Fixed warnings

.github/workflows/r.yml

@@ -19,10 +19,10 @@ permissions:
 
 jobs:
   build:
-    runs-on: macos-latest
+    runs-on: [macos-latest, linux]
     strategy:
       matrix:
-        r-version: ['3.6.3', '4.1.1']
+        r-version: ['4.4.1']
 
     steps:
       - uses: actions/checkout@v4
@@ -32,7 +32,7 @@ jobs:
           r-version: ${{ matrix.r-version }}
       - name: Install dependencies
         run: |
-          install.packages(c("remotes", "rcmdcheck", "gatepoints", "ggplot2", "pbmcapply", "paralle", "BiocManager", "dineq", "npreg", "reshape2", "segmented", "knitr"))
+          install.packages(c("remotes", "rcmdcheck", "gatepoints", "ggplot2", "pbmcapply", "parallel", "BiocManager", "dineq", "npreg", "reshape2", "segmented", "knitr"))
           remotes::install_deps(dependencies = TRUE)
           BiocManager::install("GenomicRanges")
         shell: Rscript {0}

R/broken_stick.R

@@ -7,7 +7,7 @@
 #' Diversity and determinants of recombination landscapes in flowering plants.
 #' PLOS Genetics, 18(8), Article 8. https://doi.org/10.1371/journal.pgen.1010141
 #'
-#' @param marey a `comparative_marey_map` object
+#' @param x a `comparative_marey_map` object
 #' @param k the number of segments (default = 10)
 #' @param method the method to infer the breakpoint of segments, either `strict` to cut a marker position, or `segmented` to interpolate segments breakpoints
 #' @param plot (logical) whether to plot the broken stick directly or return a data frame (default = `TRUE` will plot the figure)
@@ -25,19 +25,19 @@
 #' 
 #' @export
 #' 
-brokenstick = function(marey, k = 10, method = "strict", plot = TRUE) {
+brokenstick = function(x, k = 10, method = "strict", plot = TRUE) {
 
   # the list of set and names to process
-  s = marey$set
-  n = marey$map
+  s = x$set
+  n = x$map
 
   list_bs = list()
 
   for (i in 1:length(s)) {
     idx = (s == s[i] & n == n[i])
     cat(s[i], n[i], "\n")
 
-    subs = subset_comparative_marey(marey, subset = idx)
+    subs = subset_comparative_marey(x, subset = idx)
     subs = comparative_marey_to_dataframe(subs)
 
     bs = list(brokenstick_one_map(subs, k = k, method = method))
@@ -67,7 +67,7 @@ brokenstick = function(marey, k = 10, method = "strict", plot = TRUE) {
   # Besides, estimates the ratio expected/observed (longer than expected will have lower relative recombination rate)
   brokenstick$ratio = brokenstick$proportion.length/(1/k)
 
-  p = ggplot(data = brokenstick, aes(x=sample, y=proportion.length, fill = log10(ratio)))+
+  p = ggplot(data = brokenstick, aes(x=.data$sample, y=.data$proportion.length, fill = log10(.data$ratio)))+
     geom_bar(stat='identity', width = 1) +
     # scale_fill_manual(values = color) +
     scale_fill_viridis_c(breaks = c(-1, 0, 1), labels = c("-1", "0", "1"), direction = -1, limits = c(-1, 1),
@@ -109,6 +109,12 @@ brokenstick = function(marey, k = 10, method = "strict", plot = TRUE) {
 #' @description
 #' Estimate the proportions of a broken stick model for a `comparative_marey_map` object
 #' i.e. proportion of relative genetic length (cM) in k segments of equal genomic size (bp) along the chromosome
+#' 
+#' @param marey a single `mareyMap` object
+#' @param k the number of segments (default = 10)
+#' @param method the method used to infer segments breakpoints
+#' 
+#' 
 brokenstick_one_map = function(marey, k = 10, method = "strict") {
 
   marey$map = as.character(marey$map)

