feat: add filterPrecursorMzValues (issue #230)

- Add the `filterPrecursorMzValues` method to enable filtering based on multiple
  target precursor m/z values.

Author: jorainer

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: Spectra
 Title: Spectra Infrastructure for Mass Spectrometry Data
-Version: 1.5.2
+Version: 1.5.3
 Description: The Spectra package defines an efficient infrastructure
    for storing and handling mass spectrometry spectra and functionality to
    subset, process, visualize and compare spectra data. It provides different

NAMESPACE

@@ -71,6 +71,7 @@ exportMethods(filterMzValues)
 exportMethods(filterPolarity)
 exportMethods(filterPrecursorCharge)
 exportMethods(filterPrecursorMz)
+exportMethods(filterPrecursorMzValues)
 exportMethods(filterPrecursorScan)
 exportMethods(filterRt)
 exportMethods(intensity)

NEWS.md

@@ -1,5 +1,10 @@
 # Spectra 1.5
 
+## Changes in 1.5.3
+
+- Add `filterPrecursorMzValues` method to filter `Spectra` keeping all spectra
+  with matching precursor m/z (supports multiple target precursor m/z values).
+
 ## Changes in 1.5.2
 
 - Small documentation update (related to `MsCoreUtils` issue

R/AllGenerics.R

@@ -35,6 +35,9 @@ setGeneric("filterMzRange", function(object, ...)
 setGeneric("filterMzValues", function(object, ...)
     standardGeneric("filterMzValues"))
 #' @rdname hidden_aliases
+setGeneric("filterPrecursorMzValues", function(object, ...)
+    standardGeneric("filterPrecursorMzValues"))
+#' @rdname hidden_aliases
 setGeneric("isReadOnly", function(object, ...)
     standardGeneric("isReadOnly"))
 #' @rdname hidden_aliases

R/MsBackend.R

@@ -90,7 +90,12 @@
 #'
 #' @param mz For `filterIsolationWindow`: `numeric(1)` with the m/z value to
 #'     filter the object. For `filterPrecursorMz`: `numeric(2)` with the lower
-#'     and upper m/z boundary.
+#'     and upper m/z boundary. For `filterPrecursorMzValues`: `numeric` with the
+#'     m/z value(s) to filter the object.
+#'
+#' @param ppm For `filterPrecursorMzValues`: `numeric(1)` with the m/z-relative
+#'     maximal acceptable difference for a m/z to be considered matching. See
+#'     [closest()] for details.
 #'
 #' @param z For `filterPrecursorCharge`: `integer()` with the precursor charges
 #'     to be used as filter.
@@ -112,6 +117,10 @@
 #' @param spectraVariables For `selectSpectraVariables`: `character` with the
 #'     names of the spectra variables to which the backend should be subsetted.
 #'
+#' @param tolerance For `filterPrecursorMzValues`: `numeric(1)` with the
+#'     maximal absolute acceptable difference for an m/z value to be considered
+#'     matching. See [closest()] for details.
+#'
 #' @param use.names For `lengths`: whether spectrum names should be used.
 #'
 #' @param value replacement value for `<-` methods. See individual
@@ -253,6 +262,11 @@
 #'   Implementation of this method is optional since a default implementation
 #'   for `MsBackend` is available.
 #'
+#' - `filterPrecursorMzValues`: retains spectra with a precursor m/z matching
+#'   any of the provided m/z values (given `ppm` and `tolerance`).
+#'   Implementation of this method is optional since a default implementation
+#'   for `MsBackend` is available.
+#'
 #' - `filterPrecursorCharge`: retains spectra with the defined precursor
 #'   charge(s).
 #'   Implementation of this method is optional since a default implementation
@@ -844,6 +858,17 @@ setMethod("filterPrecursorMz", "MsBackend",
               } else object
           })
 
+#' @exportMethod filterPrecursorMzValues
+#'
+#' @rdname MsBackend
+setMethod("filterPrecursorMzValues", "MsBackend",
+          function(object, mz = numeric(), ppm = 20, tolerance = 0) {
+              if (length(mz)) {
+                  object[.values_match_mz(precursorMz(object), mz = mz,
+                                          ppm = ppm, tolerance = tolerance)]
+              } else object
+          })
+
 #' @exportMethod filterPrecursorCharge
 #'
 #' @importMethodsFrom ProtGenerics filterPrecursorCharge
@@ -857,8 +882,6 @@ setMethod("filterPrecursorCharge", "MsBackend",
               } else object
           })
 
