The Science & Technology desk gathers a weekly digest with impactful and interesting research publications and developments at Stanford. Read the latest in this week’s Research Roundup.

An unusual player in brain degeneration

A Stanford-led study published in Nature on Feb. 26 found that age-related changes witnessed in diseases like Alzheimer’s may be related to a relatively untapped area of research in the brain. 

The study looked at the effects of disruptions to the glycocalyx, a sugary coating on cells. The glycocalyx is a key component of the blood-brain barrier because it serves as a gateway to the brain. Like a semi-permeable membrane, these cells of the glycocalyx are responsible for filtering out harmful molecules from entering the brain while allowing helpful ones to pass through to keep our brains healthy. 

The researchers found that a deficit in mucin – a sugar-coated protein responsible for proper glycocalyx function – led to neuroinflammation in older mice. When mucin was reintroduced to the mice, neuroinflammation dropped, a sign that glycocalyx integrity had been better restored.

Sophia Shi, Stanford Bio-X Graduate Fellow and lead author of the study, explained to the Stanford Report that sugar-coated proteins, like mucin, can play key roles in the permeability of the blood brain barrier.

“Modulating glycans has a major effect on the brain – both negatively in aging, when these sugars are lost, and positively, when they are restored,” Shi said.

While it’s unclear why exactly the glycocalyx fatigues with time and whether these effects are also present in humans, researchers are optimistic about the future. Carolyn Bertozzi, a professor of chemistry and Nobel Laureate, highlighted the importance of continued research into this avenue explored by Shi.

“[U]nderstanding whether similar mechanisms are at play in humans will be crucial for translating these discoveries into therapies,” Bertozzi told the Stanford Report.

A machine learning algorithm to detect diseases

In a study published in Science on Feb. 21, Stanford Medicine researchers outlined their creation of a machine learning model to diagnose diseases by analyzing key details of the immune system.

B cells and T cells help fight off infections and are key components of our immune system. Both of these cell types can recall their interactions with harmful antigens by creating memory cells that have the information needed to recognize the antigen. This allows them to quickly respond in the future as part of the body’s adaptive immune system. 

The researchers created a new algorithm “Mal-ID” which uses the structural sequences of B and T cell receptors to diagnose individuals. 

Maxim Zaslavsky, an author of the study and postdoctoral scholar, explained that the immune system has not always been a prime target of investigation when it comes to identifying conditions.

“The diagnostic toolkits that we use today don’t make much use of the immune system’s internal record of the diseases it has encountered…but our immune system is constantly surveilling our bodies with B and T cells, which act like molecular threat sensors,” Zaslavsky told Stanford Medicine.

The results indicated that a combination of the data from the T and B cells allowed a better diagnosis overall for individuals. The researchers are hopeful that this algorithm can help identify more specific subtypes of these conditions.

“Patients can struggle for years before they get a diagnosis, and even then, the names we give these diseases are like umbrella terms that overlook the biological diversity behind complex diseases,” Zaslavsky told Stanford Medicine. 

AI tool helps predict disease

Stanford scientists have created a generative AI tool that can create genetic sequences of DNA that have never been synthesized before. 

Brian Hie, an assistant professor of chemical engineering, co-led the creation of the tool, Evo2, which uses AI like ChatGPT to create new genetic code.

“In a natural language processor, like ChatGPT, you can prompt it with some text, and it will autocomplete the sentence based on patterns from previously written words,” Hie told the Stanford Report. “If you want to design a new gene, you prompt the model with the beginning of a gene sequence of base pairs, and Evo 2 will autocomplete the gene.” 

While it is not unusual for mutations – accidental changes in the genetic code – to occur in our cells without serious consequences, a slim fraction of them can have drastic effects, like causing cancer. Evo2’s can help predict the specific mutations that cause these diseases. It can also create novel forms of genetic sequences that can create beneficial mddteeed4utations. This results in proteins playing a beneficial role in the body through DNA transcription and translation.

“Evo2 also includes machine learning models that will tell you if the sequence exists in nature and predict how this new sequence will function in real life. Then we go into the lab and synthesize the DNA and insert it into a living cell to test it using a gene editing technology like CRISPR,” Hie told the Stanford Report.