LFQData R6 class

LFQData R6 class

LFQData R6 class

See also

Other LFQData: LFQDataAggregator, LFQDataPlotter, LFQDataStats, LFQDataSummariser, LFQDataToSummarizedExperiment(), LFQDataWriter

Public fields

config

AnalysisConfiguration

data

data.frame or tibble matching AnalysisConfiguration.

is_pep

todo

prefix

e.g. "peptide_", "protein_", "compound_"

Methods

Public methods

• LFQData$new()

• LFQData$get_copy()

• LFQData$get_sample()

• LFQData$get_subset()

• LFQData$subject_Id()

• LFQData$is_transformed()

• LFQData$remove_small_intensities()

• LFQData$filter_proteins_by_peptide_count()

• LFQData$omit_NA()

• LFQData$complete_cases()

• LFQData$to_wide()

• LFQData$factors()

• LFQData$hierarchy()

• LFQData$response()

• LFQData$rename_response()

• LFQData$hierarchy_counts()

• LFQData$summarize_hierarchy()

• LFQData$get_Plotter()

• LFQData$get_Writer()

• LFQData$get_Summariser()

• LFQData$get_Stats()

• LFQData$get_Transformer()

• LFQData$get_Aggregator()

• LFQData$filter_difference()

• LFQData$clone()

---

Method new()

initialize

Usage

LFQData$new(data, config, is_pep = TRUE, prefix = "ms_", setup = FALSE)

Arguments

data

data.frame

config

configuration

is_pep

todo

prefix

will be use as output prefix

setup

is data setup needed, default = FALSE, if TRUE, calls setup_analysis on data first.

---

Method get_copy()

get deep copy

Usage

LFQData$get_copy()

---

Method get_sample()

samples subset of data

Usage

LFQData$get_sample(size = 100, seed = NULL)

Arguments

size

size of subset default 100

seed

set seed

---

Method get_subset()

get subset of data

Usage

LFQData$get_subset(x)

Arguments

x

data frame with columns containing subject_Id

---

Method subject_Id()

get subject ID columns

Usage

LFQData$subject_Id()

---

Method is_transformed()

is data transformed

Usage

LFQData$is_transformed(is_transformed)

Arguments

is_transformed

logical

Returns

logical

---

Method remove_small_intensities()

some software is reporting NA's as 0, you must remove it from your data

Usage

LFQData$remove_small_intensities(threshold = 4)

Arguments

threshold

default 4.

Returns

self

---

Method filter_proteins_by_peptide_count()

remove proteins with less than X peptides

Usage

LFQData$filter_proteins_by_peptide_count()

Returns

self

---

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

Usage

LFQData$omit_NA(nrNA = 0, factorDepth = NULL)

Arguments

nrNA

number of NA values

factorDepth

you control for nrNA per condition or experiment etc. e.g. factorDepth = 0 then per experiment

Returns

LFQData with NA omitted.

---

Method complete_cases()

some software is reporting NA's as 0, you must remove it from your data

Usage

LFQData$complete_cases()

Arguments

threshold

default 4.

Returns

self

---

Method to_wide()

converts the data to wide

Usage

LFQData$to_wide(as.matrix = FALSE, value = c("response", "nr_children"))

Arguments

as.matrix

return as data.frame or matrix

value

either response or nr chidren

Returns

list with data, annotation, and configuration

---

Method factors()

Annotation table

Usage

LFQData$factors()

Returns

data.frame

---

Method hierarchy()

Hierarchy table

Usage

LFQData$hierarchy()

---

Method response()

name of response variable

Usage

LFQData$response()

Returns

data.frame

---

Method rename_response()

new name of response variable

Usage

LFQData$rename_response(newname = "Intensity")

Arguments

newname

default Intensity

---

Method hierarchy_counts()

number of elements at each level

Usage

LFQData$hierarchy_counts()

---

Method summarize_hierarchy()

e.g. number of peptides per protein etc

Usage

LFQData$summarize_hierarchy()

Returns

data.frame

---

Method get_Plotter()

get Plotter

Usage

LFQData$get_Plotter()

Returns

LFQDataPlotter

---

Method get_Writer()

get Writer

Usage

LFQData$get_Writer(format = "xlsx")

Arguments

format

array of formats to write to supported are xlsx, csv and html

Returns

LFQDataPlotter

---

Method get_Summariser()

get Summariser

Usage

LFQData$get_Summariser()

Returns

LFQDataSummarizer

---

Method get_Stats()

Get LFQDataStats. For more details see LFQDataStats.

Usage

LFQData$get_Stats(stats = c("everything", "interaction", "all"))

Arguments

stats

default interaction, computes statistics within interaction.

Returns

LFQDataStats

---

Method get_Transformer()

get Stats

Usage

LFQData$get_Transformer()

Returns

LFQDataTransformer

---

Method get_Aggregator()

get Aggregator

Usage

LFQData$get_Aggregator()

Returns

LFQDataAggregator

---

Method filter_difference()

get difference of self with other if other is subset of self

Usage

LFQData$filter_difference(other)

Arguments

other

a filtered LFQData set

Details

Use to compare filtering results obtained from self, e.g. which proteins and peptides were removed (other)

Returns

LFQData

---

Method clone()

The objects of this class are cloneable with this method.

Usage

LFQData$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

istar <- sim_lfq_data_peptide_config()
#> creating sampleName from fileName column
#> Warning: no nr_children column specified in the data, adding column nr_children and setting to 1.
#> completing cases
#LFQData$debug("omit_NA")
lfqdata <- LFQData$new(istar$data, istar$config)
lfqdata$filter_proteins_by_peptide_count()
#> removing proteins with less than: 2 peptpides
#> Column added : nr_peptide_Id_IN_protein_Id
tmp <- lfqdata$to_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$data))
tmp <- lfqdata$to_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$omit_NA(nrNA = 0)
#> [1] "group_"
#> completing cases
#> Joining with `by = join_by(protein_Id, peptide_Id)`
stopifnot(f1$hierarchy_counts() <= lfqdata$hierarchy_counts())

f2 <- lfqdata$omit_NA(factorDepth = 0)
#> NULL
#> completing cases
#> Joining with `by = join_by(protein_Id, peptide_Id)`
stopifnot(f2$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()))
#> [1] "group_"
#> completing cases
#> NULL
#> completing cases
stopifnot("LFQDataSummariser" %in% class(lfqdata$get_Summariser()))
stopifnot("LFQDataPlotter" %in% class(lfqdata$get_Plotter()))
stopifnot("LFQDataWriter" %in% class(lfqdata$get_Writer()))
stopifnot("LFQDataAggregator" %in% class(lfqdata$get_Aggregator()))

lfqdata2 <- lfqdata$get_copy()
lfqdata2$data <- lfqdata2$data[1:100,]
res <- lfqdata$filter_difference(lfqdata2)
stopifnot(nrow(res$data) == nrow(lfqdata$data) - 100)

tmp <- lfqdata$get_sample(5, seed = 4)
#> Sampling 5protein_Id
#> Joining with `by = join_by(protein_Id)`
stopifnot(nrow(tmp$hierarchy()) == 5)

lw <- lfqdata$get_Writer()
stopifnot(names(lw$get_wide()) %in% c("data", "annotation"))

stopifnot("data.frame" %in% class(lw$get_long()))