Add new information to
mass_dataset
Xiaotao Shen (https://www.shenxt.info/)
Created on 2021-12-04 and updated on 2023-10-01
Source:vignettes/add_information.Rmd
add_information.RmdFor one mass_dataset class object, we can add some new
information to mass_dataset class.
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
)
Add new information to
sample_info
Use mutate_xxx() functions
library(tidyverse)
###add NA frequency (%) in sample_info
object2 =
object %>%
mutate_sample_na_freq()
extract_sample_info(object2) %>% head()
#> sample_id injection.order class group na_freq
#> 1 Blank_3 1 Blank Blank 0.682
#> 2 Blank_4 2 Blank Blank 0.702
#> 3 QC_1 3 QC QC 0.397
#> 4 QC_2 4 QC QC 0.381
#> 5 PS4P1 5 Subject Subject 0.424
#> 6 PS4P2 6 Subject Subject 0.427
###add NA number (%) in sample_info
object2 =
object %>%
mutate_sample_na_number()
extract_sample_info(object2) %>% head()
#> sample_id injection.order class group na_number
#> 1 Blank_3 1 Blank Blank 682
#> 2 Blank_4 2 Blank Blank 702
#> 3 QC_1 3 QC QC 397
#> 4 QC_2 4 QC QC 381
#> 5 PS4P1 5 Subject Subject 424
#> 6 PS4P2 6 Subject Subject 427If you want to add NA number/frequency based on specific variables, just provide the variable IDs.
###add NA number (%) in sample_info based on variables with mz > 200
variable_id =
object %>%
activate_mass_dataset(what = "variable_info") %>%
filter(mz > 200) %>%
pull(variable_id)
object2 =
object %>%
mutate_sample_na_number(according_to_variables = variable_id)
extract_sample_info(object2) %>% head()
#> sample_id injection.order class group na_number
#> 1 Blank_3 1 Blank Blank 457
#> 2 Blank_4 2 Blank Blank 474
#> 3 QC_1 3 QC QC 248
#> 4 QC_2 4 QC QC 236
#> 5 PS4P1 5 Subject Subject 240
#> 6 PS4P2 6 Subject Subject 241Use mutate() from tidyverse
mass_dataset support tidyverse functions.
So we can just use the mutate() to add new columns in
sample_info.
###add a new column named as sample_id2 in sample_info
object2 =
object %>%
activate_mass_dataset(what = "sample_info") %>%
mutate(sample_id2 = sample_id)
extract_sample_info(object2) %>% head()
#> sample_id injection.order class group sample_id2
#> 1 Blank_3 1 Blank Blank Blank_3
#> 2 Blank_4 2 Blank Blank Blank_4
#> 3 QC_1 3 QC QC QC_1
#> 4 QC_2 4 QC QC QC_2
#> 5 PS4P1 5 Subject Subject PS4P1
#> 6 PS4P2 6 Subject Subject PS4P2Use left_join() from tidyverse
new_sample_info =
data.frame(sample_id = c("PS4P1", "PS4P2"),
BMI = c(20, 22))
object2 =
object %>%
activate_mass_dataset(what = "sample_info") %>%
left_join(new_sample_info, by = "sample_id")
extract_sample_info(object2) %>% head()
#> sample_id injection.order class group BMI
#> 1 Blank_3 1 Blank Blank NA
#> 2 Blank_4 2 Blank Blank NA
#> 3 QC_1 3 QC QC NA
#> 4 QC_2 4 QC QC NA
#> 5 PS4P1 5 Subject Subject 20
#> 6 PS4P2 6 Subject Subject 22
Add new information to
variable_info
Use mutate_xxx() functions
library(tidyverse)
###add mean intensity in variable_info
object2 =
object %>%
mutate_mean_intensity()
extract_variable_info(object2) %>% head()
#> variable_id mz rt mean_intensity
#> M136T55_2_POS M136T55_2_POS 136.06140 54.97902 1808605.7
#> M79T35_POS M79T35_POS 79.05394 35.36550 2671173.4
#> M307T548_POS M307T548_POS 307.14035 547.56641 276256.3
#> M183T224_POS M183T224_POS 183.06209 224.32777 5103244.9
#> M349T47_POS M349T47_POS 349.01584 47.00262 6789862.4
#> M182T828_POS M182T828_POS 181.99775 828.35712 4326865.8
###add median intensity in variable_info
object2 =
object %>%
mutate_median_intensity()
extract_variable_info(object2) %>% head()
#> variable_id mz rt median_intensity
#> M136T55_2_POS M136T55_2_POS 136.06140 54.97902 1676180.4
#> M79T35_POS M79T35_POS 79.05394 35.36550 2777897.0
#> M307T548_POS M307T548_POS 307.14035 547.56641 273687.8
#> M183T224_POS M183T224_POS 183.06209 224.32777 5103244.9
#> M349T47_POS M349T47_POS 349.01584 47.00262 7169041.1
#> M182T828_POS M182T828_POS 181.99775 828.35712 4433034.2If you want to add mean/median intensity based on specific samples, just provide the sample IDs.
