\\_End_Function_\\ #
tag_subtract(
dataC_mfi,
tag_antigens,
mean_best_CV_var,
tag_file,
batch_vars,
sampleID_var = "sampleID",
antigen_var = "antigen"
)A dataframe
A character vector with the names of proteins or antigens used as TAG.
A character string containing the identifier of the variable with the MFI values.
A data frame with variables antigen, TAG, TAG_name
to show the TAG for the different antigens or proteins in dataC_mfi
A list of characters identifying variables in dataC_mfi for indicating batch.
A character string containing the name of the sample identifier variable. Default set to 'sampleID'
A character string containing the name of the features/protein variable. Default to 'antigen'
A data frame of TAG values subtracted
Subtract the purification TAG data
tag_file <- readr::read_csv(system.file("extdata", "TAG_antigens.csv",
package="protGear"))
#> Rows: 126 Columns: 3
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: ","
#> chr (2): antigen, TAG_name
#> dbl (1): TAG
#>
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
tag_antigens <- c("CD4TAG", "GST", "MBP")
batch_vars <- list(machine = "m1", day = "0520")
dataC <- readr::read_csv(system.file("extdata", "dataC.csv",
package="protGear"))
#> Rows: 567 Columns: 11
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: ","
#> chr (3): sampleID, antigen, iden
#> dbl (8): sample_array_ID, FMedian, BGMedian, FMedianBG_correct, Block, Colum...
#>
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## this file has 3 lab replicates and the default names
dataCV <- cv_estimation(dataC ,lab_replicates=3)
#> Warning: The replicates are as expected per sample per antigen
dataCV_best2 <- best_CV_estimation(dataCV,slide_id = "iden",
lab_replicates = 3, cv_cut_off = 20)
#> Adding missing grouping variables: `row`
tag_subtract(dataCV_best2,tag_antigens=tag_antigens,
mean_best_CV_var="mean_best_CV",
tag_file = tag_file,antigen_var = "antigen", batch_vars = batch_vars)
#> # A tibble: 126 × 35
#> sampleID sample_ar…¹ TAG antigen meanX sdX sdX2_X3 sdX1_X3 sdX1_X2 CVX
#> <chr> <dbl> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 0.0085 11 0 AMA1 643. 98.5 70 69.3 139. 15.3
#> 2 0.0255 8 0 AMA1 699 52.6 74.2 33.9 40.3 7.52
#> 3 0.076 5 0 AMA1 633. 81.3 35.4 77.1 112. 12.8
#> 4 0.23 2 0 AMA1 1725. 60.5 32.5 84.8 52.3 3.51
#> 5 0.73 19 0 AMA1 2504. 119. 166. 61.5 105. 4.75
#> 6 177.78 4 0 AMA1 58262 709. 994. 383. 612. 1.22
#> 7 19.75 10 0 AMA1 64143. 353. 476. 367. 109. 0.55
#> 8 2.19 16 0 AMA1 9243 383. 528. 156. 372. 4.15
#> 9 533 1 0 AMA1 53180. 559. 117. 735. 619. 1.05
#> 10 59.26 7 0 AMA1 61601 894. 1078. 1111. 32.5 1.45
#> # … with 116 more rows, 25 more variables: CVX2_X3 <dbl>, CVX1_X3 <dbl>,
#> # CVX1_X2 <dbl>, cvCat_all <chr>, cvSelected_all <dbl>, iden <chr>,
#> # `1` <dbl>, `2` <dbl>, `3` <dbl>, x <chr>, meanX1_X2 <dbl>, meanX1_X3 <dbl>,
#> # meanX2_X3 <dbl>, meanSelected <dbl>, mean_best_CV <dbl>, best_CV <dbl>,
#> # best_CV_cat <chr>, TAG_name <chr>, CD4TAG <dbl>, GST <dbl>, MBP <dbl>,
#> # TAG_mfi <dbl>, mean_best_CV_tag <dbl>, machine <chr>, day <chr>, and
#> # abbreviated variable name ¹sample_array_ID