Researchers from Human Longevity, Inc. Use Whole Genome Sequence Data and Machine Learning to Identify Individuals Through Face and Other Physical Trait Prediction

The authors believe that, while the study offers novel approaches for forensics, the work has serious implications for data privacy, deidentification and adequately informed consent. The team concludes that much more public deliberation is needed as more and more genomes are generated and placed in public databases. For the IRB approved study, 1,061 ethnically diverse people ranging in age from 18 to 82 participated by having their genomes sequenced to an average depth of at least 30x. Researchers also collected phenotype data in the form of 3D facial images, voice samples, eye and skin color, age, height, and weight. The team predicted eye color, skin color and sex with high accuracy, but other more complex genetic traits proved more difficult.