The AI and Machine Learning Platform for Healthcare Industries

Biosymetrics Inc. has built the state-of-the-art AugustaTM platform that allows rapid and effective integrated analytics and Machine Learning (ML) on many different kinds of biomedical and healthcare data types. Our AI ML platform capabilities include over 140 data modules that can be leveraged in data science and predictive analytics initiatives.

NEW RELEASE: v1.3

  • Improved visualization incorporating Seaborn and Matplotlib packages
  • Increased Machine Learning model types
  • Expanded preprocessing for tabular data sets with Pandas integration
Artificial Intelligence

Notable features of Augusta™ 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
  • Machine learning of massive data at unprecedented speeds

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)
  • Construction of customized clusters for performance optimization
  • Delivery and distribution using Apache Spark of processing jobs using different types of clusters (e.g. Sun Grid Engines, Spark Clusters)
  • Management of results using a distributed storage infrastructure (e.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

Biomedical Machine Learning Using Multiple Data Pipelines

Augusta™ performs predictive analytics and biomedical machine learning for use cases in bioinformatics, R&D clinical informatics, target discovery, and computational biology:

  • MRI/fMRI and other imaging modalities
  • EEG
  • EKG/ECG
  • Genetics, Proteomics
  • Wearables data
  • EHR/EMR data
  • Real Time Integrative Analytics, e.g. combining genomics with clinical data
  • Precision medicine applications in real time
  • Drug compound and small molecule activity prediction
  • Patient care quality and program analysis
  • Drug discovery and development analysis
  • Hospital telemetry and operational data

Connect to a Variety of Data Sources

  • Through integration with Python, Augusta™ can connect to and read from any data source (g. local storage, databases, cloud storage).
  • Modular and customizable pipelines for processing raw phenotypic, imaging, drug, and genomic data sets using any combination of data types.

Integrate with Existing Business Processes

  • Augusta™ can deploy where the data reside, saving valuable time and development effort.
  • Seamlessly integrates into existing business processes or embedded directly within user applications.
  • Capabilities available for IPython notebooks with Plotly-powered visualizations.

Parallel and Distributed Computing Enabled

  • Augusta™ leverages the performance of the most advanced parallel processors – multi-core CPUs and GPUs – for increased performance during model rebuilds.
  • Augusta™ is integrated with Apache Spark for distributed execution.
  • Deployable on standalone servers, through the Amazon Web Service and Microsoft Azure, with an Apache Spark distributed framework for all steps above.
  • Connection to Apache Kafka to retrieve and organize streaming data.
Augusta™ Learning

BioSymetrics

Using data available in the DrugBank Database we generated binding prediction profiles for every known protein target having 5 or more described ligands (607 protein-drug binding models made, 7,149 potential ligands for each, over 4 million drug-ligand activity predictions total)