.menu { height: 105px; } .menu .logo img { height: 73px; } .menu.sticky,.menu.sticky.hide { opacity:1; -webkit-transform: translateZ(0); -moz-transform: translateZ(0); -o-transform: translateZ(0); transform: translateZ(0); }

Knowledge Discovery Powers Agile R&D

Defining R&D Direction

Case Study: Top 20 Pharma with a Focus on Rare Disease

  • The Goal

    An easy, comprehensive and data driven method to prioritize therapeutic area focus by mining the competitive landscape for rare disease groups.

  • The Challenges

    An in-house person assigned disease classes.

    Arbitrary, subjective and inconsistent - No one person can have in-depth knowledge about every disease

    The analyst evaluated the competitive landscape by manually collecting Clinical Trials data for each disease in the class.

    Laborious, time consuming and error prone

  • The Solution

    A web based tool allowed the analyst to build a view of the competitive landscape and identify white spaces to pursue.

    Approach

    - Resolved diseases across data sets and varied taxonomies.
    - Created a connected knowledge graph with disease data such as targets, pathways, tissue expression and trials across sources.
    - Used machine learning to stratify diseases by molecular mechanisms.
    - Identified biologically relevant entities using Natural language processing to map data from structured and unstructured sources.

  • The Benefit

    The analyst can now arrive at the Top 3 therapeutic focus areas in a few hours instead of weeks, freeing up time to focus on the merits of pursuing each area.

    A rational data driven approach to prioritize therapeutic areas.