Back

The 3D point spread function can be autoencoded in latent space

Truedson, A.; Gras, K.; Elf, J.

2024-10-15 biophysics
10.1101/2024.10.14.618231 bioRxiv
Show abstract

The 3D point spread function of a fluorescence emitter in a living cell is often different from that of the z-stack of bead images typically used as a reference. Here we show that the location in z of a fluorescent emitter can be directly accessed in the latent space of an autoencoder trained on the sample images without z-reference data. The corresponding decoding network represents an accurate point spread function.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

1
Nature Methods
○ 385 papers in training set
Top 0.3%
22.3%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 11%
15.3%
Similar papers in this journal
3
Scientific Reports
○ 3612 papers in training set
Top 6%
8.0%
Similar papers in this journal
4
Communications Biology
○ 993 papers in training set
Top 2%
5.2%
Similar papers in this journal
50% of probability mass above
5
eLife
● 5828 papers in training set
Top 30%
4.1%
Similar papers in this journal
6
Nature Protocols
○ 33 papers in training set
Top 0.1%
3.6%
7
Biophysical Journal
○ 631 papers in training set
Top 2%
3.3%
8
Journal of Microscopy
○ 20 papers in training set
Top 0.1%
2.4%
9
SLAS Discovery
○ 25 papers in training set
Top 0.1%
1.8%
10
Science Advances
● 1243 papers in training set
Top 20%
1.7%
11
Molecular Biology of the Cell
● 311 papers in training set
Top 2%
1.5%
12
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 31%
1.5%
13
PLOS ONE
● 5266 papers in training set
Top 50%
1.4%
14
Lab on a Chip
● 96 papers in training set
Top 0.7%
1.4%
15
The Journal of Physical Chemistry B
● 167 papers in training set
Top 1%
1.4%
16
ACS Nano
● 113 papers in training set
Top 1%
1.4%
17
Biophysical Reports
○ 37 papers in training set
Top 0.3%
1.1%
18
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.1%
19
Wellcome Open Research
○ 67 papers in training set
Top 0.7%
1.1%
20
Methods
○ 34 papers in training set
Top 0.5%
1.1%
21
Light: Science & Applications
○ 16 papers in training set
Top 0.3%
0.9%
22
ACS Photonics
● 13 papers in training set
Top 0.2%
0.9%
23
Nature Photonics
○ 10 papers in training set
Top 0.1%
0.6%
24
npj Imaging
○ 12 papers in training set
Top 0.3%
0.6%
25
iScience
○ 1154 papers in training set
Top 40%
0.6%
26
Small Methods
○ 29 papers in training set
Top 0.8%
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.