Big Data To Knowledge (BD2K)

The BD2K Mission

The NIH Big Data to Knowledge (BD2K) initiative addresses four major aims that, in combination, are meant to enhance the utility of biomedical Big Data. The first is to facilitate broad use of biomedical digital assets by making them discoverable, accessible, and citable. The Second Aim is to conduct research and develop the methods, software, and tools needed to analyze biomedical Big Data. The Third Aim is to enhance training in the development and use of methods and tools necessary for biomedical Big Data science. The Fourth Aim is to support a data ecosystem that accelerates discovery as part of a digital enterprise.

Overall, the focus of the BD2K program is to support the research and development of innovative and transforming approaches and tools to maximize and accelerate the integration of Big Data and data science into biomedical research.

The OHSU Department of Medical Informatics has several funded BD2K grants that are focused on enhancing data science training in biomedical research, as well as supporting the development of new methods. 

Visual of the research lifecycle

The BD2K Skills Course

The first offering of the OHSU BD2K Skills Course was held July 6-10th, 2015 and was focused on novice learners and undergraduates. Click here to see the schedule from the first skills course. 

The second offering of the OHSU BD2K Skills Course, "Data After Dark," was held January 13-14th, 2016 as a two part evening course. This short course offering focused on novice learners from the OHSU community. This Skills Course offering was also sponsored by the International Society for Biocuration. Click here to see the schedule from the second skills course. Materials from these courses are available online, in our FigShare collection. For Day 1 presentations, click here. For Day 2 presentations, click here

The third skills course offering was "Advanced Data After Dark" and was held May 23-26th, 2016 for two hour sessions across four nights. This course examined more advanced topics dealing with Big Data wrangling, exploration, and algorithms. To view the schedule, click here.

The introductory "Data and Donuts" courses were held June 28 and 29, and July 21, 2016. This course provided an overview of big data, discussed finding data resources, basic data handling, ethics and exploratory data analysis and visualizing your data. To view the schedule, click here

 The fifth skills course offering was "BD2K Clinical Risk Prediction Workshop" and was held May 15th and 16th, 2017 for three hour sessions across two nights. This course examined more advanced topics dealing with using a synthetic patient cohort, understanding issues with the use of both clinical and genetic data using Exploratory Data Analysis and the use of machine learning to build a predictive model of cardiovascular risk in the patient population using clinical and genetic covariates. To view the schedule and content, click here and click here


The BD2K Open Educational Resources Project

The OHSU BD2K OER Project is developing open educational resources (OERs) for use in courses, programs, workshops, and related activities for informatics graduate students, established investigators and  senior trainees seeking to learn more about data science to expand their research programs. The OER project is led by Bill Hersh, Melissa Haendel and Shannon McWeeney.  The material is focused on a list of topics that were informed in part by a needs assessment we carried out with Oregon undergraduate colleges and universities in early 2015.

Click here to view the OER website.