Prediction of the risk of fatal vascular disease from the genome sequence – ScienceDaily

Although the method, which uses a form of artificial intelligence called machine learning, has so far only been used to predict the likelihood of this particular condition – called abdominal aortic aneurysm – or AAA -. nuances that put people at risk for just about any complex genetic condition.

"Currently, genome sequencing is starting to prove itself," said Michael Snyder, PhD, professor and chair of genetics at Stanford. "It's used a lot in the fight against cancer or to solve mysterious diseases, but there's still a big open question: how much can we use to predict the risk of disease?"

It turns out that a lot.

Typically, researchers and health care providers use genetic testing to look for DNA sequences that may correspond to an increased risk for a particular disease. Mutations in the BRCA1 and BRCA2 genes, for example, may signal an increased risk of breast cancer. But the method developed by Snyder and his colleagues does not work like that. He is not looking for a remarkable gene or mutation; She is researching a multitude of complex mutation patterns and how these genetic errors affect a person's health and risk of illness.

The method seeks to identify the probable culprits of the disease in an "agnostic" manner, which means that it resolves an attack of genetic information from patients with AAA, at the search for common points. According to Snyder, this is the key to unraveling a large number of genetic diseases. This is not often the case that one, two or even a few genes take full responsibility for a condition. It is much more likely that it is a bunch of them. The idea is that it takes a village to cause disease and using this new method, these villagers can be identified.

The study will be published on September 6th at Cell. Snyder and Philip Tsao, Ph.D., professor of medicine, share the same author rights. Instructor Jingjing Li, PhD; research director Cuiping Pan, PhD; and postdoctoral researchers Sai Zhang, PhD, are the lead authors.

Often diagnosed at death

AAA affects more than 3 million people each year and is the 10th killer in the United States. Patients with AAA have an enlarged aorta, the main artery of the body, which swells slowly over time until it breaks in the worst case. To make matters worse, these types of aneurysms rarely show symptoms. So, in many cases, the situation escalates silently, which is part of what makes it so dangerous.

Yet, AAA is quite supportive of behavior change. Things like smoking and high blood pressure intensify the condition, while higher levels of HDL, or "good" cholesterol, help lower the risk. So, if people know that they are in danger from the beginning, they can ideally adjust their lifestyle to avoid exacerbation or total onset.

"What's important to note about AAA is that it's irreversible, so once the aorta begins to grow, it's not like it's getting bigger." said Snyder, Stanford W. Ascherman, MD, FACS, professor of genetics. "So, here is this irreversible disease, no way to predict it.Nobody has ever set up predictive test and, from a genome sequence, we have been able to predict with a precision of about 70% AAA. "According to Snyder, when other details from electronic patient records were added, such as the fact that a patient smoked and his cholesterol levels, the accuracy went up to 80% .

The method developed by Snyder and his team is based on an algorithm called Hierarchical Agnostic Learning Estimate or HEAL, which analyzes genomic data from 268 patients with AAA and analyzes the mass of information on mutated genes. in the population. . The algorithm has identified 60 genes that have been hypermutured in AAA patients. Some genes have played a role in blood vessel function and the development of aneurysms – a nod to the accuracy of HEAL – but other, more surprising, have been associated with the regulation of function immune system, revealing that the mutational landscape of this disease is complex. it was not necessarily planned.

The team further confirmed its findings using HEAL in a control group, verifying that AAA-related mutation patterns were not observed in 133 healthy individuals. And indeed, there was no significant overlap.

"HEAL could therefore discover new avenues of research and potential therapeutic targets for devastating diseases such as AAA," said Tsao, also director of the Palo Alto Center for Research and Information in Epidemiology. Affairs.

Any disease with a genetic component

The key, said Snyder, is that the results were entirely unbiased. The researchers did not say, "We think X, Y and Z genes could play a role in AAA." They fed the genetic information into HEAL and asked if there were genes or sets of genes that were enriched for the mutation. "We let the machine learn to understand it, and it's something that, to our knowledge, has never been done before," Snyder said.

Even for diseases that have these big "blatant" genomic markers, HEAL could give a boost, Snyder said. "For example, in familiar cases like breast cancer, for which we know specific" culprit "genes, we must not forget that these genes – BRCA1, BRCA2 and some others – only explain that 30% of the genetics of breast cancer. disease, "said Snyder. "This means that 70% is still unexplained.There are probably several genes and mutations involved, and that's where we think HEAL could be a great moment."

In their next phase of work, Snyder and his group plan to use HEAL to detect the elusive genetic underpinnings of prematurity and autism.

"I see a future in which everyone will be born with their sequenced genome, or soon after," Snyder said. "Both your unique gene and your complex disease risk will be used to predict your overall disease risk and you will be able to take action based on that information."

The work is an example of Stanford Medicine's focus on health accuracy, which aims to anticipate and prevent disease in healthy people and accurately diagnose and treat disease in patients.

Other authors of the Stanford study are Joshua Spin, MD, Ph.D., clinical assistant professor in cardiovascular medicine; Life Science Research Assistant Alicia Deng; Professor of Medicine Lawrence Leung, MD; and Ronald Dalman, MD, professor of vascular surgery.

Snyder and Tsao are members of Stanford Bio-X and the Stanford Child Health Research Center. Snyder is also a member of the Stanford Cancer Institute and the Stanford Neurosciences Institute. Snyder and Tsao are members of the Stanford Cardiovascular Institute.

The research was funded by the National Institutes of Health (CEGS Fellowships 5P50HG00773504, 1P50HL083800, 1R01HL101388, 1R01HL122939 and S10OD020141), the University of California and the Office of Veterans Affairs Research and Development.

The Stanford Genetics Department also supported the work.