an genomics wizards make an informed guesstimate on what a person looks like, based on his or her DNA? J. Craig Venter sure thinks so, per a new PNAS paper. Yet his Human Longevity Institute study is facing Twitter blowback for that claim.

Venter’s proof-of-concept study used a machine learning algorithm to analyze the genomic and biometric data of 1,061 volunteers. It looked at gender, facial structure, age, height, weight, skin color, eye color, and voice, generating a facsimile of the person based on their genetic analysis.

This is a STAT Plus article and you can unlock it by subscribing to STAT Plus today. It's easy! Your first 30 days are free and if you don't enjoy your subscription you can cancel any time.
Already a subscriber? Log in here.

Leave a Comment

Please enter your name.
Please enter a comment.

  • Proof on concept is a great way to a postulate in this specific case.
    There is absolute genomic involvement and also statistical variants/uncertainty, among all genomic factors involved.
    There is also uncertainty/approximatetions/limits in development and application in almost any algorithm.
    I think it is an a great way to make a multi-genomic base approximation of what a person might look like or might have looked like in the pass.
    Bringing familial genomic and physic association could make it even more accurate.
    I respect scientist(s) who were associated in research and disagree but, I believe it is very viable research.

Sign up for our Morning Rounds newsletter

Your daily dose of what’s new in health and medicine.