Accelerating New Drug Discovery
Feb 6, 2020Shiyu Chen
Summary
This post details the application of Milvus for chemical fingerprint similarity search using RDKit. It explains how chemical fingerprints are generated using RDKit's Morgan fingerprints and then imported into Milvus for substructure, similarity, and exact search. The post also clarifies the relationship between Tanimoto distance and Jaccard distance in the context of chemical fingerprint computation within Milvus, and presents a demo of searching over 90 million chemical fingerprints.
More from the AI Data Storage Engine trail
- Milvus Snapshots: Point-in-Time Collection Views Without Copying Data
- Announcing Milvus 3.0: Lake-Native Vector Search and a More Powerful Retrieval Engine
- How to Recover Milvus Data After etcd Corruption Without a Backup
- Open Tag: An Open-Source Claude Tag for Claude Code and Codex
- How Force Merge Compaction Nearly Doubled Milvus Search QPS