Develop functions based on mass_dataset
Xiaotao Shen
Created on 2022-02-18 and updated on 2026-03-02
Source:vignettes/based_on_mass_dataset.Rmd
based_on_mass_dataset.RmdDevelop new function based on mass_dataset class
If you want to develop new functions based on the
mass_dataset class in your own package, add
massdataset as a package dependency.
R code
Please set “mass_dataset” class as your new function primary input data. If the function is directory to process one component of “mass_dataset”, just get the component and then process it.
library(massdataset)
data("expression_data")
data("sample_info")
data("sample_info_note")
data("variable_info")
data("variable_info_note")
object =
create_mass_dataset(
expression_data = expression_data,
sample_info = sample_info,
variable_info = variable_info,
sample_info_note = sample_info_note,
variable_info_note = variable_info_note
)
object
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 1000 x 8 data.frame]
#> 2.sample_info:[ 8 x 4 data.frame]
#> 8 samples:Blank_3 Blank_4 QC_1 ... PS4P3 PS4P4
#> 3.variable_info:[ 1000 x 3 data.frame]
#> 1000 variables:M136T55_2_POS M79T35_POS M307T548_POS ... M232T937_POS M301T277_POS
#> 4.sample_info_note:[ 4 x 2 data.frame]
#> 5.variable_info_note:[ 3 x 2 data.frame]
#> 6.ms2_data:[ 0 variables x 0 MS2 spectra]
#> --------------------
#> Processing information
#> 1 processings in total
#> create_mass_dataset ----------
#> Package Function.used Time
#> 1 massdataset create_mass_dataset() 2026-03-02 09:27:39For example, we can create a function named
get_class_test() to get “class” from “sample_info”.
get_class_test <- function(object){
object@sample_info$class
}
get_class_test(object)
#> [1] "Blank" "Blank" "QC" "QC" "Subject" "Subject" "Subject"
#> [8] "Subject"If the function is general, you can use the
activate_mass_dataset() to tell you function which
component you want to preocess.
For example, we can create a function named
remove_blank() from “sample_info” or “expression_data”.
remove_blank <- function(object) {
if (length(object@activated) == 0) {
stop("activate_mass_dataset() first.\n")
}
if (object@activated == "sample_info") {
sample_info <-
object@sample_info
sample_info <-
sample_info %>%
dplyr::filter(class != "Blank")
object@sample_info <-
sample_info
object <-
update_mass_dataset(object)
return(object)
}
if (object@activated == "expression_data") {
expression_data <-
object@expression_data
expression_data <-
expression_data %>%
dplyr::select(-dplyr::contains("Blank"))
object@expression_data <-
expression_data
object <-
update_mass_dataset(object)
return(object)
}
if (object@activated != "expression_data" & object@activated != "sample_info") {
stop("Only support sample_info or expression_data.\n")
}
}
object %>%
remove_blank()
object %>%
activate_mass_dataset(what = "sample_info") %>%
remove_blank()
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 1000 x 6 data.frame]
#> 2.sample_info:[ 6 x 4 data.frame]
#> 6 samples:QC_1 QC_2 PS4P1 ... PS4P3 PS4P4
#> 3.variable_info:[ 1000 x 3 data.frame]
#> 1000 variables:M136T55_2_POS M79T35_POS M307T548_POS ... M232T937_POS M301T277_POS
#> 4.sample_info_note:[ 4 x 2 data.frame]
#> 5.variable_info_note:[ 3 x 2 data.frame]
#> 6.ms2_data:[ 0 variables x 0 MS2 spectra]
#> --------------------
#> Processing information
#> 2 processings in total
#> create_mass_dataset ----------
#> Package Function.used Time
#> 1 massdataset create_mass_dataset() 2026-03-02 09:27:39
#> update_mass_dataset ----------
#> Package Function.used Time
#> 1 massdataset update_mass_dataset() 2026-03-02 09:27:39
object %>%
activate_mass_dataset(what = "expression_data") %>%
remove_blank()
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 1000 x 6 data.frame]
#> 2.sample_info:[ 6 x 4 data.frame]
#> 6 samples:QC_1 QC_2 PS4P1 ... PS4P3 PS4P4
#> 3.variable_info:[ 1000 x 3 data.frame]
#> 1000 variables:M136T55_2_POS M79T35_POS M307T548_POS ... M232T937_POS M301T277_POS
#> 4.sample_info_note:[ 4 x 2 data.frame]
#> 5.variable_info_note:[ 3 x 2 data.frame]
#> 6.ms2_data:[ 0 variables x 0 MS2 spectra]
#> --------------------
#> Processing information
#> 2 processings in total
#> create_mass_dataset ----------
#> Package Function.used Time
#> 1 massdataset create_mass_dataset() 2026-03-02 09:27:39
#> update_mass_dataset ----------
#> Package Function.used Time
#> 1 massdataset update_mass_dataset() 2026-03-02 09:27:39
object %>%
activate_mass_dataset(what = "variable_info") %>%
remove_blank()Make functions from other package support mass_dataset
If you want to make other functions from other package support “mass_dataset”. We have two examples here:
#' @title head
#' @method head mass_dataset
#' @param x x
#' @export
#' @rdname processing-mass_dataset
#' @return mass_dataset class object
head.mass_dataset = function(x, ...){
x@expression_data = head(x@expression_data, ...)
