Neo4j Case Studies Novartis Leverages IoT for Enhanced Drug Discovery

Edit This Case Study Record

	Novartis Leverages IoT for Enhanced Drug Discovery Neo4j

Novartis Leverages IoT for Enhanced Drug Discovery

Neo4j

Technology Category	Analytics & Modeling - Computer Vision Software Application Infrastructure & Middleware - Data Visualization
Applicable Industries	Healthcare & Hospitals Mining
Applicable Functions	Product Research & Development
Use Cases	Clinical Image Analysis Traffic Monitoring
Challenge	Novartis, a global healthcare company, was faced with the challenge of managing and making sense of a vast amount of data. The company had decades of data on how various compounds affect protein targets, with about a billion data points in total. This historical data was critical but sparse compared to the granular data currently being collected. Novartis uses an automated process that captures high-content image data showing how a particular compound has affected an entire cell culture, generating terabytes of phenotypic data. The challenge was to combine this historical data with the burgeoning phenotypic data and place it within the larger context of ongoing medical research from around the world. The team also wanted to combine its data with medical information from NIH’s PubMed, which contains about 25 million abstracts from some 5,600 scientific journals. Read More
About Customer	Novartis is a global healthcare company based in Basel, Switzerland that provides solutions to address the evolving needs of patients. It is one of the largest pharmaceutical companies by both market capitalization and sales. The Novartis Institutes for BioMedical Research comprise the innovation arm of Novartis, with 6,000 researchers at six locations around the globe. The company has amassed decades of data on how various compounds affect protein targets, and uses an automated process that captures high-content image data showing how a particular compound has affected an entire cell culture. Read More
Customer Name	Novartis Read More
Solution	Novartis decided to create a knowledge graph stored in Neo4j, and devised a processing pipeline for ingesting the latest medical research. Text mining is used at the beginning of the pipeline to extract relevant text data from PubMed. That data is then fed into Neo4j, along with Novartis’s own historical and image data. The data pipeline populates the 15 kinds of nodes that were devised to encode the data. The next phase fills in the relationship information that links the nodes together. The team identified more than 90 different relationships. Novartis uses Neo4j graph algorithms to traverse the graph and identify a desired triangular node pattern linking the three classes of data together. Graph analytics not only find relevant nodes in the desired triangular relationship, but also employ a metric the team designed to gauge the associated strength between each node in each triangle. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Computer Vision Software

Application Infrastructure & Middleware - Data Visualization

Applicable Industries

Healthcare & Hospitals

Mining

Applicable Functions

Product Research & Development

Use Cases

Clinical Image Analysis

Traffic Monitoring

Challenge

Novartis, a global healthcare company, was faced with the challenge of managing and making sense of a vast amount of data. The company had decades of data on how various compounds affect protein targets, with about a billion data points in total. This historical data was critical but sparse compared to the granular data currently being collected. Novartis uses an automated process that captures high-content image data showing how a particular compound has affected an entire cell culture, generating terabytes of phenotypic data. The challenge was to combine this historical data with the burgeoning phenotypic data and place it within the larger context of ongoing medical research from around the world. The team also wanted to combine its data with medical information from NIH’s PubMed, which contains about 25 million abstracts from some 5,600 scientific journals.

About Customer

Novartis is a global healthcare company based in Basel, Switzerland that provides solutions to address the evolving needs of patients. It is one of the largest pharmaceutical companies by both market capitalization and sales. The Novartis Institutes for BioMedical Research comprise the innovation arm of Novartis, with 6,000 researchers at six locations around the globe. The company has amassed decades of data on how various compounds affect protein targets, and uses an automated process that captures high-content image data showing how a particular compound has affected an entire cell culture.

Customer Name

Novartis

Solution

Novartis decided to create a knowledge graph stored in Neo4j, and devised a processing pipeline for ingesting the latest medical research. Text mining is used at the beginning of the pipeline to extract relevant text data from PubMed. That data is then fed into Neo4j, along with Novartis’s own historical and image data. The data pipeline populates the 15 kinds of nodes that were devised to encode the data. The next phase fills in the relationship information that links the nodes together. The team identified more than 90 different relationships. Novartis uses Neo4j graph algorithms to traverse the graph and identify a desired triangular node pattern linking the three classes of data together. Graph analytics not only find relevant nodes in the desired triangular relationship, but also employ a metric the team designed to gauge the associated strength between each node in each triangle.

Impact #1	The use of Neo4j has enabled Novartis to flexibly navigate all of their data sources, which has greatly benefited their research. The merging of data has created a giant graph that aids in understanding biology and how scientific knowledge can be used to develop the next generation of medicines. The Neo4j knowledge graph captures elements needed for an operational system of biological understanding that continues to grow with expanding medical science. Researchers can now see which compounds and genes are most closely associated with diseases, and drill down into the medical literature to examine the evidence for the association. The flexibility to navigate all of these data sources has proven to be extremely powerful.

Impact #1

The use of Neo4j has enabled Novartis to flexibly navigate all of their data sources, which has greatly benefited their research. The merging of data has created a giant graph that aids in understanding biology and how scientific knowledge can be used to develop the next generation of medicines. The Neo4j knowledge graph captures elements needed for an operational system of biological understanding that continues to grow with expanding medical science. Researchers can now see which compounds and genes are most closely associated with diseases, and drill down into the medical literature to examine the evidence for the association. The flexibility to navigate all of these data sources has proven to be extremely powerful.

Benefit #1	The knowledge graph currently has half a billion relationships.
Benefit #2	The team expects to easily triple the number of relationships in the knowledge graph as data is added.
Benefit #3	The data pipeline populates 15 kinds of nodes.

Benefit #1

The knowledge graph currently has half a billion relationships.

Benefit #2

The team expects to easily triple the number of relationships in the knowledge graph as data is added.

Benefit #3

The data pipeline populates 15 kinds of nodes.

Download PDF Version

Overview

Novartis Leverages IoT for Enhanced Drug Discovery

Operational Impact

Quantitative Benefit