近日，中国科学技术大学胡伟团队研究了分子结构与振动谱双向转换的深度学习。2025年7月23日出版的《美国化学会志》发表了这项成果。

人们开发了两个深度学习模型TranSpec和SpecGNN，用于在分子振动光谱和简化的分子输入线输入系统（SMILES）表示之间建立双向映射，类似于光谱语言和分子结构语言之间的“翻译”。最初，TranSpec在量子化学（QC）计算的红外和拉曼光谱数据集上分别达到了55%和63%的准确率，但在NIST的实验红外数据集上，它的准确率下降到了11%。

为了解决这个问题，研究组结合了红外和拉曼光谱作为输入；扩充数据集；采用模型学习、迁移学习和多视角学习；应用分子质量过滤；并利用SpecGNN进行光谱模拟和候选重排序。这些改进将TranSpec在实验红外数据集上的准确率提高到了53.6%。值得注意的是，SpecGNN在光谱精度和计算效率方面都优于传统的QC方法。最后，研究组展示了TranSpec识别官能团和区分异构体或同源物的能力。TranSpec和SpecGNN模型共同为解释分子结构和光谱提供了高效、准确的人工智能驱动框架，推动了光谱学和化学信息学的应用。

附：英文原文

Title: Deep Learning for Bidirectional Translation between Molecular Structures and Vibrational Spectra

Author: Tianqing Hu, Zihan Zou, Bo Li, Tong Zhu, Shaonan Gu, Jun Jiang, Yi Luo, Wei Hu

Issue&Volume: July 23, 2025

Abstract: Two deep learning models, TranSpec and SpecGNN, were developed to establish a bidirectional mapping between molecular vibrational spectra and simplified molecular input line entry system (SMILES) representations, akin to a “translation” between the language of spectra and the language of molecular structures. Initially, TranSpec achieved accuracy rates of 55 and 63% for quantum chemistry (QC)-calculated IR and Raman spectral data sets, respectively, but its performance dropped to 11% for the NIST experimental IR data set. To address this, we combined IR and Raman spectra as input; augmented the data set; employed model fusion, transfer learning, and multisource learning; applied molecular mass filtering; and leveraged SpecGNN for spectral simulation and candidate reordering. These improvements boosted TranSpec’s accuracy to 53.6% for the experimental IR data set. Notably, SpecGNN outperformed traditional QC methods in terms of both spectral accuracy and computational efficiency. Finally, we demonstrated TranSpec’s ability to recognize functional groups and distinguish isomers or homologues. Together, TranSpec and SpecGNN models provide an efficient and accurate AI-driven framework for interpreting molecular structures and spectra, advancing applications in spectroscopy and cheminformatics.

DOI: 10.1021/jacs.5c05010

Source: https://pubs.acs.org/doi/abs/10.1021/jacs.5c05010