Google’s AI division releases open source update to DeepVariant

Google has released the open source version of DeepVariant, a deep learning technology to reconstruct the true genome sequence from HTS sequencer data with significantly greater accuracy than previous classical methods. This work is the product of more than two years of research by the Google Brain team, in collaboration with Verily Life Sciences.

The Brain team programmed it in TensorFlow, a library of open source programming code for numerical computation that is popular for deep learning applications. The technology works well on data from all types of sequencers and eases the process of transitioning to new sequencers.

DeepVariant is being released as open source software to encourage collaboration and to accelerate the use of this technology to solve real world problems. The software will make it easier to receive inputs from researchers about the use cases they were interested in. This is part of a broader effort to make the data of genomics compatible with the way deep learning machinery works. Also, this move will push Google technologies to healthcare and other scientific applications, and make the results of these efforts broadly accessible.