AI-assisted phenotyping in a zebrafish hypophosphatasia model enables early and precise detection of skeletal alterations.

Abstract

Hypophosphatasia (HPP) is a rare genetic disorder mainly affecting bone and tooth mineralization in patients due to ALPL gene mutations. Understanding genotype-phenotype correlations in HPP remains challenging due to different severities and the disease's heterogeneity. To address this, we established a novel zebrafish animal model (alpl), which mimics severe HPP disease forms. To bypass limitations in human-based phenotypic classification of skeletal alterations in this transgenic line, we developed and trained an artificial intelligence (AI) model capable of image-based classification with 68% accuracy-an improvement of 79% over manual classification. Our AI model could successfully identify early developmental alterations independent of altered image magnification, coloration quality and executing scientists. Using attention rollout, we further visualized AI decision-making, revealing not only expected focus on early bone structures but also unexpected emphasis on the otoliths-parts of the zebrafish's hearing and balancing organ. We see applications of our AI system in analyzing other skeletal disorder models as well as in providing an unbiased, high-throughput phenotypic rescue quantification assay for potential drug screening applications in zebrafish larvae. Overall, our findings establish an integrated platform for studying HPP and open new avenues for AI-assisted phenotyping and therapeutic discovery.