fillmissing (#60)

* do not infer states for chrY * update test-coverage * Input cell list for phasing * Add ability to annotate with a flat dataframe * Add annotation test * Adjust hscn test * Update hscn test to choose cells correctly * Update tests * Increment version number to 0.12.0
shahcompbio · Jan 7, 2025 · 1be71aa · 1be71aa
1 parent 5a53d08
commit 1be71aa
Show file tree

Hide file tree

Showing 9 changed files with 299 additions and 62 deletions.
diff --git a/.github/workflows/test-coverage.yaml b/.github/workflows/test-coverage.yaml
@@ -1,47 +1,61 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
   push:
-    branches:
-      - master
+    branches: [main, master]
   pull_request:
-    branches:
-      - master
 
-name: test-coverage
+name: test-coverage.yaml
+
+permissions: read-all
 
 jobs:
   test-coverage:
-    runs-on: macOS-latest
+    runs-on: ubuntu-latest
     env:
       GITHUB_PAT: ${{ secrets.GH_TOKEN }}
+
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::covr, any::xml2
+          needs: coverage
 
-      - uses: r-lib/actions/setup-pandoc@v1
-      - name: Install xquartz
-        run: brew install --cask xquartz
-      - name: Query dependencies
+      - name: Test coverage
         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")
+          cov <- covr::package_coverage(
+            quiet = FALSE,
+            clean = FALSE,
+            install_path = file.path(normalizePath(Sys.getenv("RUNNER_TEMP"), winslash = "/"), "package")
+          )
+          covr::to_cobertura(cov)
         shell: Rscript {0}
 
-      - name: Cache R packages
-        uses: actions/cache@v1
+      - uses: codecov/codecov-action@v4
         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-
+          # Fail if error if not on PR, or if on PR and token is given
+          fail_ci_if_error: ${{ github.event_name != 'pull_request' || secrets.CODECOV_TOKEN }}
+          file: ./cobertura.xml
+          plugin: noop
+          disable_search: true
+          token: ${{ secrets.CODECOV_TOKEN }}
 
-      - name: Install dependencies
+      - name: Show testthat output
+        if: always()
         run: |
-          install.packages(c("remotes"))
-          remotes::install_deps(dependencies = TRUE)
-          remotes::install_cran("covr")
-        shell: Rscript {0}
+          ## --------------------------------------------------------------------
+          find '${{ runner.temp }}/package' -name 'testthat.Rout*' -exec cat '{}' \; || true
+        shell: bash
 
-      - name: Test coverage
-        run: covr::codecov()
-        shell: Rscript {0}
+      - name: Upload test results
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-test-failures
+          path: ${{ runner.temp }}/package
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: signals
 Title: Single Cell Genomes with Allele Specificity
-Version: 0.11.4
+Version: 0.12.0
 Author@R: c(person("Marc", "Williams", email = "[email protected]",
                   role = c("aut", "cre")),
             person("Tyler", "Funnell",
@@ -41,7 +41,7 @@ Imports:
     grid,
     ggforce,
     ggtree
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Suggests: 
     knitr,
     rmarkdown,

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,9 @@
+# signals 0.12.0
+
+* option to input cells to use for phasing for each chromosome
+* plotHeatmap with arbitrary annotation dataframe
+* remove chrY
+
 # signals 0.11.4
 
