Cross-Modal Retrieval between ¹³C NMR Spectra and Structures for Compound Identification Using Deep Contrastive Learning

Abstract

Library matching using carbon-13 nuclear magnetic resonance ( 13 C NMR) spectra has been a popular method adopted in compound identification systems. However, the usability of existing approaches has been restricted as enlarging a library containing both a chemical structure and spectrum is a costly and time-consuming process. Therefore, we propose a fundamentally different, novel approach to match 13 C NMR spectra directly against a molecular structure library. We develop a cross-modal retrieval between spectrum and structure (CReSS) system using deep contrastive learning, which allows us to search a molecular structure library using the 13 C NMR spectrum of a compound. In the test of searching 41,494 13 C NMR spectra against a reference structure library containing 10.4 million compounds, CReSS reached a recall@10 accuracy of 91.64% and a processing speed of 0.114 s per query spectrum. When further incorporating a filter with a molecular weight tolerance of 5 Da, CReSS achieved a new remarkable recall@10 of 98.39%. Furthermore, CReSS has potential in detecting scaffolds of novel structures and demonstrates great performance for the task of structural revision. CReSS is built and developed to bridge the gap between 13 C NMR spectra and structures and could be generally applicable in compound identification.

Study on yellowing mechanism and inhibiting technology based on amide salts modified polyester

“…13 C-NMR determined the substance structure by the intensity, chemical shift, and coupling constant of the absorption peak. 38 The 13 C-NMR spectrum of the yellowing substances is observed in Figure 7(b). According to the division of the 13 C-NMR spectrum, the C protons (1∼6) corresponded to the different positions of the AP salts sequentially, and peaks A and B were attributed to the TFA solvent.…”

Conditional Molecular Generation Net Enables Automated Structure Elucidation Based on 13C NMR Spectra and Prior Knowledge

“…For the first stage of fine-tuning, 45.3 million molecules were collected from PubChem, and 13 C NMR spectral data were calculated using Gaussian software. The experimental 13 C NMR spectra for the second stage of fine-tuning were consistent with the data set of our previous work . The resulting three spectral data sets were as follows: training set (370,898 molecules), test set (6471 molecules), and external test set (41,494 molecules).…”

Preparation and characterization of poly(ethylene terephthalate‐co‐aliphatic amide) copolymer fibers with excellent hygroscopicity and softness

“…13 C-NMR analysis 13 C-NMR is used to determine the structure of the compound by the strength, position (i.e., chemical shift) of the absorption peak, the spin-spin splitting, and coupling constant. 38 The structures of the copolymers (PET/APs and PET/APA) were further analyzed by 13 C-NMR spectroscopy. The different numbers represent the C atom at the various positions in the structural formula (Figure 5).…”