R/comparative_marey_map.R

@@ -50,7 +50,7 @@ comparative_marey_map = function(x = data.frame(),
 #' @param x a `comparative_marey_map` object
 #' @param method the interpolation method to apply
 #' @param verbose whether to print messages and progress bar
-#' 
+#' @param ... additional arguments
 #' 
 #' @return a `comparative_marey_map` object with recombination maps updated
 #' @export
@@ -71,7 +71,7 @@ comparative_recombination_maps = function(x,
 #'
 #' @param x a `comparative_marey_map` object
 #' @param statistics a vector of statistics to compute
-#' @param verbose whether to print messages and progress bar
+#' @param ... additional arguments
 #' 
 #' @slot set a vector of dataset names
 #' @slot map a vector of chromosome names
@@ -85,7 +85,8 @@ comparative_recombination_maps = function(x,
 #' @return a list of summary statistics
 #' @export
 #'
-compute_stats_marey = function(x, statistics = c('mean', 'median'), ...) {
+compute_stats_marey = function(x,
+                               statistics = c('mean', 'median'), ...) {
   list_stats = list()
   list_stats$set = as.character(x$set)
   list_stats$map = as.character(x$map)
@@ -160,44 +161,44 @@ compute_stats_marey = function(x, statistics = c('mean', 'median'), ...) {
 #' @return a `ggplot2` object of Marey maps
 #' @export
 #'
-plot_comparative_marey = function(x, group = 'set + map') {
+plot_comparative_marey = function(x, group = 'set + map', ...) {
 
   df = comparative_marey_to_dataframe(x)
 
   # Add the Marey interpolated function
   marey = comparative_interpolation_to_dataframe(x)
 
   if (group == 'set') {
-    grouping = as.formula(~as.factor(set))
+    grouping = as.formula(~as.factor(.data$set))
     facet = facet_wrap(grouping, scales = "free")
-    point_rec = geom_point(aes(colour = as.factor(map), fill = as.factor(map)), alpha = 0.2)
-    line_rec = geom_line(data = marey, aes(x = physicalPosition/10^6, y = geneticPositioncM, group = as.factor(map)), fill = "black")
-    ribbon_rec = geom_ribbon(data = marey, aes(x = physicalPosition/10^6, y = geneticPositioncM, ymin = lowerGeneticPositioncM, ymax = upperGeneticPositioncM, group = as.factor(map)),
+    point_rec = geom_point(aes(colour = as.factor(.data$map), fill = as.factor(.data$map)), alpha = 0.2)
+    line_rec = geom_line(data = marey, aes(x = .data$physicalPosition/10^6, y = .data$geneticPositioncM, group = as.factor(.data$map)), fill = "black")
+    ribbon_rec = geom_ribbon(data = marey, aes(x = .data$physicalPosition/10^6, y = .data$geneticPositioncM, ymin = .data$lowerGeneticPositioncM, ymax = .data$upperGeneticPositioncM, group = as.factor(.data$map)),
                              alpha = 0.4)
 
