Year: 2026
Type: preprint
Abstract: Chemical structures can be named systematically, and the 2013 IUPAC recommendations define one preferred name for each. For most of history, only a specially trained chemist or dedicated closed software tools could generate a correct, systematic molecule name from a chemical structure. Published neural structure-to-name translators can produce a fluent name for the wrong molecule. Here we present Orthonym: a generator of verified IUPAC names for chemical structures. This open, deterministic, rule-based generator emits a name only after verifying that it correctly describes the input structure. OPSIN reads back each candidate name, and the InChIKey of the parsed structure must equal that of the input; otherwise, the engine declines to name. On 2.2 million selected molecules from ChEBI, QM9, PubChem and ZINC22, it named 97.37% correctly and emitted no name for the wrong molecule. Orthonym is available under the MIT licence as a Python package and a web application.
Source: ChemRxiv
Institutions: Beilstein-Institut, Friedrich Schiller University Jena
Language: English
Subfield: Drug Discovery
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7216000663