Abstract
State-of-the-art identification of the functional groups present in an unknown chemical entity requires the expertise of a skilled spectroscopist to analyse and interpret Fourier transform infra-red (FTIR), mass spectroscopy (MS) and/or nuclear magnetic resonance (NMR) data. This process can be time-consuming and error-prone, especially for complex chemical entities that are poorly characterised in the literature, or inefficient to use with synthetic robots producing molecules at an accelerated rate. Herein, we introduce a fast, multi-label deep neural network for accurately identifying all the functional groups of unknown compounds using a combination of FTIR and MS spectra. We do not use any database, pre-established rules, procedures, or peak-matching methods. Our trained neural network reveals patterns typically used by human chemists to identify standard groups. Finally, we experimentally validated our neural network, trained on single compounds, to predict functional groups in compound mixtures. Our methodology showcases practical utility for future use in autonomous analytical detection.
Highlights
The arrangement of atoms within a molecule dictates its physical, chemical, and spectral properties
The binary classi er approach did not improve the performance of the multi-layer perceptron (MLP) model signi cantly as these models only produced an improvement in the functional group F1 score of 0.006 over that of the multilabel model, suggesting that transfer learning is not a signi cant factor in the multi-label network
We present a machine learning method for de novo prediction of functional groups using a combination of Fourier transform infra-red (FTIR) and mass spectroscopy (MS) data
Summary
The arrangement of atoms within a molecule dictates its physical, chemical, and spectral properties. Large repeating arrangements of atoms which give rise to measurable changes in a molecule's reactivity,[1,2,3] boiling point,[4,5] melting point,[6,7] and other characteristics are called functional groups. Given the structural formula of a molecule, a chemist can identify functional groups present (e.g. aldehyde, carboxylic acid, alcohol, etc.) and can postulate characteristic reactivity and physical properties for a given molecule based on the presence of these groups. The identi cation of functional groups present within an unknown compound is a key step in qualitative organic synthesis and structure elucidation; it is routinely practiced by chemists to validate the synthesis of novel small molecules or identify unknown structures in complex mixtures. Techniques for assigning functional groups based on ‘rules of thumb’ or by matching pro les from known databases are commonly applied in organic chemistry,[8] metabolomics,[9,10] and forensic sciences.[11,12,13] monitoring of functional group changes can be used to determine the progress of a reaction,[14] and can even be used to identify the components of complex mixtures for a reaction coordinate
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
