Nuclear magnetic resonance (NMR) spectroscopy plays a pivotal role in various
scientific fields, offering insights into structural information, electronic
properties and dynamic behaviors of molecules. Accurate NMR spectrum prediction
efficiently produces candidate molecules, enabling chemists to compare them
with actual experimental spectra. This process aids in confirming molecular
structures or pinpointing discrepancies, guiding further investigation. Machine
Learning (ML) has then emerged as a promising alternative approach for
predicting atomic NMR chemical shits of molecules given their structures.
Although significant progresses have been made in predicting one-dimensional
(1D) NMR, two-dimensional (2D) NMR prediction via ML remains a challenge due to
the lack of annotated NMR training datasets. To address this gap, we propose an
iterative self-training (IST) approach to train a deep learning model for
predicting atomic 2DNMR shifts and assigning peaks in experimental spectra. Our
model undergoes an initial pre-training phase employing a Multi-Task Training
(MTT) approach, which simultaneously leverages annotated 1D NMR datasets of
both $^{1}\text{H}$ and $^{13}\text{C}$ spectra to enhance its understanding of
NMR spectra. Subsequently, the pre-trained model is utilized to generate
pseudo-annotations for unlabelled 2D NMR spectra, which are subsequently used
to refine the 2D NMR prediction model. Our approach iterates between annotated
unlabelled 2D NMR data and refining our 2D NMR prediction model until
convergence. Finally, our model is able to not only accurately predict 2D NMR
but also annotate peaks in experimental 2D NMR spectra. Experimental results
show that our model is capable of accurately handling medium-sized and large
molecules, including polysaccharides, underscoring its effectiveness.

利用迭代自训练的深度学习模型，我们提出了一种预测原子二维核磁共振（NMR）位移并标记实验光谱峰值的方法，该方法能准确处理中等和大分子，包括多糖。