“Individual faces and other physical traits were predicted using whole genome sequencing data.”

Everything that makes you is in your genome and can be predicted


Fri, Sep 8th, 2017 11:00 by capnasty NEWS

Phys brings to attention the work done by researchers from Human Longevity, Inc., where they were able to predict faces and traits of individuals using genome sequencing and machine learning. The article is prompt to note that while this could prove beneficial in forensics, it has a serious impact on privacy.

The team predicted eye color, skin color and sex with high accuracy, but other more complex genetic traits proved more difficult. The team believes their predictive models are sound, but that large cohorts are needed to make prediction more robust. The team also developed a machine learning algorithm called a maximum entropy algorithm, which had novelty in that it found an optimal combination of all predictive models to match whole-genome sequencing data with phenotypic and demographic data and enabled the correct identification of, on average, 8 out of 10 participants of diverse ethnicity, and 5 out of 10 African American or European participants.

Venter, HLI's co-founder, executive chairman and head of scientific strategy, commented, "We set out to do this study to prove that your genome codes for everything that makes you, you. This is clearly a proof of concept with a limited cohort but we believe that as we increase the numbers of people in this study and in the HLI database to hundreds of thousands we will be able to accurately predict all that can be predicted from individuals' genomes."



You may also be interested in:

How Far Away is the Moon? (The Scale of the Universe)
Using Computers to Understand the Brain, in Order to Build Better Computers
"Gravity may simply not exist."
Brain Implant Allows Paralysed Person to Type Six Words per Minute
Single Injection Reverses Down Syndrome in Newborn Mice