Genes that Shape Bones Identified, Offering Clues About Our Past and Future

An application of AI to medical imaging datasets has revealed genetics of the skeletal form for the first time.
An application of AI to medical imaging datasets has revealed the genetics of the skeletal form for the first time (Representational Image: Unsplash)
An application of AI to medical imaging datasets has revealed the genetics of the skeletal form for the first time (Representational Image: Unsplash)

Using artificial intelligence to analyze tens of thousands of X-ray images and genetic sequences, researchers from The University of Texas at Austin and New York Genome Center have been able to pinpoint the genes that shape our skeletons, from the width of our shoulders to the length of our legs.

Using artificial intelligence to analyze tens of thousands of X-ray images and genetic sequences (Representational Image: Unsplash)
Using artificial intelligence to analyze tens of thousands of X-ray images and genetic sequences (Representational Image: Unsplash)

The research, published as the cover article in Science, pulls back a curtain on our evolutionary past and opens a window into a future where doctors can better predict patients’ risks of developing conditions such as back pain or arthritis in later life.

“Our research is a powerful demonstration of the impact of AI in medicine, particularly when it comes to analyzing and quantifying imaging data, as well as integrating this information with health records and genetics rapidly and at large scale.”
Vagheesh Narasimhan, Assistant Professor of integrative biology as well as statistics and data science

Humans are the only large primates to have longer legs than arms, a change in the skeletal form that is critical in enabling the ability to walk on two legs. The scientists sought to determine which genetic changes underlie anatomical differences that are clearly visible in the fossil record leading to modern humans, from Australopithecus to Neanderthals. They also wanted to find out how these skeletal proportions allow bipedalism to affect the risk of many musculoskeletal diseases such as arthritis of the knee and hip — conditions that affect billions of people in the world and are the leading causes of adult disability in the United States.

Using deep learning models, the researchers conducted automatic quantification on an extensive dataset of 39,000 medical images, precisely measuring the distances between various points in the body, such as shoulders, knees, and ankles. By cross-referencing these measurements with the genetic sequences of each individual, they successfully identified 145 specific points in the genome that govern skeletal proportions.

Tarjinder (T.J.) Singh, one of the co-authors of the study and an associate member at NYGC and assistant professor in the Columbia University Department of Psychiatry, highlighted the significance of their work as it provides a valuable roadmap that connects particular genes to different skeletal lengths, enabling developmental biologists to systematically investigate these connections.

Additionally, the team explored how these skeletal proportions are associated with major musculoskeletal diseases. Their findings indicated that individuals with a higher ratio of hip width to height have a greater likelihood of developing osteoarthritis and experiencing hip pain. Similarly, those with higher ratios of femur (thigh bone) length to height are more prone to arthritis in their knees, knee pain, and other knee-related issues. Moreover, individuals with a higher ratio of torso length to height are at an elevated risk of developing back pain.

Eucharist Kun, the lead author of the paper and a UT Austin biochemistry graduate student, explained that these disorders manifest due to biomechanical stresses on the joints over a lifetime. As skeletal proportions influence fundamental aspects of our movement, posture, and biomechanics, it is logical for them to be influential risk factors in these musculoskeletal conditions.

Overall, the combination of deep learning techniques, genetic analysis, and the study of skeletal proportions has yielded invaluable insights into the genetic underpinnings of skeletal development, offering potential avenues for further research and a deeper understanding of musculoskeletal diseases.

Genetic analysis (Unsplash)
Genetic analysis (Unsplash)

The researchers' findings also hold significance for our understanding of evolution. They observed that several genetic segments responsible for controlling skeletal proportions showed unexpected overlap with areas of the genome known as human accelerated regions. These regions are shared by great apes and various vertebrates but have undergone significant divergence in humans. This genetic insight provides a compelling genomic rationale for the distinct evolution of our skeletal anatomy.

Drawing a fascinating parallel, the iconic Renaissance artwork, Leonardo Da Vinci's "The Vitruvian Man," depicted similar ideas regarding the ratios and lengths of limbs and other components that constitute the human body.

"In some ways, we are delving into the same inquiry that Da Vinci grappled with," Narasimhan explained. "What constitutes the fundamental human form and its proportions? However, our approach employs modern methods and investigates how these proportions are genetically influenced."

By leveraging cutting-edge research techniques and exploring the genetic basis of skeletal proportions, the researchers have not only shed light on our evolutionary history but also provided a contemporary perspective on the age-old question of human anatomy and its genetic underpinnings.

In addition to Kun and Narasimhan, the co-authors are Tarjinder Singh of the New York Genome Center and Columbia University; Emily M. Javan, Olivia Smith, Javier de la Fuente, Brianna I. Flynn, Kushal Vajrala, Zoe Trutner, Prakash Jayakumar and Elliot M. Tucker-Drob of UT Austin; Faris Gulamali of Icahn School of Medicine at Mount Sinai; and Mashaal Sohail of Universidad Nacional Autonoma de Mexico.

The research was funded by the Allen Institute, Good Systems, the Ethical AI research grand challenge at UT Austin, and the National Institutes of Health, with graduate student fellowship support provided by the National Science Foundation and UT Austin’s provost’s office.

(Newswise/SS)

An application of AI to medical imaging datasets has revealed the genetics of the skeletal form for the first time (Representational Image: Unsplash)
AI Helps Identify New Antibiotic than Can Take One of Three Top ‘Superbugs'

Related Stories

No stories found.
logo
Medbound
www.medboundtimes.com