FUSION models inform decision making in the lab and serve as a key enabling technology for personalized medicine.
IOMICS announced April 27, 2016 in Boston, MA, the release of the FUSION Analytics Platform™, a cloud-based software system for predictive analytics and rapid prototyping of advanced decision models.
“The pace and complexity of medical research is increasing rapidly. The industry has become data rich, yet transforming complex data sets into actionable knowledge remains a challenge” said CTO Joseph Gormley and Senior Software Architect at IOMICS. “The problem today is more complex than just collecting more data or re-organizing the data you have. To maintain progress, the industry must embrace new methods and new computational models capable of extracting meaning from a broader range of chemical and molecular data types.”
“FUSION utilizes the most effective practices in data science while automating many of the manual, tedious and error-prone steps in prescriptive model building and deployment” said Dan Corkill, PhD, computer scientist and senior adviser at IOMICS. “One of the most innovative features in the platform is its ability to continually assess and improve model performance under varying conditions and as new data and supporting information become available.”
“We are not a traditional desktop tool or pipeline product.” said Tom Zisk, Technical Lead on the product. “We worked hard to encapsulate many of the most important aspects of predictive and prescriptive model building into a streamlined cloud-deployed service. Our user interface permits dataset development, model build, model validation, and model deployment without ever having to leave the platform.”
FUSION augments the best machine learning techniques with on-demand access to over eighty biochemical and omic data sources including the 200 million substances and 1 million assays in Pubchem. FUSION is different by design. FUSION focuses on automating data-driven model development supported by semantic integration and retrieval of diverse biochemical and molecular data types. In contrast to general analytics products and services today, FUSION is purpose-built for biochemical design, modeling biological response, and patient state analytics. “What is most unique about this platform is that it was designed from the ground up to analyze a broad range of multiscale omic and clinical data types to identify the patterns and interactions that drive complex biochemical processes. We believe, FUSION will change how the industry will think about and perform data-driven model development and advanced analytics.” said Gormley.
For chemical engineering and medical research FUSION can be utilized to model and characterize biochemical activity to predict toxicity or other behaviors of interest in support of safer food production, green chemical design, and biomarker and drug discovery. FUSION can also be live linked with chemical assays, production instrumentation and environmental sensors for a new class of real-time analysis and control. For clinical care, FUSION can be utilized to stratify patient populations and generate high-fidelity point-of-care models that improve outcomes, reduce costs, and forge stronger value-added relationships between the institution and the patient.
The idea for the platform was originated in 2004 by a team of engineers led by Gormley at Massachusetts Biomedical Initiatives. The emphasis was to support resource-limited academics and SMBCs attempting to analyze increasingly complex data sets. The cloud-based FUSION Analytics Platform is now hosted at the Massachusetts High Performance Computing Center (MGHPCC), which provides the computational infrastructure needed to support large-scale academic and commercial applications. “The Biotechnology Industry Access Program at the MGHPCC was designed to support just this type of new commercial endeavor that will not only promote economic development but also increase Massachusetts’ worldwide presence in the rapidly evolving field of data science,” said Ralph Zottola, PhD, CTO Research Computing at the University of Massachusetts.
The IOMICS Corporation is an innovative analytics company based in Worcester and Cambridge Massachusetts. IOMICS believes the freedom to explore new ideas and rapidly deploy advanced analytics is essential to accelerating science and improving healthcare. Its mission is to put advanced decision models to work everywhere — in the lab, in the clinic, and in the environment. IOMICS encourages collaborative model development and co-branding of turnkey applications for chemical engineering, medical research, and clinical care. Additional company and product detail can be found at www.iomics2022.mystagingwebsite.com.
Director New Business Development