Back

Diffusion models learn underlying trends in actomyosin networks and predict behavior at unseen filament turnover

Rennert, E.; Behera, A. K.; Qiu, Y.; Vaikuntanathan, S.

2026-05-29 biophysics
10.64898/2026.05.26.727950 bioRxiv
Show abstract

Generative diffusion models have demonstrated an ability to produce novel images sampled from the learned underlying data distribution. These models are able to infer system characteristics for parameter combinations that were not seen during training. We investigate the ability of these models to infer trends in biological data from limited samples. Specifically, we consider the response of system scale behaviors such as cortical flow in a simulated actomyosin system as we tune filament turnover rates. We train a diffusion model on coarse grained actin curvature and density heatmap images, and are able to generate images from conditioning variables not seen during training. These images are predictive of nonlinear trends in the system. We also consider characteristics of the system that allows this level of inference, such as the strong linear relationship between average density and filament turnover in the system, and by exploring minimal underlying dynamics with a motor binding model.

Matching journals

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

1
PLOS Computational Biology
1633 papers in training set
Top 0.1%
41.6%
2
Physical Biology
43 papers in training set
Top 0.1%
6.6%
3
Journal of The Royal Society Interface
189 papers in training set
Top 0.5%
6.6%
50% of probability mass above
4
Nature Communications
4913 papers in training set
Top 35%
4.5%
5
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 16%
4.5%
6
Biophysical Journal
545 papers in training set
Top 1%
3.8%
7
Scientific Reports
3102 papers in training set
Top 32%
3.8%
8
PLOS ONE
4510 papers in training set
Top 46%
2.2%
9
Molecular Biology of the Cell
272 papers in training set
Top 1%
2.0%
10
eLife
5422 papers in training set
Top 37%
2.0%
11
Physical Review X
23 papers in training set
Top 0.2%
1.8%
12
Cell Reports
1338 papers in training set
Top 28%
1.3%
13
Development
440 papers in training set
Top 3%
0.8%
14
Journal of Theoretical Biology
144 papers in training set
Top 2%
0.8%
15
Physical Review E
95 papers in training set
Top 1%
0.8%
16
Cell Systems
167 papers in training set
Top 12%
0.8%
17
Journal of the Royal Society Interface
18 papers in training set
Top 0.2%
0.7%
18
Neural Computation
36 papers in training set
Top 0.8%
0.7%
19
Bulletin of Mathematical Biology
84 papers in training set
Top 2%
0.7%
20
Biomechanics and Modeling in Mechanobiology
25 papers in training set
Top 1%
0.5%
21
Communications Biology
886 papers in training set
Top 31%
0.5%
22
eneuro
389 papers in training set
Top 10%
0.5%
23
iScience
1063 papers in training set
Top 39%
0.5%
24
Nature Methods
336 papers in training set
Top 7%
0.5%