v1.5.1 (#9)

Bug fixes, performance improvements for mega datasets, explicit checking for OpenMP support. Improved testing
Sudaraka88 · Jul 18, 2024 · f841ba2 · f841ba2
1 parent fc9e21f
commit f841ba2
Show file tree

Hide file tree

Showing 19 changed files with 342 additions and 147 deletions.
diff --git a/.github/workflows/r.yml b/.github/workflows/r.yml
@@ -21,10 +21,10 @@ jobs:
       matrix:
         config:
           - {os: macos-latest,   r: 'release'}
-          - {os: windows-latest, r: 'release'}
-         # - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
+          #- {os: windows-latest, r: 'release'}
+          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
           - {os: ubuntu-latest,   r: 'release'}
-         # - {os: ubuntu-latest,   r: 'oldrel-1'}
+          - {os: ubuntu-latest,   r: 'oldrel-1'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
@@ -38,7 +38,7 @@ jobs:
       - uses: r-lib/actions/setup-r@v2
         with:
           r-version: ${{ matrix.config.r }}
-          http-user-agent: ${{ matrix.config.http-user-agent }}
+          # http-user-agent: ${{ matrix.config.http-user-agent }}
           use-public-rspm: true
 
       - uses: r-lib/actions/setup-r-dependencies@v2
@@ -47,7 +47,10 @@ jobs:
           extra-packages: any::rcmdcheck
           needs: check
 
+
       - uses: r-lib/actions/check-r-package@v2
         with:
           upload-snapshots: true
           error-on: '"error"'
+
+
diff --git a/.gitignore b/.gitignore
@@ -6,8 +6,3 @@
 *.o
 .DS_Store
 *.Rmd
-Makevars
-
-testscripts.R
-testscript_op
-tests
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: LDWeaver
 Type: Package
 Title: Genomewide Epistasis Analysis on Bacteria
-Version: 1.5
+Version: 1.5.1
 Authors@R: person("Sudaraka", "Mallawaarachchi", email = "smallawaarachchi@gmail.com", role = c("aut", "cre"))
 Maintainer: Sudaraka Mallawaarachchi <smallawaarachchi@gmail.com>
 Description: Perform genomewide epistasis analysis by evaluating the LD structure in bacteria.
@@ -10,7 +10,7 @@ Encoding: UTF-8
 LazyData: true
 biocViews: Software
 Depends: R (>= 4.0.0),
-Imports:          
+Imports: 
          ape,
          Biostrings,
          chromoMap,
@@ -39,13 +39,15 @@ Imports:
          utils,
          VariantAnnotation
 Suggests:
-         phytools,
-         ggtree,
-         ggnewscale,
-         spam,
-         spam64
+    phytools,
+    ggtree,
+    ggnewscale,
+    spam,
+    spam64,
+    testthat (>= 3.0.0)
 LinkingTo: Rcpp, RcppArmadillo
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 URL: https://github.com/Sudaraka88/LDWeaver
 BugReports: https://github.com/Sudaraka88/LDWeaver/issues
 Biarch: TRUE
+Config/testthat/edition: 3
diff --git a/NAMESPACE b/NAMESPACE
@@ -52,9 +52,6 @@ importFrom(Matrix,rowSums)
 importFrom(Matrix,sparseMatrix)
 importFrom(Matrix,t)
 importFrom(Matrix,which)
-importFrom(MatrixExtra,crossprod)
-importFrom(MatrixExtra,t)
-importFrom(MatrixExtra,tcrossprod)
 importFrom(RColorBrewer,brewer.pal)
 importFrom(Rcpp,sourceCpp)
 importFrom(RcppArmadillo,fastLm)
@@ -114,4 +111,7 @@ importFrom(utils,stack)
 importFrom(utils,timestamp)
 importFrom(utils,txtProgressBar)
 importFrom(utils,write.table)
+importMethodsFrom(MatrixExtra,crossprod)
+importMethodsFrom(MatrixExtra,t)
+importMethodsFrom(MatrixExtra,tcrossprod)
 useDynLib(LDWeaver)
diff --git a/R/BacGWES.R b/R/BacGWES.R
@@ -46,20 +46,24 @@
 #' dset <- "full_dset"
 #' gbk_path <- system.file("extdata", "sample.gbk", package = "LDWeaver")
 #' aln_path <- system.file("extdata", "sample.aln.gz", package = "LDWeaver")
-#' LDWeaver::LDWeaver(dset = dset,  aln_path = aln_path,  gbk_path = gbk_path, validate_ref_ann_lengths = F)
+#' LDWeaver::LDWeaver(dset = dset,  aln_path = aln_path,  gbk_path = gbk_path,
+#'                    validate_ref_ann_lengths = F)
 #'
 #' # Example 2- using a SNP only alignment
 #' dset <- "snp_dset"
 #' gbk_path <- system.file("extdata", "sample.gbk", package = "LDWeaver")
 #' aln_path <- system.file("extdata", "snp_sample.fa.gz", package = "LDWeaver")
-#' pos <- as.numeric(readLines(system.file("extdata", "snp_sample.fa.pos", package = "LDWeaver")))
-#' LDWeaver::LDWeaver(dset = dset,  aln_path = aln_path, aln_has_all_bases = F, pos = pos, gbk_path = gbk_path)
+#' pos <- as.numeric(readLines(system.file("extdata", "snp_sample.fa.pos",
+#'                   package = "LDWeaver")))
+#' LDWeaver::LDWeaver(dset = dset,  aln_path = aln_path, aln_has_all_bases = F,
+#'                   pos = pos, gbk_path = gbk_path)
 #'
 # Example 3 - Redoing the full analysis as a mega scale dataset
 #' dset <- "full_dset_spam"
 #' gbk_path <- system.file("extdata", "sample.gbk", package = "LDWeaver")
 #' aln_path <- system.file("extdata", "sample.aln.gz", package = "LDWeaver")
-#' LDWeaver::LDWeaver(dset = dset,  aln_path = aln_path,  gbk_path = gbk_path, validate_ref_ann_lengths = F, mega_dset = T)
+#' LDWeaver::LDWeaver(dset = dset,  aln_path = aln_path,  gbk_path = gbk_path,
+#'                    validate_ref_ann_lengths = F, mega_dset = T)
 #' }
 #' @export
 LDWeaver = function(dset, aln_path, aln_has_all_bases = T, pos = NULL, gbk_path = NULL, gff3_path = NULL,
@@ -239,7 +243,8 @@ LDWeaver = function(dset, aln_path, aln_has_all_bases = T, pos = NULL, gbk_path
   ######## Welcome message ########
   {
     timestamp()
-    cat("\n ***** This is LDWeaver", as.character(packageVersion(pkg = "LDWeaver")), " *****")
+    cat("\n ***** This is LDWeaver", as.character(packageVersion(pkg = "LDWeaver")), " *****\n")
+    test_openmp()
     if(ncores > 1) cat(paste("\n\n Performing GWES analysis on:", dset, " - using", ncores, "cores\n\n"))
     if(ncores == 1) cat(paste("\n\n Performing GWES analysis on:", dset, "\n\n"))
     if(perform_SR_analysis_only) cat("Only short-range analysis requested. \n")

