This presentation will show how Neo4j was used to build a chemistry recommendation system. I’ll give a brief introduction to fragment-based drug discovery, and how one might find fragments that bind to a protein of interest.
Once you have identified a fragment hit, the next step is to explore the surrounding chemical space.
We have built the fragment network, a graph database that allows a user to efficiently search chemical space around a compound of interest.
The result set is chemically intuitive, naturally grouped by substitution pattern and meaningfully sorted according to the number of observations of each transformation in medicinal chemistry databases.
YOU MAY ALSO LIKE:
The Fragment Network: A Chemistry Recommendation Engine Built Using Neo4j
Richard Hall is a cheminformatician at Astex Pharmaceuticals, based in Cambridge, UK. He has been mixing computers and chemistry since the early 90s at UMIST and the University of Manchester and later at companies like Protherics and AstraZeneca.