Removal of batch effects using distribution‐matching residual networks

By Uri Shaham, Kelly P. Stanton, Jun Zhao, Huamin Li, K. Raddassi, Ruth R. Montgomery, Yuval Kluger. 2016

177 citations recorded by the source corpus.

Motivation: Sources of variability in experimentally derived data include measurement error in addition to the physical phenomena of interest. This measurement error is a combination of systematic components, originating from the measuring instrument and random measurement errors. Several novel biological technologies, such as mass cytometry and single‐cell RNA‐seq (scRNA‐seq), are plagued with systematic errors that may severely affect statistical analysis if the data are not properly calibrated. Results: We propose a novel deep learning approach for removing systematic batch effects. Our method is based on a residual neural network, trained to minimize the Maximum Mean Discrepancy between the multivariate distributions of two replicates, measured in different batches. We apply our method to mass cytometry and scRNA‐seq datasets, and demonstrate that it effectively attenuates batch effects. Availability and Implementation: our codes and data are publicly available at https://github.com/ushaham/BatchEffectRemoval.git Contact: yuval.kluger@yale.edu Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Biophysics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Molecular Biology

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Deep learning has also been useful for dealing with batch effects [218].”
Bayesian Inference for a Generative Model of Transcriptome Profiles from Single-cell RNA Sequencing (2018, background): “Interpreting scRNA-seq remains challenging, however, as the data is confounded by nuisance factors such as variation in capture efficiency and sequencing depth [5], amplification bias, batch effects [6] and transcriptional noise [7].”
Probabilistic harmonization and annotation of single‐cell transcriptomics data with deep generative models (2019, unknown): “Datasets are listed and referenced in Appendix Table S1.”
A benchmark of batch-effect correction methods for single-cell RNA sequencing data (2020, methodology): “Shaham et al. proposed a deep learning approach for removing batch effects based on the residual neural network algorithm, or “ MMD-ResNet ” in 2016 [15].”