# radiator 1.3.2 2024-04-30

* works with R 4.3.4
* Fix issue #186 related some particular DArT files

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: radiator
 Type: Package
 Title: RADseq Data Exploration, Manipulation and Visualization using R
-Version: 1.3.1
-Date: 2024-04-24
+Version: 1.3.2
+Date: 2024-04-30
 Encoding: UTF-8
 Authors@R: c(
   person("Thierry", "Gosselin", email = "[email protected]", role = c("aut", "cre")),

NEWS.md

@@ -1,3 +1,10 @@
+# radiator 1.3.2 2024-04-30
+
+* works with R 4.3.4
+* Fix issue #186 related some particular DArT files
+
+
+
 # radiator 1.3.1 2024-04-24
 
 * works with R 4.3.3

R/filter_coverage.R

@@ -197,15 +197,12 @@ filter_coverage <- function(
   if (interactive.filter) message("\nStep 1. Coverage visualization and helper table\n")
 
   # Generate coverage stats-----------------------------------------------------
-  # info <- extract_coverage(gds = data, individuals = FALSE, markers = TRUE, dp = TRUE, ad = FALSE, verbose = verbose)
-
   info <- generate_stats(
     gds = data,
     individuals = FALSE,
     markers = TRUE,
     missing = FALSE,
     coverage = TRUE,
-    # allele.coverage = TRUE,
     allele.coverage = FALSE,
     mac = FALSE,
     heterozygosity = FALSE,

R/filter_dart_reproducibility.R

@@ -186,7 +186,10 @@ filter_dart_reproducibility <- function(
     if (verbose) message("File written: dart_reproducibility_stats.tsv")
 
     # Generate box plot ---------------------------------------------------------
-    outlier.rep <- ceiling(rep.stats[[8]] * 1000) / 1000
+    # Previously using IQR and I think it's an error that was introduced.
+    # pretty sure it should be the outlier low threshold..
+    # outlier.rep <- ceiling(rep.stats[[8]] * 1000) / 1000
+    outlier.rep <- ceiling(rep.stats[["OUTLIERS_LOW"]] * 1000) / 1000
     bp.filename <- stringi::stri_join("dart_reproducibility_boxplot_", file.date, ".pdf")
     rep.fig <- boxplot_stats(
       data = rep.stats,

R/gds.R

@@ -908,18 +908,34 @@ extract_genotypes_metadata <- function(
       sum <- summary_gds(gds, verbose = FALSE)
       n.obs <- sum$n.ind * sum$n.markers
       if (nrow(genotypes.meta) != n.obs) {
+
+        m.s <- "M_SEQ"
+        if ("MARKERS" %in% genotypes.meta.select) m.s <- "MARKERS"
+        i.s <- "ID_SEQ"
+        if ("INDIVIDUALS" %in% genotypes.meta.select) m.s <- "INDIVIDUALS"
+
         markers <- extract_markers_metadata(
           gds = gds,
-          markers.meta.select = "MARKERS",
+          markers.meta.select = m.s,
           whitelist = TRUE
-        ) %$% MARKERS
+        )
+        markers <- markers[[m.s]]
+
         individuals <- extract_individuals_metadata(
           gds = gds,
-          ind.field.select = "INDIVIDUALS",
+          ind.field.select = i.s,
           whitelist = TRUE
-        ) %$% INDIVIDUALS
-        genotypes.meta %<>%
-          dplyr::filter(MARKERS %in% markers, INDIVIDUALS %in% individuals)
+        )
+        individuals <- individuals[[i.s]]
+
+        genotypes.meta <- dplyr::filter(
+          .data = genotypes.meta,
+          genotypes.meta[[m.s]] %in% markers,
+          genotypes.meta[[i.s]] %in% individuals
+          )
+
+        # genotypes.meta %<>%
+        #   dplyr::filter(MARKERS %in% markers, INDIVIDUALS %in% individuals)
       }
     }
     if (!whitelist && !blacklist && !rlang::has_name(genotypes.meta, "FILTERS")) {
@@ -2463,6 +2479,7 @@ generate_stats <- function(
     )
     if (!"DP" %in% got.coverage && !"READ_DEPTH" %in% got.coverage) coverage <- FALSE
     if (!"AD" %in% got.coverage) allele.coverage <- FALSE
+    if ("ALLELE_ALT_DEPTH" %in% got.coverage) allele.coverage <- TRUE
     if (!exhaustive) allele.coverage <- FALSE
     got.coverage <- NULL
   }
@@ -2578,20 +2595,51 @@ generate_stats <- function(
 
