Back

Deep-learning deconvolution and segmentation of fluorescent membranes for high-precision bacterial cell-size profiling

Reyes-Matte, O.; Fortmann-Grote, C.; Gericke, B.; Hüttmann, N.; Ojkic, N.; Lopez-Garrido, J.

2025-10-27 cell biology
10.1101/2025.10.26.684635 bioRxiv
Show abstract

Evolutionary studies in bacteria have emphasized genetic and metabolic diversity, while cell-size variation has received less attention. Here we introduce MEDUSSA, a high-throughput method for precise bacterial cell-size profiling based on automatic segmentation of fluorescent membrane images, well suited to studying cell-size diversity. The approach couples deep-learning for mem-brane deconvolution and for cell segmentation with error-corrected cell measurement to extract accurate sizes from individual bacterial cells regardless of shape, size, chaining, or clustering. Our method overcomes limitations of phase-contrast segmentation, yielding reliable single-cell dimen-sions. We applied MEDUSSA to six strains of Priestia megaterium and found over twofold differ-ences in cell volume across strains, largely driven by differences in cell width. We identified a partially-functional PBP1 allele that underlies the reduced width of one strain. Together, these results demonstrate the power of comparative analyses in bacterial cell biology and expand the toolkit to investigate the evolution of bacterial cell size.

Published in Communications Biology (predicted rank #10) · training set

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
eLife
● 5828 papers in training set
Top 3%
18.4%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 18%
9.6%
Similar papers in this journal
3
Cell
○ 431 papers in training set
Top 0.6%
7.8%
Similar papers in this journal
4
Journal of Cell Biology
● 392 papers in training set
Top 0.8%
6.7%
Similar papers in this journal
5
Nature Methods
○ 385 papers in training set
Top 2%
5.5%
Similar papers in this journal
6
Cell Systems
○ 201 papers in training set
Top 1%
3.2%
50% of probability mass above
7
Journal of Cell Science
● 393 papers in training set
Top 2%
3.2%
8
Molecular Biology of the Cell
● 311 papers in training set
Top 1%
3.2%
9
Life Science Alliance
● 285 papers in training set
Top 2%
2.7%
Communications Biology · published here
○ 993 papers in training set
Top 8%
2.6%
11
Molecular Systems Biology
○ 162 papers in training set
Top 0.9%
2.6%
12
Cell Reports Methods
○ 165 papers in training set
Top 1%
2.1%
13
Cell Reports
○ 1498 papers in training set
Top 18%
1.9%
14
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 27%
1.7%
15
The EMBO Journal
○ 309 papers in training set
Top 3%
1.7%
16
Current Biology
○ 665 papers in training set
Top 7%
1.7%
17
Nature Biotechnology
○ 172 papers in training set
Top 3%
1.5%
18
PLOS Biology
● 486 papers in training set
Top 6%
1.4%
19
Developmental Cell
○ 196 papers in training set
Top 3%
1.3%
20
PLOS Computational Biology
● 1863 papers in training set
Top 17%
1.1%
21
iScience
○ 1154 papers in training set
Top 27%
1.1%
22
Molecular Cell
○ 350 papers in training set
Top 4%
1.1%
23
Scientific Reports
○ 3612 papers in training set
Top 67%
1.1%
24
Science Advances
● 1243 papers in training set
Top 27%
1.0%
25
Nature
○ 645 papers in training set
Top 10%
1.0%
26
Biology Open
● 156 papers in training set
Top 4%
0.8%
27
Science
● 477 papers in training set
Top 10%
0.6%
28
Genome Biology
○ 637 papers in training set
Top 10%
0.6%
29
New Phytologist
○ 346 papers in training set
Top 5%
0.6%
30
Bioinformatics
◐ 1204 papers in training set
Top 9%
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.