Detecting signs of this debilitating disease with AI before bones start to break
Melissa Formosa is an osteoporosis expert at the University of Malta in Msida. She shares her AlphaFold story.
Currently, medicine relies too heavily on radiographic imaging techniques to diagnose osteoporosis. It can be a debilitating disease that develops slowly over several years, weakening bones and making them dangerously brittle. Such diagnostic radiographic tools have their own limitations, since they only detect osteoporosis once it has already developed. This means that it is already too late to control it properly.
People tend to think that bones are unchanging, but this is a misconception. They are actually very active organs, made up of calcium-enhanced connective tissue and unique bone cells, most of which also contain bone marrow in which blood cells are made. Bone tissue is constantly renewed throughout our lives, with these specialized cells absorbing old tissue and laying down new tissue. These processes work hand in hand to maintain a healthy and strong skeleton.
The complex 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, even requiring permanent hospital care in some cases, if someone breaks their back for example.
The disease mainly affects older women: one in three women over the age of 50 are diagnosed with osteoporosis, while one in five men in the same age group will suffer from osteoporosis. Often overlooked by scientific research is how and why the disease develops in some people but not others – but it is becoming increasingly clear that osteoporosis has a significant genetic component.
Take the WNT1 gene, active in osteoblasts, the cells that create bones. Mutations in this gene disrupt the bone-building process, meaning that people with this genetic mutation have weak bones and suffer from early-onset osteoporosis. Such findings are important because they demonstrate that osteoporosis is not – and can no longer be considered – a disease that only affects older people.
However, a fracture often remains the first sign of the presence of osteoporosis. What we need is 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 help people start fighting the disease before it even starts.
To help us achieve this, we use AlphaFold to try to better understand genetic causes. We quickly realized that this could revolutionize treatments if used to develop personalized medicine. In this case, it is a model capable of providing tailored prevention and treatment strategies for defined groups of individuals.
A person suffering from the disease could then have their genome sequenced. This genetic analysis would give us a better idea if this person is at risk of fracture in the near future and, above all, would allow preventive measures to be taken. It could also help us understand disease progression and give patients more control over which intervention is best for them. Ultimately, the goal is to manage osteoporosis at the earliest possible stage and prevent progression, fractures and the pain and weakness they cause.
When we enter the amino acid sequence into the AlphaFold software, it creates a 3D image of the protein structure and allows us to compare the protein structures encoded by normal and defective genes. With AlphaFold, we can visualize the impact of specific genetic mutations, some of which may only cause subtle structural changes. Others induce significant deformations of the protein, reducing its ability to function properly, thereby contributing to disease.
Ultimately, our goal is to develop simple blood tests for young adults to help them predict disease and find new genes and proteins associated with the disease so we can develop better drugs to treat it. Early detection and the introduction of personalized medicine could make it possible to manage osteoporosis much more effectively. Millions of lives could be dramatically improved.
This type of AI is becoming central to our work and will be essential for future researchers in this area. We finally have a chance to get a head start on this debilitating disease – it’s priceless.