Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
This work addresses the challenge of interpreting complex scientific data in bioimaging, offering a tool for scientific discovery, though it is incremental as it adapts existing dictionary learning methods to a new domain.
The researchers tackled the problem of extracting meaningful biological concepts from vision foundation models trained on cell microscopy images, where prior knowledge is limited, and successfully retrieved concepts like cell types and genetic perturbations using a novel sparse dictionary learning approach combined with PCA whitening.
Sparse dictionary learning (DL) has emerged as a powerful approach to extract semantically meaningful concepts from the internals of large language models (LLMs) trained mainly in the text domain. In this work, we explore whether DL can extract meaningful concepts from less human-interpretable scientific data, such as vision foundation models trained on cell microscopy images, where limited prior knowledge exists about which high-level concepts should arise. We propose a novel combination of a sparse DL algorithm, Iterative Codebook Feature Learning (ICFL), with a PCA whitening pre-processing step derived from control data. Using this combined approach, we successfully retrieve biologically meaningful concepts, such as cell types and genetic perturbations. Moreover, we demonstrate how our method reveals subtle morphological changes arising from human-interpretable interventions, offering a promising new direction for scientific discovery via mechanistic interpretability in bioimaging.