Advances in automation and imaging have made it possible to capture large imagedatasets for experiments that span multiple weeks (i.e. batches). However, almostall images experience batch-to-batch variation due to uncontrollable noise (e.g.different stain intensity or illumination conditions), and such complication makesit difficult to make biological comparison across all of the conditions spanningmultiple batches. To address the batch variation in these images, we developed abatch equalization method that can transfer image between batches (style) whilepreserving the semantic content of the image (i.e. the biological phenotype), andby equalizing all the images to the same batch, we can effectively mediate thebatch variation and highlight the biological variation. The equalization method istrained as a generative adversarial network (GAN) which has been quite successfulin doing style transfer for consumer images. By incorporating a new featuredisentanglement objective, our batch equalization GAN is able to reduce the batchvariation observed in the images and in the same time maintain the biologicalfeatures that correlated with the treatment conditions.