 * fix typo assigning A->B

diff --git a/R/callHSCN.R b/R/callHSCN.R
@@ -624,14 +624,15 @@ filter_haplotypes <- function(haplotypes, fraction){
 #' @param phased_haplotypes Use this if you want to manually define the haplotypes phasing if for example the default heuristics used by signals does not return a good fit.
 #' @param clustering_method Method to use to cluster cells for haplotype phasing, default is `copy` (using copy column), other option is `breakpoints` (using breakpoint for clustering)
 #' @param maxloherror Maximum value for LOH error rate
+#' @param chr_cell_list Cells to use for phasing for each chromosome, this should be a named list with a vector of cell_ids for each chromosome eg list("1" = c("cell_id1", "cell_id2)) etc. Default is null. If provided overrides internal phasing.
 #' @param mincells Minimum cluster size used for phasing, default = 7
 #' @param overwritemincells Force the number of cells to use for clustering/phasing rather than use the output of the clustering
 #' @param viterbver Version of viterbi algorithm to use (cpp or R)
 #' @param cluster_per_chr Whether to cluster per chromosome to rephase alleles or not
 #' @param filterhaplotypes filter out haplotypes present in less than X fraction, default is 0.1
 #' @param firstpassfiltering Filter out cells with large discrepancy after first pass state assignment
 #' @param smoothsingletons Remove singleton bins by smoothing over based on states in adjacent bins
-#' @param fillmissing For bins with missing counts fill in values based on neighbouring bins
+#' @param fillmissing For bins with missing counts fill in values based on neighbouring bins, this ensures that the returned object is the same size as input CNbins
 #' @param global_phasing_for_diploid When using cluster_per_chr, use all cells for phasing diploid regions within the cluster
 #' @param chrs_for_global_phasing Which chromosomes to phase using all cells for diploid regions, default is NULL which uses all chromosomes
 #' @param female Default is `TRUE`, if set to `FALSE` and patient is "XY", X chromosome states are set to A|0 where A=Hmmcopy state
@@ -692,6 +693,7 @@ callHaplotypeSpecificCN <- function(CNbins,
                                     smoothsingletons = TRUE,
                                     fillmissing = TRUE,
                                     global_phasing_for_balanced = FALSE,
+                                    chr_cell_list = NULL,
                                     chrs_for_global_phasing = NULL,
                                     female = TRUE) {
   if (!clustering_method %in% c("copy", "breakpoints")) {
@@ -724,13 +726,13 @@ callHaplotypeSpecificCN <- function(CNbins,
 
   if (female == TRUE){
     #do not infer states for chr "Y"
-    #haplotypes <- dplyr::filter(haplotypes, chr != "Y")
-    #CNbins <- dplyr::filter(CNbins, chr != "Y")
+    haplotypes <- dplyr::filter(haplotypes, chr != "Y")
+    CNbins <- dplyr::filter(CNbins, chr != "Y")
   } else{
     #do not infer states for chr "X" or "Y"
-    #haplotypes <- dplyr::filter(haplotypes, chr != "Y")
+    haplotypes <- dplyr::filter(haplotypes, chr != "Y")
     haplotypes <- dplyr::filter(haplotypes, chr != "X")
-    #CNbins <- dplyr::filter(CNbins, chr != "Y")
+    CNbins <- dplyr::filter(CNbins, chr != "Y")
   }
 
   nhaplotypes <- haplotypes %>% 
@@ -842,7 +844,7 @@ callHaplotypeSpecificCN <- function(CNbins,
 
   ascn_filt$balance <- ifelse(ascn_filt$phase == "Balanced", 0, 1)
 
-  if (is.null(phased_haplotypes)) {
+  if (is.null(phased_haplotypes) & is.null(chr_cell_list)){
     chrlist <- proportion_imbalance(ascn_filt,
                                     haplotypes_filt,
                                     phasebyarm = phasebyarm,
@@ -854,6 +856,24 @@ callHaplotypeSpecificCN <- function(CNbins,
     )
     propdf <- chrlist$propdf
     chrlist <- chrlist$chrlist
+  } else{
+    message("Using user provided cell list for phasing chromosomes")
+    #use the user provided list of cells to use for phasing
+    chrlist <- chr_cell_list
+    propdf <- NULL
+
+    #check user provided chrcellist contains info for all chromosomes
+    check_chr <- all(names(chr_cell_list) %in% unique(ascn_filt$chr))
+    if (check_chr == FALSE){
+      stop("Cells for phasing not specified for all chromosomes in chr_cell_list")
+    }
+    check_cells <- all(as.vector(unlist(chr_cell_list)) %in% unique(ascn_filt$cell_id))
+    if (check_cells == FALSE){
+      stop("Not all cell_id's in chr_cell_list are present in CNbins or haplotypes")
+    }
+  }
+
+  if (is.null(phased_haplotypes)) {
     phased_haplotypes <- phase_haplotypes_bychr(
       ascn = ascn_filt,
       haplotypes = haplotypes_filt,