Yang Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yang Yan has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Ningshao Xia
Xiamen University
3 shared publications - Dongxu Zhang
Xiamen University
2 shared publications - Fajie Yuan
School of Engineering, Westlake University, Hangzhou, China
2 shared publications - Huaizong Shen
Key Laboratory of Structural Biology of Zhejiang Province, School of Life Sciences, Westlake University, Hangzhou, China
2 shared publications - Jiageng Wu
Zhejiang University
2 shared publications - Qingbing Zheng
State Key Laboratory of Vaccines for Infectious Diseases, Xiang An Biomedicine Laboratory, School of Public Health, School of Life Sciences, Xiamen University, Xiamen, China
2 shared publications
Latest Publications
- 27 November 2025
- Published by Springer Nature in Nature Methods
A comprehensive foundation model for cryo-EM image processing
Cryogenic electron microscopy (cryo-EM) has become a premier technique for determining high-resolution structures of biological macromolecules. However, its broad application is constrained by the demand for specialized expertise. Here, to address this limitation, we introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, a versatile tool pre-trained on ~65 million cryo-EM particle images through unsupervised learning. Cryo-IEF performs diverse cryo-EM processing tasks, including particle classification by structure, pose-based clustering and image quality assessment. Building on this foundation, we developed CryoWizard, a fully automated single-particle cryo-EM processing pipeline enabled by fine-tuned Cryo-IEF for efficient particle quality ranking. CryoWizard resolves high-resolution structures across samples of varied properties and effectively mitigates the prevalent challenge of preferred orientation in cryo-EM.
- 27 November 2025
- Published by Springer Nature in Nature Methods
A comprehensive foundation model for cryo-EM image processing
Cryogenic electron microscopy (cryo-EM) has become a premier technique for determining high-resolution structures of biological macromolecules. However, its broad application is constrained by the demand for specialized expertise. Here, to address this limitation, we introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, a versatile tool pre-trained on ~65 million cryo-EM particle images through unsupervised learning. Cryo-IEF performs diverse cryo-EM processing tasks, including particle classification by structure, pose-based clustering and image quality assessment. Building on this foundation, we developed CryoWizard, a fully automated single-particle cryo-EM processing pipeline enabled by fine-tuned Cryo-IEF for efficient particle quality ranking. CryoWizard resolves high-resolution structures across samples of varied properties and effectively mitigates the prevalent challenge of preferred orientation in cryo-EM.
- Open Access
A comprehensive foundation model for cryo-EM image processing
Cryogenic electron microscopy (cryo-EM) has become a premier technique for high-resolution structural determination of biological macromolecules 1–4 . However, its widespread adoption is hampered by the need for specialized expertise. We introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, pre-trained on an extensive dataset of approximately 65 million cryo-EM particle images using unsupervised learning. Cryo-IEF excels in various cryo-EM data processing tasks, such as classifying particles from different structures, clustering particles by pose, and assessing the quality of particle images. Upon fine-tuning, the model effectively ranks particle images by quality at high efficiency, enabling the creation of CryoWizard—a fully automated single-particle cryo-EM data processing pipeline. This pipeline has successfully resolved high-resolution structures of diverse properties and proven adept at mitigating the prevalent preferred orientation challenge in many cryo-EM samples. The Cryo-IEF model and CryoWizard pipeline collectively represent a significant advancement in rendering cryo-EM technology more accessible, efficient, and robust, with substantial implications for life sciences research.
Open AccessA comprehensive foundation model for cryo-EM image processing
Cryogenic electron microscopy (cryo-EM) has become a premier technique for high-resolution structural determination of biological macromolecules 1–4 . However, its widespread adoption is hampered by the need for specialized expertise. We introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, pre-trained on an extensive dataset of approximately 65 million cryo-EM particle images using unsupervised learning. Cryo-IEF excels in various cryo-EM data processing tasks, such as classifying particles from different structures, clustering particles by pose, and assessing the quality of particle images. Upon fine-tuning, the model effectively ranks particle images by quality at high efficiency, enabling the creation of CryoWizard—a fully automated single-particle cryo-EM data processing pipeline. This pipeline has successfully resolved high-resolution structures of diverse properties and proven adept at mitigating the prevalent preferred orientation challenge in many cryo-EM samples. The Cryo-IEF model and CryoWizard pipeline collectively represent a significant advancement in rendering cryo-EM technology more accessible, efficient, and robust, with substantial implications for life sciences research.
