Gene-Level Representation Learning via Interventional Style Transfer in Optical Pooled Screening

TL;DR

This paper introduces a style-transfer based method to learn gene-level representations from optical pooled screening images, improving clustering of gene functions and revealing biological relationships.

Contribution

It presents a novel style-transfer approach for extracting biologically meaningful features from OPS images, outperforming traditional engineered features.

Findings

Better clustering of gene functions

Reveals latent biological relationships

Outperforms engineered feature methods

Abstract

Optical pooled screening (OPS) combines automated microscopy and genetic perturbations to systematically study gene function in a scalable and cost-effective way. Leveraging the resulting data requires extracting biologically informative representations of cellular perturbation phenotypes from images. We employ a style-transfer approach to learn gene-level feature representations from images of genetically perturbed cells obtained via OPS. Our method outperforms widely used engineered features in clustering gene representations according to gene function, demonstrating its utility for uncovering latent biological relationships. This approach offers a promising alternative to investigate the role of genes in health and disease.