AI helps uncover hidden role of gene in Alzheimer’s disease

A new study showed that a gene that is recently recognized as a biomarker for Alzheimer’s disease is actually a cause of it, because of the previously unknown secondary function. Researchers from the University of California San Diego used artificial intelligence to unravel both this mystery of Alzheimer’s disease and to discover a possible treatment that hinders the moonlight role of the gene.

The research team published their results on April 23 in the magazine Cell.

About one in nine people aged 65 and older has Alzheimer’s disease, the most common cause of dementia. Although some specific genes, when mutated, can lead to Alzheimer’s, that connection is only good for a small percentage of all patients of Alzheimer’s. The vast majority of patients have no mutation in a well -known morbid genes; Instead, they have “spontaneous” Alzheimer’s, and the causes are unclear.

Discovering these causes could ultimately improve medical care.

Unfortunately, treatment options for Alzheimer’s disease are very limited. And treatment reactions are not excellent at the moment. “

Sheng Zhong, Study Senior Author, Professor in the Shu Chien-Gene Lay Department of Biogineing, UC San Diego Jacobs School of Engineering

So Zhong and his team have looked at the phosphoglycase Dehydrogenase (PHGDH), which they had previously discovered as a potential blood biomarker for early detection of Alzheimer’s disease. In a follow-up study, they later found that the expressions of the PHGDH gene were immediately correlated with changes in the brain in Alzheimer’s disease; In other words, the higher the levels of proteins and RNA produced by the PHGDHGen, the more advanced the disease. That correlation has since been verified in several cohorts from different medical centers, according to Zhong.

Intrigged by this reproducible correlation, the research team decided to investigate in this last study whether there was a causal effect. With the help of mice and human brain organoids, the researchers discovered that changing the quantities of PHGDH expression had consistent effects on Alzheimer’s disease: lower levels corresponded to less disease progression, while increasing levels led to more progress. The researchers have therefore established that PHGDH is indeed a causal gene for the disease of spontaneous Alzheimer’s.

When supporting that finding, the researchers have established that with the help of AI DAT PHGDH plays a rather undiscovered role: it activates a route that disrupts how cells in the brain genes change and out. And such a disturbance can cause problems, such as the development of Alzheimer’s disease.

Moonlight roll

PHGDH creates an enzyme key for the production of Serine, an essential amino acid and a neurotransmitter. Because the enzymatic activity of PHGDH was the only known role, the researchers put the hypothesis that the metabolic function must be connected to an outcome of an Alzheimer’s. However, all their experiments that have been designed to prove this has failed.

“At that moment our studies hit a wall and we had no idea what mechanism it is,” said Zhong.

But another project by Alzheimer’s in his lab, which did not focus on PHGDH, all changed this. A year ago, that project revealed a characteristic of Alzheimer’s disease: a widespread imbalance in the brain in the process where cells regulate which genes are called in and eliminated to perform their specific roles.

The researchers were curious whether PHGDH had an unknown regulatory role in that process and they turned to modern AI for help.

With AI they were able to visualize the three-dimensional structure of the PHGDH protein. Within that structure, they discovered that the protein has a substance that is very similar to a well-known DNA-binding domain in a class of well-known transcription factors. The parable is exclusively in the structure and not in the protein sequence.

Zhong said: “It really demanded that Modern AI formulated the three -dimensional structure very accurately to make this discovery.”

After discovering the substructure, the team then demonstrated that the protein can thus activate two critical targets. That distracts the delicate balance, which leads to various problems and ultimately the early stages of Alzheimer’s disease. In other words, PHGDH has a previously unknown role, independent of the enzymatic function, which leads to spontaneous disease of Alzheimer’s disease through a new route.

This is in line with the earlier studies of the team: the PHGDH gene produced more proteins in the brains of the patients of Alzheimer’s compared to the control brain, and those increased quantities of protein in the brain caused the imbalance. Although everyone has the PHGDH gene, the difference comes down to the express level of the gene, or how many proteins are made through it.

Treatment option

Now that the researchers revealed the mechanism, they wanted to find out how to intervene and therefore identify a therapeutic candidate who could help the disease to aim.

Although many current treatments focus on treating the abnormal structure of the sticky protein called beta-amyloid in the brain, some studies suggest that treating those plaques cannot be effective: essentially the treatment is too late. But the critical path discovered in this study is upstream, so preventing this route can reduce the formation of the amyloid plaque in the first place.

Since PHGDH is such an important enzyme, there are earlier studies into the possible inhibitors. One small molecule, known as NCT-503, stood out the researchers because it is not entirely effective in obstructing the enzymatic activity of PHGDH (the production of serine), which they did not want to change. NCT-503 is also able to invade the blood-brain barier, which is a desirable feature.

They once again turned to AI for three -dimensional visualization and modeling. They discovered that NCT-503 has access to that DNA-binding substructure of PHGDH, thanks to a binding bag. With more tests they saw that NCT-503 indeed the regulating role of PHGDH Belt.

When the researchers tested NCT-503 in two mouse models of Alzheimer’s disease, they saw that it considerably enlightened the progression of Alzheimer’s. The treated mice showed a significant improvement in their memory and anxiety tests. These tests were chosen because the patients of Alzheimer’s suffer from cognitive decline and increased fear.

The researchers recognize restrictions on their studies. One is that there is no perfect animal model for spontaneous Alzheimer’s disease. They could only test NCT-503 in the available mouse models, which are with mutations with those well-known pathogenic genes.

Yet the results are promising, according to Zhong.

“Now there is a therapeutic candidate with proven activity that has the potential to be further developed into clinical tests,” said Zhong. “There can be completely new classes of small molecules that could possibly be used for development in future therapeutics.”

An advantage of small molecules is that they could even be administered orally, he added, in contrast to the current treatments that require infusions.

The following steps are to optimize the connection and to subject to FDA IND integration studies.