How Knowledge-Based Analytics Can Drive Drug Discovery

Knowledge and data analytics will fuel the next frontier in healthcare.

Louisa Roberts | IBM Watson Health

Data-driven analytics is far from a new concept in healthcare. From improving population health and disease management to advancing precision medicine initiatives, data-driven analytics have laid the foundation for more targeted care for decades.

Pullquote share icon. Share

Data-driven analytics have laid the foundation for more targeted care for decades.

But in today’s information-overloaded environment, where the data is only as powerful as the insights generated from it, the key actually lies in the application of the cognitive as well.

Specifically, cognitive allows life science organizations to systematically analyze knowledge sources – clinical study reports, licensed publications and patents – because it has been trained in the scientific domain and can understand the language of researchers.

To understand why cognitive insights and knowledge-based analytics are critical to the future of life sciences, it’s important to understand the state of the current drug development process.

Today’s world

Carrying an astronomical price tag of $2.6 billion and a 10 to 12 year timeline, discovery of a new drug today is anything but speedy or efficient.

From the thousands of medical journals and papers published each year to the myriad of large and complex data sets available, researchers face a potentially costly, uphill battle when it comes to trying to synthesize the incredible amount of data that exists to develop the most effective therapies possible.

However, when cognitive capabilities and knowledge-based analytics are integrated into the process, the opportunity for more targeted drug development becomes more realistic.

[Also on Longitudes: Why 3D Printing is the Next Model T]

New discoveries

For example, using the 25 million Medline abstracts, more than 1 million full-text medical journal articles and 4 million patents it has ingested, Watson for Drug Discovery (WDD) uses machine learning, natural language processing and other cognitive reasoning technologies to uncover hidden patterns and novel connections amidst a truly massive amount of data – patterns that may otherwise have gone overlooked or undiscovered.

These findings can then help our life sciences customers determine how and which drug therapy targets should be prioritized and developed first.

Identifying a new target can take anywhere from six to 18 months of research, but WDD can help researchers complete the task in a matter of weeks or months.

By layering knowledge-based analytics on top of today’s standard data-driven practices, life science researchers and drug developers can:

  • Effectively accelerate the drug discovery process – improving efficiency and getting more targeted therapies to market and in the hands of the patients who need them.
  • Make better, faster decisions – identifying and prioritizing potential targets that researchers can evaluate and pursue based on comprehensive, evidence-based reasoning.
  • Deepen understanding of patient cohorts and their potential impact on a drug’s impact – for example, better identification of biomarkers and how comorbidities stand to impact a therapy’s efficacy.

[Also on Longitudes: The Daily Grind of Diabetes Control]

Pullquote share icon. Share

With cognitive capabilities and data analytics, researchers can identify connections that would otherwise be hidden.

Starting a journey

Though we’re early on in the journey, WDD is already helping life science organizations see the power and potential of the blended-knowledge and data-analytics approach.

From helping a leading neurological institute develop novel ALS treatments to predicting optimal target therapies for cardiovascular disease to our recently announced collaboration with Pfizer, we’re already seeing the impact this blended approach can have for both researchers and the patient populations depending on them.

We look forward to working with Pfizer and continuing our mission to advance and improve drug discovery in the months and years to come.

When cognitive capabilities are layered on top of data-driven practices, researchers have access to a massive and diverse landscape of information and can identify connections that would otherwise be hidden.

And when armed with this information, life science organizations can effectively move down the drug discovery value chain and bring the drug development process to scale, layering the complementary approaches possibly in real-time and using real-world clinical data to fuel the next frontier of drug discovery. goldbrown2

This article first appeared on IBM THINK and was republished with permission.

button

Every morning, wake up to the blog that gives you the latest trends shaping tomorrow.

Louisa Roberts is a Solution Executive at IBM Watson Health – Life Sciences.

Click the RSS icon to subscribe to future articles by this author. RSS Feed