 
       if (ad) {
-        #temp object contains AD for REF and ALT
-        ref <- SeqArray::seqGetData(
-          gdsfile = gds,
-          var.name = "annotation/format/AD"
-        )$data
 
 
-        # to extract the REF and ALT
-        column.vec <- seq_len(length.out = dim(ref)[2])
-        alt <- ref[, column.vec %% 2 == 0]
-        alt[alt == 0] <- NA
-        ref <- ref[, column.vec %% 2 == 1]
-        ref[ref == 0] <- NA
-        column.vec <- NULL
+        if ("dart" %in% data.source) {
+          dart.data <- radiator::extract_genotypes_metadata(
+            gds = gds,
+            genotypes.meta.select = c("M_SEQ", "ID_SEQ", "ALLELE_ALT_DEPTH", "ALLELE_REF_DEPTH"),
+            whitelist = TRUE
+          )
+
+          ref <- radiator::rad_wide(
+              x = dart.data,
+              formula = "ID_SEQ ~ M_SEQ",
+              values_from = "ALLELE_REF_DEPTH"
+            ) %>%
+            dplyr::select(-ID_SEQ)
+          colnames(ref) <- NULL
+          ref <- as.matrix(ref)
+
+          alt <- radiator::rad_wide(
+            x = dart.data,
+            formula = "ID_SEQ ~ M_SEQ",
+            values_from = "ALLELE_ALT_DEPTH"
+          ) %>%
+            dplyr::select(-ID_SEQ)
+          colnames(alt) <- NULL
+          alt <- as.matrix(alt)
+          dart.data <- NULL
+
+
+        } else {
+          #temp object contains AD for REF and ALT
+          ref <- SeqArray::seqGetData(
+            gdsfile = gds,
+            var.name = "annotation/format/AD"
+          )$data
+
+
+          # to extract the REF and ALT
+          column.vec <- seq_len(length.out = dim(ref)[2])
+          alt <- ref[, column.vec %% 2 == 0]
+          alt[alt == 0] <- NA
+          ref <- ref[, column.vec %% 2 == 1]
+          ref[ref == 0] <- NA
+          column.vec <- NULL
+        }
 
         ad_f <- function(coverage.stats, x, margin = c("markers", "individuals")) {
 

R/radiator.R

@@ -72,6 +72,7 @@
 
 
 radiator_common_arguments <- function(
+  interactive.filter = TRUE,
   gds,
   data,
   parallel.core = parallel::detectCores() - 1,

README.Rmd

@@ -66,6 +66,7 @@ packages: `gdsfmt` and
 devtools::package_info(pkgs = "SeqArray") # to verify version
 
