Filtering samples/variables
Xiaotao Shen
Created on 2021-12-04 and updated on 2026-03-02
Source:vignettes/filtering.Rmd
filtering.RmdData preparation
library(massdataset)
library(tidyverse)
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 09:27:58Filtering samples
filter_samples()
###only remain the samples with NA number < 4 in all variables
filter_samples(object, function(x) {
sum(is.na(x)) / length(x) < 0.4
})
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 1000 x 2 data.frame]
#> 2.sample_info:[ 2 x 4 data.frame]
#> 2 samples:QC_1 QC_2
#> 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 09:27:58
#> filter_samples ----------
#> Package Function.used Time
#> 1 massdataset filter_samples() 2026-03-02 09:27:59
###give the index
filter_samples(object, function(x) {
sum(is.na(x)) / length(x) < 0.4
}, prune = FALSE)
#> Blank_3 Blank_4 QC_1 QC_2 PS4P1 PS4P2 PS4P3 PS4P4
#> FALSE FALSE TRUE TRUE FALSE FALSE FALSE FALSEdplyr::filter() function
###only remain the "QC" samples
object %>%
activate_mass_dataset(what = "sample_info") %>%
filter(class == "QC")
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 1000 x 2 data.frame]
#> 2.sample_info:[ 2 x 4 data.frame]
#> 2 samples:QC_1 QC_2
#> 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 09:27:58
#> filter ----------
#> Package Function.used Time
#> 1 massdataset filter() 2026-03-02 09:27:59dplyr::select() function
###only remain samples whose names contain "QC"
object2 =
object %>%
activate_mass_dataset(what = "expression_data") %>%
select(contains("QC"))
colnames(object2)
#> [1] "QC_1" "QC_2"
###only remain first 3 samples
object2 =
object %>%
activate_mass_dataset(what = "expression_data") %>%
select(1:3)
colnames(object2)
#> [1] "Blank_3" "Blank_4" "QC_1"Filtering variables
filter_variables() function
####Filter variables which have more than 50% MVs in all samples.
filter_variables(object, function(x) {
sum(is.na(x)) / length(x) < 0.5
}, prune = FALSE) %>%
head()
#> M136T55_2_POS M79T35_POS M307T548_POS M183T224_POS M349T47_POS
#> TRUE TRUE TRUE FALSE TRUE
#> M182T828_POS
#> TRUE
filter_variables(object, function(x) {
sum(is.na(x)) / length(x) < 0.5
},
prune = TRUE)
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 422 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:[ 422 x 3 data.frame]
#> 422 variables:M136T55_2_POS M79T35_POS M307T548_POS ... M236T543_POS M232T937_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 09:27:58
#> filter_variables ----------
#> Package Function.used Time
#> 1 massdataset filter_variables() 2026-03-02 09:27:59dplyr::filter() function
####Filter variables which mz > 500
object %>%
activate_mass_dataset(what = "variable_info") %>%
filter(mz > 500)
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 0 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:[ 0 x 3 data.frame]
#> 0 variables:
#> 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 09:27:58
#> filter ----------
#> Package Function.used Time
#> 1 massdataset filter() 2026-03-02 09:27:59
####Filter variables which mz > 500 and rt > 100
object %>%
activate_mass_dataset(what = "variable_info") %>%
filter(mz > 500 & rt > 100)
#> --------------------
#> massdataset version: 0.99.1
#> --------------------
#> 1.expression_data:[ 0 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:[ 0 x 3 data.frame]
#> 0 variables:
#> 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 09:27:58
#> filter ----------
#> Package Function.used Time
#> 1 massdataset filter() 2026-03-02 09:27:59Session 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] lubridate_1.9.4 forcats_1.0.0 stringr_1.5.1 purrr_1.1.0
#> [5] readr_2.1.5 tidyr_1.3.1 tibble_3.3.0 tidyverse_2.0.0
#> [9] 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 timechange_0.3.0
#> [7] lifecycle_1.0.4 cluster_2.1.8.1
#> [9] compiler_4.5.2 rlang_1.1.6
#> [11] sass_0.4.10 tools_4.5.2
#> [13] yaml_2.3.10 knitr_1.50
#> [15] S4Arrays_1.8.1 htmlwidgets_1.6.4
#> [17] DelayedArray_0.34.1 RColorBrewer_1.1-3
#> [19] abind_1.4-8 withr_3.0.2
#> [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 parallel_4.5.2
#> [41] XVector_0.48.0 matrixStats_1.5.0
#> [43] vctrs_0.6.5 Matrix_1.7-4
#> [45] jsonlite_2.0.0 IRanges_2.42.0
#> [47] hms_1.1.3 GetoptLong_1.0.5
#> [49] S4Vectors_0.48.0 clue_0.3-66
#> [51] systemfonts_1.2.3 foreach_1.5.2
#> [53] jquerylib_0.1.4 glue_1.8.0
#> [55] pkgdown_2.1.3 codetools_0.2-20
#> [57] stringi_1.8.7 shape_1.4.6.1
#> [59] gtable_0.3.6 GenomeInfoDb_1.44.2
#> [61] GenomicRanges_1.60.0 UCSC.utils_1.4.0
#> [63] ComplexHeatmap_2.24.1 pillar_1.11.0
#> [65] htmltools_0.5.8.1 GenomeInfoDbData_1.2.14
#> [67] circlize_0.4.16 R6_2.6.1
#> [69] textshaping_1.0.1 doParallel_1.0.17
#> [71] evaluate_1.0.4 Biobase_2.68.0
#> [73] lattice_0.22-7 png_0.1-8
#> [75] openxlsx_4.2.8 bslib_0.9.0
#> [77] Rcpp_1.1.0 zip_2.3.3
#> [79] SparseArray_1.8.1 xfun_0.53
#> [81] fs_1.6.6 MatrixGenerics_1.20.0
#> [83] pkgconfig_2.0.3 GlobalOptions_0.1.2