Elucidating structures from spectra using multimodal embeddings and discrete optimization

25 November 2024, Version 2
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Structure elucidation --- determining molecular structures from spectroscopic data -- remains one of chemistry's most fundamental and challenging tasks, essential for advancing fields from drug discovery to materials science. While machine learning approaches have attempted to automate this process, they typically focus on single spectroscopic techniques and lack crucial confidence metrics, limiting their practical utility. Here, we present spec2struct, a framework that synergistically combines multimodal embeddings, contrastive learning, and evolutionary algorithms to mimic how expert chemists approach structure determination. By aligning encoders for diverse spectroscopic techniques with molecular representations, our system can simultaneously interpret multiple types of spectroscopic evidence. This alignment guides genetic algorithms to evolve chemically valid candidates that best match the experimental data. spec2struct not only outperforms existing methods but also provides calibrated and contextualized confidence estimates. We demonstrate its real-world impact by identifying several published structures incorrectly assigned in the literature. The combination of performance, reliability, and versatility positions spec2struct as a powerful tool for accelerating chemical discovery.

Keywords

structure elucidation
CASE
molecule prediction from spectra

Supplementary weblinks

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.