Introducing SciBite Search

Pharmaceutical and biomedical professionals need to unravel enormous amounts of data, get fast insights from data that's locked up in both internal and external documents and can't afford to miss any crucial details.

Watch the video to find out how our intelligent scientific search platform, SciBite Search, enables researchers to quickly find meaningful insights from structured and unstructured public and proprietary biomedical data.

The Evolution of Search

The diagram illustrates how SciBite Search better addresses scientific search using Fingolimod as an example. Fingolimod (FTY720) is an FDA approved immunomodulatory drug for treating multiple sclerosis, also sold under the brand name Gilenya.

Traditional keyword search relies on a user providing all the names ("strings") by which Fingolimod is known. These are then matched to text found in the document corpus. Semantic search goes further, adding the concept of entities (things) including classes and relationships (taxonomy). Augmented search further enriches this data, enabling users to find results beyond what is inherently present in the data. Deep learning approaches are designed to handle more challenging questions and address issues such as imprecise search terms and badly indexed data.

FAIR Data Principles

The explosion of data in life sciences is leading many organisations to review their approach to data stewardship in an effort to extract maximum return from their research investment.

FAIR (Findable, Accessible, Interoperable and Reusable) Data Principles aim to promote the integrity and re-use of scientific data. However, up to 80% of this data is stored as unstructured text such as Word documents and PDFs. At SciBite, we believe that the combination of ontologies, deep learning and FAIR data provide a powerful solution to this challenge, and our standards-based semantic tools enable FAIR data across the entire enterprise.

Advanced Search Queries

SciBite Search enables users to get accurate results without the need to understand the complexities of TERMite: our Named Entity Recognition (NER) engine. TERMite finds mentions of genes, diseases, drugs, companies, processes and chemicals within a document corpus. Co-occurrence matrices help users explore the resulting datasets and quickly identify relationships across thousands of related concepts.

SciBite Search offers powerful search capabilities with an intuitive user interface. Users can undertake basic keyword queries or employ our advanced query language to create more complex questions.


Product Highlights

SciBite Search offers a variety of domain-specific and generic connectors making it simple to load both open source and proprietary data. Built-in parsers also make it easy to render popular datasets and make formats searchable. Both document and sentence-level searches are supported, plus full document-level security including role-based access. SciBite Search has several API endpoints for integration with other key research systems.

SciBite Search allows organisations to incorporate their own branding via UI themes, colour schemes and logos. Personalisation settings provide tailored support for expert users and those who require less sophisticated functionality.

The Way Ahead

The SciBite Search development roadmap will focus on several key areas with the objective of becoming the best biomedical research solution for your department or small enterprise.

Our plans include providing seamless access to additional insights, answers and content sources together with more augmented search, question-answering capabilities and connectors for both structured and unstructured data sources. We will also have deeper integration with SciBite AI models and SciBite’s CENtree ontology management solution so that customers can leverage our full ecosystem of tools.

SciBite Search 2.2 contains:

- Includes upgraded versions of TERMite, and VOCabs
- New TSV export of search results
- More intuitive Help pages
- New sFTP connector
- Easier data ingestion and processing with option to extend (create a new copy of) an existing schema
- Simpler loading of individual SciBite Search assets (e.g., Help, vocabularies) for improved initialization/updates


- Expansion of asynchronous API endpoints for better handling of large export jobs
- Configurable API throttling to manage heavy API use
- More secure and flexible API client generation/management

Leverage our Experience of Semantics for Intelligent Scientific Search

At SciBite we have experience in developing and deploying semantic deep learning models that perform a wide variety of functions:-

Take the next step...

Contact us to discuss your requirements or read a more in-depth description of SciBite Search