AI tool compares 125 cell types across 700 million years of evolution
A KAUST-led team has developed the AI tool Unify to help scientists compare similar cell types across distant species. This comparison can help researchers assess which findings from animal studies may be most relevant to human health. Their study is published in the journal Nature Communications.
Researchers led by King Abdullah University of Science and Technology (KAUST) have created an artificial intelligence (AI) tool called Unify to compare cell types across various species separated by over 700 million years of evolution. Traditionally, cells are compared using single-cell RNA sequencing, which helps create a cell tree mapping different cell types and their activity.
However, this method relies on direct gene matches, which become less reliable as species evolve over time, potentially missing important biological similarities.
To address this issue, Unify employs AI models that analyze protein sequences and scientific descriptions of gene functions. By identifying shared biological meanings rather than direct gene matches, Unify groups genes into function-based "macrogenes," allowing it to recognize cells performing similar jobs even when their individual genes no longer match.
The tool successfully reconstructed relationships among 125 cell types from seven species, distinguishing between identical genes, similar genes that evolved new functions, and different genes that independently fulfilled similar roles.
One notable application of Unify was its analysis of immune cells across multiple species, which identified shared defense tactics that would be challenging to detect using traditional gene comparison methods. In another experiment, Unify predicted the response of human blood cells to a specific immune-signaling protein based on the response of mouse lymph node immune cells, demonstrating its accuracy in predicting human immune-cell reactions from mouse data.
The KAUST team is currently working on extending Unify to incorporate information about gene regulation and cell positions within tissues, which will provide researchers with a more comprehensive understanding of the biological principles shared across life. This enhanced tool can inform further advancements in human health research by helping scientists identify which discoveries in model organisms are most relevant to human health and disease.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
