Back

IsoNet2 determines cellular structures at submolecular resolution without averaging

Liu, Y.; Fan, H.; Jih, J.; Tran, L.; Zhang, X.; Zhou, Z. H.

2025-12-11 cell biology
10.64898/2025.12.09.693325 bioRxiv
Show abstract

AbstractWe introduce IsoNet2, an end-to-end self-supervised deep-learning method that directly reconstructs high-quality 3D densities from cryogenic electron tomography. A unified network simultaneously performs denoising, contrast transfer function correction, and missing-wedge restoration, achieving [~]20 [A] resolution without averaging. A feature-rich GUI enables rapid, dataset-specific fine-tuning for end-users. IsoNet2 resolves domain organization in HIV capsid proteins, tRNA occupancy in individual ribosomes, and in situ architectures of mitochondrial respiration-related complexes, enabling atomic-level interpretation of cellular environments.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 4%
26.5%
Similar papers in this journal
2
Nature Methods
○ 385 papers in training set
Top 0.4%
18.5%
Similar papers in this journal
3
Nature
○ 645 papers in training set
Top 0.8%
16.5%
Similar papers in this journal
50% of probability mass above
4
Nature Structural & Molecular Biology
236 papers in training set
Top 1%
4.1%
5
Nature Biotechnology
○ 172 papers in training set
Top 1%
3.2%
Similar papers in this journal
6
Nature Machine Intelligence
○ 70 papers in training set
Top 0.8%
3.2%
7
Communications Biology
○ 993 papers in training set
Top 7%
2.6%
8
eLife
● 5828 papers in training set
Top 42%
2.4%
9
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 23%
2.1%
10
Scientific Data
○ 209 papers in training set
Top 1%
1.7%
11
Science Advances
● 1243 papers in training set
Top 22%
1.5%
12
Nature Genetics
○ 286 papers in training set
Top 3%
1.5%
13
Science
● 477 papers in training set
Top 7%
1.1%
14
Structure
○ 193 papers in training set
Top 2%
1.1%
15
Nature Cell Biology
○ 118 papers in training set
Top 2%
1.1%
16
Journal of Cell Biology
● 392 papers in training set
Top 4%
0.8%
17
Molecular Cell
○ 350 papers in training set
Top 5%
0.6%
18
Nucleic Acids Research
◐ 1281 papers in training set
Top 15%
0.6%
19
Nature Neuroscience
○ 252 papers in training set
Top 5%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.