NovoMCP Open Corpus (lite)

Description

122,454,458 PubChem compounds with RDKit physicochemical descriptors, ~30 ADMET/toxicity predictions (NovoMCP models, trained on the public Therapeutics Data Commons benchmark), and PAINS structural-alert flags. One row per PubChem CID, stored as Apache Parquet (Snappy) for direct in-place querying (Athena, DuckDB, PyArrow, pandas). An analysis-ready cheminformatics substrate for drug discovery: virtual screening, drug-likeness (QED) filtering, similarity search, chemical-space exploration, and training ADMET models at scale — so you don't recompute descriptors and property predictions across all of PubChem yourself. Computed properties and model predictions for research use — not experimental measurements or regulatory determinations.

Update Frequency

Static release; refreshed periodically as models improve (versioned).

License

CC-BY-4.0 (https://creativecommons.org/licenses/by/4.0/)

Documentation

https://github.com/NovoMCP/open-data-examples/tree/main/novomcp-open-corpus-lite

Managed By

NovoMCP

See all datasets managed by NovoMCP.

Contact

https://github.com/NovoMCP/novomcp/issues

How to Cite

NovoMCP Open Corpus (lite) was accessed on DATE from https://registry.opendata.aws/novomcp-open-corpus-lite.

Usage Examples

Tutorials

• Get To Know A Dataset: NovoMCP Open Corpus (lite) by Ari Harrison, NovoMCP
  

Tools & Applications

• Kaggle mirror by Ari Harrison, NovoMCP
  
• NovoMCP engine (open computational-chemistry engine that produced this corpus) by Ari Harrison, NovoMCP
  

Publications

• NovoMCP Open Corpus (lite): 122M compounds (Zenodo record, DOI) by Ari Harrison, NovoMCP