AI protocol for retrieving protein dynamic structures from two-dimensional infrared spectra

S Sheng Ye (School of Artificial Intelligence) L Lvshuai Zhu (Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Engineering Research Center for Unmanned System and Intelligent Technology, School of AI, Anhui University) Z Zhicheng Zhao (Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Engineering Research Center for Unmanned System and Intelligent Technology, School of AI, Anhui University) F Fan Wu Z Zhipeng Li (Beijing Huairou Laboratory) B Binbin Wang (Department of Chemistry, Key Laboratory of Surface & Interface Science of Polymer Materials of Zhejiang Province) K Kai Zhong (Zernike Institute for Advanced Materials, Department of Nanoscience and Materials Science, University of Groningen) C Changyin Sun (Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Engineering Research Center for Unmanned System and Intelligent Technology, School of AI, Anhui University) S Shaul Mukamel (Department of Chemistry, University of California) J Jun Jiang (State Key Laboratory of Precision and Intelligent Chemistry, Hefei National Research Center for Physical Sciences at the Microscale, School of Chemistry and Materials Science)

Abstract

Understanding the dynamic evolution of protein structures is crucial for uncovering their biological functions. Yet, real-time prediction of these dynamic structures remains a significant challenge. Two-dimensional infrared (2DIR) spectroscopy is a powerful tool for analyzing protein dynamics. However, translating its complex, low-dimensional signals into detailed three-dimensional structures is a daunting task. In this study, we introduce a machine learning-based approach that accurately predicts dynamic three-dimensional protein structures from 2DIR descriptors. Our method establishes a robust “spectrum-structure” relationship, enabling the recovery of three-dimensional structures across a wide variety of proteins. It demonstrates broad applicability in predicting dynamic structures along different protein folding trajectories, spanning timescales from microseconds to milliseconds. This approach also shows promise in identifying the structures of previously uncharacterized proteins based solely on their spectral descriptors. The integration of AI with 2DIR spectroscopy offers insights and represents a significant advancement in the real-time analysis of dynamic protein structures.

Article Details

Volume / Issue Vol. 122, Issue 7
Published February 18, 2025
ISSN 0027-8424
Publisher National Academy of Sciences

Authors (10)

S

Sheng Ye

School of Artificial Intelligence

L

Lvshuai Zhu

Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Engineering Research Center for Unmanned System and Intelligent Technology, School of AI, Anhui University

Z

Zhicheng Zhao

Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Engineering Research Center for Unmanned System and Intelligent Technology, School of AI, Anhui University

F

Fan Wu

Z

Zhipeng Li

Beijing Huairou Laboratory

B

Binbin Wang

Department of Chemistry, Key Laboratory of Surface & Interface Science of Polymer Materials of Zhejiang Province

K

Kai Zhong

Zernike Institute for Advanced Materials, Department of Nanoscience and Materials Science, University of Groningen

C

Changyin Sun

Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Engineering Research Center for Unmanned System and Intelligent Technology, School of AI, Anhui University

S

Shaul Mukamel

Department of Chemistry, University of California

J

Jun Jiang

State Key Laboratory of Precision and Intelligent Chemistry, Hefei National Research Center for Physical Sciences at the Microscale, School of Chemistry and Materials Science