AILSA reference database: 13C NMR shifts and HOSE statistics for natural-product dereplication and shift prediction (COCONUT + NMRShiftDB)

<p dir="ltr">Pre-built SQLite reference database for AILSA (AI + LSD + Agents), an AI-agent system for computer-assisted structure elucidation (CASE) of organic natural products from NMR spectra.</p><p dir="ltr">AILSA is built on the LSD structure generator by Jean-Marc Nuzillard (Université de Reims Champagne-Ardenne).</p><p dir="ltr">Contents: 928,443 compounds (COCONUT: 895,099 natural products with predicted 13C shifts;</p><p dir="ltr">NMRShiftDB: 33,344 compounds with experimental 13C shifts), 111,493 unique molecular formulas, 7.9 million HOSE-code statistics.

One file serves both dereplication and 13C prediction.</p><p dir="ltr">Data source: the 13C shifts of the 895,099 COCONUT natural products are predicted, not measured, the 33,344 NMRShiftDB compounds carry experimental 13C shifts.</p><p dir="ltr">COCONUT 13C shifts: from J.-M. Nuzillard, Zenodo, doi:10.5281/zenodo.6561449, CC BY 4.0</p><p dir="ltr">(doi.org/10.5281/zenodo.6561449).</p><p><br></p><p dir="ltr">Usage: install AILSA (github.com/steinbeck/ailsa), run "ailsa database download" - it fetches this file and installs it as data/reference/ailsa-derep.db - and check it with "ailsa database info".