Adversarial Batch Representation Augmentation for Batch Correction in High-Content Cellular Screening

2026-03-05

AI Summary

This work addresses the challenge of biological batch effects in high-content cellular screening, where experimental batch variations induce covariate shift and degrade model generalization. Framing the problem as a domain generalization task, the authors propose an adversarial batch representation augmentation method that actively synthesizes worst-case batch perturbations in the representation space while preserving class-discriminative features. The approach innovatively models batch statistics through structured uncertainty and integrates angular geometric constraints with a co-distribution alignment mechanism to effectively prevent representation collapse during adversarial optimization. Evaluated on the RxRx1 and RxRx1-WILDS benchmarks, the method achieves state-of-the-art performance in siRNA perturbation classification, demonstrating its robustness and effectiveness in mitigating batch-induced distribution shifts.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Game Theory and Economic Paradigms: Adversarial Learning
• Search and Optimization: Adversarial Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

High-Content Screening routinely generates massive volumes of cell painting images for phenotypic profiling. However, technical variations across experimental executions inevitably induce biological batch (bio-batch) effects. These cause covariate shifts and degrade the generalization of deep learning models on unseen data. Existing batch correction methods typically rely on additional prior knowledge (e.g., treatment or cell culture information) or struggle to generalize to unseen bio-batches. In this work, we frame bio-batch mitigation as a Domain Generalization (DG) problem and propose Adversarial Batch Representation Augmentation (ABRA). ABRA explicitly models batch-wise statistical fluctuations by parameterizing feature statistics as structured uncertainties. Through a min-max optimization framework, it actively synthesizes worst-case bio-batch perturbations in the representation space, guided by a strict angular geometric margin to preserve fine-grained class discriminability. To prevent representation collapse during this adversarial exploration, we introduce a synergistic distribution alignment objective. Extensive evaluations on the large-scale RxRx1 and RxRx1-WILDS benchmarks demonstrate that ABRA establishes a new state-of-the-art for siRNA perturbation classification.

Problem

• batch effect
• domain generalization
• high-content screening
• covariate shift
• generalization

Innovation

• Adversarial Batch Representation Augmentation
• Domain Generalization
• Batch Effect Correction
• Representation Learning
• Distribution Alignment