Cryogenic electron microscopy (cryo-EM) has the potential to capture snapshots of proteins in motion and generate hypotheses linking conformational states to biological function. This potential has been increasingly realized by the advent of machine learning models that allow 100s-1,000s of 3D density maps to be generated from a single dataset. How to identify distinct structural states within these volume ensembles and quantify their relative occupancies remain open questions. Here, we present an approach to inferring variable regions directly from a volume ensemble based on the statistical co-occupancy of voxels, as well as a 3D convolutional neural network that predicts binarization thresholds for volumes in an unbiased and automated manner. We show that these tools recapitulate known heterogeneity in a variety of simulated and real cryo-EM datasets and highlight how integrating these tools with existing data processing pipelines enables improved particle curation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.str.2025.02.004 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Development and Validation of Machine Learning Models for Outcome Prediction in Patients with Poor-Grade Aneurysmal Subarachnoid Hemorrhage Following Endovascular Treatment.
Ther Clin Risk Manag
March 2025
Department of Neurosurgery, The second Affiliated Hospital, Jiangxi Medical College of Nanchang University, Nanchang, 330006, People's Republic of China.
Background: Endovascular treatment (EVT) has been recommended as a superior modality for the treatment of intracranial aneurysm. However, there still exists a worse percentage of poor functional outcome in patients with poor-grade aneurysmal subarachnoid hemorrhage (aSAH) undergoing EVT. Therefore, it is urgently needed to investigate the risk factors and develop a critical decision model in the subtype of such patients.
View Article and Find Full Text PDFAutomated model-free analysis of cryo-EM volume ensembles with SIREn.
Structure
March 2025
Department of Biology, Massachusetts Institute of Technology, Cambridge, MA, USA; Computational and Systems Biology Graduate Program, Massachusetts Institute of Technology, Cambridge, MA, USA. Electronic address:
Cryogenic electron microscopy (cryo-EM) has the potential to capture snapshots of proteins in motion and generate hypotheses linking conformational states to biological function. This potential has been increasingly realized by the advent of machine learning models that allow 100s-1,000s of 3D density maps to be generated from a single dataset. How to identify distinct structural states within these volume ensembles and quantify their relative occupancies remain open questions.
View Article and Find Full Text PDFMachine learning prediction for lung dose in locally advanced esophageal cancer using volumetric modulated arc therapy.
Med Dosim
March 2025
Department of Radiation Oncology, National Cancer Center Hospital, Tokyo 104-0045, Japan.
We developed machine learning (ML) models for predicting lung dose-volume histogram (DVH) metrics [V , V , and mean lung dose (MLD)] in locally advanced esophageal cancer volumetric modulated arc therapy and assessed the prediction accuracy of the models. Four ML models (linear regression, support vector machine, decision tree, and ensemble) were built with fivefold cross-validation of the predicted lung DVH metrics using a developed program by MATLAB R2022a. Eight explanatory variables were employed: gender, with/without simultaneous integrated boost and jaw tracking, age, height, weight, the ratio of the total irradiation angle to the total rotation angle of the gantry, and the ratio of the longitudinal length of the planning target volume overlapped with the whole lung to the length of the whole lung.
View Article and Find Full Text PDFRISE-Editing: Rotation-invariant neural point fields with interactive segmentation for fine-grained and efficient editing.
Neural Netw
February 2025
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering at Beihang University, Beijing, China; Qingdao Research Institute of Beihang University, Qingdao, China. Electronic address:
Neural Radiance Fields (NeRF) have shown great potential for synthesizing novel views. Currently, despite the existence of some initial controllable and editable NeRF methods, they remain limited in terms of efficient and fine-grained editing capabilities, hinders the creative editing abilities and potential applications for NeRF. In this paper, we present the rotation-invariant neural point fields with interactive segmentation for fine-grained and efficient editing.
View Article and Find Full Text PDFOpto-digital molecular analytics.
Chem Soc Rev
March 2025
School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, 637457, Singapore.
In contrast to conventional ensemble-average-based methods, opto-digital molecular analytic approaches digitize detection by physically partitioning individual detection events into discrete compartments or directly locating and analyzing the signals from single molecules. The sensitivity can be enhanced by signal amplification reactions, signal enhancement interactions, labelling by strong signal emitters, advanced optics, image processing, and machine learning, while specificity can be improved by designing target-selective probes and profiling molecular dynamics. With the capabilities to attain a limit of detection several orders lower than the conventional methods, reveal intrinsic molecular information, and achieve multiplexed analysis using a small-volume sample, the emerging opto-digital molecular analytics may be revolutionarily instrumental to clinical diagnosis, molecular chemistry and science, drug discovery, and environment monitoring.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!