Google’s AI Will Analyze Your Genome For Free. Here’s Why That’s Important.

The better we can understand any and all genomes, the more comprehensive understanding we will have of anything that is genetically linked.

Typically tech companies aren't in the business of giving things away for free, but Google made a big and important exception on December 4 when the giant released a tool that uses artificial intelligence (AI) techniques and machine learning to assemble complete human genomes.

Called DeepVariant, Wired reports said tool is free and more accurate than all the existing methods of genome sequencing, but what does that mean, and why exactly does it matter? 

In short, a genome is the complete set of genes or genetic material present in a cell or organism. The better we can understand any and all genomes, the more comprehensive understanding we will have of anything that is genetically linked, such as heart disease, diabetes, and certain forms of cancer.

For example, if we can isolate the genes responsible for certain cancers (as we have already seen with the BRCA1 and BRCA2 genes) the thought is we can get a clearer idea of what causes said cancers, and be that much closer to developing more effective treatments and eventually finding a cure.

In an essay for HuffPost, scientist Stephane Budel, who had her own genome sequenced, explained why sequencing multiple human genomes is so crucial. "Just like the Internet, the value in genomics resides in the number of its participants, and the value of each individual genome increases as we sequence (and make sense of) more genomes," she said. "Most diseases are complex, and involve multiple genes, epigenetic variations, environmental factors, etc. In order to get a better picture of human in health and disease, we will need millions of genomes."

A post shared by Google (@google) on

As society as a whole shifts from population-based medicine to personalized medicine for most medical conditions, Budel argues "genomics will be front and center in this conversion."

It's worth noting that while Broad/Harvard human geneticist Daniel MacArthur tells Wired DeepVariant "isn't currently scalable to a very large number of samples because it's just too computationally expensive," there is hope it will get to that point in the near future, which is very advantageous for us all.

Cover image via achinthamb / Shutterstock.com.

GET SOME POSITIVITY IN YOUR INBOX

Subscribe to our newsletter and get the latest news and exclusive updates.