Merge pull request #5 from kbroman/main

Add MUGA maps + cross2_to_grcm39()

.Rbuildignore

@@ -3,3 +3,5 @@ Makefile$
 \.Rout$
 ^\.github$
 ^README\.Rmd$
+\.csv$
+^\.here$

.github/workflows/R-CMD-check.yaml

@@ -1,14 +1,10 @@
-# For help debugging build failures open an issue on the RStudio community with the 'github-actions' tag.
-# https://community.rstudio.com/new-topic?category=Package%20development&tags=github-actions
+# Workflow derived from https://github.com/r-lib/actions/tree/master/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
   push:
-    branches:
-      - main
-      - master
+    branches: [main, master]
   pull_request:
-    branches:
-      - main
-      - master
+    branches: [main, master]
 
 name: R-CMD-check
 
@@ -22,59 +18,37 @@ jobs:
       fail-fast: false
       matrix:
         config:
+          - {os: macOS-latest,   r: 'release'}
           - {os: windows-latest, r: 'release'}
-          - {os: macOS-latest, r: 'release'}
-          - {os: ubuntu-20.04, r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
-          - {os: ubuntu-20.04, r: 'devel', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
+          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-latest,   r: 'release'}
+          - {os: ubuntu-latest,   r: 'oldrel-1'}
 
     env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
 
     steps:
       - uses: actions/checkout@v2
 
+      - uses: r-lib/actions/setup-pandoc@v1
+
       - uses: r-lib/actions/setup-r@v1
         with:
           r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
 
-      - uses: r-lib/actions/setup-pandoc@v1
-
-      - name: Query dependencies
-        run: |
-          install.packages('remotes')
-          saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
-          writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")
-        shell: Rscript {0}
-
-      - name: Cache R packages
-        if: runner.os != 'Windows'
-        uses: actions/cache@v2
+      - uses: r-lib/actions/setup-r-dependencies@v1
         with:
-          path: ${{ env.R_LIBS_USER }}
-          key: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-
-
-      - name: Install system dependencies
-        if: runner.os == 'Linux'
-        run: |
-          while read -r cmd
-          do
-            eval sudo $cmd
-          done < <(Rscript -e 'writeLines(remotes::system_requirements("ubuntu", "20.04"))')
+          extra-packages: rcmdcheck
 
-      - name: Install dependencies
-        run: |
-          remotes::install_deps(dependencies = TRUE)
-          remotes::install_cran("rcmdcheck")
-        shell: Rscript {0}
+      - uses: r-lib/actions/check-r-package@v1
 
-      - name: Check
-        env:
-          _R_CHECK_CRAN_INCOMING_REMOTE_: false
-        run: rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), error_on = "warning", check_dir = "check")
-        shell: Rscript {0}
+      - name: Show testthat output
+        if: always()
+        run: find check -name 'testthat.Rout*' -exec cat '{}' \; || true
+        shell: bash
 
       - name: Upload check results
         if: failure()

.gitignore

@@ -0,0 +1 @@
+inst/scripts/*.csv

DESCRIPTION

@@ -1,22 +1,21 @@
 Package: mmconvert
-Version: 0.1-5
-Date: 2021-09-28
+Version: 0.2-3
+Date: 2021-10-12
 Title: Mouse Map Converter
 Description: Function to convert mouse genome positions between the build 39 physical map and the Cox genetic map <doi:10.1534/genetics.109.105486>.
 Author: Karl W Broman [aut, cre] (<https://orcid.org/0000-0002-4914-6671>)
 Maintainer: Karl W Broman <[email protected]>
 Authors@R: person("Karl W", "Broman", role=c("aut", "cre"),
-		  email="[email protected]", comment=c(ORCID = "0000-0002-4914-6671"))
+          email="[email protected]", comment=c(ORCID = "0000-0002-4914-6671"))
 Depends:
     R (>= 3.5.0)
 Imports:
-    Rcpp (>= 0.12.12),
-    utils,
-    stats
+    Rcpp (>= 0.12.12)
 Suggests:
     testthat,
     devtools,
-    roxygen2
+    roxygen2,
+    qtl2
 License: GPL-3
 URL: https://github.com/rqtl/mmconvert
 BugReports: https://github.com/rqtl/mmconvert/issues

Makefile

@@ -1,6 +1,6 @@
 .PHONY: doc test all
 
-all: doc README.md
+all: doc README.md data/MUGAmaps.RData
 
 README.md: README.Rmd
 	R -e "knitr::knit('$<')"
@@ -12,3 +12,6 @@ doc:
 # run tests
 test:
 	R -e 'devtools::test()'
+
+data/MUGAmaps.RData: inst/scripts/grab_muga_array_annot.R
+	R -e "source('$<')"

