Back

DeepFace: A High-Precision and Scalable Deep Learning Pipeline for Predicting Large-Scale Brain Activity from Facial Dynamics in Mice

Ozdemirli, K.; Connor, T.; Lacin, M. E.; Kim, K.; Maldonado, M.; Peixoto, T. L.; oksuz, c.; mata, i.; Yildirim, M.

2025-06-15 neuroscience
10.1101/2025.06.10.658952 bioRxiv
Show abstract

We present DeepFace, a next-generation facial analysis pipeline that enhances orofacial tracking and cortical activity prediction in mice. Rather than replacing existing tools, DeepFace builds upon DeepLabCut and Facemap to address scalability bottlenecks and improve behavioral quantification. It offers high precision, keypoint customization, and robust performance across GCaMP6s, GCaMP6f, and jGCaMP8m lines. With scalable batch processing and high-performance computing compatibility, DeepFace enables high-throughput brain-behavior analysis in large-scale preclinical neuroscience.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Nature Methods
○ 385 papers in training set
Top 0.3%
21.7%
Similar papers in this journal
2
Journal of Neuroscience Methods
○ 122 papers in training set
Top 0.1%
9.6%
Similar papers in this journal
3
Neurophotonics
● 42 papers in training set
Top 0.1%
7.8%
Similar papers in this journal
4
eneuro
● 439 papers in training set
Top 0.5%
7.8%
Similar papers in this journal
5
Nature Communications
○ 5641 papers in training set
Top 27%
5.4%
Similar papers in this journal
50% of probability mass above
6
eLife
● 5828 papers in training set
Top 28%
4.3%
7
Scientific Data
○ 209 papers in training set
Top 0.7%
3.4%
8
Scientific Reports
○ 3612 papers in training set
Top 29%
3.4%
9
Communications Biology
○ 993 papers in training set
Top 6%
3.2%
10
Cell Reports Methods
○ 165 papers in training set
Top 0.8%
2.7%
11
Science Advances
● 1243 papers in training set
Top 15%
2.4%
12
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 22%
2.4%
13
Neuron
○ 337 papers in training set
Top 3%
2.1%
14
Imaging Neuroscience
● 282 papers in training set
Top 3%
1.7%
15
Nature Neuroscience
○ 252 papers in training set
Top 3%
1.7%
16
Journal of Visualized Experiments
● 34 papers in training set
Top 0.3%
1.7%
17
Cell Reports
○ 1498 papers in training set
Top 23%
1.1%
18
PLOS Computational Biology
● 1863 papers in training set
Top 17%
1.1%
19
PLOS Biology
● 486 papers in training set
Top 8%
1.1%
20
PLOS ONE
● 5266 papers in training set
Top 55%
1.0%
21
Nature
○ 645 papers in training set
Top 9%
1.0%
22
Advanced Science
○ 286 papers in training set
Top 8%
1.0%
23
Nature Protocols
○ 33 papers in training set
Top 0.5%
0.8%
24
Nature Biomedical Engineering
○ 47 papers in training set
Top 2%
0.8%
25
iScience
○ 1154 papers in training set
Top 37%
0.8%
26
NeuroImage
○ 903 papers in training set
Top 6%
0.6%
27
Journal of Neurophysiology
● 302 papers in training set
Top 4%
0.6%
28
Nature Biotechnology
○ 172 papers in training set
Top 5%
0.6%
29
Patterns
○ 78 papers in training set
Top 3%
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.