Identify biomarkers

Source: R/find_biomarker.R

Identify biomarkers

find_biomarker(
  MAE,
  tax_level,
  input_select_target_biomarker,
  nfolds = 3,
  nrepeats = 3,
  seed = 99,
  percent_top_biomarker = 0.2,
  model_name = c("logistic regression", "random forest")
)

Arguments

MAE

A multi-assay experiment object
tax_level

The taxon level used for organisms
input_select_target_biomarker

Which condition is the target condition
nfolds

number of splits in CV
nrepeats

number of CVs with different random splits
seed

for repeatable research
percent_top_biomarker

Top importance percentage to pick biomarker
model_name

one of 'logistic regression', 'random forest'

Value

A list

Examples

data_dir = system.file('extdata/MAE.rds', package = 'animalcules')
toy_data <- readRDS(data_dir)
p <- find_biomarker(toy_data,
                    tax_level='family',
                    input_select_target_biomarker=c('DISEASE'),
                    nfolds = 3,
                    nrepeats = 3,
                    seed = 99,
                    percent_top_biomarker = 0.2,
                    model_name = 'logistic regression')

#> Loading required package: lattice
#> Loading required package: ggplot2
p

#> $biomarker
#>        biomarker_list
#> 1 Geodermatophilaceae
#> 2  Intrasporangiaceae
#> 3       Didymellaceae
#> 4   Streptomycetaceae
#> 5      Coccodiniaceae
#> 6         Nectriaceae
#> 7   Staphylococcaceae
#> 8       Moraxellaceae
#> 9      Malasseziaceae
#> 
#> $importance_plot
#> 
#> $roc_plot
#>