vignettes/extract_data.Rmd
extract_data.Rmdextract_xxx functions
We first created a mass_dataset class object.
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: 1.0.12
#> --------------------
#> 1.expression_data:[ 1000 x 8 data.frame]
#> 2.sample_info:[ 8 x 4 data.frame]
#> 3.variable_info:[ 1000 x 3 data.frame]
#> 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 (extract_process_info())
#> 1 processings in total
#> create_mass_dataset ----------
#> Package Function.used Time
#> 1 massdataset create_mass_dataset() 2022-08-07 19:23:39In massdataset package, there are a series of functions
named as extract_xxx(), users can use them to extract data
from mass_dataset calss object.
##sample_info
extract_sample_info(object)
#> sample_id injection.order class group
#> 1 Blank_3 1 Blank Blank
#> 2 Blank_4 2 Blank Blank
#> 3 QC_1 3 QC QC
#> 4 QC_2 4 QC QC
#> 5 PS4P1 5 Subject Subject
#> 6 PS4P2 6 Subject Subject
#> 7 PS4P3 7 Subject Subject
#> 8 PS4P4 8 Subject Subject
##variable_info
extract_variable_info(object) %>% head()
#> variable_id mz rt
#> 1 M136T55_2_POS 136.06140 54.97902
#> 2 M79T35_POS 79.05394 35.36550
#> 3 M307T548_POS 307.14035 547.56641
#> 4 M183T224_POS 183.06209 224.32777
#> 5 M349T47_POS 349.01584 47.00262
#> 6 M182T828_POS 181.99775 828.35712
##expression_data
extract_expression_data(object) %>% head()
#> Blank_3 Blank_4 QC_1 QC_2 PS4P1 PS4P2 PS4P3
#> M136T55_2_POS NA NA 1857924.8 1037763.8 1494436.1 3496912.1 1959179
#> M79T35_POS NA NA 2821550.2 1304875.3 2471336.1 3333582.7 2734244
#> M307T548_POS NA NA 410387.6 273687.8 288590.2 137297.5 NA
#> M183T224_POS NA NA NA NA NA 5059068.1 5147422
#> M349T47_POS NA NA 8730104.8 4105598.5 5141073.2 8424315.6 7896633
#> M182T828_POS 3761893 2572593 NA 3662819.1 5700534.8 4600172.4 5557015
#> PS4P4
#> M136T55_2_POS 1005418.8
#> M79T35_POS 3361452.3
#> M307T548_POS 271318.3
#> M183T224_POS NA
#> M349T47_POS 6441449.0
#> M182T828_POS 4433034.2
##sample_info_note
extract_sample_info_note(object)
#> name meaning
#> 1 sample_id sample_id
#> 2 injection.order injection.order
#> 3 class class
#> 4 group group
##variable_info_note
extract_variable_info_note(object)
#> name meaning
#> 1 variable_id variable_id
#> 2 mz mz
#> 3 rt rt
##ms2_data
extract_ms2_data(object)
#> list()
##process_info
extract_annotation_table(object)
#> data frame with 0 columns and 0 rows
##process_info
extract_process_info(object)
#> $create_mass_dataset
#> --------------------
#> pacakge_name: massdataset
#> function_name: create_mass_dataset()
#> time: 2022-08-07 19:23:39
#> parameters:
#> no : no
slot(object = object, name = "sample_info")
#> sample_id injection.order class group
#> 1 Blank_3 1 Blank Blank
#> 2 Blank_4 2 Blank Blank
#> 3 QC_1 3 QC QC
#> 4 QC_2 4 QC QC
#> 5 PS4P1 5 Subject Subject
#> 6 PS4P2 6 Subject Subject
#> 7 PS4P3 7 Subject Subject
#> 8 PS4P4 8 Subject Subject
slot(object = object, name = "variable_info") %>% head()
#> variable_id mz rt
#> 1 M136T55_2_POS 136.06140 54.97902
#> 2 M79T35_POS 79.05394 35.36550
#> 3 M307T548_POS 307.14035 547.56641
#> 4 M183T224_POS 183.06209 224.32777
#> 5 M349T47_POS 349.01584 47.00262
