Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Aug 9;23(16):8872. doi: 10.3390/ijms23168872

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© 2022 by the authors.

Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

PMC Copyright notice

Performance evaluation of 3D classification by AlphaCryo4D on the synthetic dataset with non-uniform distribution of conformational continuum. (A) The non-uniform distribution of 20 conformers of another simulated NLRP3 dataset at an SNR of 0.01 was used to examine the performance of AlphaCryo4D. This dataset was utilized to calculate the pseudo-energy landscape shown in panels (B,C) and its corresponding outcome of 3D classification by AlphaCryo4D shown in panels (D–F), which tests the robustness of AlphaCryo4D in the case of non-uniform distributions of the underlying conformational states. (B) Dimensionality reduction of resampled 3D volumes and their corresponding feature maps from the simulated dataset by t-SNE. The colors of data points indicate the ground truth of their corresponding 3D volumes. (C) Reconstruction of the pseudo-energy landscape of the simulated NLRP3 dataset. (D–F) The number of correctly classified particles in each class, the particle number of each class, the precision of 3D classification and the corresponding recall of AlphaCryo4D blind tests using this simulated dataset when the class number is set to 20 (D), 25 (E) and 30 (F).