ADImpute

Description

Single-cell RNA sequencing (scRNA-seq) methods are typically unable to quantify the expression levels of all genes in a cell, creating a need for the computational prediction of missing values (‘dropout imputation’). Most existing dropout imputation methods are limited in the sense that they exclusively use the scRNA-seq dataset at hand and do not exploit external gene-gene relationship information. Here we propose two novel methods: a gene regulatory network-based approach using gene-gene relationships learnt from external data and a baseline approach corresponding to a sample-wide average. ADImpute can implement these novel methods and also combine them with existing imputation methods (currently supported: DrImpute, SAVER). ADImpute can learn the best performing method per gene and combine the results from different methods into an ensemble.

Test coverage is not measured for Bioconductor packages; nodes fall back to a neutral fill.

Code

Per-file churn detail lives in the source pipeline: https://github.com/r-observatory/bioc-code-metrics.

Topics

People

• Ana Carolina Leote maintainer author