Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • ADVERTISEMENT FEATURE Advertiser retains sole responsibility for the content of this article

Advancing data discovery in the life sciences through artificial intelligence

Vyasa, which was founded in 2016 and is based in Boston, Massachusetts, provides highly scalable deep-learning software and analytics for healthcare and life-sciences applications. Named after the Sanskrit व्यास (Vyāsaḥ, a legendary sage who compiled the Hindu epic Mahabharata), Vyasa enables organizations to access, integrate and distill disparate data sources, regardless of their location or structure and without moving or replicating the data. The company’s suite of deep-learning-based applications is designed to optimize the path from large-scale, noisy data to critical insights, and support faster, more accurate, research and business decisions.

At the heart of Vyasa’s platforms are deep-learning algorithms that can help unlock, fuse and extract invaluable information contained in previously intractable data types, such as unstructured text and images (Fig. 1). In combination with an industry-leading infrastructure for securely providing these deep-learning systems at scale, the company’s analytics solutions are rapidly becoming the deep-learning platform of choice for partners looking to effectively advance their therapeutics and diagnostics research and development programs.

“The top challenge today for life sciences and healthcare organizations is to effectively extract and operationalize information from complex and disparate sources to generate novel insights, support effective decision-making, and ultimately advance innovation,” said Christopher Bouton, Vyasa’s founder and CEO. “Vyasa’s sophisticated deep-learning platform offers integrated, end-to-end solutions for partners seeking to enhance their R&D programs through optimized knowledge.”

Vyasa’s network of artificial intelligence platforms

Fig. 1 | Vyasa’s network of artificial intelligence platforms can advance data discovery in the life sciences. Vyasa combines a suite of deep-learning algorithms to help unlock, fuse and extract information from difficult-to-analyze data types with an industry-leading infrastructure for securely providing these deep-learning systems at scale.

A tapestry of deep-learning solutions

Vyasa has developed a suite of platforms to address different challenges in the life sciences and healthcare space.

The company’s core platform is Layar, a next-generation data fabric that enables secure and highly scalable data management, cataloging, tagging and indexing for integrated analytics. Layar contextualizes an organization’s data to dynamically derive properties and content patterns that provide valuable insights for critical analytics tasks, such as R&D and business decision-making.

Layar’s capabilities are augmented by: Cortex, a tool for intuitively creating and managing data fabrics; Axon, a dynamic knowledge-graphing capability for visualizing data relationships and evidence; Retina, a platform for the management, analysis and classification of medical imagery; and Synapse, a smart spreadsheet technology for extracting unstructured content into structured insights.

Deep learning at work

The flexible, modular and extensible nature of Layar makes Vyasa an ideal partner for organizations looking for the rapid cloud-based or on-site implementation of deep-learning solutions customized to their needs. Here are some illustrative examples of such implementations.

Harmonization of clinical-trial protocols. Biopharma companies spend substantial time and financial resources analyzing clinical trials, including extracting and compiling information from large volumes of unstructured information. Given the strategic relevance of such analysis for R&D and treatment decisions, harmonizing data sources would dramatically improve a company’s access to critical intelligence, and help accelerate product innovation. Pairing Vyasa’s Synapse technology with the Layar canonical data fabric provides a quick and seamless solution for harmonizing key data and extracting structured insights that will help the company save time and money.

Acquisition of competitive intelligence and trend analytics. Biopharma companies typically use a patchwork of tools to stitch together competitive intelligence, resulting in inefficiencies and often a lack of comprehensiveness. Vyasa helps to streamline the process by providing an end-to-end pipeline to gather information from sources such as national patent offices, and identify competitor filings around new technologies and therapeutics. The analytics can be delivered as user-friendly spreadsheets, dynamic knowledge graphs, and real-time dashboards that greatly facilitate decision-making around new product development or other strategic business initiatives.

Charting a patient’s journey. Post-commercialization, biopharma companies need comprehensive and dynamic systems to monitor and understand patients’ experiences with their products. Collecting and analyzing diverse data streams such as clinician notes, published research, social-media feeds, RSS and patient fora is a complex task.

Through its application programming interface setup, Vyasa offers companies a solution to rapidly execute a Layar implementation that allows the company to structure the information and extract the most-relevant insights about a patient’s journey in real time.

“Today, deep learning is the most promising technology in predictive analytics for extracting information from previously intractable data types,” said Bouton. “By providing the tools for researchers and analysts to easily access such data, we are removing the single most pressing barrier to innovation in the life sciences, and we are ultimately helping accelerate the improvement in quality of care for patients.”


Quick links