   }
   if (group == 'map') {
-    grouping = as.formula(~ as.factor(map))
+    grouping = as.formula(~ as.factor(.data$map))
     facet = facet_wrap(grouping, scales = "free")
-    point_rec = geom_point(aes(colour = as.factor(set), fill = as.factor(set)), alpha = 0.2)
-    line_rec = geom_line(data = marey, aes(x = physicalPosition/10^6, y = geneticPositioncM, group = as.factor(set)), fill = "black")
-    ribbon_rec = geom_ribbon(data = marey, aes(x = physicalPosition/10^6, y = geneticPositioncM, ymin = lowerGeneticPositioncM, ymax = upperGeneticPositioncM, group = as.factor(set)),
+    point_rec = geom_point(aes(colour = as.factor(.data$set), fill = as.factor(.data$set)), alpha = 0.2)
+    line_rec = geom_line(data = marey, aes(x = .data$physicalPosition/10^6, y = .data$geneticPositioncM, group = as.factor(.data$set)), fill = "black")
+    ribbon_rec = geom_ribbon(data = marey, aes(x = .data$physicalPosition/10^6, y = .data$geneticPositioncM, ymin = .data$lowerGeneticPositioncM, ymax = .data$upperGeneticPositioncM, group = as.factor(.data$set)),
                              alpha = 0.4)
   }
   if (group == 'set + map') {
-    grouping = as.formula(~as.factor(map) + as.factor(set))
+    grouping = as.formula(~as.factor(.data$map) + as.factor(.data$set))
     facet = facet_grid(grouping, scales = "free")
     point_rec = geom_point(alpha = 0.2)
-    line_rec = geom_line(data = marey, aes(x = physicalPosition/10^6, y = geneticPositioncM), colour = "black")
-    ribbon_rec = geom_ribbon(data = marey, aes(x = physicalPosition/10^6, y = geneticPositioncM, ymin = lowerGeneticPositioncM, ymax = upperGeneticPositioncM),
+    line_rec = geom_line(data = marey, aes(x = .data$physicalPosition/10^6, y = .data$geneticPositioncM), colour = "black")
+    ribbon_rec = geom_ribbon(data = marey, aes(x = .data$physicalPosition/10^6, y = .data$geneticPositioncM, ymin = .data$lowerGeneticPositioncM, ymax = .data$upperGeneticPositioncM),
                                fill = "darkorange", colour = "darkorange", alpha = 0.3)
   }
 
 
   if (nrow(marey) > 0) {
     marey$vld = TRUE
 
-    p = ggplot2::ggplot(data = df, aes(x = phys/10^6, y = gen)) +
+    p = ggplot2::ggplot(data = df, aes(x = .data$phys/10^6, y = .data$gen)) +
       point_rec +
       line_rec +
       ribbon_rec +
@@ -215,7 +216,7 @@ plot_comparative_marey = function(x, group = 'set + map') {
             axis.text=element_text(colour="black"),
             legend.position = "right")
   } else {
-    p = ggplot2::ggplot(data = df, aes(x = phys/10^6, y = gen)) +
+    p = ggplot2::ggplot(data = df, aes(x = .data$phys/10^6, y = .data$gen)) +
       point_rec +
       facet +
       labs(x = "Genomic position (Mb)", y = "Genetic distance (cM)", colour = "dataset") +
@@ -258,25 +259,25 @@ plot_comparative_recmap = function(x, group = 'set + map') {
   x$lowerRecRate = x$lowerRecRate * 10^6
 
   if (group == 'set') {
-    grouping = as.formula(~as.factor(set))
+    grouping = as.formula(~as.factor(.data$set))
     facet = facet_wrap(grouping, scales = "free")
-    line_rec = geom_line(aes(group = map, color = map))
-    ribbon_rec = geom_ribbon(aes(x = point/10^6, ymin = lowerRecRate, ymax = upperRecRate, fill = map), alpha = 0.2)
+    line_rec = geom_line(aes(group = .data$map, color = .data$map))
+    ribbon_rec = geom_ribbon(aes(x = .data$point/10^6, ymin = .data$lowerRecRate, ymax = .data$upperRecRate, fill = .data$map), alpha = 0.2)
   }
   if (group == 'map') {
-    grouping = as.formula(~as.factor(map))
+    grouping = as.formula(~as.factor(.data$map))
     facet = facet_wrap(grouping, scales = "free")
-    line_rec = geom_line(aes(group = set, color = set))
-    ribbon_rec = geom_ribbon(aes(x = point/10^6, ymin = lowerRecRate, ymax = upperRecRate, fill = set), alpha = 0.2)
+    line_rec = geom_line(aes(group = .data$set, color = .data$set))
+    ribbon_rec = geom_ribbon(aes(x = .data$point/10^6, ymin = .data$lowerRecRate, ymax = .data$upperRecRate, fill = .data$set), alpha = 0.2)
   }
   if (group == 'set + map') {
-    grouping = as.formula(~as.factor(map) + as.factor(set))
+    grouping = as.formula(~as.factor(.data$map) + as.factor(.data$set))
     facet = facet_grid(grouping, scales = "free")
     line_rec = geom_line()
-    ribbon_rec = geom_ribbon(aes(x = point/10^6, ymin = lowerRecRate, ymax = upperRecRate), fill = 'darkgray', alpha = 0.2)
+    ribbon_rec = geom_ribbon(aes(x = .data$point/10^6, ymin = .data$lowerRecRate, ymax = .data$upperRecRate), fill = 'darkgray', alpha = 0.2)
   }
 
