mm-shah/MetaNeighbor: Method to rapidly assess cell type identity using gene sets
Version 0.99.12

MetaNeighbor is a replication framework, that allows researchers to quantify the degree to which cell types replicate across datasets, and to rapidly identify clusters with high similarity for further testing. It calculates correlations between all pairs of cells that user aims to compare across datasets based on the expression of a set of genes. It then performs crosdataset validation by hiding all type labels for one dataset at a time. Finally it predicts the cell type labels of the test set by running a neighbor voting algorithm to predict the identity of the held-out cells based on the similarity to the training data.

Getting started

Package details

Authorc(person("Megan", "Crow", email = "[email protected]",role = c("aut", "cre")), person("Sara", "Ballouz", email = "[email protected]",role = c("ctb")), person("Manthan", "Shah", email = "[email protected]",role = c("ctb")), person("Jesse", "Gillis", email = "[email protected]",role = c("aut")))
Bioconductor views GO GeneExpression MultipleComparison SingleCell Transcriptomics
MaintainerManthan Shah <[email protected]>
LicenseMIT + file LICENSE
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
mm-shah/MetaNeighbor documentation built on Dec. 16, 2017, 3:37 p.m.