Merge two mass_dataset
Xiaotao Shen (https://www.shenxt.info/)
Created on 2021-12-04 and updated on 2023-10-01
Source:vignettes/merge_two_mass_dataset.Rmd
merge_two_mass_dataset.RmdIn massdataset package, the
merge_mass_dataset is more powerful to merge tow
mass_dataset 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
)
object1 = object[1:10, 1:5]
object2 = object[5:15, 3:7]
colnames(object1)
#> [1] "Blank_3" "Blank_4" "QC_1" "QC_2" "PS4P1"
colnames(object2)
#> [1] "QC_1" "QC_2" "PS4P1" "PS4P2" "PS4P3"
rownames(object1)
#> [1] "M136T55_2_POS" "M79T35_POS" "M307T548_POS" "M183T224_POS"
#> [5] "M349T47_POS" "M182T828_POS" "M299T359_POS" "M348T844_POS"
#> [9] "M344T471_POS" "M181T436_POS"
rownames(object2)
#> [1] "M349T47_POS" "M182T828_POS" "M299T359_POS" "M348T844_POS" "M344T471_POS"
#> [6] "M181T436_POS" "M345T195_POS" "M304T825_POS" "M137T196_POS" "M359T638_POS"
#> [11] "M270T507_POS"
Merge two mass_dataset
object =
merge_mass_dataset(x = object1, y = object2,
sample_direction = "left",
variable_direction = "left",
sample_by = "sample_id",
variable_by = "variable_id")
extract_expression_data(object1)
#> Blank_3 Blank_4 QC_1 QC_2 PS4P1
#> M136T55_2_POS NA NA 1857924.8 1037763.8 1494436.1
#> M79T35_POS NA NA 2821550.2 1304875.3 2471336.1
#> M307T548_POS NA NA 410387.6 273687.8 288590.2
#> M183T224_POS NA NA NA NA NA
#> M349T47_POS NA NA 8730104.8 4105598.5 5141073.2
#> M182T828_POS 3761892.6 2572593.4 NA 3662819.1 5700534.8
#> M299T359_POS NA NA 3688690.6 2892719.6 1401632.7
#> M348T844_POS NA NA NA 3131157.7 NA
#> M344T471_POS NA NA 589957.0 408610.8 NA
#> M181T436_POS 249352.6 131374.5 248764.1 208789.4 423991.8
extract_expression_data(object2)
#> QC_1 QC_2 PS4P1 PS4P2 PS4P3
#> M349T47_POS 8730104.8 4105598.5 5141073.2 8424315.6 7896633.3
#> M182T828_POS NA 3662819.1 5700534.8 4600172.4 5557014.6
#> M299T359_POS 3688690.6 2892719.6 1401632.7 4055989.5 1577496.3
#> M348T844_POS NA 3131157.7 NA NA 3643606.4
#> M344T471_POS 589957.0 408610.8 NA 276913.4 304611.5
#> M181T436_POS 248764.1 208789.4 423991.8 449021.6 357037.7
#> M345T195_POS NA 5776921.1 NA NA NA
#> M304T825_POS 2816826.6 237776.3 439981.6 510661.8 415109.5
#> M137T196_POS NA 11028014.0 NA NA NA
#> M359T638_POS 1367524.9 1044288.4 1786016.1 1878777.4 1025039.9
#> M270T507_POS 107442.7 NA NA NA 60286.3
extract_expression_data(object)
#> Blank_3 Blank_4 QC_1 QC_2 PS4P1
#> M136T55_2_POS NA NA 1857924.8 1037763.8 1494436.1
#> M79T35_POS NA NA 2821550.2 1304875.3 2471336.1
#> M307T548_POS NA NA 410387.6 273687.8 288590.2
#> M183T224_POS NA NA NA NA NA
#> M349T47_POS NA NA 8730104.8 4105598.5 5141073.2
#> M182T828_POS 3761892.6 2572593.4 NA 3662819.1 5700534.8
#> M299T359_POS NA NA 3688690.6 2892719.6 1401632.7
#> M348T844_POS NA NA NA 3131157.7 NA
#> M344T471_POS NA NA 589957.0 408610.8 NA
#> M181T436_POS 249352.6 131374.5 248764.1 208789.4 423991.8Session 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] masstools_1.0.2 forcats_0.5.1.9000 stringr_1.4.0 dplyr_1.0.9
#> [5] purrr_0.3.4 readr_2.1.2 tidyr_1.2.0 tibble_3.1.7
#> [9] ggplot2_3.3.6 tidyverse_1.3.1 magrittr_2.0.3 tinytools_0.9.1
#> [13] 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 desc_1.4.1
#> [93] MSnbase_2.22.0 lattice_0.20-45
#> [95] ProtGenerics_1.28.0 Matrix_1.4-1
#> [97] ggsci_2.9 vctrs_0.4.1
#> [99] pillar_1.7.0 lifecycle_1.0.1
#> [101] BiocManager_1.30.18 jquerylib_0.1.4
#> [103] MALDIquant_1.21 GlobalOptions_0.1.2
#> [105] data.table_1.14.2 bitops_1.0-7
#> [107] GenomicRanges_1.48.0 R6_2.5.1
#> [109] pcaMethods_1.88.0 affy_1.74.0
#> [111] IRanges_2.30.0 codetools_0.2-18
#> [113] MASS_7.3-57 assertthat_0.2.1
#> [115] SummarizedExperiment_1.26.1 rprojroot_2.0.3
#> [117] rjson_0.2.21 withr_2.5.0
#> [119] S4Vectors_0.34.0 GenomeInfoDbData_1.2.8
#> [121] parallel_4.2.1 hms_1.1.1
#> [123] grid_4.2.1 rmarkdown_2.14
#> [125] MatrixGenerics_1.8.1 Biobase_2.56.0
#> [127] lubridate_1.8.0