Xinyu Lu

Xinyu Lu

逯新宇

Molecular AI · Spectra ↔ Structures · Geometric AI

I develop molecular AI systems that connect molecular structures and experimental spectra—in both directions.

I am a Ph.D. candidate in Physical Chemistry at Xiamen University and a joint research trainee at Shanghai Innovation Institute, advised by Prof. Bin Ren and Prof. Tong Zhu. My research combines bidirectional spectrum–structure learning with equivariant architectures and molecular foundation models—from predicting spectroscopic observables to recovering molecular identity and conformation.

I am particularly interested in closing the loop between molecular models and real experiments through large-scale scientific data and automated experimentation. I welcome collaborations in molecular AI, spectroscopy, and AI for Science.

Publications

For the complete and current publication record, visit Google Scholar.

Selected publications

Selected work on spectrum–structure learning and molecular foundation models.

4 publications
Published Co-first author

Vib2Conf: AI-driven discrimination of molecular conformations from vibrational spectra

Xinyu Lu*, De-Yi Lin*, Hao Ma, Tong Zhu, Bin Ren, Guo-Kun Liu

* Equal contribution

Analytical Chemistry • 2026
Abstract
An AI framework for distinguishing molecular conformations directly from vibrational spectra.
Code
Spectral Representation Molecular Modeling
Vib2Conf graphical abstract showing spectral and molecular encoders for conformation discrimination
Preprint First author

Vib2Mol: From Vibrational Spectra to Molecular Structures—A Unified Deep Learning Framework

Xinyu Lu, Hao Ma, Hui Li, Jia Li, Yi Rong, Yuqiang Li, , Bin Ren
arXiv preprint arXiv:2503.07014 • 2025
Abstract
A unified framework connecting spectrum–structure retrieval and de novo molecular generation across Raman and infrared spectroscopy.
Code Models
Spectral Representation Molecular Modeling
Vib2Mol graphical abstract showing spectrum retrieval and molecular generation tasks
Preprint

Suiren-1.0 Technical Report: A Family of Molecular Foundation Models

Junyi An, Xinyu Lu, Yun-Fei Shi, Li-Cheng Xu, Nannan Zhang, Chao Qu, , Fenglei Cao
arXiv preprint arXiv:2603.21942 • 2026
Abstract
A family of molecular foundation models bridging three-dimensional conformational geometry and two-dimensional statistical ensemble spaces.
Code Models
Molecular Modeling
Suiren graphical abstract illustrating molecular representations conformational distributions and ensemble properties
Preprint Co-first author

Equivariant Spherical Transformer for Efficient Molecular Modeling

Junyi An, Chao Qu, Xinyu Lu, Yunfei Shi, Qianwei Tang, Peijia Lin, , Yuan Qi
arXiv preprint arXiv:2505.23086 • 2025
Abstract
An expressive and efficient SE(3)-equivariant Transformer for molecular property prediction and atomistic modeling.
Molecular Modeling
EST graphical abstract comparing spherical representations tensor products and the proposed Transformer operation

More publications

Additional peer-reviewed work, ordered newest first.

9 publications

Open-set deep learning-enabled single-cell Raman spectroscopy for rapid identification of airborne pathogens in real-world environments

Longji Zhu, Yunan Yang, Fei Xu, Xinyu Lu, Mingrui Shuai, Zhulin An, , Li Cui
Science Advances • 2025
First author

Deep Learning-Assisted Spectrum–Structure Correlation: State-of-the-Art and Perspectives

Xinyu Lu, Hao-Ping Wu, Hao Ma, Hui Li, Jia Li, Yan-Ti Liu, , Guo-Kun Liu
Analytical Chemistry • 2024

Signal2signal: Pushing the Spatiotemporal Resolution to the Limit by Single Chemical Hyperspectral Imaging

Si-Heng Luo, Xiao-Jiao Zhao, Mao-Feng Cao, Jing Xu, Wei-Li Wang, Xinyu Lu, , Zhong-Qun Tian
Analytical Chemistry • 2024
First author

Patch-Based Convolutional Encoder: A Deep Learning Algorithm for Spectral Classification Balancing the Local and Global Information

Xinyu Lu, Chen-Yue Wang, Hui Tang, Yi-Fei Qin, Li Cui, Xiang Wang, , Bin Ren
Analytical Chemistry • 2024

Rapidly determining the 3D structure of proteins by surface-enhanced Raman spectroscopy

Hao Ma, Sen Yan, Xinyu Lu, Yi-Fan Bao, Jia Liu, Langxing Liao, , Bin Ren
Science Advances • 2023

1D Gradient-Weighted Class Activation Mapping, Visualizing Decision Process of Convolutional Neural Network-Based Models in Spectroscopy Analysis

Guo-Yang Shi, Hao-Ping Wu, Si-Heng Luo, Xinyu Lu, Bin Ren, Qian Zhang, , Guo-Kun Liu
Analytical Chemistry • 2023
Co-first author

Deep Learning-Enabled Raman Spectroscopic Identification of Pathogen-Derived Extracellular Vesicles and the Biogenesis Process

Yi-Fei Qin*, Xinyu Lu*, Zheng Shi, Qian-Sheng Huang, Xiang Wang, Bin Ren, Li Cui

* Equal contribution

Analytical Chemistry • 2022

Correlation Coefficient-Directed Label-Free Characterization of Native Proteins by Surface-Enhanced Raman Spectroscopy

Ping-Shi Wang, Hao Ma, Sen Yan, Xinyu Lu, Hui Tang, Xiao-Han Xi, , Bin Ren
Chemical Science • 2022

Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

Hao He, Sen Yan, Danya Lyu, Mengxi Xu, Ruiqian Ye, Peng Zheng, , Bin Ren
Analytical Chemistry • 2021

CV

Research at the intersection of molecular AI and spectroscopy, spanning spectrum–structure learning, equivariant foundation models, and molecular generation.

Experience & education