CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy

KMS > 信息科学与技术学院 > 博士生

CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy

Zhang, Jiakai1,2

; Chen, Qihe1,2

; Zeng, Yan1,2

; Gao, Wenyuan1

; He, Xuming1

; Liu, Zhijie1,3

; Yu, Jingyi1

2024-12

会议录名称

THE THIRTY-EIGHTH ANNUAL CONFERENCE ON NEURAL INFORMATION PROCESSING SYSTEMS

发表状态

已发表

摘要

In the past decade, deep conditional generative models have revolutionized the generation of realistic images, extending their application from entertainment to scientific domains. Single-particle cryo-electron microscopy (cryo-EM) is crucial in resolving near-atomic resolution 3D structures of proteins, such as the SARSCOV-2 spike protein. To achieve high-resolution reconstruction, a comprehensive data processing pipeline has been adopted. However, its performance is still limited as it lacks high-quality annotated datasets for training. To address this, we introduce physics-informed generative cryo-electron microscopy (CryoGEM), which for the first time integrates physics-based cryo-EM simulation with a generative unpaired noise translation to generate physically correct synthetic cryo-EM datasets with realistic noises. Initially, CryoGEM simulates the cryo-EM imaging process based on a virtual specimen. To generate realistic noises, we leverage an unpaired noise translation via contrastive learning with a novel mask-guided sampling scheme. Extensive experiments show that CryoGEM is capable of generating authentic cryoEM images. The generated dataset can used as training data for particle picking and pose estimation models, eventually improving the reconstruction resolution.

文献类型

会议论文

条目标识符

https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/500248

专题

信息科学与技术学院_博士生
iHuman研究所
信息科学与技术学院_PI研究组_何旭明组
信息科学与技术学院_PI研究组_虞晶怡组
信息科学与技术学院_硕士生
信息科学与技术学院_本科生

共同第一作者

Chen, Qihe

通讯作者

Yu, Jingyi

作者单位

1.ShanghaiTech University
2.Cellverse
3.iHuman Institute