Imperial College London
Portrait Picture

Professor Jake Baum

Faculty of Natural Sciences, Department of Life Sciences

Visiting Professor
 
 
 
//

Contact

 

+44 (0)20 7594 5420jake.baum Website

 
 
//

Location

 

c/o Baum labSir Alexander Fleming BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Qian:2020:bioinformatics/btaa819,
author = {Qian, WW and Xia, C and Venugopalan, S and Narayanaswamy, A and Dimon, M and Ashdown, GW and Baum, J and Peng, J and Ando, DM},
doi = {bioinformatics/btaa819},
journal = {Bioinformatics},
pages = {I875--I883},
title = {Batch equalization with a generative adversarial network},
url = {http://dx.doi.org/10.1093/bioinformatics/btaa819},
volume = {36},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - MotivationAdvances in automation and imaging have made it possible to capture a large image dataset that spans multiple experimental batches of data. However, accurate biological comparison across the batches is challenged by batch-to-batch variation (i.e. batch effect) due to uncontrollable experimental noise (e.g. varying stain intensity or cell density). Previous approaches to minimize the batch effect have commonly focused on normalizing the low-dimensional image measurements such as an embedding generated by a neural network. However, normalization of the embedding could suffer from over-correction and alter true biological features (e.g. cell size) due to our limited ability to interpret the effect of the normalization on the embedding space. Although techniques like flat-field correction can be applied to normalize the image values directly, they are limited transformations that handle only simple artifacts due to batch effect.ResultsWe present a neural network-based batch equalization method that can transfer images from one batch to another while preserving the biological phenotype. The equalization method is trained as a generative adversarial network (GAN), using the StarGAN architecture that has shown considerable ability in style transfer. After incorporating new objectives that disentangle batch effect from biological features, we show that the equalized images have less batch information and preserve the biological information. We also demonstrate that the same model training parameters can generalize to two dramatically different types of cells, indicating this approach could be broadly applicable.Availability and implementationhttps://github.com/tensorflow/gan/tree/master/tensorflow_gan/examples/starganSupplementary informationSupplementary data are available at Bioinformatics online.
AU  - Qian,WW
AU  - Xia,C
AU  - Venugopalan,S
AU  - Narayanaswamy,A
AU  - Dimon,M
AU  - Ashdown,GW
AU  - Baum,J
AU  - Peng,J
AU  - Ando,DM
DO  - bioinformatics/btaa819
EP  - 883
PY  - 2020///
SN  - 1367-4803
SP  - 875
TI  - Batch equalization with a generative adversarial network
T2  - Bioinformatics
UR  - http://dx.doi.org/10.1093/bioinformatics/btaa819
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000606794900037&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://academic.oup.com/bioinformatics/article/36/Supplement_2/i875/6055901
VL  - 36
ER  -
Download