A predictive genomic matching engine on Hadoop

Jan 25, 2018 · Minneapolis, United States of America

For the thousands of people diagnosed every year with life-threatening blood cancers like leukemia and lymphoma, a cure exists. For the past 25 years, Be the Match, operated by the National Marrow Donor Program (NMDP), has managed the largest and most diverse marrow registry in the world and works every day to save lives through bone marrow transplant. The program recently moved its core transplant matching platform onto Hadoop. We’ll share why the program chose Hadoop and shares its big data goals: to increase the number of donors and matches, make the process more efficient, and make transplants more effective.

Be the Match’s Haplogic℠ solution utilizes Spark, Kudu, and Sentry to build a predictive matching engine that compares the patient DNA type to the donor DNA type from a global donor registry of 30 million potential donors. Haplogic supports a RESTful services API that powers a customer-facing search application used by Transplant Center hospitals.


Tony McAllister is the Director of Enterprise Architecture at Be The Match. He has led architecture and software development teams at Be The Match, Target, Level(3) Communications, and Cummins Inc. He earned a BS in Computer Science from Rose-Hulman Institute of Technology and MBA from Indiana University. When not working or with his family, Tony enjoys beating Biren Desai like a drum at table tennis.

Anthony Barber is a Principal Software Engineer at Be The Match. He has been working at the NMDP for 13 years in the roles of QA Automation, Bioinformatics development supporting our Bioinformatics research department, and now a Software Engineer for Search Services supporting the Haplogic ( Search Server ) application. The Haplogic application is currently being replatformed as a Spark application on Hadoop using Cloudera.

Andy Hansen is a Systems Engineer at Be The Match. Andy has been working in various roles for the last 4 years at Be The Match, most recently working as a Linux/Unix Engineer. He currently is working on Hadoop infrastructure for the Data Center Services team.

Map from Parking to Event: http://bit.ly/2DpAAaZ

Food: Pizza and drinks, first come first serve, starting at 6:30PM provided by Cloudera.

Event organizers

Are you organizing A predictive genomic matching engine on Hadoop?

Claim the event and start manage its content.

I am the organizer

based on 0 reviews