Discussions around AI's possibilities have been taking the healthcare industry by storm. It comes as no surprise to me, that Google has capitalized on this opportunity, announcing the release of their AI tool DeepVariant.
The tool, developed by the Google Brain team and Verily, uses deep learning technology to transform high-throughput sequencing (HTS) outputs into an individual's complete genome sequence. This is a ground breaking innovation as HTS offers only a partial and fallible selection of a genome. Although there are several tools already that can interpret the HTS readouts, the challenges around inaccurate and incomplete genome sequencing had not been resolved.
It is exciting to see the practical application of AI in healthcare, but what is more fascinating, is the way in which Google has released this tool: as open source software on their Google Cloud Platform. Their objective, is to "encourage collaboration and accelerate the use of this technology to solve real world problems." This comes days after they announced three new partnerships between Google Cloud and IT healthcare companies: Change Healthcare, Nautilus Medical and Ambra Health. These partnerships will leverage the Cloud to create more easily accessible networks, uncover actionable insights and to share advanced imaging analytics in a secure way.
It's clear that Google is betting on Cloud as the tool that will transform digital health. They are already working with several clients in the healthcare space to "help create better patient experiences, empower care teams to work together and accelerate research." What I am interested to watch is how a company of technology early adopters will bring an industry of technology laggards up to pace.
DeepVariant is the first of what we hope will be many contributions that leverage Google's computing infrastructure and ML expertise to both better understand the genome and to provide deep learning-based genomics tools to the community. This is all part of a broader goal to apply Google technologies to healthcare and other scientific applications, and to make the results of these efforts broadly accessible.