Deep learning models link local cellular features with whole-animal growth dynamics in zebrafish.

Animal growth is driven by the collective actions of cells, which are reciprocally influenced in real-time by the animal's overall growth state. Whereas cell behavior and animal growth state are expected to be tightly coupled, it is not yet determined whether local cellular features at the micrometer scale might correlate with the body size of an animal at the macroscopic level. By inputting 722 skin cell images and corresponding size data for each zebrafish larva into machine learning models, we determined that the Vision Transformer (ViT) with a random cropping and voting strategy was able to achieve high predictive performance (F-score of 0.91). Remarkably, analyzing as few as 27 skin cells within a single image of 0.01 mm(2) was sufficient to predict the individual's overall size, ranging from 0.9 to 3.1 mm(2) Using a gradient-weighted class activation map (Grad-CAM), we further identified the cellular features influencing the model's decisions. These findings provide a proof-of-concept that macroscopic organismic information may be de-encrypted from a snapshot of only a few dozen cells using deep learning approaches.