Project description:Automatic single particle picking is a critical step in the data processing pipeline of cryo-electron microscopy structure reconstruction. In recent years, several deep learning-based algorithms have been developed, demonstrating their potential to solve this challenge. However, current methods highly depend on manually labeled training data, which is labor-intensive and prone to biases especially for high-noise and low-contrast micrographs, resulting in suboptimal precision and recall. To address these problems, we propose UPicker, a semi-supervised transformer-based particle-picking method with a two-stage training process: unsupervised pretraining and supervised fine-tuning. During the unsupervised pretraining, an Adaptive Laplacian of Gaussian region proposal generator is proposed to obtain pseudo-labels from unlabeled data for initial feature learning. For the supervised fine-tuning, UPicker only needs a small amount of labeled data to achieve high accuracy in particle picking. To further enhance model performance, UPicker employs a contrastive denoising training strategy to reduce redundant detections and accelerate convergence, along with a hybrid data augmentation strategy to deal with limited labeled data. Comprehensive experiments on both simulated and experimental datasets demonstrate that UPicker outperforms state-of-the-art particle-picking methods in terms of accuracy and robustness while requiring fewer labeled data than other transformer-based models. Furthermore, ablation studies demonstrate the effectiveness and necessity of each component of UPicker. The source code and data are available at https://github.com/JachyLikeCoding/UPicker.

| S-EPMC11631311 | biostudies-literature

CryoTransformer: A Transformer Model for Picking Protein Particles from Cryo-EM Micrographs.

Project description:Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structures of large protein complexes. Picking single protein particles from cryo-EM micrographs (images) is a crucial step in reconstructing protein structures from them. However, the widely used template-based particle picking process requires some manual particle picking and is labor-intensive and time-consuming. Though machine learning and artificial intelligence (AI) can potentially automate particle picking, the current AI methods pick particles with low precision or low recall. The erroneously picked particles can severely reduce the quality of reconstructed protein structures, especially for the micrographs with low signal-to-noise (SNR) ratios. To address these shortcomings, we devised CryoTransformer based on transformers, residual networks, and image processing techniques to accurately pick protein particles from cryo-EM micrographs. CryoTransformer was trained and tested on the largest labelled cryo-EM protein particle dataset - CryoPPP. It outperforms the current state-of-the-art machine learning methods of particle picking in terms of the resolution of 3D density maps reconstructed from the picked particles as well as F1-score and is poised to facilitate the automation of the cryo-EM protein particle picking.

| S-EPMC10634673 | biostudies-literature

Cryo-EM micrographs of human ABCA1

Project description: Not available

| EMPIAR-10798 | biostudies-other

Cryo-EM structure and polymorphism of Aβ amyloid fibrils purified from Alzheimer's brain tissue.

Project description:The formation of Aβ amyloid fibrils is a neuropathological hallmark of Alzheimer's disease and cerebral amyloid angiopathy. However, the structure of Aβ amyloid fibrils from brain tissue is poorly understood. Here we report the purification of Aβ amyloid fibrils from meningeal Alzheimer's brain tissue and their structural analysis with cryo-electron microscopy. We show that these fibrils are polymorphic but consist of similarly structured protofilaments. Brain derived Aβ amyloid fibrils are right-hand twisted and their peptide fold differs sharply from previously analyzed Aβ fibrils that were formed in vitro. These data underscore the importance to use patient-derived amyloid fibrils when investigating the structural basis of the disease.

| S-EPMC6820800 | biostudies-literature

Cryo-EM micrographs of GABA(A)Rs purified from cells expressing human full-length alpha4, beta3 and gamma2 subunits, in presence of GABA and nanobody Nb25

Project description: Not available

| EMPIAR-10909 | biostudies-other

Cryo-EM micrographs of GABA(A)Rs purified from cells expressing human full-length alpha4, beta3 and delta subunits, in presence of HEPES and nanobody Nb25

Project description: Not available

| EMPIAR-10913 | biostudies-other