How AI and network science transform our understanding of food and health

Network science and artificial intelligence can identify food molecules that negatively affect health as well as disease disease by offering food changes, according to an expert in northeast.

Since the human genome was decoded in 2003, Albert -László Barabási – an eminent professor of physics at the Northeast University and director of the Center for Complex Network Research – used Network science To map the connections between proteins in human cells. “This is where network medicine comes into play,” explains Barabási.

Finally, network medicine will be able to provide personalized recommendations and food treatments, he says, based on genetics, diet and an individual’s disease.

The genes define the proteins, he says, and the disease occurs when a mute gene.

“The mutations change the network protein, which then changes the network itself,” he said.

However, genetic changes can only explain only a fraction of diseases, says Barabási.

“A few percent of cases perhaps 30%, according to the disease,” he said.

The remaining causes come from lifestyle, including stress, exercise and sleep and the environment, he says, food being the most important factor.

Recognizing this, Barabási shared about ten years ago to integrate the diet into network medicine – one area Appointed in 2007 This applies network of the network to biological systems to understand diseases and develop drugs.

This research has led to a series of scientific articles on subjects ranging from the definition of the “dark matter” of nutrition to discover the universal laws of chemical concentration in food and the measurement of the degree of food transformation.

The culmination of this work is a recent review article, “Foodom decoding: molecular networks connecting diet and health“Published in the Annual nutrition examination. It shows how network science and AI can reveal how food molecules affect health and diseases.

When food molecules enter the blood circulation and reach cells, some are used for energy, says Barabási, while others can bind to cell proteins or DNA, influencing Biological processes. These molecules can either prevent certain processes from producing them or accelerating them.

Initially, Barabási assumed the mapping of the interactions of food molecules with human cells would be simple. To his surprise, he and his team discovered that scientists had only identified a limited number of chemical components of food.

The American department of agriculture systematically measured 150 micro and essential macronutrients mainly linked to energy supply and metabolism, including fatty acids, amino acids, sugars, fibers, minerals and vitamins. Since 2003, he has extended his list to 188 components, including certain flavonoids –plant compounds Responsible for color that have antioxidant, anti-inflammatory and immune abotis properties.

“We have made many molecules in the food that has known Health consequences are not included in this nutritional list, “explains Barabási.

His team began by examining tens of thousands of food compounds found in the Canadian Foodb, a complete database detailing the chemical composition of food, but largely neglected by epidemiological studies. In 2019, they nicknamed these unrecognized molecules “dark matter” of nutrition.

Since then, Barabási and his collaborators have compiled a library of more than 139,000 food molecules, from specialized scientific literature, various databases, mass spectrometry benchmarks and mass spectrometry experiences.

However, the underlying molecular mechanisms through which the “dark matter” of nutrition affects human health remains largely unexplored. Researchers argue that food compounds should not be studied in isolation, as was common in the 20th century, but rather in the context of their interactions between them.

Another discovery of the Barabási laboratory concerns ultra-adjustment food. They found that the relative relationships of individual chemical concentrations in different natural foods are consistent and predictable. The differences in relation to these ratios, says Barabási, indicate that food has undergone a transformation.

“No matter what foods you look at, as long as there are natural ingredients, there will be relatively minor variations from one food to another,” he said. “The reason is that, in the end, we and what we eat is really the same chemical engine.”

Almost all the ingredients of the human diet, known as Barabási, were formerly living organisms, producing and regulating nutrients according to universal biochemical rules.

“These chemical engines cannot produce something (with the concentration of a certain chemical product) 100 times more than normal, because there are clear production constraints,” explains Barabási. “As a rule, the difference is like two or three times more in one (food) compared to the other.”

Ultra -processed foods such as margarine, packed, sweet bread Breakfast cereals Or cookies generally have longer lists of ingredients, including substances not commonly used in domestic cuisine.

Since the industrial revolution, food processing technology has grown considerably. However, human biology and physiology, known as Barabási, have not changed as much. This disalcher is supposed to contribute to modern diseases.

The transformation of food changes the natural concentration of nutrients and often involves adding salt, sugar, fats and other additives to improve taste and hide unwanted qualities. Over the past decade, epidemiological studies have linked ultra-transformed foods to higher risks of obesity, type 2 diabetes, cardiovascular conditions, cancer and depression.

The precise underlying mechanisms remain vague.

“We believe that the problem most likely comes from the chemical changes that treatment makes you,” said Barabási. “For example, he has chemicals that deactivate the feeling of satiety. It is really for the most part to make us eat more.”

According to one of Barabási’s studies, more than 73% of the American food supply is ultra-transformed.

“This shows on the scale and in the health problems we face,” said Barabási.

His best advice for better health is to eat foods that our great-grandmothers would recognize as a good back when ultra-treatment did not exist.

Barabási advocates a large -scale project combining AI, mass spectrometry and network medicine to map the chemical composition of the foods we consume.

He says that the project is “feasible with current technologies”.

With appropriate financing, Barabási estimates that scientists could discover 50% to 60% of the “dark matter” of nutrition within five years, which is enough to cover more than 99% of the foods we consume. The decoding of the remaining portion could become more difficult and take more time.

This story is republished thanks to Northeastern Global News News.northeastern.edu.