Back

SpotMAX: a generalist framework for multi-dimensional automatic spot detection and quantification

Padovani, F.; Cavka, I.; Neves, A. R. R.; Lopez, C. P.; Al-Refaie, N.; Bolcato, L.; Chatzitheodoridou, D.; Chadha, Y.; Su, X. A.; Lengefeld, J.; Cabianca, D. S.; Köhler, S.; Schmoller, K. M.

2024-10-23 cell biology Community evaluation
10.1101/2024.10.22.619610 bioRxiv
Show abstract

The analysis of spot-like structures is a widespread task in microscopy-based cell biology. Existing solutions are typically specific to single applications and do not use multi-dimensional information from 5D datasets. Therefore, experimental scientists often resort to subjective manual annotation. Here, we present SpotMAX, a generalist AI-driven framework for automated spot detection and quantification. SpotMAX leverages the full scope of multi-dimensional datasets with an easy-to-use interface and an embedded framework for cell segmentation and tracking. SpotMAX outperforms state-of-the-art tools, and in some cases, even expert human annotators. We applied SpotMAX across diverse experimental questions, ranging from meiotic crossover events in C. elegans to mitochondrial DNA dynamics in S. cerevisiae and telomere length in mouse stem cells, leading to new biological insights. With its flexibility in integrating AI workflows, we anticipate that SpotMAX will become the standard for spot analysis in microscopy data. Source code: https://github.com/SchmollerLab/SpotMAX

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 0.8%
39.5%
Similar papers in this journal
2
Nature Methods
○ 385 papers in training set
Top 1%
7.9%
Similar papers in this journal
3
Communications Biology
○ 993 papers in training set
Top 1%
6.2%
Similar papers in this journal
50% of probability mass above
4
eLife
● 5828 papers in training set
Top 22%
5.5%
Similar papers in this journal
5
Nature Cell Biology
○ 118 papers in training set
Top 0.7%
4.4%
Similar papers in this journal
6
Journal of Cell Biology
● 392 papers in training set
Top 2%
2.6%
7
Molecular Systems Biology
○ 162 papers in training set
Top 1.0%
2.4%
8
Nucleic Acids Research
◐ 1281 papers in training set
Top 7%
2.1%
9
Life Science Alliance
● 285 papers in training set
Top 2%
2.1%
10
Genome Biology
○ 637 papers in training set
Top 5%
2.1%
11
Scientific Reports
○ 3612 papers in training set
Top 46%
2.1%
12
Cell Reports Methods
○ 165 papers in training set
Top 1%
1.7%
13
Nature Biotechnology
○ 172 papers in training set
Top 2%
1.7%
14
Science Advances
● 1243 papers in training set
Top 19%
1.7%
15
iScience
○ 1154 papers in training set
Top 19%
1.7%
16
Nature
○ 645 papers in training set
Top 7%
1.5%
17
The EMBO Journal
○ 309 papers in training set
Top 4%
1.3%
18
Cell Reports
○ 1498 papers in training set
Top 23%
1.1%
19
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 37%
1.0%
20
Nature Structural & Molecular Biology
236 papers in training set
Top 3%
0.8%
21
PLOS Biology
● 486 papers in training set
Top 11%
0.8%
22
BMC Biology
○ 265 papers in training set
Top 5%
0.8%
23
Cell Systems
○ 201 papers in training set
Top 5%
0.6%
24
Current Biology
○ 665 papers in training set
Top 11%
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.