Grad-CAMO: Learning Interpretable Single-Cell Morphological Profiles from 3D Cell Painting Images

arXiv:2403.17615v1 Announce Type: cross
Abstract: Despite their black-box nature, deep learning models are extensively used in image-based drug discovery to extract feature vectors from single cells in microscopy images. To better understand how these networks perform representation learning, we employ visual explainability techniques (e.g., Grad-CAM). Our analyses reveal several mechanisms by which supervised models cheat, exploiting biologically irrelevant pixels when extracting morphological features from images, such as noise in the background. This raises doubts regarding the fidelity of learned single-cell …

arxiv cs.cv eess.iv images painting profiles q-bio.qm type