June 16-20, 2013

Leipzig, Germany

Presentation Details

Name: Bioinformatics, Big Data & HPC: Practice & Thoughts
Time: Wednesday, June 19, 2013
9:00 AM - 9:30 AM
Room:   Hall 2
CCL - Congress Center Leipzig
Speakers:   BingQiang Wang, BGI
Abstract:   Advances in sequencing technology enable rapid growth of genomics data in terms of both volume and diversity. To turn raw data to scientific discovery and practical applications, state of the art computational tools and infrastructure is of extreme importance. For typical analysis like sequence alignment and variant calling, heterogeneous computing tools have been developed, examples are GPU accelerated SOAP3-DP and GSNP. On the other hand, traditional bioinformatics features very high throughput of vast workloads, as well as imbalance between computation and data access. Simulation has been conducted to improve scheduling efficiency thus better resource utilization, toward a more balanced future architecture. Data management is the foundation for big data enabled life science research. Metadata based system is deployed to facilitate efficient mining of huge volume of complex dataset. As concluded, power efficient software, balanced infrastructure, and good data management practice will be the key to bring life science into big data era.  
Program may be subject to changes.