PubMind-DB

PubMind-DB is a literature-derived knowledgebase of variant–disease–pathogenicity associations, curated and summarized by PubMind.

Variant Identifier Search
Enter one identifier per line. The p. and c. notation is required for protein and cDNA variants. For protein change, 1 letter and 3 letter are both supported. E.g., BRCA1:p.R133C and BRCA1:p.Arg133Cys are the same.
Even though user could search cDNA change using either BRCA1:c.A122T or BRCA1: c.122A>T (they are considered the same), PubMind uses the representation of A122T instead of 122A>T to represent DNA change.
Term Search (more options for each vairant type)
SNV Input Settings
Enter one term per line. Choose AND to require all lines to match, OR to match any line.
Genomic Search
The PVID search provides individual records (per paragraph/abstract) for a PVID instead of the consolidated information.
Latest Update
🧬 August 24, 2026 – PubMind-DB v1.0.0 Release and Publication

To support reproducibility, transparency, and version tracking, the first public release of PubMind-DB is designated PubMind-DB v1.0.0. This database release was generated using PubMind v0.1.0, the first public release of the PubMind framework.

Reference: Wang, P. & Wang, K. (2026). PubMind: literature-based genetic variant extraction and functional annotation using large language models. Nature Communications. Published online August 20, 2026. https://doi.org/10.1038/s41467-026-76834-4

Updated: Aug 24, 2026