During last year's Big Data in Biomedicine conference, David Glazer, director of engineering at Google, described how the search giant is developing technological tools to help those working in life sciences to store, process, explore, and share genomic data.
In this 2014 Big Data in Biomedicine video, Glazer explains how he and colleagues fed a computer network 10 million random YouTube videos and asked the system to look for patterns. The computer determined that most frequently occurring sequence of 1s and 0s in the sample was that of a human face. Not surprisingly, the face of a cat was the second most-frequent pattern the computer found.
While these examples of machine pattern-recognition capabilities may not be earth-shattering to those who spent an inordinate amount of time watching YouTube videos, the findings demonstrate the potential of computers to rapidly identify significant patterns in large volumes of biomedical information. Imagine researchers performing the same experiment, but instead of YouTube videos they used genomic data. "We don't have 10 million genomes available for this type of analysis, yet," he said. "But as we move in that direction the tools are ready."
Watch the full presentation to learn how Google is working to remove computing restraints to advance genomic research. And check out Glazer at the 2015 Big Data in Biomedicine conference, which will be held May 20-22 at the Li Ka Shing Center for Learning and Knowledge at Stanford.
Previously: Countdown to Big Data in Biomedicine: Mining medical records to identify patterns in public health, Stanford bioengineer discusses mining social media and smartphone data for biomedical research, Using genetics to answer fundamental questions in biology, medicine and anthropology, Examining the potential of big data to transform health care and Registration for Big Data in Biomedicine conference now open