Anchoring to Exemplars for Training Mixture-of-Expert Cell Embeddings

12/06/2021
by   Siqi Wang, et al.
0

Analyzing the morphology of cells in microscopy images can provide insights into the mechanism of compounds or the function of genes. Addressing this task requires methods that can not only extract biological information from the images, but also ignore technical variations, ie, changes in experimental procedure or differences between equipments used to collect microscopy images. We propose Treatment ExemplArs with Mixture-of-experts (TEAMs), an embedding learning approach that learns a set of experts that are specialized in capturing technical variations in our training set and then aggregates specialist's predictions at test time. Thus, TEAMs can learn powerful embeddings with less technical variation bias by minimizing the noise from every expert. To train our model, we leverage Treatment Exemplars that enable our approach to capture the distribution of the entire dataset in every minibatch while still fitting into GPU memory. We evaluate our approach on three datasets for tasks like drug discovery, boosting performance on identifying the true mechanism of action of cell treatments by 5.5-11 state-of-the-art.

READ FULL TEXT

page 1

page 2

page 4

page 5

research
03/30/2021

Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification

Learning robust representations to discriminate cell phenotypes based on...
research
01/10/2023

Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation

Deep learning provides us with powerful methods to perform nucleus or ce...
research
05/10/2021

DEEMD: Drug Efficacy Estimation against SARS-CoV-2 based on cell Morphology with Deep multiple instance learning

Drug repurposing can accelerate the identification of effective compound...
research
06/07/2023

ContriMix: Unsupervised disentanglement of content and attribute for domain generalization in microscopy image analysis

Domain generalization is critical for real-world applications of machine...
research
11/18/2016

Expert Gate: Lifelong Learning with a Network of Experts

In this paper we introduce a model of lifelong learning, based on a Netw...
research
11/02/2017

Correcting Nuisance Variation using Wasserstein Distance

Profiling cellular phenotypes from microscopic imaging can provide meani...
research
09/02/2019

Semantic filtering through deep source separation on microscopy images

By their very nature microscopy images of cells and tissues consist of a...

Please sign up or login with your details

Forgot password? Click here to reset