SciBite AI 2.0: Combine deep learning models with powerful semantic algorithms

SciBite AI combines deep learning Artificial Intelligence models with our powerful semantic algorithms, enabling the pharmaceutical and healthcare sectors to exploit and rapidly use life science data in research and development.

SciBite AI

Cambridge, UK – SciBite, an Elsevier company, and award-winning semantic technology company, today announced the release of SciBite AI 2.0, a framework for leveraging AI and deep learning models alongside semantic technologies to unlock insights into Life Science data.

SciBite’s AI framework enables you to:

  • Unlock unstructured text using our standards-based semantic tools that enable Findable Accessible Interoperable Reusable (FAIR) across your enterprise, crucial for high-quality training data required by machine learning models
  • Access expert-created models, focussed on named-entity recognition (NER) and relationship extraction
  • Deploy models for your users and applications quickly and simply using the API
  • Implement deep learning models across your enterprise

At the heart of SciBite AI are our series of dynamic deep learning Named Entity Recognition and Relationship Extraction models, built from a combination of our industry-leading semantic technology, proprietary pipeline methodology, and specialist training data. These perform a wide variety of functions:

  • Named Entity Recognition (NER): Identifying concepts not covered by existing vocabularies;
  • Context-Specific Detection: Examples include new vs. pre-existing conditions and the anatomical sites of tutors;
  • Relationship Identification: Identify complex relationships between concepts such as proteins or adverse events;
  • Assisted ontology development: Use AI to suggest new terms, identify inconsistencies, accelerate ontology development and quality control;
  • Predictors: Spot patterns in data that help predict future outcomes;
  • Clustering and classification: Group documents and concepts based on their underlying data relationships.

SciBite AI 2.0 includes new architecture with major speed and scaling improvements, providing users with a suite of language comprehension models including:

  • Named-entity recognition (NER) models for context-driven disambiguation
  • Find relationships within text, including our NEW Genetic Variation–Disease model, that allows you to identify genetic mutations linked to a disease
  • Approaches to create new vocabularies or ‘learn’ new entities to enrich existing resources

SciBite AI combines the context and language capabilities of machine learning with the NER algorithms of our expert-curated vocabularies to create a host of new opportunities for our customers’ data,” says Product Manager, Andy Balfe. “From identifying novel connections, building custom ontologies to clustering data, our technology can help.

Find out more please get in touch.

Get in touch

About SciBite

SciBite is an award-winning semantic software company offering an ontology-led approach to transforming unstructured content into machine-readable data. Supporting the top 20 pharma with use cases across life sciences, SciBite empowers customers with fast, flexible, deployable API technologies, making it a critical component in data-led strategies.

Related articles

  1. SciBite launches SciBite AI relationship extraction models

    SciBite announces the release of SciBite AI relationship extraction models, which provide the enhanced ability to identify complex relationships within text to further unlock insights from Life Sciences data.

  2. Launch of Artificial Intelligence software platform for Life Sciences organisations

    SciBite announces the launch of SciBite AI, a state-of-the-art Artificial Intelligence software platform for leveraging machine learning models alongside semantic technologies to unlock insights into Life Sciences data.


How could the SciBite semantic platform help you?

Get in touch with us to find out how we can transform your data

Contact us