Classify BL samples into genetic subgroups. — classify

Assemble the binary feature matrix and use the random forest prediction model to classify BL tumors into genetic subgroups. Please see PMID 36201743 on genetic subgroups of BL.

Usage

classify_bl(
  these_samples_metadata,
  maf_data,
  projection = "grch37",
  output = "both",
  ashm_cutoff = 3
)

Arguments

these_samples_metadata: The metadata data frame that contains sample_id column with ids for the samples to be classified. Required input.
maf_data: The MAF data frame to be used for matrix assembling. Any maf columns can be provided, but the required are "Hugo_Symbol", "NCBI_Build", "Chromosome", "Start_Position", "End_Position", "Variant_Classification", "HGVSp_Short", and "Tumor_Sample_Barcode". Required input.
projection: The projection of the samples. Defaults to grch37.
output: The output to be returned after prediction is done. Can be one of predictions, matrix, or both. Defaults to both.
ashm_cutoff: Numeric value indicating number of mutations for binarizing aSHM feature. Recommended to use the default value (3).

Value

data frame with classification, binary matrix used in classification, or both

Examples

if (FALSE) { # \dontrun{
test_meta <- get_gambl_metadata()  %>%
    filter(pathology == "BL")
maf <- get_ssm_by_samples(
    these_samples_metadata = test_meta
)
predictions <- classify_bl(
     these_samples_metadata = test_meta,
     maf_data = maf
)
predictions <- classify_bl(
     these_samples_metadata = test_meta,
     maf_data = maf,
     output = "predictions"
)
} # }