How Novo Nordisk Is Using NLP To Advance Intelligence-Gathering For External Partnerships

Establishing partnerships with external collaborators is a key part of pharmaceutical companies’ growth strategies – but identifying the right candidates for these partnerships before competitors remains a challenge.

The evolution toward drug-development partnership models has been forming over decades but has accelerated in recent years as the health care industry has become more cost-conscious. Scientific and technical barriers have become increasingly complex, and pharmaceutical companies are seeking other ways to gain new efficiencies.

In general, pharmaceutical companies have realized that their strengths lie in areas outside of traditional early-stage discovery, such as designing and conducting clinical studies, manufacturing, managing regulatory compliance and marketing. As a result, pharma companies are increasingly looking to capture innovative early-stage ideas from partners such as small biotech startups and university technology transfer offices. 

Novo Nordisk faced similar challenges in its goal to increase the number of external partnerships in its pipeline of diabetes and obesity drug candidates. To beat its competitors in identifying the most promising external collaboration opportunities, Novo Nordisk knew it would need to find a way to mine and consolidate huge volumes of external information to generate a bird’s-eye-view of partnership opportunities as early as possible.

Using NLP To Develop An Evidence Hub

For pharma companies, one of the greatest difficulties in identifying external partners is sifting through the ongoing and never-ending avalanche of information that may contain hints and insights for collaboration opportunities.

Specifically, pharma companies seek information about novel drugs, targets and pathways, biotech companies of interest, university technology offerings and clinical trials in relevant therapeutic areas. Obtaining this information requires scouring a wide array of structured and unstructured source material that may include news reports, patent filings, scientific papers and conference abstracts – all of which must be combined to build a landscape of knowledge, also known as an “evidence hub.”

To create its early scientific intelligence evidence hub, Novo Nordisk turned to natural language processing (NLP) technology. NLP can deliver substantial value to the process of identifying collaboration partners by automating text mining, enabling companies to uncover valuable information hidden among an abundance of unstructured data.

Text mining is the process of examining large collections of documents to discover new information or help answer specific research questions. NLP-based text mining empowers computers to, in essence, read text by simulating the human ability to understand a natural language, enabling the analysis of unlimited amounts of text-based data without fatigue in a consistent, unbiased manner.

The Novo Nordisk team has developed a semi-automated workflow incorporating Linguamatics NLP to extract key information from a broad range of data sources (both internal and external). These include scientific abstracts, patents, grants, news, tech transfer offices from universities around the world, and more. NLP queries run across sources, for the key therapeutic areas of interest to the Novo Nordisk R&D community. The resulting output are curated into summaries, written by information scientists with experience in the respective therapy areas. These are provided via InfoDesk as easy-to-consume alerts to the broader Novo Nordisk researchers. The combination of Linguamatics NLP and InfoDesk newsletters means that the pipeline delivers data that the end users can interact with, drill down into, investigate and assess, so the data have a long afterlife.

The Novo Nordisk group viewed the creation of the early scientific intelligence evidence hub as a means of enabling all members of relevant research teams to act as “scouts,” empowering researchers to discover, share and discuss newly gained insights with colleagues. Use of this technology enables the team to scale-up surveillance, and combined with curation from domain experts, the system delivers the intelligence required.

An Early View Of Collaboration Opportunities

Novo Nordisk used its evidence hub to create two tools to help researchers become scouts: a newsletter that is easy to digest on mobile devices and a dashboard with up-to-date landscapes for each therapeutic area of interest.

As an example: a news article is published on a biotech startup that is pursuing an obesity drug candidate. Based on predetermined criteria, Novo Nordisk's evidence hub flags the article and publishes it to the appropriate dashboard.

Next, the system searches the source material for all relevant background on the company and reveals that the company recently raised venture funding, has published patents with a novel method of action for the drug candidate and is scheduled to present new data at an upcoming conference. A Novo Nordisk researcher recognizes that one of her former colleagues is currently working for the startup, and provides an introduction to a Novo Nordisk colleague that leads to a meeting at the conference with an executive from the biotech startup.

This example illustrates how the evidence hub enables Novo Nordisk to pull data from a wide variety of sources, extract key data elements from those sources, increase researcher productivity by automating the process and empower employees to connect the dots behind a collaboration opportunity. In the future, Novo Nordisk plans to augment the system by adding data sources such as social media that will help capture consumer sentiment. This will provide another facet to the landscape of information being surfaced, and when combined with the intelligence from news, patents, scientific and clinical reports, gives a 360-degree view of what the world is talking about, relating to the disease areas of interest.

Given the financial and operating pressure facing pharmaceutical companies, external collaborations will grow in importance as an essential drug development strategy. And Novo Nordisk intends to get ahead of the field by finding the novel ideas that will bring innovation to their drug pipeline. By leveraging NLP technology, pharma companies can give more employees the ability to gather the intelligence necessary to find and evaluate the best external collaboration opportunities.