NAMESPACE

@@ -1,5 +1,6 @@
 # Generated by roxygen2: do not edit by hand
 
+export(cross2_to_grcm39)
 export(mmconvert)
 importFrom(Rcpp,sourceCpp)
 useDynLib(mmconvert, .registration=TRUE)

NEWS.md

@@ -1,3 +1,14 @@
+## mmconvert 0.2-3 (2021-10-12)
+
+- Added a dataset with the MUGA array annotations for markers on the
+  autosomes or X chromosome, with mouse build GRCm39 positions and
+  the revised Cox Map genetic map locations.
+
+- Add function `cross2_to_grcm39()` for converting an R/qtl2 cross2
+  object to use the new GRCm39 mouse build and the revised Cox genetic
+  map.
+
+
 ## mmconvert 0.1-5 (2021-09-28)
 
 - New package

R/MUGAmaps-data.R

@@ -0,0 +1,26 @@
+#' @name MUGAmaps
+#' @aliases MUGAmaps
+#'
+#' @title Array annotation information for the mouse MUGA arrays
+#' in mouse genome build 39.
+#'
+#' @description A list of four data frames with annotation information for the four MUGA arrays,
+#' GigaMUGA ("gm"), MegaMUGA ("mm"), MiniMUGA ("mini") and the original MUGA ("muga").
+#' Each has columns marker, chromosome, build 39 basepair position, and sex-averaged cM position (in Cox Map v3).
+#'
+#' @details
+#' SNP probes for the MUGA arrays were blasted against mouse genome
+#' build GRCm39 and locations interpolated using theRevised Cox maps.
+#' See <https://github.com/kbroman/MUGAarrays> for the array
+#' annotations and <https://github.com/kbroman/CoxMapV3> for the
+#' genetic maps. Note that for the genetic map locations, markers were
+#' shifted so that 0 cM corresponds to 3 Mbp, using the chromosome-
+#' and sex-specific recombination rate.
+#'
+#' @source <https://github.com/kbroman/MUGAarrays>
+#'
+#' @keywords datasets
+#'
+#' @examples
+#' data(MUGAmaps)
+NULL

R/cross2_to_grcm39.R

@@ -0,0 +1,111 @@
+#' Convert a cross2 object to use mouse build GRCm39
+#'
+#' Convert a cross2 object (with genotypes from one of the MUGA
+#' arrays) to use mouse build GRCm39 and the revised Cox map
+#' positions, revising marker order and omitting markers that are not
+#' found.
+#'
+#' @param cross Object of class `"cross2"`, as produced by
+#' [qtl2::read_cross2()]. Must have markers from just one of the MUGA arrays.
+#'
+#' @param array Character string indicating which of the MUGA arrays
+#' was used ("gm" for GigaMUGA, "mm" for MegaMUGA, "mini" for
+#' MiniMUGA, or "muga" for the original MUGA), or "guess" (the
+#' default) to pick the array with the most matching marker names.
+#'
+#' @export
+#'
+#' @return The input `cross` object with markers subset to those in build GRCm39
+#' and with `pmap` and `gmap` replaced with the GRCm39 physical map and
+#' revised Cox genetic map, respectively.
+#'
+#' @seealso [MUGAmaps]
+#'
+#' @examples
+#' \dontrun{
+#' file <- paste0("https://raw.githubusercontent.com/rqtl/",
+#'                "qtl2data/master/DOex/DOex.zip")
+#' DOex <- read_cross2(file)
+#' DOex_rev <- cross2_to_grcm39(DOex)
+#' }
+
+cross2_to_grcm39 <-
+    function(cross, array=c("guess", "gm", "mm", "mini", "muga"))
+{
+    # check that it's cross2
+    if(!inherits(cross, "cross2")) stop('Input cross must have class "cross2"')
+
+    # markers in the cross object
+    markers <- unlist(lapply(cross$geno, colnames))
+
+    # MUGA maps (internal dataset)
+    muga_maps <- mmconvert::MUGAmaps
+
+    array <- match.arg(array)
+    if(array == "guess") {
+        # compare marker names to the four MUGA arrays
+        # use the one with the most matches
+
+        n_match <- vapply(muga_maps, function(a,b) sum(b %in% a$marker), 0, markers)
+        if(!any(n_match > 0)) {
+            stop("No markers found in the MUGA arrays")
+        }
+
+        array <- names(n_match)[which.max(n_match)]
+    }
+
+    map <- muga_maps[[array]]
+
+    # number of markers found
+    n_found <- sum(markers %in% map$marker)
+
+    # if no markers found, stop with an error
+    if(n_found == 0) {
+        stop("No markers found in MUGA array")
+    }
+
+    n_notfound <- length(markers) - n_found
+
+    # if more than 5% of markers omitted, give a warning
+    if(n_notfound / length(markers) >= 0.05) {
+        warning("Omitting ", n_notfound, " (", round(n_notfound/length(markers)*100), "%) markers")
+    } else if(n_notfound > 0) {
+        message("Omitting ", n_notfound, " markers")
+    }
+
+    map <- map[map$marker %in% markers, , drop=FALSE]
+
+    gmap <- map_df_to_list(map, "chr", "cM_cox", "marker")
+    map$Mbp_grcm39 <- map$bp_grcm39/1e6
+    pmap <- map_df_to_list(map, "chr", "Mbp_grcm39", "marker")
+
+    # reorder markers in geno
+    cross$geno <- cross$geno[names(pmap)]
+    for(chr in names(pmap)) {
+        g <- cross$geno[[chr]]
+        g <- g[, names(pmap[[chr]]), drop=FALSE]
+        cross$geno[[chr]] <- g
+    }
+
+
+    # reorder markers in founder_geno
+    if("founder_geno" %in% names(cross)) {
+        cross$founder_geno <- cross$founder_geno[names(pmap)]
+        for(chr in names(pmap)) {
+            fg <- cross$founder_geno[[chr]]
+            fg <- fg[, names(pmap[[chr]]), drop=FALSE]
+            cross$founder_geno[[chr]] <- fg
+        }
+    }
+
+    # paste in new genetic map
+    cross$gmap <- gmap
+
+    # paste in new physical map
+    cross$pmap <- pmap
+
+    # make sure that is_x_chr gets subset, if necessary
+    cross$is_x_chr <- cross$is_x_chr[names(pmap)]
+
+    cross
+}

