Operating at the Intersection of
Big Data and Genomics
Building on top of big data technologies such as Apache Spark, Hadoop, and elastic cloud-based infrastructure, Bina’s products are fundamentally made for scale. Bina unites high performance computing practices from industries such as finance and consumer web services, leveraging those skillsets to address the ever-growing complexity of the genomic analysis field.
high accuracy, efficiency and speed
Bina uses scientific genomic algorithms that represent best practices in the field. We then complement them with ensemble analyses that leverage the strength of multiple tools, improving accuracy beyond what any single tool can deliver. This approach earned Bina first place for indel detection and second place for somatic SNV detection sub-challenges in stage five of the DREAM challenge.
As data volumes and sample sizes grow, computing costs are becoming a more significant expense. By making intelligent choices about how to parallelize alignment and variant calling processes, we can significantly reduce overall compute costs per sample, thereby reducing overall project costs.
An equally important measure is turnaround time. The sooner variant calls are in the hands of scientists, the sooner they can explore the results in a biological context, identify recurring mutations and attribute statistical significance to the findings - all while propelling scientific discovery forward more rapidly.
Built for a globally distributed organizationOn-premises, cloud and hybrid deployment options
Every organization is different; different infrastructures, different budgets, different project complexities. Bina solutions can be deployed in multiple ways, including on-premises, in the cloud or as hybrid deployments that can be implemented on a global scale. Let us know your needs and we’ll work with you.
Bina’s experts have you covered
Bina is a unique interdisciplinary team of software engineers, big data scientists, biologists, and more, contributing expertise in the areas of computer architecture, parallelization, machine learning and scientific algorithm development. See our list of key publications for contributions we have made to the genomics community in just the last year.