A gene that can be an early indicator for Alzheimer’s disease actually is a cause of the degenerative-brain disorder, said researchers at the University of California, San Diego. That finding, which they discovered using AI, could result in new treatment options.
In a paper published in April in the scientific journal Cell, a team at UCSD found that the gene PHGDH—previously considered a mere biomarker of the disease—?plays a direct role in causing “spontaneous” Alzheimer’s by disrupting the way the brain normally regulates genes.
While some gene mutations can lead to Alzheimer’s, that only accounts for a small percentage of the more than 7 million Americans living with the disease. Identifying the other spontaneous Alzheimer’s causes can help lead to better medical care, the researchers said.
Currently, “treatment options for Alzheimer’s disease are very limited,” said senior author Sheng Zhong, a professor in the Shu Chien-Gene Lay Department of Bioengineering at the UCSD Jacobs School of Engineering. “And treatment responses are not outstanding at this moment.”
AI was instrumental in identifying PHGDH’s secondary function, which can trigger harmful cellular changes leading to Alzheimer’s. The UCSD scientists used advanced computer models to find out how PHGDH helps the disease move forward.

Researchers used NVIDIA RTX A6000 and NVIDIA H100 GPUs to develop computationally intensive structural biology and molecular models, including the Latent Prompt Transformer, which played a critical part in advancing ?the research.
Beyond identifying PHGDH’s role in triggering the dementia-causing disease, the researcher’s AI model also helped identify a promising therapeutic candidate: a small molecule, NCT-503, that can block PHGDH’s damaging activity without interfering with its essential functions.
When tested in mice, this compound significantly slowed the disease’s progression and improved cognitive functions. This breakthrough highlights how AI is impacting medical research, enabling scientists to uncover complex biological interactions that were previously difficult to detect.
“Now there is a therapeutic candidate with demonstrated efficacy that has the potential of being further developed into clinical tests,” Zhong said. “There may be entirely new classes of small molecules that can potentially be leveraged for development into future therapeutics.”
The researchers are planning to optimize the compound and pursue additional pre-clinical research before seeking FDA approval for a potential new drug.
Read the research paper in Cell.
And check out additional coverage of the UCSD research.