library(tidyverse)
###add mean intensity in variable_info based on QC sample
qc_id =
object %>%
activate_mass_dataset(what = "sample_info") %>%
pull(sample_id)
object2 =
object %>%
mutate_mean_intensity(according_to_samples = qc_id, na.rm = TRUE)
extract_variable_info(object2) %>% head()
#> variable_id mz rt mean_intensity
#> M136T55_2_POS M136T55_2_POS 136.06140 54.97902 1808605.7
#> M79T35_POS M79T35_POS 79.05394 35.36550 2671173.4
#> M307T548_POS M307T548_POS 307.14035 547.56641 276256.3
#> M183T224_POS M183T224_POS 183.06209 224.32777 5103244.9
#> M349T47_POS M349T47_POS 349.01584 47.00262 6789862.4
#> M182T828_POS M182T828_POS 181.99775 828.35712 4326865.8
###add RSD for each variable
object2 =
object %>%
mutate_rsd()
extract_variable_info(object2) %>% head()
#> variable_id mz rt rsd
#> M136T55_2_POS M136T55_2_POS 136.06140 54.97902 50.756560
#> M79T35_POS M79T35_POS 79.05394 35.36550 28.257007
#> M307T548_POS M307T548_POS 307.14035 547.56641 35.041286
#> M183T224_POS M183T224_POS 183.06209 224.32777 1.224228
#> M349T47_POS M349T47_POS 349.01584 47.00262 27.715030
#> M182T828_POS M182T828_POS 181.99775 828.35712 25.534063
###add na
object2 =
object %>%
mutate_sample_na_freq()
extract_variable_info(object2) %>% 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
###add na
object2 =
object %>%
mutate_sample_na_number()
extract_variable_info(object2) %>% 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 828.35712Use mutate() from tidyverse
###add a new column named as variable_id2 in variable_info
object2 =
object %>%
activate_mass_dataset(what = "variable_info") %>%
mutate(variable_id2 = variable_id)
extract_sample_info(object2) %>% head()
#> 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 SubjectUse left_join() from tidyverse
new_variable_info =
data.frame(variable_id = c("M136T55_2_POS", "M79T35_POS"),
marker = c("yes", "no"))
object2 =
object %>%
activate_mass_dataset(what = "variable_info") %>%
left_join(new_variable_info, by = "variable_id")
extract_variable_info(object2) %>% head()
#> variable_id mz rt marker
#> 1 M136T55_2_POS 136.06140 54.97902 yes
#> 2 M79T35_POS 79.05394 35.36550 no
#> 3 M307T548_POS 307.14035 547.56641 <NA>
#> 4 M183T224_POS 183.06209 224.32777 <NA>
#> 5 M349T47_POS 349.01584 47.00262 <NA>
#> 6 M182T828_POS 181.99775 828.35712 <NA>
Add new samples to
expression_data
Just use the mutate() to add new samples to
expression_data.
colnames(object)
#> [1] "Blank_3" "Blank_4" "QC_1" "QC_2" "PS4P1" "PS4P2" "PS4P3"
#> [8] "PS4P4"
object2 =
object %>%
activate_mass_dataset(what = "expression_data") %>%
mutate(QC_3 = QC_2,
QC_4 = 1:1000)
colnames(object2)
#> [1] "Blank_3" "Blank_4" "QC_1" "QC_2" "PS4P1" "PS4P2" "PS4P3"
#> [8] "PS4P4" "QC_3" "QC_4"
plot(object2$QC_2, object2$QC_3)
extract_sample_info(object2)
#> 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
#> 9 QC_3 4 QC QC
#> 10 QC_4 NA <NA> <NA>Session 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 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