-child relationships from multiple runs {#phylogmult}

 If you use `oncoSimulPop` you can store and plot the

-``phylogenies" of the different runs:

+"phylogenies" of the different runs:

 ```{r}

@@ -8759,7 +8761,7 @@ increase the computational burden by many orders of magnitude.

 <!-- > pruned to free computer memory.  When the simulation is completed, -->

 <!-- > the properties of the origination and fixation point processes may -->

 <!-- > be studied by 'climbing' the tree and recording the origination and -->

-<!-- > fixation times of sites." -->

+<!-- > fixation times of sites. -->

 ### `sampleEvery`, `keepPhylog`, and pruning {#prune}

@@ -9362,5 +9364,5 @@ set.seed(NULL)

 <!-- fill-column: 68 -->

 <!-- End: -->

-<!--  LocalWords:  genotype Genotyping

- -->

+<!--  LocalWords:  genotype Genotyping -->

+

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

 \usepackage[%

-		shash={fd5f72e},

-		lhash={fd5f72ece0484508a63cf408dbe6ab2cdb5cb5b2},

-		authname={Ramon Diaz-Uriarte (at Coleonyx)},

+		shash={501dfef},

+		lhash={501dfefb4ffa60570ca4dcdeebff305d9b2942fd},

+		authname={ramon diaz-uriarte (at Phelsuma)},

 		authemail={rdiaz02@gmail.com},

-		authsdate={2018-05-04},

-		authidate={2018-05-04 18:44:29 +0200},

-		authudate={1525452269},

-		commname={Ramon Diaz-Uriarte (at Coleonyx)},

+		authsdate={2019-03-18},

+		authidate={2019-03-18 08:53:11 +0100},

+		authudate={1552895591},

+		commname={ramon diaz-uriarte (at Phelsuma)},

 		commemail={rdiaz02@gmail.com},

-		commsdate={2018-05-04},

-		commidate={2018-05-04 18:44:29 +0200},

-		commudate={1525452269},

+		commsdate={2019-03-18},

+		commidate={2019-03-18 08:53:11 +0100},

+		commudate={1552895591},

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

 	]{gitsetinfo}

\ No newline at end of file