Skip to main content


Linguamatics I2E has a track record of delivering text mining capabilities across a broad range of applications. Its agile design allows users to develop queries with the precision required for even the most demanding tasks.

  1. Overview
  2. Key benefits of I2E
  3. Key Features of I2E
  4. Ways to access I2E

I2E: Full-power, flexible Natural Language Processing

The Linguamatics I2E application has a proven track record in delivering best of breed text mining capabilities across a broad range of application areas. Its agile nature allows tuning of query strategies to deliver the precision and recall needed for specific tasks, but at an enterprise scale.


I2E is an agile and interactive text mining application for the extraction and analysis of information. Because of its underlying Natural Language Processing (NLP) technology, I2E is particularly strong in its ability to answer a wide range of questions, from apparently simple open queries to questions that need advanced linguistic analytics. For example:

  • What treatments are being used for breast cancer?
  • What positive comments have been made by a group of opinion leaders about my product?
  • Which of my patients are smokers or former smokers
  • Do I have freedom to operate for my chemical lead series?

Results are structured, like information in a database. So you can visualize them in many different ways, such as html tables, interaction networks, mind maps, charts, and so on.

Actionable information extracted using I2E can be presented in a variety of ways depending on your needs.

Key benefits of I2E

Speed R&D and clinical processes:

I2E can speed many research and development and clinical processes. Tasks that used to take months, or were previously not feasible with manual methods, can be done in hours or minutes.

According to customers, I2E gets to actionable results at least 10 times faster than a traditional keyword search.

Boost Innovation:

I2E enables pharmaceuticals to boost innovation by providing vital, previously hidden insights needed to speed up drug discovery and identify new candidate targets - while cutting significant costs and wasted time in later drug discovery phases by failing early.

Improve patient outcomes:

I2E is able to provide high-accuracy results across large datasets of unstructured data for population stratification - to more rapidly and better identify at-risk patients and close care gaps.

Customers and return on investment:

I2E is used widely by knowledge-driven organizations, with a large number of customers across pharmaceutical, biotech, payers/health insurers, hospitals, academic medical centers and cancer research organizations.

Find out more about who uses I2E and the return on investment.

Key features of I2E

  • Intuitive, interactive querying based on natural language processing (NLP): quickly interpreting the meaning of unstructured text sources and returning high value, relevant results
  • Search engine approach: to build and refine queries on-the-fly and return the results in real time
  • Intuitive reporting: presenting extracted information in a structured form, that is easy to analyze, with drill-down to supporting evidence
  • Domain knowledge plug-in: enhancing semantic search capabilities using taxonomies, thesauri and ontologies
  • Powerful chemistry-enabled text mining allows you to identify facts for structurally-similar chemical compounds
  • Web Services
    • I2E incorporates a comprehensive RESTful Web Services API that gives access to the majority of the functions in I2E
    • Users can create new, customized interfaces to I2E that are tailored to different types of use and specific projects
    • The API is available to use from any programming language with a Client Software Development Kit (SDK) provided for popular languages (Python, JavaScript, Java)
  • I2E uses the Extraction And Search Language (EASL) based on YAML to automate creation, development and maintenance of I2E queries.
    • An EASL Software Development Kit (SDK) is provided for both Python and JavaScript

Ways to Access I2E

There are multiple ways to access the power of I2E, NLP text mining platform.

I2E Enterprise – I2E is installed on-premise or on a private cloud instance. The customer manages the software, documents, terminologies and other data. The installation includes many Resources queries and processing templates to simplify the creation of I2E indexes from customer documents. All data remains within the customer’s machine.

We provide regular updates to I2E and upgrades are simple to perform on Linux and Windows. I2E Enterprise provides options for both interactive and batch querying mode and is the foundation for other Linguamatics products such as I2E AMP and Web Portals.

I2E OnDemand - our entry-level cloud-based solution. Here the software and data are hosted by Linguamatics and we can provide interface query access to all of the Linguamatics Content Store and its standard Ontology set. Every customer organization accesses their own Linguamatics gateway server via HTTPS on a different AWS instance.

I2E OnDemand plus – our fully-featured cloud-based solution for access to I2E. Here we provide everything that is in I2E OnDemand with additional options to use automated queries via Web Services and processing of your own documents, ontologies and data. Each I2E OnDemand plus is matched to the appropriate AWS instance type to ensure that that customers get the most benefit from their particular tier of service.

Linguamatics also provides AWS HIPAA-compliant I2E installations on I2E OnDemand for customers with specialized requirements. This is critical for some of our customers, particularly in healthcare organizations, where patient data must be stored and handled in a compliant manner.

Hybrid Combination – if you have licensed both I2E Enterprise and I2E OnDemand, you can link these two systems together using Linguamatics Connected Data Technology: our unique federated text mining architecture. This technology gives you the ability to keep your internal documents on-premise and to have Linguamatics manage its Content Store on I2E OnDemand and yet be able to run queries across both data stores and return results in a single results set.

If you’re looking to provide an NLP interface to your end user scientists – find out more about NLP Insights Hub.

Ready to get started?

Request a Demo

Questions? Ask our experts