diff --git a/R/LDSummaryPlot.R b/R/LDSummaryPlot.R
@@ -2,7 +2,7 @@
 #'
 #' Function to generate the bird's-eye view of the genomewide LD structure (measured as weighted-MI)
 #'
-#' @importFrom MatrixExtra crossprod
+#' @importMethodsFrom MatrixExtra crossprod
 #' @importFrom Matrix sparseMatrix t
 #' @importFrom grDevices colorRampPalette png
 #' @importFrom heatmap3 heatmap3
@@ -97,7 +97,8 @@ genomewide_LDMap = function(lr_links_path, sr_links_path, plot_save_path, reduce
     cat(paste("Reducing dimensionality from", length(pos_vec) ,"x", length(pos_vec), "-> "))
     x = .mat(length(pos_vec), reducer)
     cat(paste(ncol(x) ,"x", ncol(x), "...\n"))
-    reduced_mat = MatrixExtra::crossprod(x, MatrixExtra::crossprod(sprs, x))
+    # reduced_mat = MatrixExtra::crossprod(x, MatrixExtra::crossprod(sprs, x))
+    reduced_mat = crossprod(x, crossprod(sprs, x))
     htm = as(reduced_mat, 'matrix')/reducer^2
     nms = as.character(pos_vec[seq(from = 1, to = length(pos_vec), by = reducer-1)])
     colnames(htm) = rownames(htm) = nms[1:nrow(htm)]

diff --git a/R/RcppExports.R b/R/RcppExports.R
@@ -37,6 +37,10 @@
     .Call('_LDWeaver_extractRef', PACKAGE = 'LDWeaver', file)
 }
 
+test_openmp <- function() {
+    invisible(.Call('_LDWeaver_test_openmp', PACKAGE = 'LDWeaver'))
+}
+
 .readFasta <- function(file, pos_len) {
     .Call('_LDWeaver_readFasta', PACKAGE = 'LDWeaver', file, pos_len)
 }