Discussion with 23AndMe Director, Subarna Sinha
Talk on: Building End-to-End Machine Learning Systems for Providing Personalized Health and Ancestry Insights
Topic: Tremendous advances in genomics over the last couple of decades has made it relatively cheap to identify DNA variants at millions of locations on the genome. At 23andMe, we have accumulated large amounts of genetic data from our 13M+ customers, >80% of whom have consented that their data be used for research purposes. Besides genetic data, we also have non-genetic data that capture diverse information related to diet, lifestyle, disease status, etc. These data give us the unique ability to build machine learning models that can provide our customers personalized insights about their health and/or ancestry. In this talk, we will provide a broad overview of the types of health and ancestry insights that can be generated using the data we have. We will also describe an end-to-end machine learning system that can train and deploy these models at scale.
Bio: Subarna Sinha currently leads the Data and Machine Learning Engineering teams at 23andMe. After getting her PhD in logic synthesis, she worked in EDA research groups at Intel and Synopsys for several years. Her interests in EDA spanned logic synthesis, physical design and verification. She then joined Stanford University where she pivoted her research to computational cancer biology and developed statistical methods to derive insights from large cancer omics datasets. Following Stanford, she moved to SRI International, where she was a NIH-funded Principal Investigator with a focus on developing novel computational tools for identifying novel drug targets. Her current position at 23andMe enables her to build systems at the intersection of engineering and computational biology. She is the recipient of numerous awards, including the Donald O. Pederson/IEEE best paper award and the Synopsys Inventor of the Year award. She holds a B.Tech. in electronics and electrical communication engineering from the Indian Institute of Technology, Kharagpur, and a Ph.D. in electrical engineering and computer sciences from the University of California, Berkeley.