Building, Analyzing and Querying Biomedical Knowledge Graphs using Graphster: A New Spark-Based Open-Source Library

Knowledge Graphs provide healthcare and life-sciences companies with a connected and meaningful view into their data. However currently, this involves a complex, multi-step process of data collection, mapping, inference, NLP and loading into a Graph Database before a knowledge graph can truly be made operational.

In this talk, We will be introducing a unique open source library: graphster that makes the process of building, analyzing and querying knowledge graphs simple and seamless all using Apache Spark.

We’ll show you how to ingest clinical trials data, infer relationships from text, reveal the semantic content by fusing it with the MeSH ontology and then analyze it at scale using SPARQL queries all using the power of Spark NLP and Graphster.

The talk will be focused on annotating medical notes for patients experiencing a particular symptom. The rule-based algorithm extracts knowledge in the form of rules from the classification model, which are easy to comprehend and very expressive

This algorithm annotates each note as having or not having a particular symptom, thus making it easier for annotators with non-medical background to annotate medical records.

This approach is not only helpful for annotators with non-medical background but also a no cost method to annotate notes.

About the speaker

Vishnu Vettrivel

Founder at Wisecube

Vishnu Vettrivel is the Founder and CTO of Wisecube, a startup focused on accelerating biomedical research using AI. He has decades of experience building Data platforms and teams in healthcare, financial services and digital marketing.


Alex Thomas

Principal Data Scientist Wisecube

Alex Thomas is a principal data scientist at Wisecube. He is the author of the newly published O’reilly book ‘Natural Language Processing with Spark NLP’ and has used natural language processing and machine learning with clinical data, identity data, employer and jobseeker data, and now biochemical data. He is now incorporating data from NLP along with structured data to make a massive-scale biomedical knowledge graph.



Sessions: October 4 – 6
Trainings: October 11 – 14


Presented by