Direct deduction of chemical class from NMR spectra
This addresses automation challenges in cheminformatics for researchers and engineers, though it is incremental as it builds on existing deep learning methods.
The paper tackles the problem of automating chemical compound classification from NMR spectra by using a convolutional neural network, achieving a proof-of-concept that reduces the need for human intervention in structure matching.
This paper presents a proof-of-concept method for classifying chemical compounds directly from NMR data without doing structure elucidation. This can help to reduce time in finding good structure candidates, as in most cases matching must be done by a human engineer, or at the very least a process for matching must be meaningfully interpreted by one. Therefore, for a long time automation in the area of NMR has been actively sought. The method identified as suitable for the classification is a convolutional neural network (CNN). Other methods, including clustering and image registration, have not been found suitable for the task in a comparative analysis. The result shows that deep learning can offer solutions to automation problems in cheminformatics.