Identifying the fragment structure of the organic compounds by deeply learning the original NMR data
This work addresses the imbalance issue in NMR datasets for chemists, but it is incremental as it applies existing deep learning methods to a specific domain.
The study tackled the problem of identifying organic compound fragment structures by preprocessing raw NMR spectra and comparing feature selection methods, finding that peak sampling features outperformed equidistant sampling in SVM and KNN models, and an RNN model showed easier hyperparameter optimization and better generalization than traditional methods.
We preprocess the raw NMR spectrum and extract key characteristic features by using two different methodologies, called equidistant sampling and peak sampling for subsequent substructure pattern recognition; meanwhile may provide the alternative strategy to address the imbalance issue of the NMR dataset frequently encountered in dataset collection of statistical modeling and establish two conventional SVM and KNN models to assess the capability of two feature selection, respectively. Our results in this study show that the models using the selected features of peak sampling outperform the ones using the other. Then we build the Recurrent Neural Network (RNN) model trained by Data B collected from peak sampling. Furthermore, we illustrate the easier optimization of hyper parameters and the better generalization ability of the RNN deep learning model by comparison with traditional machine learning SVM and KNN models in detail.