arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.21579physics.chem-ph
收藏

TERS-ABNet:一种基于深度学习的自动单分子结构重建方法,用于从TERS映射中以原子精度重建单分子结构

TERS-ABNet: A Deep Learning Approach for Automated Single-Molecule Structure Reconstruction with Atomic Precision from TERS Mapping

Hefei National Research Center for Physical Sciences at the Microscale and CAS Center for Excellence in Quantum Information and Quantum Physics, University of Science and Technology of China(中国科学技术大学合肥微尺度物质科学国家研究中心和量子信息科学研究院);Hefei National Laboratory, University of Science and Technology of China(中国科学技术大学合肥国家实验室);School of Physical Sciences and Department of Chemical Physics, University of Science and Technology of China(中国科学技术大学物理科学学院化学物理系)

Jie Cui, Yao Zhang, Yang Zhang, Yi Luo, Zhen-Chao Dong

AI总结:

本文提出TERS-ABNet,通过将单分子结构确定转化为图像到图的推理任务,实现了从TERS映射中高精度重建单分子结构,达到94%的原子类型分类准确率。

摘要:

确定从光谱数据中获得单分子表面化学结构代表了一个具有挑战性的高维逆问题。尖端增强拉曼光谱(TERS)能够以亚纳米空间分辨率进行化学特异性成像,但通过TERS映射重建完整分子结构仍然困难,因为振动特征具有歧义性且依赖专家解释。本文引入TERS-ABNet,一种深度学习框架,将单分子结构确定从光谱图像中转化为图像到图的推理任务。使用“双通道”架构,模型联合预测概率原子和键图,能够直接构建显式原子-键图,而无需依赖预定义的化学规则。在模拟数据集上训练后,TERS-ABNet实现了约94%的原子类型分类准确率(平均坐标误差约为0.23 Å),能够可靠地恢复分子连接并从其TERS映射中完全重建单分子结构。该框架通过迁移学习在不同空间分辨率和结构复杂性之间泛化,成功从实验TERS数据中重建单个卟啉分子的原子结构。本工作建立了一种通用的深度学习策略,用于从高维光谱成像数据中推断显式的原子-键图表示,为纳米尺度表征中的自动化分子结构确定提供了新路径。

英文摘要:

Determining the chemical structure for a single molecule on surface from spectroscopic data represents a challenging high-dimensional inverse problem. Tip-enhanced Raman spectroscopy (TERS) enables chemically specific imaging of single molecules with sub-nanometer spatial resolution, yet reconstructing complete molecular structures from TERS maps remains difficult owing to the ambiguous vibrational signatures and reliance on expert interpretation. Here, we introduce TERS-ABNet, a deep-learning framework that formulates single-molecule structure determination from spectroscopic images as an image-to-graph inference task. Using a "two-track" architecture, the model jointly predicts probabilistic atom and bond maps, enabling direct construction of explicit atom-bond graphs without relying on predefined chemical rules. Trained on simulated datasets, TERS-ABNet achieves about 94% atom-type classification accuracy (with a mean coordinate error of about 0.23 Å), enabling to reliably recovering molecular connectivity and fully reconstruct single-molecule structure from its TERS maps. The framework generalizes across varying spatial resolutions and structural complexity through transfer learning, and successfully reconstructs the atomic structure of a single porphyrin molecule from experimental TERS data. This work establishes a general deep-learning strategy for inferring explicit atom-bond graph representations from high-dimensional spectroscopic imaging data, providing a new pathway towards automated molecular structure determination in nanoscale characterization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