Back

Generalized cell phenotyping for spatial proteomics with language-informed vision models

Wang, X.; Dilip, R.; Iqbal, A. R.; Bussi, Y.; Brown, C.; Pradhan, E.; Jain, Y.; Yu, K.; Li, S.; Abt, M.; Borner, K.; Keren, L.; Yue, Y.; Barnowski, R.; Van Valen, D. A.

2025-08-22 bioinformatics
10.1101/2024.11.02.621624 bioRxiv
Show abstract

We present DeepCell Types, a novel approach to cell phenotyping for spatial proteomics that addresses the challenge of generalization across diverse datasets with varying marker panels collected across different platforms. Our approach utilizes a transformer with channel-wise attention to create a language-informed vision model; this models semantic understanding of the underlying marker panel enables it to learn from and adapt to heterogeneous datasets. Leveraging a curated, diverse dataset named Expanded TissueNet with cell type labels spanning the literature and the NIH Human BioMolecular Atlas Program (HuBMAP) consortium, our model demonstrates robust performance across various cell types, tissues, and imaging modalities. Comprehensive benchmarking shows superior accuracy and generalizability of our method compared to existing methods. This work significantly advances automated spatial proteomics analysis, offering a generalizable and scalable solution for cell phenotyping that meets the demands of multiplexed imaging data.

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%
41.1%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 11%
15.7%
Similar papers in this journal
50% of probability mass above
3
Cell Systems
○ 201 papers in training set
Top 0.3%
8.2%
Similar papers in this journal
4
Nature Machine Intelligence
○ 70 papers in training set
Top 0.2%
7.6%
Similar papers in this journal
5
Nature Biotechnology
○ 172 papers in training set
Top 1%
4.2%
Similar papers in this journal
6
Molecular Systems Biology
○ 162 papers in training set
Top 1%
1.8%
7
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.8%
8
PLOS Computational Biology
● 1863 papers in training set
Top 15%
1.6%
9
Briefings in Bioinformatics
◐ 354 papers in training set
Top 5%
1.4%
10
Cell
○ 431 papers in training set
Top 7%
1.4%
11
Nature Biomedical Engineering
○ 47 papers in training set
Top 1%
1.4%
12
Patterns
○ 78 papers in training set
Top 2%
1.2%
13
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 36%
1.1%
14
Genome Biology
○ 637 papers in training set
Top 8%
1.1%
15
Nature
○ 645 papers in training set
Top 10%
0.9%
16
Science Advances
● 1243 papers in training set
Top 32%
0.6%
17
Communications Biology
○ 993 papers in training set
Top 33%
0.6%
18
Nature Chemical Biology
○ 119 papers in training set
Top 4%
0.5%
19
Advanced Science
○ 286 papers in training set
Top 12%
0.5%
20
Cell Reports Methods
○ 165 papers in training set
Top 5%
0.5%
21
Nucleic Acids Research
◐ 1281 papers in training set
Top 16%
0.5%

"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.