PNMRNP: Predicted Carbon-13 NMR Data for 211,280 Natural Products

PNMRNP contains structure, properties, and classification data for 211,280 natural products. The dataset was created by Jean‐Marc Nuzillard at the Centre National de la Recherche Scientifique, starting from the ISDB and UNPD databases. It includes predicted carbon-13 NMR chemical shifts and a hierarchical chemical classification.

Use Cases

• Predicting NMR chemical shifts for novel compounds based on structural data.
• Classifying natural products into hierarchical chemical categories based on substructure presence.
• Linking chemical structures with identifiers and synonyms from PubChem.
• Benchmarking computational methods for NMR prediction against a large, structured dataset.

Strengths

• Contains data for 211,280 natural product compounds.
• Integrates multiple data sources: ISDB, UNPD, PubChem, and nmrshiftdb2.
• Provides a three-level hierarchical classification for compounds.
• Includes predicted NMR chemical shifts from ACD/Labs C+H NMR Predictors.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

ISDB and UNPD databases, processed with RDKit and linked to PubChem.

Collection Method

Structures were generated from InChI strings using RDKit; NMR shifts were predicted using nmrshiftdb2 and ACD/Labs tools.