Detecting the symptoms of this devastating disease using AI before any bones start to break
Melissa Formosa is an osteoporosis expert at the University of Malta in Msida. She shares her story AlphaFold.
Currently, medicine is too dependent on radiographic imaging techniques to diagnose osteoporosis. It can be a devastating disease that develops slowly over several years, weakening bones and making them dangerously delicate. Such radiographic diagnostic tools have their limitations, detecting osteoporosis only after it has already developed. This means that it is too tardy to properly control it.
People tend to think of bones as immutable, but that’s a misconception. In fact, they are highly lively organs, made up of connective tissue fortified with calcium and unique bone cells, most of which also contain bone marrow, where blood cells are made. Bone tissue is constantly being replenished throughout our lives, and these specialized cells absorb aged tissue and lay down fresh tissue. These processes work together to keep the skeleton fit and robust.
The elaborate nature of bones means that there are many different mechanisms by which osteoporosis can develop. Injuries caused by osteoporosis can be very painful and often debilitating, and in some cases, for example, require ongoing hospital care.
The disease primarily affects older women: one in three women over the age of 50 will be diagnosed with osteoporosis, while one in five men of the same age will develop osteoporosis. Research into how and why the disease develops in some people and not others is often overlooked by scientific research – but it is becoming increasingly clear that osteoporosis has a significant genetic component.
Take the WNT1 gene, which is lively in osteoblasts, the cells that make bone. Mutations in this gene disrupt the bone-building process, meaning that people with this genetic mutation have brittle bones and early osteoporosis. Discoveries like these are essential in showing that osteoporosis is not—and can no longer be viewed as—a disease that affects only older people.
But a fracture is still often the first sign of osteoporosis. We need to find biomarkers—a blood test or an identified gene or protein that we can look for in people who are predisposed or at high risk of developing osteoporosis. We need to lend a hand people start fighting the disease before it even starts.
To lend a hand us do this, we used AlphaFold to better understand the genetic causes. We quickly realized that this could revolutionize treatment if we used it to develop personalized medicine. In this case, a model that could provide tailored prevention and treatment strategies for specific groups of people.
The person with the disease could then have their genome sequenced. This genetic analysis would give us a better idea of whether they are at risk of fracture in the near future and, most importantly, allow us to take preventive measures. It could also lend a hand us understand the progression of the disease and give patients more control over deciding what intervention is best for them. Ultimately, the goal is to treat osteoporosis at the earliest possible stage and prevent progression, fractures, and the pain and weakness that come with them.
When we enter an amino acid sequence into AlphaFold software, it creates a 3D image of the protein’s structure and allows us to compare the structures of proteins encoded by both normal and defective genes. With AlphaFold, we can visualize the impact of specific genetic mutations, some of which may cause only subtle structural changes. Others cause significant deformations in the protein, reducing its ability to function properly, contributing to disease.
Ultimately, our goal is to develop straightforward blood tests for juvenile adults that can lend a hand predict the disease, and to find fresh genes and proteins associated with the disease so that we can develop better drugs to treat it. Early detection and the introduction of personalized medicine could mean that osteoporosis can be treated much more effectively. Millions of lives could be greatly improved.
This type of AI is becoming a central part of our work and will be crucial for future researchers in this field. We finally have the chance to get one step ahead of this devastating disease – that’s priceless.