- 14 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 223-227
Renewable Energy Output Prediction Method Based on Recurrent Neural Network of Double Attention Mechanism
In recent years, the implementation of the concept of sustainable development, new energy is widely connected to the grid. However, the power generation of wind power, photovoltaic and other renewable energy sources is influenced by external factors and has obvious volatility and intermittency. The time series of electrical energy output in the system is a typical non-stationary signal, which is difficult to predict accurately. In order to improve the prediction accuracy of the short-term renewable energy output prediction model from the data level, a recurrent neural network based on a dual-attention mechanism (DA-RNN) is established in this paper. In the encoder stage, the input features are extracted based on the driving sequence. In the decoder stage, the importance weights of relevant encoder information on time are adaptively optimized when predicting the target sequence. Through the prediction experiments of solar power and wind power, the method used in this paper has improved the prediction accuracy compared with the statistical method and LSTM, and can effectively smooth out the volatility of new energy production.
- 14 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 223-227
Renewable Energy Output Prediction Method Based on Recurrent Neural Network of Double Attention Mechanism
In recent years, the implementation of the concept of sustainable development, new energy is widely connected to the grid. However, the power generation of wind power, photovoltaic and other renewable energy sources is influenced by external factors and has obvious volatility and intermittency. The time series of electrical energy output in the system is a typical non-stationary signal, which is difficult to predict accurately. In order to improve the prediction accuracy of the short-term renewable energy output prediction model from the data level, a recurrent neural network based on a dual-attention mechanism (DA-RNN) is established in this paper. In the encoder stage, the input features are extracted based on the driving sequence. In the decoder stage, the importance weights of relevant encoder information on time are adaptively optimized when predicting the target sequence. Through the prediction experiments of solar power and wind power, the method used in this paper has improved the prediction accuracy compared with the statistical method and LSTM, and can effectively smooth out the volatility of new energy production.
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (5) , 1509-1521
Unsupervised Cryo-EM Images Denoising and Clustering Based on Deep Convolutional Autoencoder and K-Means++
Cryo-electron microscopy (cryo-EM) is a widely used structural determination technique. Because of the extremely low signal-to-noise ratio (SNR) of images captured by cryo-EM, clustering single-particle cryo-EM images with high accuracy is challenging. To address this, we proposed an iterative denoising and clustering method based on a deep convolutional variational autoencoder and K-means++. The proposed method contains two modules: a denoising ResNet variational autoencoder (DRVAE), and Balance size K-means++ (BSK-means++). First, the DRVAE is trained in a fully unsupervised manner to initialize the neural network and obtain preliminary denoised images. Second, BSK-means++ is built for clustering denoised images, and images closer to class centers are divided into reliable samples. Third, the training of DRVAE is continued, while the class-average images are used as pseudo supervision of reliable samples to reserve more detailed information of denoised images. Finally, the second and third steps mentioned above can be performed jointly and iteratively until convergence occurs. The experimental results showed that the proposed method can generate reliable class average images and achieve better clustering accuracy and normalized mutual information than current methods. This study confirmed that DRVAE with BSK-means++ could achieve a good denoise performance on single-particle cryo-EM images, which can help researchers obtain information such as symmetry and heterogeneity of the target particles. In addition, the proposed method avoids the extreme imbalance of class size, which improves the reliability of the clustering result.
