IBM Watson for Drug Discovery


IBM Watson for Drug Discovery is a cloud-based, cognitive platform for life sciences researchers.

The platform generates insights at a scale and speed beyond human capability, improves decision making and can help researchers uncover new connections rapidly, which may lead to new insights and scientific breakthroughs. With the cost of developing a single drug now exceeding $2.5 billion, cognitive systems can help to reduce this expenses.

IBM Watson for Drug Discovery has the ability to synthesize massive public and private datasets. Its capacity to processing natural language enables the platform to read millions of pages of unstructured data including scientific articles, patents, clinical trial data, electronic lab notes, toxicology reports and other proprietary data and understand contextual meaning.


Watson’s cognitive capabilities can eliminate bias, and detect connections and patterns that researchers may not necessarily see to generate novel hypotheses to predict potential relationships for further evaluation.

Watson for Drug Discovery has dynamic visualization to help the researches identify gene, protein, drug, and disease interactions in order to see hidden connections and identify valid relationships. The Dynamic Visualization allows researchers to explore relationships on various levels and views.

In collaboration with IBM Watson Health, scientists at the Barrow Neurological Institute identified five proteins altered in amyotrophic lateral sclerosis (ALS) that have never before been linked to the disease.  Watson for Drug Discovery is also helping Pfizer make new discoveries in immune-oncology.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s