Immuno-oncology: building knowledge for translational science

April 28 2016

There's been a lot of excitement around recent studies on immuno-oncology in which the body’s immune defences are corralled to fight cancer. Experts consider it the most exciting advance since the development of chemotherapy half a century ago.

Many of our customers are involved in anti-cancer approaches based on modulation of immunosuppressive properties of immune cells; and are using I2E to help generate insight around immuno-oncology and the tumor microenvironment (TME). Cancers can be viewed as complex ‘rogue’ organs, with malignant cells surrounded by blood vessels and a variety of other cells, including immune cells, fibroblasts, lymphocytes, and more. The tumor cells and the surrounding non-transformed cells interact constantly, and developing a better understanding of these TME interactions is a valuable approach in immuno-oncology drug development.

Knowledge in this field is growing very rapidly which makes it very difficult for scientists to capture it manually, both because of the volume of publications, but also the variety and complexity of information.

Challenges include ensuring a thorough search to capture relationships between genes/proteins and their effect or correlation on or with a variety of cellular actors. These cellular actors included many of the immune system cells currently under investigation for immunotherapeutic approaches to oncology.

I2E provides the capability to find and extract these interactions from textual data, including capture of negation where needed. I2E allows efficient and effective searches over millions of text documents, and can harmonize the output to enable computational post-processing and visualization of these complex data.

One of our pharma customers needed to quickly build a literature knowledgebase around the tumor microenvironment. Using I2E, the scientists were able to run a single query across the entire set of MEDLINE, equivalent to 20 billion unique keyword searches, and extract over 60,000 relevant structured facts. They were able to rapidly add new knowledge to an internal translational science database for direct use in projects; a task that they felt would have taken weeks or not be possible at all without I2E.

Comprehensive coverage of the literature enabled their scientists to better understand the microenvironment of tumours, the genes or proteins involved, the cellular actors, and the changes triggered.

This speed to insight drives cost reduction. This is just one example of applying text analytics for literature searches – imagine if all your literature search projects could be reduced from weeks to days.  Good search and extraction of facts from the scientific literature is crucial to underpin any research project or any intelligence gathering - text analytics provides the solution to this challenge.

 

The primary tumor microenvironment consists of tumor cells surrounded by normal epithelial cells, mesenchymal stem cells (MSC), endothelial progenitor cells (EPCs) and various bone marrow derived cells (BMDC). Presence of heterogeneous cells and their secreted soluble factors, signaling molecules, extracellular matrix and mechanical cues with in the tumor microenvironment promote neoplastic transformations, support tumor growth and invasion. Taken from Upreti et al. 2013.