Fighting cancer with AI? “Groundbreaking” digital platform pinpoints food-based cancer-beating molecules
New research could pave the way for personalized “food passports” with nutritious, tailored and therapeutically functional foods
05 Jul 2019 --- A network-based machine learning platform which can identify food-based, cancer-beating molecules has been created by Imperial College London researchers. The platform uses artificial intelligence (AI) to process huge volumes of data on a network of smartphones while they charge overnight. It has shown that plant-based foods, such as carrot, celery, orange, grape, coriander, cabbage and dill, contain the largest number of flavonoid molecules with high anti-cancer properties. The researchers note that the analysis underpins the design of next-generation cancer preventative and therapeutic nutrition strategies, as well as underlining the necessity of a personalized approach to health.
According to the study, food represents the single biggest modifiable aspect of an individual’s health and the machine learning strategy described here is a first step in realizing the potential role for “smart” nutritional programs in the prevention and treatment of cancer.
Indeed, the use of technologies such as AI and 3D printing to boost the growing nutrigenomic market was predicted to expand this year. The use of technology in the nutritional space aids personalization, which is expected to become increasingly important to consumers who are “Eating for Me,” touted by Innova Market Insights as a top trend for 2019.
The Imperial team, led by Dr. Kirill Veselkov from the Department of Surgery and Cancer, has worked with the Vodafone Foundation – who make the DreamLab app – to carry out the research.
The analysis underpins the design of next-generation cancer preventative and therapeutic nutrition strategies.
“This is a ground-breaking moment for us. The next step is to use AI technologies to explore the impact that different combinations of drugs and food-based molecules could have on individuals. We have built a team of molecular gastronomists, computer scientists, biochemical/ microbiota scientists, sensory scientists, Michelin-star chefs, health economists and clinicians to advance the next phase of the project,” Dr. Veselkov is quoted saying on the University website.
The latest findings from the project, published in the journal Scientific Reports, used the platform to analyze data on the molecular content of more than 8,000 everyday foods, identifying more than 110 cancer-beating molecules.
Many of the molecules identified fall into the flavonoids category.
Flavonoids are classified as polyphenols, which are a large group of chemical compounds synthesized by fruits, vegetables, teas, cocoa and other plants that possess certain health benefits.
Innovation in this space has been ubiquitous over the past year. French producer of natural ingredients Fytexia has previously highlighted the potential for weight management ingredients as part of an active lifestyle, combining citrus polyphenols, guarana and L-carnitine to support weight loss and healthier body composition. One of its key ingredients is Sinetrol, which is derived from citrus fruits.
Also among the findings are insights into existing medicines for diabetes and infections and their potential to be repurposed to target cancer, as well as identifying hundreds of anti-cancer molecules in everyday foods such as oranges, cabbages and grapes, notes the university’s website. The compounds discovered closely resemble those already used in licensed drugs, the researchers note.
An image from the study published in Scientific Reports.
They also found anti-cancer properties associated with several existing medicines, highlighting the potential for the drugs to be “repurposed” to target cancer. Chief among these are the anti-diabetic drug Metformin and the anti-microbial Rosoxacin. The team says as the drugs have already been in therapeutic use, their approval for use as cancer therapies carries fewer risks, substantially lower costs and will involve shorter timescales than developing completely new drugs.
The next move
While these early-stage findings are encouraging, the researchers say that further work is now needed to confirm any clinical properties of the molecules identified in the foods, as well as the effectiveness of repurposing the drugs.
“Our large-scale computational analysis further demonstrates more cancer-beating potential of certain foods, calling for more tailored nutritional strategies,” notes the study.
However, the researchers say that it is important to note some limitations of the model.
Among these is that the concentrations of the bioactive molecules are not taken into account. This means that the concentration needed for them to exert their benefit remains unknown. A further limitation comes in the form of drug-food interactions, as these have not yet been evaluated.
However, the model extrapolated in this study is not only limited to cancer, meaning that it will be applicable to other health conditions in the future.
“Applying the modern technology of AI to the fundamental practice of food.”
The researchers believe it could pave the way for the future of hyperfoods and gastronomic medicine, encouraging the introduction of personalized “food passports” to provide nutritious, tailored and therapeutically functional foods for every individual in order to benefit the wider population.
“Applying the modern technology of AI to the fundamental practice of food”
The London team are not the first to apply cutting edge technologies to food products. Irish biotech company Nuritas is also unlocking life-changing molecules in commonly consumed, everyday staple foods.
Since 2014, Nuritas has been “using the most modern of technologies, AI, and applying it to one of the fundamentals of human existence, food.”
Nurita has translated its finding into products available on the market. Nuritas’ PeptAIde was launched last November, in collaboration with BASF, as a sports nutrition ingredient containing a unique set of plant-based peptides identified using AI, for regulating inflammation.
The company also partnered with supplement manufacturer Pharmavite in a bid to “transform” the dietary supplements industry earlier this year.
By Laxmi Haigh
