Back

AI-directed voxel extraction and volume EM identify intrusions as sites of mitochondrial contact

Padman, B. S.; Lindblom, R. S. J.; Lazarou, M.

2025-04-16 cell biology
10.1101/2024.11.20.624606 bioRxiv
Show abstract

Membrane contact sites (MCS) establish organelle interactomes in cells to enable communication and exchange of materials. Volume electron microscopy (vEM) is ideally suited for MCS analyses, but semantic segmentation of large vEM datasets remains challenging. Recent adoption of artificial intelligence (AI) for segmentation has greatly enhanced our analysis capabilities. However, we show that organelle boundaries, which are important for defining MCS, are the least confident predictions made by AI. We outline a segmentation strategy termed AI-directed Voxel Extraction (AIVE), that combines AI predictions with image electron signals to confidently segment membrane boundaries irrespective of the AI model used. We demonstrate the precision conferred by AIVE by applying it to the quantitative analysis of organelle interactomes from multiple FIB-SEM datasets. Through AIVE, we discover a previously unknown category of mitochondrial contact that we term the mitochondrial intrusion. We hypothesise that intrusions serve as anchors that stabilize MCS and promote organelle communication.

Published in Journal of Cell Biology (predicted rank #4) · training set

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 12%
14.9%
Similar papers in this journal
2
Nature Methods
○ 385 papers in training set
Top 1%
7.8%
Similar papers in this journal
3
Cell
○ 431 papers in training set
Top 0.6%
7.8%
Similar papers in this journal
Journal of Cell Biology · published here
● 392 papers in training set
Top 0.8%
6.7%
Similar papers in this journal
5
eLife
● 5828 papers in training set
Top 20%
6.2%
Similar papers in this journal
6
Nature Cell Biology
○ 118 papers in training set
Top 0.4%
5.5%
7
Advanced Science
○ 286 papers in training set
Top 1%
5.4%
50% of probability mass above
8
Science Advances
● 1243 papers in training set
Top 6%
4.8%
9
Science
● 477 papers in training set
Top 2%
4.8%
10
Nano Letters
● 71 papers in training set
Top 0.4%
3.2%
11
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 18%
3.1%
12
Nature Biotechnology
○ 172 papers in training set
Top 2%
2.4%
13
Communications Biology
○ 993 papers in training set
Top 9%
2.4%
14
Cell Reports Methods
○ 165 papers in training set
Top 1%
2.1%
15
Angewandte Chemie International Edition
○ 93 papers in training set
Top 1%
1.4%
16
Journal of Structural Biology
○ 64 papers in training set
Top 0.5%
1.3%
17
Cell Systems
○ 201 papers in training set
Top 4%
1.1%
18
Genome Biology
○ 637 papers in training set
Top 8%
1.0%
19
Current Biology
○ 665 papers in training set
Top 9%
1.0%
20
iScience
○ 1154 papers in training set
Top 32%
1.0%
21
PLOS Biology
● 486 papers in training set
Top 10%
0.9%
22
Developmental Cell
○ 196 papers in training set
Top 4%
0.8%
23
Cell Reports
○ 1498 papers in training set
Top 29%
0.6%
24
Molecular Biology of the Cell
● 311 papers in training set
Top 4%
0.6%
25
npj Imaging
○ 12 papers in training set
Top 0.3%
0.6%
26
Nature
○ 645 papers in training set
Top 12%
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.