R/test_util.R

@@ -0,0 +1,13 @@
+# used to skip tests when not on *my* computer in interactive mode
+# needed for testing mult-core code, which isn't allowed within R CMD check
+isnt_karl <-
+    function()
+{
+    !(interactive() &&
+      identical(Sys.getenv("KARL_LOCAL"), "true"))
+}
+
+# is a number? (from assertthat)
+is_number <- function(x) is.numeric(x) && length(x)==1
+is_nonneg_number <- function(x) is_number(x) && x >= 0
+is_pos_number <- function(x) is_number(x) && x > 0

README.Rmd

@@ -23,8 +23,12 @@ Install the mmconvert package from
 
 ### Usage
 
-[mmconvert](https://github.com/rqtl/mmconvert) contains a single
-function `mmconvert()`. It takes a set of positions as input, plus and
+[mmconvert](https://github.com/rqtl/mmconvert) contains two functions:
+`mmconvert()` and `cross2_to_grcm39()`.
+
+#### `mmconvert()`
+
+`mmconvert()` takes a set of positions as input, plus and
 indication of whether they are basepairs or Mbp (in build 39) or
 sex-averaged, female, or male cM (from the [revised Cox genetic
 map](https://github.com/kbroman/CoxMapV3)).
@@ -47,8 +51,8 @@ third column or included as row names.
 
 ```{r input_df}
 input_df <- data.frame(chr=c(14,14,14),
-		       pos=c(6738536, 67215850, 121955310),
-		       marker=c("rs13482072", "rs13482231", "gnf14.117.278"))
+               pos=c(6738536, 67215850, 121955310),
+               marker=c("rs13482072", "rs13482231", "gnf14.117.278"))
 ```
 
 For either of these cases, the output is a data frame with seven
@@ -73,6 +77,27 @@ But note that the bp or Mbp positions must be in mouse genome build
 39, and cM positions must be according to the
 [Cox Map V3](https://github.com/kbroman/CoxMapV3).
 
+#### `cross2_to_grcm39()`
+
+`cross2_to_grcm39()` takes a cross2 object from
+[R/qtl2](https://kbroman.org/qtl2/) with mouse genotype data from one
+of the MUGA arrays and converts it to mouse genome build GRCm39, by
+possibly subsetting the markers, reordering them according to the
+GRCm39 build, and plugging in GRCm39 Mbp positions and the revised Cox
+genetic map. See <https://github.com/kbroman/MUGAarrays> for the
+MUGA array annotations and <https://github.com/kbroman/CoxMapV3> for
+the revised Cox genetic map.
+
+```{r cross2_to_grcm39, eval=FALSE}
+file <- paste0("https://raw.githubusercontent.com/rqtl/",
+               "qtl2data/master/DOex/DOex.zip")
+
+library(qtl2)
+DOex <- read_cross2(file)
+
+DOex_rev <- cross2_to_grcm39(DOex)
+```
+
 ---
 
 #### License