Metadata-guided Consistency Learning for High Content Images
This addresses the problem of batch effects in high-content imaging for drug discovery researchers, offering a novel self-supervised method to improve feature extraction, though it is incremental as it builds on existing self-supervised techniques.
The paper tackles the challenge of extracting representative features from high-content images for drug discovery, where batch effects hinder self-supervised learning, and introduces Cross-Domain Consistency Learning (CDCL) to learn biological similarities while ignoring batch-specific signals, resulting in more useful representations for downstream tasks like distinguishing treatments and mechanisms of action.
High content imaging assays can capture rich phenotypic response data for large sets of compound treatments, aiding in the characterization and discovery of novel drugs. However, extracting representative features from high content images that can capture subtle nuances in phenotypes remains challenging. The lack of high-quality labels makes it difficult to achieve satisfactory results with supervised deep learning. Self-Supervised learning methods have shown great success on natural images, and offer an attractive alternative also to microscopy images. However, we find that self-supervised learning techniques underperform on high content imaging assays. One challenge is the undesirable domain shifts present in the data known as batch effects, which are caused by biological noise or uncontrolled experimental conditions. To this end, we introduce Cross-Domain Consistency Learning (CDCL), a self-supervised approach that is able to learn in the presence of batch effects. CDCL enforces the learning of biological similarities while disregarding undesirable batch-specific signals, leading to more useful and versatile representations. These features are organised according to their morphological changes and are more useful for downstream tasks -- such as distinguishing treatments and mechanism of action.