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

arXiv: https://arxiv.org/abs/2406.05308 · HTML: https://mlsanity.com/paper/2406.05308/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 8 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [RxRx1: A Dataset for Evaluating Experimental Batch Correction Methods](https://mlsanity.com/paper/2301.05768/) (2023)
- [Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels](https://mlsanity.com/paper/2209.07819/) (2022)
- [Masked Autoencoders are Scalable Learners of Cellular Morphology](https://mlsanity.com/paper/2309.16064/) (2023)
- [Metadata-guided Consistency Learning for High Content Images](https://mlsanity.com/paper/2212.11595/) (2022)
- [Bridging Generalization Gaps in High Content Imaging Through Online Self-Supervised Domain Adaptation](https://mlsanity.com/paper/2311.12623/) (2023)

## Built on by (most cited first, 9 of 9)

- [Benchmarking Transcriptomics Foundation Models for Perturbation Analysis : one PCA still rules them all](https://mlsanity.com/paper/2410.13956/) (2024)
- [Integrating chemical structures as treatments improves representations of microscopy images for morphological profiling](https://mlsanity.com/paper/2504.09544/) (2025)
- [C3R: Channel Conditioned Cell Representations for unified evaluation in microscopy imaging](https://mlsanity.com/paper/2505.18745/) (2025)
- [A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features](https://mlsanity.com/paper/2505.21317/) (2025)
- [Generalization of Self-Supervised Vision Transformers for Protein Localization Across Microscopy Domains](https://mlsanity.com/paper/2602.05527/) (2026)
- [Enhancing Job Salary Prediction with Disentangled Composition Effect Modeling: A Neural Prototyping Approach](https://mlsanity.com/paper/2503.12978/) (2025)
- [Group Contrastive Learning for Weakly Paired Multimodal Data](https://mlsanity.com/paper/2602.04021/) (2026)
- [Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization](https://mlsanity.com/paper/2604.10970/) (2026)
- [HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy](https://mlsanity.com/paper/2607.04353/) (2026)

## Abstract (arXiv)

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.