biology chemical biology life sciences pharmaceutical
Collection of 7 billion small molecules in SMILES notation with 28 billion fingerprints, including MACCS, ECFP4, FCFP4, and PubChem, with pre-constructed USearch indexes over them.
Not updated
https://github.com/ashvardanian/usearch-molecules
See all datasets managed by Ash Vardanian.
USearch Molecules was accessed on DATE from https://registry.opendata.aws/usearch-molecules.
arn:aws:s3:::usearch-moleculesus-west-2aws s3 ls --no-sign-request s3://usearch-molecules/