Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification

TL;DR

This paper demonstrates that contrastive learning can effectively generate robust representations of single-cell microscopy images, achieving state-of-the-art results in drug mechanism classification without supervision.

Contribution

The work introduces a contrastive learning framework for single-cell image representations, surpassing previous unsupervised methods and matching supervised approaches in accuracy.

Findings

Achieved state-of-the-art results on BBBC021 dataset

Improved NCSB accuracy by 10% over previous methods

Unsupervised approach performs well without post-processing

Abstract

Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential treatments. Early works focus on creating hand-engineered features from these images or learn such features with deep neural networks in a fully or weakly-supervised framework. Both require prior knowledge or labelled datasets. Therefore, subsequent works propose unsupervised approaches based on generative models to learn these representations. Recently, representations learned with self-supervised contrastive loss-based methods have yielded state-of-the-art results on various imaging tasks compared to earlier unsupervised approaches. In this work, we leverage a contrastive learning framework to learn appropriate representations from single-cell fluorescent microscopy images for the task of Mechanism-of-Action classification. The proposed work is evaluated on the annotated BBBC021 dataset, and we obtain state-of-the-art results in NSC, NCSB and drop metrics for an unsupervised approach. We observe an improvement of 10% in NCSB accuracy and 11% in NSC-NSCB drop over the previously best unsupervised method. Moreover, the performance of our unsupervised approach ties with the best supervised approach. Additionally, we observe that our framework performs well even without post-processing, unlike earlier methods. With this, we conclude that one can learn robust cell representations with contrastive learning.