get_splits: Split a set of reference protein-protein interactions into...

In fosterlab/CFTK: The Co-Fractionation Toolkit

Description

Split a set of reference protein-protein interactions into cross-validation folds, for use in score_interactions.

Usage

get_splits(gold_standard, n_folds = 10, split_by = c("proteins", "pairs"))

Arguments

gold_standard	a data frame with columns protein_A and protein_B, as returned by to_pairwise_df, containing 'gold standard' interacting protein pairs
n_folds	the number of folds of cross-validation to perform
split_by	the mechanism by which to split the gold standard into cross-validation folds; either by protein complex subunits ('proteins') or by pairwise interactions between those subunits ('pairs')

Value

a list of length n_folds, in which each item contains "train" and "test" data frames with the columns protein_A, protein_B, and label

fosterlab/CFTK documentation built on Jan. 19, 2021, 10:31 p.m.