-  p = ggplot2::ggplot(data = x, aes(x = point/10^6, y = recRate)) +
+  p = ggplot2::ggplot(data = x, aes(x = .data$point/10^6, y = .data$recRate)) +
     line_rec +
     ribbon_rec +
     # facet_grid(~as.factor(set)) +
@@ -352,20 +353,21 @@ subset_comparative_marey = function(x,
 
 #' Summary of a `comparative_marey_map` object
 #'
-#' @param x a `comparative_marey_map` object to summarize
+#' @param object a `comparative_marey_map` object to summarize
+#' @param ... additional arguments
 #' 
 #' @return a summary
 #'
 #' @method summary comparative_marey_map
 #' @export
 #' 
-summary.comparative_marey_map = function(x, ...) {
-  dataset = paste0(c(as.character(head(x$set, 3)), "..."))
-  n_maps = length(x$set)
-  length_linkage_map = unlist(lapply(x$data, function(x) max(x[[1]]$gen)))
-  length_genome_Mb = unlist(lapply(x$data, function(x) max(x[[1]]$phys)))
+summary.comparative_marey_map = function(object, ...) {
+  dataset = paste0(c(as.character(head(object$set, 3)), "..."))
+  n_maps = length(object$set)
+  length_linkage_map = unlist(lapply(object$data, function(x) max(x[[1]]$gen)))
+  length_genome_Mb = unlist(lapply(object$data, function(x) max(x[[1]]$phys)))
   length_genome_Mb = length_genome_Mb / 1000000
-  n_markers = unlist(lapply(x$data, function(x) length(x[[1]]$gen)))
+  n_markers = unlist(lapply(object$data, function(x) length(x[[1]]$gen)))
   density_markers = n_markers / length_genome_Mb
 
   cat("============== Summary of the comparative marey map ==============\n",

R/lorenz.R

@@ -15,10 +15,10 @@
 #' @importFrom ggplot2 .data
 #'
 lorenz = function(x, return.plot = TRUE) {
-  if (class(x) == 'mareyMap') {
+  if (is(x, 'mareyMap')) {
     df = x$recMap
   } else {
-    if (class(x) == 'comparative_marey_map') {
+    if (is(x, 'comparative_marey_map')) {
       df = comparative_recmap_to_dataframe(x)
     }
   }
@@ -62,10 +62,10 @@ lorenz = function(x, return.plot = TRUE) {
   diagonal = data.frame(x = seq(0, 1, by = 0.01),
                         y = seq(0, 1, by = 0.01))
 
-  p = ggplot(data = out, aes(x = relativePhys, y = relativeGen, fill = as.factor(map), colour = as.factor(set))) +
+  p = ggplot(data = out, aes(x = .data$relativePhys, y = .data$relativeGen, fill = as.factor(.data$map), colour = as.factor(.data$set))) +
     geom_line(alpha = 0.3) +
     # facet_wrap(~ as.factor(set)) +
-    geom_line(data = diagonal, aes(x = x, y = y, fill = NA, colour = NA), color = "black") +
+    geom_line(data = diagonal, aes(x = .data$x, y = .data$y, fill = NA, colour = NA), color = "black") +
     xlim(0, 1) +
     ylim(0, 1) +
     xlab("Proportion of genomic distance") +

