AI-powered study pinpoints genes that shape bones

Using artificial intelligence to investigate tens of 1000’s of X-ray images and genetic sequences, researchers from The University of Texas at Austin and Latest York Genome Center have been in a position to pinpoint the genes that shape our skeletons, from the width of our shoulders to the length of our legs.

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

“Our research is a robust demonstration of the impact of AI in medicine, particularly on the subject of analyzing and quantifying imaging data, in addition to integrating this information with health records and genetics rapidly and at large scale,” said Vagheesh Narasimhan, an assistant professor of integrative biology in addition to statistics and data science, who led the multidisciplinary team of researchers, to supply the genetic map of skeletal proportions.

Humans are the one large primates to have longer legs than arms, a change within the skeletal form that’s critical in enabling the flexibility to walk on two legs. The scientists sought to find out which genetic changes underlie anatomical differences which might be clearly visible within the fossil record resulting in modern humans, from Australopithecus to Neanderthals. In addition they desired to learn the way these skeletal proportions allowing bipedalism affect the danger of many musculoskeletal diseases corresponding to arthritis of the knee and hip -; conditions that affect billions of individuals on the earth and are the leading causes of adult disability in america.

The researchers used deep learning models to perform automatic quantification on 39,000 medical images to measure distances between shoulders, knees, ankles and other points within the body. By comparing these measurements to everyone’s genetic sequence, they found 145 points within the genome that control skeletal proportions.

Our work provides a road map connecting specific genes with skeletal lengths of various parts of the body, allowing developmental biologists to research these in a scientific way.”

Tarjinder (T.J.) Singh, the study’s co-author, and associate member at NYGC and assistant professor within the Columbia University Department of Psychiatry

The team also examined how skeletal proportions associate with major musculoskeletal diseases and showed that individuals with a better ratio of hip width to height were found to be more prone to develop osteoarthritis and pain of their hips. Similarly, individuals with higher ratios of femur (thigh bone) length to height were more prone to develop arthritis of their knees, knee pain and other knee problems. Individuals with a better ratio of torso length to height were more prone to develop back pain.

“These disorders develop from biomechanical stresses on the joints over a lifetime,” said Eucharist Kun, a UT Austin biochemistry graduate student and lead creator on the paper. “Skeletal proportions affect every little thing from our gait to how we sit, and it is sensible that they’re risk aspects in these disorders.”

The outcomes of their work even have implications for our understanding of evolution. The researchers noted that several genetic segments that controlled skeletal proportions overlapped greater than expected with areas of the genome called human accelerated regions. These are sections of the genome shared by great apes and lots of vertebrates but are significantly diverged in humans. This provides genomic rationale for the divergence in our skeletal anatomy.

Some of the enduring images of the Rennaisance-;Leonardo Da Vinci’s “The Vitruvian Man” –contained similar conceptions of the ratios and lengths of limbs and other elements that make up the human body.

“In some ways we’re tackling the identical query that Da Vinci wrestled with,” Narasimhan said. “What’s the fundamental human form and its proportion? But we at the moment are using modern methods and in addition asking how those proportions are genetically determined.”

Along with Kun and Narasimhan, the co-authors are Tarjinder Singh of the Latest 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.