On December 4th, Google released a new tool created by the Google Brain team called DeepVariant. It uses the latest artificial intelligence to build a more accurate picture of a person’s genome from sequencing data. It helps turn high-throughput sequencing readouts into a full picture of a genome. It identifies small insertion and deletion mutations and single-base-pair mutations in sequencing data.
“The team collected millions of high-throughput reads and fully sequenced genomes from the Genome in a Bottle project, a public-private effort to promote genomic sequencing tools and techniques. They fed the data to a deep-learning system and painstakingly tweaked the parameters of the model until it learned to interpret sequenced data with a high level of accuracy.”, says technologyreview.com.
DeepVariant can be the future of genomics. DeepVariant hopes to be used to tease out genetic causes of diseases to identify potential drug therapies.
“The success of DeepVariant is important because it demonstrates that in genomics, deep learning can be used to automatically train systems that perform better than complicated hand-engineered systems,” says Brendan Frey, CEO of Deep Genomics.