R/summary.R

@@ -8,6 +8,7 @@
 #'
 #' @method summary mareyMap
 #' @export
+#' 
 summary.mareyMap = function(object, ...) {
   dataset = levels(object$mareyMap$set)
   nameChromosome = object$chromosomeName

README.md

@@ -1,5 +1,11 @@
 # EasyMareyMap
 
+![license](https://badgen.net/badge/license/GPL3.0/blue)
+![release](https://badgen.net/badge/release/0.2.0/green?icon=github)
+![r-workflow](https://github.com/github/docs/actions/workflows/r.yml/badge.svg)
+
+
+
 Estimate local recombination rates with the Marey map method as described in [Brazier and Glémin 2022](https://doi.org/10.1371/journal.pgen.1010141).
 
 This R package provides an easy command line solution for the Marey map method, which is described in more detail in the original MareyMap package. The original MareyMap package is designed for interactive graphical use only and does not provide scripting capabilities. It does not allow to process many maps at a time. Hence we re-implemented the method in a more machine-friendly approach, in order to use it for batch processing and reproducible scripts. See the original MareyMap package here [Rezvoy et al. 2007](https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btm315) and [Siberchicot et al. 2017](https://CRAN.R-project.org/package=MareyMap).

vignettes/RecombinationMap.Rmd

@@ -13,22 +13,35 @@ knitr::opts_chunk$set(
   collapse = TRUE,
   comment = "#>"
 )
-
 ```
 
 
-The `EasyMareyMap` package for R has been implemented to estimate recombination maps from genetic maps (or linkage maps) using the Marey map approach [@rezvoy_mareymap:_2007]. It is designed to provide easy access to the data (stored in slots within objects) and the functions via the command line, in order to maximize scriptability, reproducibility and scalability to large datasets. It offers a statistical framework to estimate recombination maps with the automatic calibration of hyperparameters and a bootstrap procedure to measure the uncertainty of our estimates. The method has been used and validated in [@brazierDiversityDeterminantsRecombination2022].
+The `EasyMareyMap` package for R has been implemented to estimate recombination maps from genetic maps (or linkage maps) using the Marey map approach [@rezvoy_mareymap:_2007]. The original MareyMap package was designed for interactive graphical use only and does not provide scripting capabilities. It does not allow to process many maps at a time. See the original MareyMap package here [Rezvoy et al. 2007](https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btm315) and [Siberchicot et al. 2017](https://CRAN.R-project.org/package=MareyMap).
+
+
+Our `EasyMareyMap` package is designed to provide easy access to the data (stored in slots within objects) and the functions via the command line, hence a more machine-friendly approach, in order to maximize scriptability, reproducibility and scalability to large datasets. It offers a statistical framework to estimate recombination maps with the automatic calibration of hyperparameters and a bootstrap procedure to measure the uncertainty of our estimates. The method has been used and validated in [@brazierDiversityDeterminantsRecombination2022].
+
+
+
+Moreover, it offers a statistical framework to estimate recombination maps with the automatic calibration of hyperparameters and a bootstrap procedure to measure the uncertainty of our estimates, which is an advantage for robust data analyses. The method has been used and validated in [@brazierDiversityDeterminantsRecombination2022]. Our `EasyMareyMap` package adds these new features:
+* automatic calibration of the smoothing parameter
+* bootstraps to estimate a 95% confidence interval
+* graphical zone selection to exclude a bunch of outlier markers
+* a graphical and statistical framework for comparative genomics (compare Marey maps between species, populations or genomes)
+
+
+
 
 
 The package is loaded with the following command.
 
 ```{r setup, message=FALSE, warning=FALSE}
-library(ggplot2)
 library(EasyMareyMap)
+library(ggplot2)
 ```
 
 
-# Create a MareyMap object
+# Create a `MareyMap` object
 
 You can import the example dataset based on linkage maps for the five chromosomes of the plant *Arabidopsis thaliana* [@serin_construction_2017].