Back

Multi-channel high-density single-molecule localization

Sha, H.; Muller, L.-R.; Castillo Duque de Estrada, N. M.; Mathieu, M.; Jaques, A.; Marin, Z.; Zhang, Y.; Macke, J. H.; Ries, J.

2026-07-26 biophysics
10.64898/2026.07.24.740199 bioRxiv
Show abstract

Deep learning has enabled single-molecule localization microscopy (SMLM) at high emitter densities, but only for single channel systems. Here we present DECODE-Plex, a deep-learning-based framework to localize dense single molecules with overlapping point spread functions simultaneously in multiple channels. We showcase DECODE-Plex on experimental ultra-high density dual-color and 3D live-cell data. Packaged for ease of use, it will enable many groups to improve imaging speed and quality of multi-channel SMLM.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

1
Nature Methods
○ 385 papers in training set
Top 0.1%
38.3%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 5%
25.7%
Similar papers in this journal
50% of probability mass above
3
Communications Biology
○ 993 papers in training set
Top 2%
5.0%
Similar papers in this journal
4
eLife
● 5828 papers in training set
Top 41%
2.6%
Similar papers in this journal
5
Nature Biotechnology
○ 172 papers in training set
Top 2%
2.6%
Similar papers in this journal
6
Light: Science & Applications
○ 16 papers in training set
Top 0.1%
2.3%
7
Nature Photonics
○ 10 papers in training set
Top 0.1%
1.8%
8
ACS Photonics
● 13 papers in training set
Top 0.1%
1.8%
9
Scientific Reports
○ 3612 papers in training set
Top 59%
1.4%
10
Nature Biomedical Engineering
○ 47 papers in training set
Top 1%
1.1%
11
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 36%
1.1%
12
Nature Protocols
○ 33 papers in training set
Top 0.5%
1.0%
13
ACS Nano
● 113 papers in training set
Top 2%
1.0%
14
Science Advances
● 1243 papers in training set
Top 29%
0.9%
15
Biophysical Reports
○ 37 papers in training set
Top 0.5%
0.8%
16
Biophysical Journal
○ 631 papers in training set
Top 4%
0.8%
17
npj Imaging
○ 12 papers in training set
Top 0.2%
0.8%
18
Optica
● 27 papers in training set
Top 0.3%
0.6%
19
Cell Reports Methods
○ 165 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.