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (5) , 1509-1521
Unsupervised Cryo-EM Images Denoising and Clustering Based on Deep Convolutional Autoencoder and K-Means++
Cryo-electron microscopy (cryo-EM) is a widely used structural determination technique. Because of the extremely low signal-to-noise ratio (SNR) of images captured by cryo-EM, clustering single-particle cryo-EM images with high accuracy is challenging. To address this, we proposed an iterative denoising and clustering method based on a deep convolutional variational autoencoder and K-means++. The proposed method contains two modules: a denoising ResNet variational autoencoder (DRVAE), and Balance size K-means++ (BSK-means++). First, the DRVAE is trained in a fully unsupervised manner to initialize the neural network and obtain preliminary denoised images. Second, BSK-means++ is built for clustering denoised images, and images closer to class centers are divided into reliable samples. Third, the training of DRVAE is continued, while the class-average images are used as pseudo supervision of reliable samples to reserve more detailed information of denoised images. Finally, the second and third steps mentioned above can be performed jointly and iteratively until convergence occurs. The experimental results showed that the proposed method can generate reliable class average images and achieve better clustering accuracy and normalized mutual information than current methods. This study confirmed that DRVAE with BSK-means++ could achieve a good denoise performance on single-particle cryo-EM images, which can help researchers obtain information such as symmetry and heterogeneity of the target particles. In addition, the proposed method avoids the extreme imbalance of class size, which improves the reliability of the clustering result.
- 21 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (2) , 452-472
Machine Learning for Structure Determination in Single-Particle Cryo-Electron Microscopy: A Systematic Review
Recently, single-particle cryo-electron microscopy (cryo-EM) has become an indispensable method for determining macromolecular structures at high resolution to deeply explore the relevant molecular mechanism. Its recent breakthrough is mainly because of the rapid advances in hardware and image processing algorithms, especially machine learning. As an essential support of single-particle cryo-EM, machine learning has powered many aspects of structure determination and greatly promoted its development. In this article, we provide a systematic review of the applications of machine learning in this field. Our review begins with a brief introduction of single-particle cryo-EM, followed by the specific tasks and challenges of its image processing. Then, focusing on the workflow of structure determination, we describe relevant machine learning algorithms and applications at different steps, including particle picking, 2-D clustering, 3-D reconstruction, and other steps. As different tasks exhibit distinct characteristics, we introduce the evaluation metrics for each task and summarize their dynamics of technology development. Finally, we discuss the open issues and potential trends in this promising field.
- 21 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (2) , 452-472
Machine Learning for Structure Determination in Single-Particle Cryo-Electron Microscopy: A Systematic Review
Recently, single-particle cryo-electron microscopy (cryo-EM) has become an indispensable method for determining macromolecular structures at high resolution to deeply explore the relevant molecular mechanism. Its recent breakthrough is mainly because of the rapid advances in hardware and image processing algorithms, especially machine learning. As an essential support of single-particle cryo-EM, machine learning has powered many aspects of structure determination and greatly promoted its development. In this article, we provide a systematic review of the applications of machine learning in this field. Our review begins with a brief introduction of single-particle cryo-EM, followed by the specific tasks and challenges of its image processing. Then, focusing on the workflow of structure determination, we describe relevant machine learning algorithms and applications at different steps, including particle picking, 2-D clustering, 3-D reconstruction, and other steps. As different tasks exhibit distinct characteristics, we introduce the evaluation metrics for each task and summarize their dynamics of technology development. Finally, we discuss the open issues and potential trends in this promising field.
- 14 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 213-217
A Novel Clustering Method Using Variational Autoencoder with Reliable Sample Decision and Balanced K-Means++ for Single-particle Cryo-EM Images
Single-particle cryo-electron microscopy (cryo-EM) is one of the most popular technology in the field of biology molecular structure determination. Clustering for Cryo-EM particle images is very important in the structure reconstruction process, which significantly affected the reconstruction resolution. Because the signal-to-noise-ratio (SNR) of cryo-electron is extremely low, it's a challenge to improve the clustering accuracy. In this paper, we proposed a novel clustering method that combined a variational autoencoder with reliable sample decision (ReVAE) and balanced K-means++ (BK-means++). ReVAE projects cryo-EM images into low-dimensional latent variables, and BK-means++ is applied to cluster latent variables. Training of ReVAE and clustering of latent variables by BK-means++ are performed jointly and iteratively. The experimental results showed that ReVAE with BK-means++ achieved state-of-the-art results compared to traditional cryo-EM particle images clustering methods.
