modelvar: Get model variable

In bhagwataditya/autonomics: Unified statistal Modeling of Omics Data

Get model variable

Description

Get model variable

Usage

modelvar(object, ...)

## S3 method for class 'data.table'
modelvar(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit),
  ...
)

## S3 method for class 'SummarizedExperiment'
modelvar(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit),
  ...
)

effectvar(object, fit = fits(object), coef = default_coefs(object, fit = fit))

tvar(object, fit = fits(object), coef = default_coefs(object, fit = fit))

pvar(object, fit = fits(object), coef = default_coefs(object, fit = fit))

fdrvar(object, fit = fits(object), coef = default_coefs(object, fit = fit))

abstractvar(object, ...)

## S3 method for class 'data.table'
abstractvar(
  object,
  fit = fits(object),
  coef = default_coefs(object, fit = fit),
  ...
)

## S3 method for class 'SummarizedExperiment'
abstractvar(
  object,
  fit = fits(object),
  coef = default_coefs(object, fit = fit),
  ...
)

modelvec(object, ...)

## S3 method for class 'data.table'
modelvec(
  object,
  quantity,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id",
  ...
)

## S3 method for class 'SummarizedExperiment'
modelvec(
  object,
  quantity,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id",
  ...
)

effectvec(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object)[1],
  fvar = "feature_id"
)

tvec(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id"
)

pvec(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id"
)

fdrvec(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id"
)

abstractvec(object, ...)

## S3 method for class 'data.table'
abstractvec(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id",
  ...
)

## S3 method for class 'SummarizedExperiment'
abstractvec(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id",
  ...
)

modeldt(object, ...)

## S3 method for class 'data.table'
modeldt(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit),
  ...
)

## S3 method for class 'SummarizedExperiment'
modeldt(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit),
  ...
)

effectdt(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit)
)

tdt(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit)
)

pdt(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit)
)

modelmat(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit)
)

modelmat(
  object,
  quantity,
  fit = fits(object),
  coef = default_coefs(object, fit = fit)
)

effectmat(object, fit = fits(object), coef = default_coefs(object, fit = fit))

effectsizemat(
  object,
  fit = fits(object),
  coef = default_coefs(object, fit = fit)
)

tmat(object, fit = fits(object), coef = default_coefs(object, fit = fit))

pmat(object, fit = fits(object), coef = default_coefs(object, fit = fit))

fdrmat(object, fit = fits(object), coef = default_coefs(object, fit = fit))

modelfeatures(object, ...)

## S3 method for class 'data.table'
modelfeatures(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id",
  significancevar = "p",
  significance = 0.05,
  effectdirection = "<>",
  effectsize = 0,
  ...
)

## S3 method for class 'SummarizedExperiment'
modelfeatures(object, ...)

upfeatures(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id",
  significancevar = "p",
  significance = 0.05,
  effectsize = 0
)

downfeatures(
  object,
  fit = fits(object)[1],
  coef = default_coefs(object, fit = fit)[1],
  fvar = "feature_id",
  significancevar = "p",
  significance = 0.05,
  effectsize = 0
)

Arguments

object	data.table or SummarizedExperiment
...	S3 dispatch
quantity	'p', 'effect', 'fdr', 't', or 'se'
fit	string (vector)
coef	string (vector)
fvar	'feature_id' or other fvar for values (pvec) or names (upfeatures)
significancevar	'p' or 'fdr'
significance	p or fdr cutoff (fractional number)
effectdirection	'<>', '<' or '>'
effectsize	effectsize cutoff (positive number)

Value

string (tvar), matrix (tmat), numeric vector (tvec), character vector (tfeatures)

Examples

    file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics')
    object <- read_metabolon(file)
    object %<>% fit_limma(statvars = c('effect', 't', 'p'))
    object %<>% fit_lm(   statvars = c('effect', 't', 'p'))

    effectvar(object)
    effectvec(object)[1:3]
     effectdt(object)[1:3, ]
    effectmat(object)[1:3, ]

         tvar(object)
         tvec(object)[1:3]
          tdt(object)[1:3, ]
         tmat(object)[1:3, ]

         pvar(object)
         pvec(object)[1:3]
          pdt(object)[1:3, ]
         pmat(object)[1:3, ]

modelfeatures(object)
 downfeatures(object)
   upfeatures(object)

bhagwataditya/autonomics documentation built on Nov. 1, 2024, 5:47 a.m.