R/gather_spectra_stats.R

In maldipickr: Dereplicate and Cherry-Pick Mass Spectrometry Spectra

# WARNING - Generated by {fusen} from dev/flat_utils.Rmd: do not edit by hand

#' Aggregate spectra quality-check statistics
#'
#'
#' @param check_vectors A list of logical vectors from [check_spectra]
#'
#' @return A tibble of one row with the following 5 columns of integers:
#' * `n_spectra`: total number of raw spectra.
#' * `n_valid_spectra`: total number of spectra passing all quality checks
#' * `is_empty`, `is_outlier_length` and `is_not_regular`: total of spectra flagged with these irregularities.
#'
#' @seealso [check_spectra]
#' @export
#' @examples
#' # Get an example directory of six Bruker MALDI Biotyper spectra
#' directory_biotyper_spectra <- system.file(
#'   "toy-species-spectra",
#'   package = "maldipickr"
#' )
#' # Import the six spectra
#' spectra_list <- import_biotyper_spectra(directory_biotyper_spectra)
#' # Display the list of checks, with FALSE where no anomaly is detected
#' checks <- check_spectra(spectra_list)
#' # Aggregate the statistics of quality-checked spectra
#' gather_spectra_stats(checks)
gather_spectra_stats <- function(check_vectors) {
  if (typeof(check_vectors) != "list" ||
    is.null(names(check_vectors))) {
    stop(
      "check_vectors is not a named list. See maldipickr::check_spectra() help page for a correct format."
    )
  }
  equal_length <- unique(lengths(check_vectors))
  if (length(equal_length) != 1 ||
    any(names(check_vectors) != c("is_empty", "is_outlier_length", "is_not_regular"))
  ) {
    stop(
      "Unexpected format for checks_vectors. Are you sure this is the output of maldipickr::check_spectra()?"
    )
  }

  # check_vectors from maldipickr::check_spectra
  # src: https://stackoverflow.com/a/51140480/21085566
  aggregated_checks <- Reduce(`|`, check_vectors)
  check_stats <- vapply(check_vectors, sum, FUN.VALUE = integer(1)) %>%
    tibble::as_tibble_row()
  tibble::tibble(
    "n_spectra" = length(aggregated_checks),
    "n_valid_spectra" = .data$n_spectra - sum(aggregated_checks)
  ) %>%
    dplyr::bind_cols(check_stats) %>%
    return()
}