Scientists have developed an artificial intelligence tool that can identify biological similarities between cells separated by hundreds of millions of years of evolution, potentially transforming how researchers translate animal studies into human health discoveries. The tool, called Unify, was developed by a team at King Abdullah University of Science and Technology (KAUST) and published in Nature Communications on September 22, 2026. It successfully connected 125 cell types across more than seven species spanning over 700 million years of evolutionary history.

Why Can't Traditional Genetic Tools Compare Distant Species?

Researchers typically compare cells across species using single-cell RNA sequencing, a technique that identifies which genes are active in each cell type. However, this approach has a fundamental limitation: it relies on finding direct, one-to-one gene matches between organisms. As species diverge over evolutionary time, genes change so dramatically that these direct matches become impossible to find, even when cells perform nearly identical biological functions.

This creates a real problem for medical research. A mouse immune cell and a human immune cell might work in fundamentally similar ways, but the specific genes driving those functions may have diverged so much that traditional comparison tools miss the connection entirely. Researchers end up unable to confidently determine which findings from animal models will actually apply to human biology, leading to wasted research efforts and missed opportunities for translating discoveries into treatments.

How Does Unify Work Differently?

Rather than looking for matching genes, Unify takes a fundamentally different approach: it compares what genes actually do. The AI system analyzes protein sequences and scientific descriptions of gene functions to identify cells performing similar biological jobs, even when the underlying genes have completely changed. Think of it like comparing two restaurants that serve the same meal using entirely different recipes and ingredients.

The tool groups genes with certain similarities into units called "macrogenes," which allows it to recognize cells performing similar functions across species. This approach revealed relationships that would be nearly impossible to detect using traditional gene-by-gene comparison methods.

"Unify works with AI models that analyze protein sequences and scientific descriptions of gene functions. Genes with certain similarities are grouped into units called 'macrogenes.' This allows Unify to recognize cells performing similar jobs, even when their individual genes no longer match," explained Huawen Zhong, lead author and computational biologist at KAUST.

Huawen Zhong, Computational Biologist at King Abdullah University of Science and Technology

What Practical Discoveries Did Unify Make?

When researchers tested Unify on immune cells across multiple species, the tool identified shared defense tactics that would have been completely invisible to traditional comparison methods. In one particularly striking experiment, Unify predicted how human blood cells would respond to a specific immune-signaling protein based solely on how mouse lymph-node immune cells responded to the same protein. Across all genes tested, Unify's predictions were significantly more accurate than existing methods.

These results suggest that Unify could help researchers quickly identify which animal study findings are most likely to translate to human biology, potentially accelerating the path from basic research to clinical applications. Rather than pursuing every promising mouse study, researchers could prioritize those with the strongest biological parallels to human cells.

"A lot of what we know about human biology comes from studying animals like mice, but it is not always clear which findings carry over. Unify helps us identify which discoveries in model organisms are most likely to be relevant to humans, so research can be focused where it is most useful for understanding human health and disease," noted Manuel Aranda, Professor of Marine Science at KAUST.

Manuel Aranda, Professor of Marine Science at King Abdullah University of Science and Technology

How to Leverage AI for Better Genomic Research

• Cross-Species Validation: Use AI tools like Unify to validate animal study findings before investing in expensive human trials, reducing research costs and accelerating discovery timelines.
• Functional Comparison: Compare cells based on what they do rather than their genetic sequences, revealing biological similarities that traditional methods miss across evolutionary distances.
• Tissue Context Integration: The KAUST team is expanding Unify to include information about gene regulation and cell positions within tissues, providing a more complete picture of shared biological principles.

The KAUST team is already working to expand Unify's capabilities by incorporating information about gene regulation and how cells are positioned within tissues. These additions will give researchers an even fuller picture of the biological principles shared across life, potentially unlocking additional insights for human health research.

The development of Unify represents a broader shift in how AI is being applied to biology. Rather than simply processing larger amounts of genetic data faster, these tools are beginning to extract deeper biological meaning from existing information, helping researchers ask better questions about which discoveries matter most for human health. As sequencing costs continue to fall and AI models become more sophisticated, tools like Unify could fundamentally change how researchers prioritize and translate animal studies into human medicine.