refactor: add parameter onlyValid to compound_tbl_sdf

- Add parameter `onlyValid` to `compound_tbl_sdf` (issue #69).
rformassspectrometry · Nov 27, 2020 · fb877b2 · fb877b2
1 parent 5e71799
commit fb877b2
Show file tree

Hide file tree

Showing 6 changed files with 28 additions and 4 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: CompoundDb
 Type: Package
 Title: Creating and Using (Chemical) Compound Annotation Databases
-Version: 0.6.4
+Version: 0.6.5
 Authors@R: c(person(given = "Jan", family = "Stanstrup",
                     email = "stanstrup@gmail.com",
 		    role = c("aut"),

diff --git a/NAMESPACE b/NAMESPACE
@@ -67,6 +67,7 @@ importFrom(Biobase,createPackage)
 importFrom(ChemmineR,datablock)
 importFrom(ChemmineR,datablock2ma)
 importFrom(ChemmineR,read.SDFset)
+importFrom(ChemmineR,validSDF)
 importFrom(DBI,dbDisconnect)
 importFrom(DBI,dbDriver)
 importFrom(DBI,dbExecute)

diff --git a/R/createCompDbPackage.R b/R/createCompDbPackage.R
@@ -36,6 +36,9 @@
 #' @param collapse optional `character(1)` to be used to collapse multiple
 #'     values in the columns `"synonyms"`. See examples for details.
 #'
+#' @param onlyValid `logical(1)` to import only valid or all elements (defaults
+#'     to `onlyValid = TRUE`)
+#'
 #' @return A [tibble::tibble] with general compound information (one row per
 #' compound):
 #' + `compound_id`: the ID of the compound.
@@ -59,7 +62,7 @@
 #' @seealso [createCompDb()] for a function to create a SQLite-based compound
 #'     database.
 #'
-#' @importFrom ChemmineR read.SDFset datablock datablock2ma
+#' @importFrom ChemmineR read.SDFset datablock datablock2ma validSDF
 #'
 #' @examples
 #'
@@ -76,11 +79,20 @@
 #' cmps <- compound_tbl_sdf(fl, collapse = "|")
 #' cmps
 #' cmps$synonyms
-compound_tbl_sdf <- function(file, collapse) {
+compound_tbl_sdf <- function(file, collapse, onlyValid = TRUE) {
     if (missing(file))
         stop("Please provide the file name using 'file'")
     if (!file.exists(file))
         stop("Can not fine file ", file)
+    suppressWarnings(
+        sdf <- read.SDFset(file))
+    nsdf <- length(sdf)
+    if (onlyValid) {
+        sdf <- sdf[validSDF(sdf)]
+        if (length(sdf) != nsdf)
+            message("Skipped import of ", nsdf - length(sdf),
+                    " invalid elements")
+    }
     res <- .simple_extract_compounds_sdf(
         datablock2ma(datablock(read.SDFset(file))))
     if (!missing(collapse)) {

diff --git a/inst/NEWS b/inst/NEWS
@@ -1,3 +1,9 @@
+Changes in version 0.6.5
+
+- Add parameter `onlyValid` to `compound_tbl_sdf` to allow importing of only
+  valid elements
+  [issue #69](https://github.com/EuracBiomedicalResearch/CompoundDb/issues/69).
+
 Changes in version 0.6.4
 
 - Add additional filters: `MassFilter`, `FormulaFilter`, `InchiFilter` and

diff --git a/man/compound_tbl_sdf.Rd b/man/compound_tbl_sdf.Rd
diff --git a/tests/testthat/test_createCompDbPackage.R b/tests/testthat/test_createCompDbPackage.R
@@ -58,6 +58,8 @@ test_that("compound_tbl_sdf works", {
 
     hmdb <- system.file("sdf/HMDB_sub.sdf.gz", package = "CompoundDb")
     cmps <- compound_tbl_sdf(hmdb)
+    cmps2 <- compound_tbl_sdf(hmdb, onlyValid = FALSE)
+    expect_equal(cmps, cmps2)
     expect_true(is(cmps, "data.frame"))
     expect_true(is(cmps, "tbl"))
     expect_equal(colnames(cmps), c("compound_id", "name", "inchi",