x = update_mass_dataset(x)
return(x)
}
#' @title apply
#' @method apply mass_dataset
#' @param X X
#' @param MARGIN MARGIN
#' @param FUN FUN
#' @param ... ...
#' @param simplify simplify
#' @export
#' @rdname summary-mass_dataset
#' @return result
setMethod(f = "apply",
signature(X = "mass_dataset"),
function (X, MARGIN, FUN, ..., simplify = TRUE) {
apply(as.matrix(X@expression_data),
MARGIN, FUN, ..., simplify = simplify)
})Session information
sessionInfo()
#> R version 4.5.2 (2025-10-31)
#> Platform: aarch64-apple-darwin20
#> Running under: macOS Tahoe 26.3
#>
#> Matrix products: default
#> BLAS: /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib
#> LAPACK: /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.12.1
#>
#> locale:
#> [1] C.UTF-8/C.UTF-8/C.UTF-8/C/C.UTF-8/C.UTF-8
#>
#> time zone: Asia/Singapore
#> tzcode source: internal
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] magrittr_2.0.3 dplyr_1.1.4 ggplot2_4.0.2 massdataset_0.99.1
#>
#> loaded via a namespace (and not attached):
#> [1] tidyselect_1.2.1 farver_2.1.2
#> [3] S7_0.2.0 fastmap_1.2.0
#> [5] digest_0.6.37 lifecycle_1.0.4
#> [7] cluster_2.1.8.1 compiler_4.5.2
#> [9] rlang_1.1.6 sass_0.4.10
#> [11] tools_4.5.2 yaml_2.3.10
#> [13] knitr_1.50 S4Arrays_1.8.1
#> [15] htmlwidgets_1.6.4 DelayedArray_0.34.1
#> [17] RColorBrewer_1.1-3 abind_1.4-8
#> [19] withr_3.0.2 purrr_1.1.0
#> [21] BiocGenerics_0.54.0 desc_1.4.3
#> [23] grid_4.5.2 stats4_4.5.2
#> [25] colorspace_2.1-1 scales_1.4.0
#> [27] iterators_1.0.14 dichromat_2.0-0.1
#> [29] SummarizedExperiment_1.38.1 cli_3.6.5
#> [31] rmarkdown_2.29 crayon_1.5.3
#> [33] ragg_1.4.0 generics_0.1.4
#> [35] rstudioapi_0.17.1 httr_1.4.7
#> [37] tzdb_0.5.0 rjson_0.2.23
#> [39] cachem_1.1.0 stringr_1.5.1
#> [41] parallel_4.5.2 XVector_0.48.0
#> [43] matrixStats_1.5.0 vctrs_0.6.5
#> [45] Matrix_1.7-4 jsonlite_2.0.0
#> [47] IRanges_2.42.0 hms_1.1.3
#> [49] GetoptLong_1.0.5 S4Vectors_0.48.0
#> [51] clue_0.3-66 systemfonts_1.2.3
#> [53] foreach_1.5.2 tidyr_1.3.1
#> [55] jquerylib_0.1.4 glue_1.8.0
#> [57] pkgdown_2.1.3 codetools_0.2-20
#> [59] stringi_1.8.7 shape_1.4.6.1
#> [61] gtable_0.3.6 GenomeInfoDb_1.44.2
#> [63] GenomicRanges_1.60.0 UCSC.utils_1.4.0
#> [65] ComplexHeatmap_2.24.1 tibble_3.3.0
#> [67] pillar_1.11.0 htmltools_0.5.8.1
#> [69] GenomeInfoDbData_1.2.14 circlize_0.4.16
#> [71] R6_2.6.1 textshaping_1.0.1
#> [73] doParallel_1.0.17 evaluate_1.0.4
#> [75] Biobase_2.68.0 lattice_0.22-7
#> [77] readr_2.1.5 png_0.1-8
#> [79] openxlsx_4.2.8 bslib_0.9.0
#> [81] Rcpp_1.1.0 zip_2.3.3
#> [83] SparseArray_1.8.1 xfun_0.53
#> [85] fs_1.6.6 MatrixGenerics_1.20.0
#> [87] pkgconfig_2.0.3 GlobalOptions_0.1.2