Our Technology


Bina’s multidisciplinary team of big data specialists and genomics scientists have worked together to redefine the way genomics is done at scale. Using the best practices from the high–performance computing and big data industries, the Bina Platform provides a robust and scalable solution for analyzing the growing volume of genomic data.

Bina Execution Engine

Bina Desktop and Rack are powered by Bina’s Execution Engine, our job scheduling and resource management system written on top of numerous open-source big data technologies.

The execution engine allows for distributed parallelization of genomic workflows and efficient resource usage while minimizing the network and shared disk I/O footprint. A language-agnostic interface allows us to rapidly integrate many open-source and commercially-available genomics and software packages such as the most recent versions of the Genomics Analysis Toolkit (GATK), BWA, SAMTools, TopHat, and more.


Bina Annotation & Querying Engine

The Bina Annotation and Analytics Intelligence Module (Bina AAiMTM) provides tertiary analysis using output from Bina Desktop and Bina Rack.

At its heart, Bina AAiMTM is powered by Bina’s Annotation & Querying Engine. Built on top of an Apache Hadoop stack and NoSQL databases, the annotation engine provides a scalable infrastructure for continuously “joining” terabytes of open and commercial databases with variant calls generated by the Bina Platform.

The Bina Querying Engine allows for real-time (sub-second) querying and analytics on top of genomics datasets by taking advantage of Bina’s proprietary genomics variant indexing technology.

Low-level Software Optimization

When it comes to comparing billions of strings with each other, a low-level software optimizations such as SIMD can make a significant difference.

In addition to the third-party genomics software used on the Bina Platform, Bina has developed a set of software tools for in-memory sorting, storing, and routing genomic data. Coupled with the efficient static scheduling provided by the Bina Execution Engine, these software optimizations have enabled unprecedented throughput and turn-around time for large analyses.


automation diagram

Bina’s architecture is designed to bring computation to data. By seamlessly integrating with on-premises networked storage, data can be analyzed without upload overhead time. Bina Read Alignment, Variant calling, and Expression Module (Bina RAVETM) can automatically upload its output to Bina AAiMTM. This allows for rapid annotation using dozens of public and commercial annotation resources as well as real-time interactive querying and analytics on millions of variant calls.

Interaction and management of the Bina Platform can be performed simply through a modern web-based application as well as through a RESTful API for automation and integration with existing infrastructure.

Still have questions about our technology?

Don’t worry, we’re happy to answer them. Give us a call, or Test Drive Bina and experience it for yourself.