Search papers, labs, and topics across Lattice.
NISPO is an open-source Python package designed for generating systematic IUPAC names, developed through an agentic self-improvement loop utilizing OpenAI's Codex with the GPT-5.5 model. The tool was rigorously tested against 2.68 million molecules from SureChEMBL and achieved an impressive 98.1% round-trip accuracy when validated with a held-out set of 103 million PubChem molecules. This high accuracy ensures reliable communication of molecular structures, which is crucial for chemical literature and databases.
Achieving 98.1% accuracy in IUPAC name generation could revolutionize how chemists and researchers communicate molecular structures.
Systematic International Union of Pure and Applied Chemistry (IUPAC) names are standard for communicating molecular structures in chemical literature, patents, and databases. We introduce NISPO, an open-source RDKit-based Python package for IUPAC name generation. NISPO was developed by an agentic self-improvement loop using OpenAI's Codex with the GPT-5.5 model. A generated name was considered correct if the open-source OPSIN tool parsed it back to the input structure. Guided by this objective, the agent implemented and refined NISPO against 2.68 million molecules from SureChEMBL, resulting in the tool achieving 98.1% round-trip accuracy on a held-out set of 103 million PubChem molecules. NISPO is freely available at https://github.com/oxpig/nispo.
