ENC 2026 – Experimental Nuclear Magnetic Resonance Conference

Accelerating Computer-Assisted Structure Elucidation (CASE) with Fragment Recognition and AI Tools

Dimitris Argyropoulos, Sergey Golotvin, Maxim Kisko, Rostislav Pol and Mikhail Elyashberg

ACD/Labs, Toronto, ON, Canada

Over the last several decades, computer assisted structure elucidation (CASE) has become a proven method¹ for the unambiguous determination of new chemical structures from NMR data paired with a molecular formula. CASE offers many benefits over manual elucidation, including efficiency and the elimination of human bias. However, despite significant advances in computing power over its lifetime, it still takes time for CASE to generate and assess all the possible structures. In many cases, this is only a few seconds to minutes. Nonetheless, when NMR information is ambiguous or limited, elucidations can take hours or even days to complete.

In this poster, we will explore the various options available to identify possible fragments of the structure being elucidated and using these to generate modified Molecular Connectivity Diagrams (MCDs) that would allow for much faster structure generation and elucidation. We will talk about the identification of carbonyl groups as well as mono- and para-substituted aromatic rings and how this can have quite a dramatic effect on the structure generation time.

We will then explore the options of searching for fragments in either fragment libraries or databases of complete structures, like PubChem. These offer the benefit of identifying more complex fragments that could represent 50% or more of the structure, leading to a very significant reduction in the elucidation time.

Finally, we will talk about some AI tools that are being developed and offer the benefit of very rapid fragment or complete structure identification with minimal spectral input.

For each of the above cases, we will demonstrate the effect of these methods on elucidation time using representative examples as well as comparison tables.

1. M.E. Elyashberg, A.J. Williams. “Computer-based Structure Elucidation from Spectral Data. The Art of Solving Problems”, Springer, Heidelberg, 2015, 454 p.