Weakly Supervised Set-Consistency Learning Improves Morphological Profiling of Single-Cell Images

TL;DR

This paper introduces Set-DINO, a set-level consistency learning algorithm that enhances morphological profiling of single-cell images by leveraging weak supervision from replicate structures in OPS experiments, leading to more biologically meaningful representations.

Contribution

The paper presents a novel set-level consistency learning method, Set-DINO, that combines self-supervised learning with weak supervision to improve representations in high-content microscopy images.

Findings

Set-DINO improves biological relationship recall accuracy.

It mitigates confounders in morphological profiling.

Enhances reliability of insights in drug target discovery.

Abstract

Optical Pooled Screening (OPS) is a powerful tool combining high-content microscopy with genetic engineering to investigate gene function in disease. The characterization of high-content images remains an active area of research and is currently undergoing rapid innovation through the application of self-supervised learning and vision transformers. In this study, we propose a set-level consistency learning algorithm, Set-DINO, that combines self-supervised learning with weak supervision to improve learned representations of perturbation effects in single-cell images. Our method leverages the replicate structure of OPS experiments (i.e., cells undergoing the same genetic perturbation, both within and across batches) as a form of weak supervision. We conduct extensive experiments on a large-scale OPS dataset with more than 5000 genetic perturbations, and demonstrate that Set-DINO helps mitigate the impact of confounders and encodes more biologically meaningful information. In particular, Set-DINO recalls known biological relationships with higher accuracy compared to commonly used methods for morphological profiling, suggesting that it can generate more reliable insights from drug target discovery campaigns leveraging OPS.