NPClassifier PubChem Classifications (2026-04-11)
Open dataset of NPClassifier classifications for PubChem compounds.This snapshot contains 5480150 successful NPClassifier responses. Rows that ended invalid (734) or failed after bounded inline retry (26) are excluded from the release artifact.
Open dataset of NPClassifier classifications for PubChem compounds.
This snapshot contains 5480150 successful NPClassifier responses. Rows that ended invalid (734) or failed after bounded inline retry (26) are excluded from the release artifact.
The release contains a merged completed.jsonl.zst dataset and a machine-readable manifest.json describing the chunk set used to build it.
Each completed row contains the PubChem CID, SMILES, the NPClassifier pathway, superclass, and class labels as JSON arrays, plus the glycoside flag.
Format: JSON Lines compressed with Zstandard.
Excluded rows in this snapshot: 760.
Source code: npc-labeler.
📤 Share this page
Found this useful? Share it with your network.
Files are hosted on the source repository. Click download to access the full dataset.