Split mass_dataset
Xiaotao Shen (https://www.shenxt.info/)
Created on 2022-03-05 and updated on 2023-10-01
Source:vignettes/split_mass_dataset.Rmd
split_mass_dataset.RmdIn massdataset package, the
split_mass_dataset is used to split
mass_dataset to different class objects.
Data preparation
library(massdataset)
library(tidyverse)
data("expression_data")
data("sample_info")
data("variable_info")
object =
create_mass_dataset(
expression_data = expression_data,
sample_info = sample_info,
variable_info = variable_info
)Split based on sample information
object <-
activate_mass_dataset(object, what = "sample_info")
new_object <-
split_mass_dataset(object = object, by = "group")
new_object %>% lapply(dim)
#> $Blank
#> variables samples
#> 1000 2
#>
#> $QC
#> variables samples
#> 1000 2
#>
#> $Subject
#> variables samples
#> 1000 4
new_object %>% lapply(colnames)
#> $Blank
#> [1] "Blank_3" "Blank_4"
#>
#> $QC
#> [1] "QC_1" "QC_2"
#>
#> $Subject
#> [1] "PS4P1" "PS4P2" "PS4P3" "PS4P4"
extract_process_info(new_object[[1]])$split_mass_dataset
#> --------------------
#> pacakge_name: massdataset
#> function_name: split_mass_dataset
#> time: 2022-08-07 19:36:11
#> parameters:
#> by : group
#> fun : noSplit based on variable information
object <-
activate_mass_dataset(object, what = "variable_info")
new_object <-
split_mass_dataset(object = object, by = "rt", fun = function(rt) rt > 600)
new_object %>% lapply(dim)
#> [[1]]
#> variables samples
#> 245 8
#>
#> [[2]]
#> variables samples
#> 755 8
plot(extract_variable_info(new_object[[1]])$rt)
plot(extract_variable_info(new_object[[2]])$rt)
extract_process_info(new_object[[1]])$split_mass_dataset
#> --------------------
#> pacakge_name: massdataset
#> function_name: split_mass_dataset
#> time: 2022-08-07 19:36:11
#> parameters:
#> by : rt
#> fun : function (rt)rt > 600Session information
sessionInfo()
#> R version 4.2.1 (2022-06-23)
#> Platform: x86_64-apple-darwin17.0 (64-bit)
#> Running under: macOS Big Sur ... 10.16
#>
#> Matrix products: default
#> BLAS: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRblas.0.dylib
#> LAPACK: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRlapack.dylib
#>
#> locale:
#> [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] forcats_0.5.1.9000 stringr_1.4.0 dplyr_1.0.9 purrr_0.3.4
#> [5] readr_2.1.2 tidyr_1.2.0 tibble_3.1.7 tidyverse_1.3.1
#> [9] ggplot2_3.3.6 magrittr_2.0.3 masstools_1.0.2 massdataset_1.0.12
#>
#> loaded via a namespace (and not attached):
#> [1] readxl_1.4.0 backports_1.4.1
#> [3] circlize_0.4.15 systemfonts_1.0.4
#> [5] plyr_1.8.7 lazyeval_0.2.2
#> [7] BiocParallel_1.30.3 GenomeInfoDb_1.32.2
#> [9] Rdisop_1.56.0 digest_0.6.29
#> [11] foreach_1.5.2 yulab.utils_0.0.5
#> [13] htmltools_0.5.2 fansi_1.0.3
#> [15] memoise_2.0.1 cluster_2.1.3
#> [17] doParallel_1.0.17 tzdb_0.3.0
#> [19] openxlsx_4.2.5 limma_3.52.2
#> [21] ComplexHeatmap_2.12.0 modelr_0.1.8
#> [23] matrixStats_0.62.0 pkgdown_2.0.5
#> [25] colorspace_2.0-3 rvest_1.0.2
#> [27] textshaping_0.3.6 haven_2.5.0
#> [29] xfun_0.31 crayon_1.5.1
#> [31] RCurl_1.98-1.7 jsonlite_1.8.0
#> [33] impute_1.70.0 iterators_1.0.14
#> [35] glue_1.6.2 gtable_0.3.0
#> [37] zlibbioc_1.42.0 XVector_0.36.0
#> [39] GetoptLong_1.0.5 DelayedArray_0.22.0
#> [41] shape_1.4.6 BiocGenerics_0.42.0
#> [43] scales_1.2.0 vsn_3.64.0
#> [45] DBI_1.1.3 Rcpp_1.0.8.3
#> [47] mzR_2.30.0 viridisLite_0.4.0
#> [49] clue_0.3-61 gridGraphics_0.5-1
#> [51] preprocessCore_1.58.0 stats4_4.2.1
#> [53] MsCoreUtils_1.8.0 htmlwidgets_1.5.4
#> [55] httr_1.4.3 RColorBrewer_1.1-3
#> [57] ellipsis_0.3.2 pkgconfig_2.0.3
#> [59] XML_3.99-0.10 sass_0.4.1
#> [61] dbplyr_2.2.1 utf8_1.2.2
#> [63] ggplotify_0.1.0 tidyselect_1.1.2
#> [65] rlang_1.0.3 munsell_0.5.0
#> [67] cellranger_1.1.0 tools_4.2.1
#> [69] cachem_1.0.6 cli_3.3.0
#> [71] generics_0.1.3 broom_1.0.0
#> [73] evaluate_0.15 fastmap_1.1.0
#> [75] mzID_1.34.0 yaml_2.3.5
#> [77] ragg_1.2.2 knitr_1.39
#> [79] fs_1.5.2 zip_2.2.0
#> [81] ncdf4_1.19 pbapply_1.5-0
#> [83] xml2_1.3.3 compiler_4.2.1
#> [85] rstudioapi_0.13 plotly_4.10.0
#> [87] png_0.1-7 affyio_1.66.0
#> [89] reprex_2.0.1 bslib_0.3.1
#> [91] stringi_1.7.6 highr_0.9
#> [93] desc_1.4.1 MSnbase_2.22.0
#> [95] lattice_0.20-45 ProtGenerics_1.28.0
#> [97] Matrix_1.4-1 ggsci_2.9
#> [99] vctrs_0.4.1 pillar_1.7.0
#> [101] lifecycle_1.0.1 BiocManager_1.30.18
#> [103] jquerylib_0.1.4 MALDIquant_1.21
#> [105] GlobalOptions_0.1.2 data.table_1.14.2
#> [107] bitops_1.0-7 GenomicRanges_1.48.0
#> [109] R6_2.5.1 pcaMethods_1.88.0
#> [111] affy_1.74.0 IRanges_2.30.0
#> [113] codetools_0.2-18 MASS_7.3-57
#> [115] assertthat_0.2.1 SummarizedExperiment_1.26.1
#> [117] rprojroot_2.0.3 rjson_0.2.21
#> [119] withr_2.5.0 S4Vectors_0.34.0
#> [121] GenomeInfoDbData_1.2.8 parallel_4.2.1
#> [123] hms_1.1.1 grid_4.2.1
#> [125] rmarkdown_2.14 MatrixGenerics_1.8.1
#> [127] Biobase_2.56.0 lubridate_1.8.0