Researchers in California have created software for turning a person’s raw DNA data into a predictive picture of their face. Using anonymous data — the kind that genetics companies like 23andMe sell to pharmaceutical companies for research purposes — scientists from Human Longevity, Inc., a private genetics lab, have made computer generated images that resemble a person’s real face.
“When you have the whole genome, we can predict a photograph, your height, your weight, your eye color,” Craig Venter, founder of Human Longevity, Inc, told KPBS.org.
“We can generate photos from the 23andMe data,” Venter added.
In a paper published Monday, the researchers detailed how they used anonymous data from over 1,000 people to create an algorithm that could give a fairly accurate physical portrait of a person. The algorithm could not reliably predict traits like baldness and freckles, or show what a person looked like at an older age.
“No longer can one assume that exposure of her genome sequence will not be directly linked back to her,” Xiaoqian Jiang, a UC San Diego computer scientist, told KPBS.org. “She needs to realize that sharing her genomic data is just like sharing her picture, with increasingly high resolution.”
We want to hear your story. If you’ve ever learned something unusual or unexpected about your family tree through a genetic ancestry test such as 23andMe or Ancestry.com, tell us about it by filling out our Google Form. A reporter from the Forward may contact you.
23andMe Data Predicts Your Face, Say Geneticists