By Jane Z. Reed, Director of Life Sciences at Linguamatics, an IQVIA company

As large pharmaceutical companies increasingly look to outsource aspects of drug discovery and development to external collaborators, the ability to identify the right partnership candidates before competitors has become critical.

While the concept of larger pharmaceutical companies establishing drug-development partnerships is nothing new, external partnerships have generally become more important as large companies have grown more cost-conscious and the science behind drug development has gotten more complex. 

One reason why bigger, more established players in the pharmaceutical industry have looked for drug-development partners is that these companies have chosen to focus more on their own strengths, such as designing and conducting clinical studies, manufacturing, managing regulatory compliance and marketing. In these types of operating models, most early stage discovery and innovation is left to external partners such as biotech startups and university technology transfer offices. 

In line with these trends, Novo Nordisk sought to deepen its pipeline of diabetes and obesity drug candidates via collaborations with external partners, but, just as importantly, Novo Nordisk needed to identify potential partnerships before competitors did so. To accomplish this objective, Novo Nordisk had to discover a means of consolidating huge volumes of external information to generate a bird’s-eye-view of partnership opportunities as early as possible.

Using NLP to accelerate intelligence-gathering

Perhaps the greatest challenge for large pharmaceutical companies in identifying collaboration opportunities is scrutinizing the voluminous amount of information that may (or in many cases, may not) contain insightful tidbits about potential drug-development partners.

For example, established pharma players are generally looking for information regarding novel drugs, targets and pathways, biotech companies of interest, university technology offerings and clinical trials in relevant therapeutic areas. To find these important chunks of data, they must comb through numerous structured and unstructured sources of information, such as news reports, patent filings, scientific papers and conference abstracts – a significant and time-consuming challenge for humans. 

The goal of all this information-gathering is to create an “evidence hub,” a curated, data-driven landscape of knowledge. To develop a comprehensive and thorough evidence hub, Novo Nordisk decided to employ natural language processing (NLP) technology. Novo Nordisk executives realized that NLP could greatly improve the efficiency of the process of identifying collaboration opportunities by automating text mining to uncover valuable information hidden in troves of unstructured data. 

Jane Reed

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.

Novo Nordisk have developed an Early Scientific Intelligence evidence hub, utilizing NLP in a semi-automated workflow. The workflow uses a suite of NLP queries over data streams coming in from news, patents, scientific literature, conference abstracts and more. The resulting outputs 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.

One of Novo Nordisk’s most important goals associated with the Early Scientific Intelligence evidence hub was to empower members of research team to serve as “scouts” for new partnership opportunities while enabling them to discover, share and discuss newly gained insights with colleagues. 

The practical value of an evidence hub

Leveraging this integrated approach, Novo Nordisk developed two tools that assisted researchers in becoming scouts: first, a curated newsletter written by information scientists that delivers easily digestible news updates to mobile devices, and second, a dashboard with up-to-date landscapes for each therapeutic area of interest. 

Following is an example of how Novo Nordisk uses these tools to deliver value.

A news article is published that profiles a biotech startup investigating an obesity drug candidate. Using pre-established search criteria, Novo Nordisk’s NLP evidence hub flags the article and publishes it to the “obesity drug candidate” newsletter and dashboard, prompting a “scout” to write a summary. The system also surfaces relevant background on the startup, revealing that it recently raised venture-capital funding, is seeking a patent with a novel method of action for the obesity drug candidate, and is scheduled to present new data at an upcoming conference. In combination with these, a Novo Nordisk researcher recognizes that a former colleague is employed by the startup and uses LinkedIn to facilitate a meeting between the former colleague and a Novo Nordisk team member who is attending the conference.

In this example, the Early Scientific Intelligence evidence hub has enabled Novo Nordisk to analyze data from a wide array of sources, extract key data elements from those sources, increase researcher productivity by automating the process and empower employees to connect the dots to find a collaboration opportunity. For the next stage of the NLP evidence hub’s development, Novo Nordisk is planning to capture consumer sentiment by adding new data sources, including publicly available social media posts. 

The financial pressure on large publicly traded pharmaceutical companies to increase earnings is unlikely to dissipate any time soon (or ever), meaning that these companies will continue looking for any means of wringing inefficiency out of their operations. In many cases, that will prompt them to seek ways to offload the financial risk of early drug discovery and development to external collaborators. As pharmaceutical companies are searching for those partnership opportunities, NLP is the technology many will rely on to separate the signal from the noise.