- 14 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 213-217
A Novel Clustering Method Using Variational Autoencoder with Reliable Sample Decision and Balanced K-Means++ for Single-particle Cryo-EM Images
Single-particle cryo-electron microscopy (cryo-EM) is one of the most popular technology in the field of biology molecular structure determination. Clustering for Cryo-EM particle images is very important in the structure reconstruction process, which significantly affected the reconstruction resolution. Because the signal-to-noise-ratio (SNR) of cryo-electron is extremely low, it's a challenge to improve the clustering accuracy. In this paper, we proposed a novel clustering method that combined a variational autoencoder with reliable sample decision (ReVAE) and balanced K-means++ (BK-means++). ReVAE projects cryo-EM images into low-dimensional latent variables, and BK-means++ is applied to cluster latent variables. Training of ReVAE and clustering of latent variables by BK-means++ are performed jointly and iteratively. The experimental results showed that ReVAE with BK-means++ achieved state-of-the-art results compared to traditional cryo-EM particle images clustering methods.
- 15 February 2021
- Published by Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences in Optics and Precision Engineering
- Vol. 29 (2) , 400-410
Single image dehazing combining sky segmentation and transmission mapping
- 15 February 2021
- Published by Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences in Optics and Precision Engineering
- Vol. 29 (2) , 400-410
Single image dehazing combining sky segmentation and transmission mapping
- Open Access
- 7 January 2020
- Published by Wiley in Journal of Sensors
- Vol. 2020, 1-17
A Mobile Localization Method in Smart Indoor Environment Using Polynomial Fitting for Wireless Sensor Network
The main factor affecting the localization accuracy is nonline of sight (NLOS) error which is caused by the complicated indoor environment such as obstacles and walls. To obviously alleviate NLOS effects, a polynomial fitting-based adjusted Kalman filter (PF-AKF) method in a wireless sensor network (WSN) framework is proposed in this paper. The method employs polynomial fitting to accomplish both NLOS identification and distance prediction. Rather than employing standard deviation of all historical data as NLOS detection threshold, the proposed method identifies NLOS via deviation between fitted curve and measurements. Then, it processes the measurements with adjusted Kalman filter (AKF), conducting weighting filter in the case of NLOS condition. Simulations compare the proposed method with Kalman filter (KF), adjusted Kalman filter (AKF), and Kalman-based interacting multiple model (K-IMM) algorithms, and the results demonstrate the superior performance of the proposed method. Moreover, experimental results obtained from a real indoor environment validate the simulation results.
- 7 January 2020
- Published by Wiley in Journal of Sensors
- Vol. 2020, 1-17
Open AccessA Mobile Localization Method in Smart Indoor Environment Using Polynomial Fitting for Wireless Sensor Network
The main factor affecting the localization accuracy is nonline of sight (NLOS) error which is caused by the complicated indoor environment such as obstacles and walls. To obviously alleviate NLOS effects, a polynomial fitting-based adjusted Kalman filter (PF-AKF) method in a wireless sensor network (WSN) framework is proposed in this paper. The method employs polynomial fitting to accomplish both NLOS identification and distance prediction. Rather than employing standard deviation of all historical data as NLOS detection threshold, the proposed method identifies NLOS via deviation between fitted curve and measurements. Then, it processes the measurements with adjusted Kalman filter (AKF), conducting weighting filter in the case of NLOS condition. Simulations compare the proposed method with Kalman filter (KF), adjusted Kalman filter (AKF), and Kalman-based interacting multiple model (K-IMM) algorithms, and the results demonstrate the superior performance of the proposed method. Moreover, experimental results obtained from a real indoor environment validate the simulation results.
- 20 January 2018
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 96 (1-4) , 271-285
A STEP-based machining data model for autonomous process generation of intelligent CNC controller
- 20 January 2018
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 96 (1-4) , 271-285
A STEP-based machining data model for autonomous process generation of intelligent CNC controller