 # If manually installing SeqArray is necessary
+install.packages("BiocManager")
 BiocManager::install("SeqArray")
 ```
 

README.md

@@ -5,8 +5,8 @@
 [![Project Status: Active – The project has reached a stable, usable
 state and is being actively
 developed.](http://www.repostatus.org/badges/latest/active.svg)](http://www.repostatus.org/#active)
-[![packageversion](https://img.shields.io/badge/Package%20version-1.3.1-orange.svg)](commits/master)
-[![Last-changedate](https://img.shields.io/badge/last%20change-2024--04--24-brightgreen.svg)](/commits/master)
+[![packageversion](https://img.shields.io/badge/Package%20version-1.3.2-orange.svg)](commits/master)
+[![Last-changedate](https://img.shields.io/badge/last%20change-2024--04--30-brightgreen.svg)](/commits/master)
 [![R-CMD-check](https://github.com/thierrygosselin/radiator/workflows/R-CMD-check/badge.svg)](https://github.com/thierrygosselin/radiator/actions)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3687060.svg)](https://doi.org/10.5281/zenodo.3687060)
 <!-- badges: end -->
@@ -56,6 +56,7 @@ installations, linked to CRAN & Bioconductor tango problems:
 devtools::package_info(pkgs = "SeqArray") # to verify version
 
 # If manually installing SeqArray is necessary
+install.packages("BiocManager")
 BiocManager::install("SeqArray")
 ```
 

vignettes/rad_genomics_computer_setup.R

@@ -1,4 +1,4 @@
-## ---- include = FALSE---------------------------------------------------------
+## ----include = FALSE----------------------------------------------------------
 knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
 
 ## ----eval=FALSE---------------------------------------------------------------
@@ -21,25 +21,31 @@ knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
 ## ----eval=FALSE---------------------------------------------------------------
 #  file.exists("~/.Renviron")
 
-## ---- eval=FALSE--------------------------------------------------------------
+## ----eval=FALSE---------------------------------------------------------------
 #  Sys.getenv("LD_LIBRARY_PATH")
 #  # [1]""
 
-## ---- eval=FALSE--------------------------------------------------------------
+## ----eval=FALSE---------------------------------------------------------------
 #  # in R:
 #  Sys.setenv(LD_LIBRARY_PATH="/usr/local/lib/")
 #  # For Linux you could use: /usr/local/lib/:/usr/lib64
 
-## ---- eval=FALSE--------------------------------------------------------------
+## ----eval=FALSE---------------------------------------------------------------
 #  Sys.setenv(LD_LIBRARY_PATH="/usr/local/lib64/R/lib:/lib:/usr/local/lib64:/usr/lib/jvm/java-1.8.0-openjdk-1.8.0.222.b10-0.amzn2.0.1.x86_64/jre/lib/amd64/server:/usr/local/lib/:/usr/lib64")
 
-## ---- eval=FALSE--------------------------------------------------------------
+## ----eval=FALSE---------------------------------------------------------------
 #  install.packages("rgeos", repos="http://R-Forge.R-project.org", type="source")
 #  install.packages("rgdal", repos="http://R-Forge.R-project.org", type="source")
 #  devtools::install_github("r-spatial/sf", configure.args = "--with-proj-lib=/usr/local")
 #  install.packages("adegenet")
 
-## ---- eval=FALSE--------------------------------------------------------------
+## ----eval=FALSE---------------------------------------------------------------
+#  BiocManager::install("SeqArray")
+
+## ----eval=FALSE---------------------------------------------------------------
+#  remotes::install_local(path = "SeqArray_latest.tar.gz")
+
+## ----eval=FALSE---------------------------------------------------------------
 #  Error: C stack usage  7971092 is too close to the limit
 
 ## ----eval=FALSE---------------------------------------------------------------

vignettes/rad_genomics_computer_setup.Rmd

@@ -675,6 +675,22 @@ devtools::install_github("r-spatial/sf", configure.args = "--with-proj-lib=/usr/
 install.packages("adegenet")
 ```
 
+## Error: `HTTP status was 404 Not Found`
+
+This error is sometimes poping after a new R upgrade. Try installing the problematic package differently.
+
+
+Instead of: 
+
+```{r, eval=FALSE}
+BiocManager::install("SeqArray")
+```
+
+
+Try:
+```{r, eval=FALSE}
+remotes::install_local(path = "SeqArray_latest.tar.gz")
+```
 
 
 ## Error: `C stacks usage`