The Bakar Computational Health Sciences Institute (BCHSI), headed by Atul Butte, MD, PhD, is the cornerstone of UCSF’s efforts to harness the power of innovative computation paradigms, “big data”, and the machine intelligence they catalyze. BCHSIis building an infrastructure that will provide UCSF faculty, staff, and trainees with the tools and training to unlock the power of advanced machine learning and graphical network-based analytics across the spectrum of applications in basic science, clinical, translational and population health.

Examples of such applications are insights into biological processes, discovery of effective drugs and treatments, and augmenting clinical decision support with machine-generated patterns and predictions. Together, these will lead to more predictive, preventive, and precise health care.

The Institute seeks to inspire a culture shift that encourages researchers to view the vast amounts of many forms of data that already exist as an asset that can be mined for biomedically meaningful patterns.

Some of BCHSI’s foundational projects are:

  • The Wynton High-Performance Computing Cluster
    BCHSI is integrating cooperative computing facilities among dispersed clusters across campus and augmenting them with storage space. The resulting coordination of infrastructure and capabilities enables researchers to better acquire, analyze, store and use large (or small) data sets across hundreds of compute cores on demand.
  • The Information Commons is a fast, shared repository of UCSF clinical data, clinical notes, related basic science and population data, and supporting tools on Spark, a next generation Apache-based open-source platform developed at UC Berkeley.
  • The SPOKE Knowledge Network is a pilot to demonstrate the greater Knowledge Network that is at the core of UCSF Precision Medicine. It mirrors the very nature of biomedical and health pathways, with millions of entity types including gene, protein, organ, disease condition, drug compounds and side effects – built up from dozens of reference repositories as well as from UCSF clinical evidence.
  • UC-wide Electronic Health Records. As Chief Data Scientist for UC Health, Atul Butte is leading efforts to build computational infrastructure to link electronic health records (EHRs) and other data from over 15 million patient records across the six UC medical centers. This initiative will power transformative, data-driven advances in care, accelerate discovery, and improve health for Californians and beyond.

Education
BCHSI, in collaboration with partners such as the UCSF Library and UC Berkeley’s D-Lab, provides educational resources for UCSF trainees, researchers, physicians and staff to access, manage, analyze, and use “big data” such as the integrated EHR, as well as other computational tools and resources.

For information on BCHSI upcoming events, workshops and offerings, please visit their Events page.