#> 6 M182T828_POS 181.99775 828.35712
slot(object = object, name = "expression_data") %>% head()
#> Blank_3 Blank_4 QC_1 QC_2 PS4P1 PS4P2 PS4P3
#> M136T55_2_POS NA NA 1857924.8 1037763.8 1494436.1 3496912.1 1959179
#> M79T35_POS NA NA 2821550.2 1304875.3 2471336.1 3333582.7 2734244
#> M307T548_POS NA NA 410387.6 273687.8 288590.2 137297.5 NA
#> M183T224_POS NA NA NA NA NA 5059068.1 5147422
#> M349T47_POS NA NA 8730104.8 4105598.5 5141073.2 8424315.6 7896633
#> M182T828_POS 3761893 2572593 NA 3662819.1 5700534.8 4600172.4 5557015
#> PS4P4
#> M136T55_2_POS 1005418.8
#> M79T35_POS 3361452.3
#> M307T548_POS 271318.3
#> M183T224_POS NA
#> M349T47_POS 6441449.0
#> M182T828_POS 4433034.2
slot(object = object, name = "sample_info_note")
#> name meaning
#> 1 sample_id sample_id
#> 2 injection.order injection.order
#> 3 class class
#> 4 group group
slot(object = object, name = "variable_info_note")
#> name meaning
#> 1 variable_id variable_id
#> 2 mz mz
#> 3 rt rt
slot(object = object, name = "ms2_data")
#> list()
slot(object = object, name = "process_info")
#> $create_mass_dataset
#> --------------------
#> pacakge_name: massdataset
#> function_name: create_mass_dataset()
#> time: 2022-08-07 19:23:39
#> parameters:
#> no : no
slot(object = object, name = "annotation_table")
#> data frame with 0 columns and 0 rows@
mass_data class is a S4 object. So we can also use
@.
object@expression_data %>% head()
#> Blank_3 Blank_4 QC_1 QC_2 PS4P1 PS4P2 PS4P3
#> M136T55_2_POS NA NA 1857924.8 1037763.8 1494436.1 3496912.1 1959179
#> M79T35_POS NA NA 2821550.2 1304875.3 2471336.1 3333582.7 2734244
#> M307T548_POS NA NA 410387.6 273687.8 288590.2 137297.5 NA
#> M183T224_POS NA NA NA NA NA 5059068.1 5147422
#> M349T47_POS NA NA 8730104.8 4105598.5 5141073.2 8424315.6 7896633
#> M182T828_POS 3761893 2572593 NA 3662819.1 5700534.8 4600172.4 5557015
#> PS4P4
#> M136T55_2_POS 1005418.8
#> M79T35_POS 3361452.3
#> M307T548_POS 271318.3
#> M183T224_POS NA
#> M349T47_POS 6441449.0
#> M182T828_POS 4433034.2
object@sample_info
#> sample_id injection.order class group
#> 1 Blank_3 1 Blank Blank
#> 2 Blank_4 2 Blank Blank
#> 3 QC_1 3 QC QC
#> 4 QC_2 4 QC QC
#> 5 PS4P1 5 Subject Subject
#> 6 PS4P2 6 Subject Subject
#> 7 PS4P3 7 Subject Subject
#> 8 PS4P4 8 Subject Subject
object@variable_info %>% head()
#> variable_id mz rt
#> 1 M136T55_2_POS 136.06140 54.97902
#> 2 M79T35_POS 79.05394 35.36550
#> 3 M307T548_POS 307.14035 547.56641
#> 4 M183T224_POS 183.06209 224.32777
#> 5 M349T47_POS 349.01584 47.00262
#> 6 M182T828_POS 181.99775 828.35712
object@sample_info_note
#> name meaning
#> 1 sample_id sample_id
#> 2 injection.order injection.order
#> 3 class class
#> 4 group group
object@variable_info_note
#> name meaning
#> 1 variable_id variable_id
#> 2 mz mz
#> 3 rt rt
object@process_info
#> $create_mass_dataset
#> --------------------
#> pacakge_name: massdataset
#> function_name: create_mass_dataset()
#> time: 2022-08-07 19:23:39
#> parameters:
#> no : no
object@ms2_data
#> list()
object@annotation_table
#> data frame with 0 columns and 0 rows
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