De-novo Identification of Small Molecules from Their GC-EI-MS Spectra

04/04/2023

∙

by   Adam Hájek, et al.

∙

0

∙

share

Identification of experimentally acquired mass spectra of unknown compounds presents a particular challenge because reliable spectral databases do not cover the potential chemical space with sufficient density. Therefore machine learning based de-novo methods, which derive molecular structure directly from its mass spectrum gained attention recently. We present a novel method in this family, addressing a specific usecase of GC-EI-MS spectra, which is particularly hard due to lack of additional information from the first stage of MS/MS experiments, on which the previously published methods rely. We analyze strengths and drawbacks or our approach and discuss future directions.