LFQData R6 class
LFQData R6 class
Missing Data Assumptions
The filtering and imputation methods in this package assume that missing values are Missing Completely At Random (MCAR) or Missing At Random (MAR). Abundance-dependent missingness (MNAR), which is common in DDA proteomics, is not modelled. Users should be aware that MNAR can bias fold-change estimates and inflate false discovery rates.
Methods
Method new()
initialize
Usage
LFQData$new(data, config, prefix = "ms_", setup = FALSE)Arguments
datadata.frame
configconfiguration
prefixwill be use as output prefix
setupis data setup needed, default = FALSE, if TRUE, calls
setup_analysison data first.is_peptodo
Method remove_small_intensities()
some software is reporting NA's as 0, you must remove it from your data
Method filter_proteins_by_peptide_count()
remove proteins with less than X peptides
Method omit_na()
Omit NA from intensities per hierarchy (e.g. protein or peptide), idea is to use it for normalization For instance if a peptide has a missing value in more then nrNA of the samples within a condition it will be removed
Method complete_cases()
some software is reporting NA's as 0, you must remove it from your data
Method data_wide()
converts the data to wide
Method relevant_hierarchy_keys()
return hierarchy column names at current depth (alias for subject_id)
Method summarize_hierarchy()
e.g. number of peptides per protein etc
Method get_Stats()
Get LFQDataStats. For more details see LFQDataStats.
Usage
LFQData$get_Stats(stats = c("everything", "interaction", "all"))Method get_Aggregator()
get Aggregator
Method filter_difference()
get difference of self with other if other is subset of self
Examples
istar <- sim_lfq_data_peptide_config()
#> creating sampleName from file_name column
#> completing cases
#> completing cases done
#> setup done
lfqdata <- LFQData$new(istar$data, istar$config)
lfqdata$filter_proteins_by_peptide_count()
#> removing proteins with less than: 2 peptpides
#> Column added : nr_peptide_Id_IN_protein_Id
tmp <- lfqdata$data_wide()
testthat::expect_equal(nrow(tmp$data) , nrow(tmp$rowdata))
testthat::expect_equal(ncol(tmp$data) , nrow(tmp$annotation) + ncol(tmp$rowdata))
stopifnot("data.frame" %in% class(tmp$data))
tmp <- lfqdata$data_wide(as.matrix = TRUE)
stopifnot("matrix" %in% class(tmp$data))
stopifnot(lfqdata$is_transformed()==FALSE)
lfqdata$summarize_hierarchy()
#> # A tibble: 6 × 3
#> protein_Id isotopeLabel_n peptide_Id_n
#> <chr> <int> <int>
#> 1 0EfVhX~0087 1 3
#> 2 BEJI92~5282 1 2
#> 3 Fl4JiV~8625 1 4
#> 4 HvIpHG~9079 1 2
#> 5 JcKVfU~9653 1 7
#> 6 SGIVBl~5782 1 6
# filter for missing values
f1 <- lfqdata$omit_na(nr_na = 0)
#> Joining with `by = join_by(protein_Id, peptide_Id)`
stopifnot(f1$hierarchy_counts() <= lfqdata$hierarchy_counts())
f2 <- lfqdata$omit_na(factor_depth = 0)
#> Joining with `by = join_by(protein_Id, peptide_Id)`
stopifnot(f2$hierarchy_counts() <= lfqdata$hierarchy_counts())
lfqdata$response()
#> [1] "abundance"
lfqdata$rename_response("peptide.intensity")
lfqdata$response()
#> [1] "peptide.intensity"
stopifnot("LFQData" %in% class(lfqdata$get_copy()))
stopifnot("LFQDataTransformer" %in% class(lfqdata$get_Transformer()))
stopifnot("LFQDataStats" %in% class(lfqdata$get_Stats()))
stopifnot("LFQDataSummariser" %in% class(lfqdata$get_Summariser()))
stopifnot("LFQDataPlotter" %in% class(lfqdata$get_Plotter()))
stopifnot("AggregateMedpolish" %in% class(lfqdata$get_Aggregator("medpolish")))
#> Warning: You did not transform the intensities. medpolish works best with already variance stabilized intensities. Use LFQData$get_Transformer to transform the data: peptide.intensity
lfqdata2 <- lfqdata$get_copy()
lfqdata2$set_data(lfqdata2$data_long()[1:100, ])
res <- lfqdata$filter_difference(lfqdata2)
stopifnot(nrow(res$data_long()) == nrow(lfqdata$data_long()) - 100)
tmp <- lfqdata$get_sample(5, seed = 4)
#> Sampling 5protein_Id
#> Joining with `by = join_by(protein_Id)`
stopifnot(nrow(tmp$hierarchy()) == 5)