cleanet {Cleanet}R Documentation

Detect doublets in a single cytometry sample

Description

Augments data with simulated doublets, computes nearest neighbors for augmented dataset, identifies doublets as those events with a high share of simulated doublets among nearest neighbors.

Usage

cleanet(df, cols, cofactor, thresh = 5, is_debris = NULL)

Arguments

df

A data frame containing protein expression data.

cols

Columns to use in analysis.

cofactor

Parameter of arcsinh transformation, applied before computing nearest neighbors. Recommended values are 5 for mass cytometry and 500-1000 for flow cytometry.

thresh

Among the 15 nearest neighbors, how many should be simulated doublets in order for the event to be classified as doublet?

is_debris

Optional, binary array with length matching the number of rows in df. TRUE for debris events, FALSE for everything else. This package includes helper functions to compute this for flow or mass cytometry data.

Value

A list with multiple elements, among them the singlet/doublet status of each event.

Examples

path <- system.file("extdata", "df_mdipa.csv", package="Cleanet")
df_mdipa <- read.csv(path, check.names=FALSE)
cols <- c("CD45", "CD123", "CD19", "CD11c", "CD16",
          "CD56", "CD294", "CD14", "CD3", "CD20",
          "CD66b", "CD38", "HLA-DR", "CD45RA",
          "DNA1", "DNA2")
cleanet_res <- cleanet(df_mdipa, cols, cofactor=5)

[Package Cleanet version 1.0.0 Index]