-
-
 #' @exportMethod filterPrecursorScan
 #'
 #' @importMethodsFrom ProtGenerics filterPrecursorScan

R/Spectra.R

@@ -353,6 +353,10 @@ NULL
 #'   provided m/z range. See examples for details on selecting spectra with
 #'   a precursor m/z for a target m/z accepting a small difference in *ppm*.
 #'
+#' - `filterPrecursorMzValues`: retains spectra with precursor m/z matching any
+#'   of the provided m/z values (given `ppm` and `tolerance`). Spectra with
+#'   missing precursor m/z value (e.g. MS1 spectra) are dropped.
+#'
 #' - `filterPrecursorCharge`: retains spectra with the defined precursor
 #'   charge(s).
 #'
@@ -702,8 +706,8 @@ NULL
 #' @param mz For `filterIsolationWindow`: `numeric(1)` with the m/z value to
 #'     filter the object. For `filterPrecursorMz` and `filterMzRange`:
 #'     `numeric(2)` defining the lower and upper m/z boundary.
-#'     For `filterMzValues`: `numeric` with the m/z values to match peaks
-#'     against.
+#'     For `filterMzValues` and `filterPrecursorMzValues`: `numeric` with the
+#'     m/z values to match peaks or precursor m/z against.
 #'
 #' @param z For `filterPrecursorCharge`: `integer()` with the precursor charges
 #'     to be used as filter.
@@ -1943,6 +1947,18 @@ setMethod("filterPrecursorMz", "Spectra",
               object
           })
 
+#' @rdname Spectra
+setMethod("filterPrecursorMzValues", "Spectra",
+          function(object, mz = numeric(), ppm = 20, tolerance = 0) {
+              object@backend <- filterPrecursorMzValues(
+                  object@backend, mz, ppm = ppm, tolerance = tolerance)
+              object@processing <- .logging(
+                  object@processing,
+                  "Filter: select spectra with precursor m/z matching ",
+                  paste0(mz, collapse = ", "), "")
+              object
+          })
+
 #' @rdname Spectra
 setMethod("filterPrecursorCharge", "Spectra",
           function(object, z = integer()) {

R/functions-util.R

@@ -70,3 +70,22 @@ setAs("logical", "factor", function(from, to) factor(from))
 sanitize_file_name <- function(x) {
     file.path(normalizePath(dirname(x)), path_sanitize(basename(x)))
 }
+
+#' Helper function that matches `x` against `mz` (using the `closest` function)
+#' and returns the indices of `x` that match any of the values in `mz`. The
+#' function takes care of sorting `x` and `mz` and deals also with missing
+#' values.
+#'
+#' @return `integer` with the indices of values in `x` that are not `NA` and
+#'     are matching any of the values in `mz` given `ppm` and `tolerance`.
+#'
+#' @noRd
+#'
+#' @author Johannes Rainer
+.values_match_mz <- function(x, mz, ppm = 20, tolerance = 0) {
+    keep <- which(!is.na(x))
+    idx <- order(x[keep])
+    mtch <- closest(x[keep][idx], sort(mz), tolerance = tolerance, ppm = ppm,
+                    duplicates = "keep", .check = FALSE)
+    keep[!is.na(mtch[order(idx)])]
+}

man/MsBackend.Rd

@@ -27,3 +27,23 @@ test_that("sanitize_file_name works", {
     expect_equal(basename(res)[1], "memory")
     expect_equal(basename(res)[2], "path")
 })
+
+test_that(".values_match_mz works", {
+    pmz <- c(12.4, 15, 3, 12.4, 3, 1234, 23, 5, 12.4, NA, 3)
+    mz <- c(200, 12.4, 3)
+
+    res <- .values_match_mz(pmz, mz)
+    expect_true(all(pmz[res] %in% mz))
+    expect_false(any(pmz[-res] %in% mz))
+
+    pmz <- rev(pmz)
+    res <- .values_match_mz(pmz, mz)
+    expect_true(all(pmz[res] %in% mz))
+    expect_false(any(pmz[-res] %in% mz))
+
+    res <- .values_match_mz(c(NA, NA), mz)
+    expect_identical(res, integer())
+
+    res <- .values_match_mz(pmz, c(NA, 3))
+    expect_true(all(pmz[res] == 3))
+})