Integrated Data Framework

Biosymetrics Inc. has built the state-of-the-art AugustaTM platform that allows rapid and effective integration as well as analytics and machine learning for diverse data sets in medicine and health. More information on AugustaTM here.

The Machine Learning engine, SymetryMLTM, allows users to process more data at a faster rate than any other technology available today, which is important in diagnostics, healthcare, and other massive data analytics in medical research.

Notable features of AugustaTM include:

  • Modular and customizable pipelines for processing imaging (MRI/fMRI), drug design, EHR/EMR, and genomic/proteomic data sets, allowing analysis using any combination of data types
  • Workflows optimized for each specific experiment, aimed at maximizing accuracy and performance
  • Easy integration into existing business processes
  • Real-time machine learning of massive data at unprecedented speeds through integration with SymetryML

BioSymetrics delivers a customized massive data analytics and machine-learning infrastructure for biomedical and health data, which includes the following features:

  • Modular and customizable Python-based pipelines for processing phenotypic, imaging, drug, and genomic data sets using any combination of data types within any framework (cloud, diagnostic machines, private servers)
  • Integration with SymetryMLTM, our Java based real-time machine learning technology
  • Construction of customized clusters for performance optimization
  • Delivery and distribution (using Apache Spark) of processing jobs using different types of clusters (g. Sun Grid Engines, Spark Clusters)
  • Management of results using a distributed storage infrastructure (g. Cassandra, SQL, HDFS, Hive)
  • Connection to Apache Kafka to retrieve and organize streaming data
  • Workflows optimized for each specific experiment, aimed at maximizing accuracy and performance
  • Seamless integration into existing business processes