AI-assisted phenotyping in a zebrafish hypophosphatasia model enables early and precise detection of skeletal alterations
Bibliographic record
Abstract
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 wue7 ), 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".