Back

Interpretable spatial cell learning enhances the characterization of patient tissue microenvironments with highly multiplexed imaging data

Lu, P.; Oetjen, K.; Oh, S.; Thorek, D. L.

2023-03-28 bioinformatics
10.1101/2023.03.26.534306 bioRxiv
Show abstract

Multiplexed imaging technologies enable highly resolved spatial characterization of cellular environments. However, exploiting these rich spatial cell datasets for biological insight is a considerable analytical challenge. In particular, effective approaches to define disease-specific microenvironments on the basis of clinical outcomes is a complex problem with immediate pathological value. Here we present InterSTELLAR, a geometric deep learning framework for multiplexed imaging data, to directly link tissue subtypes with corresponding cell communities that have clinical relevance. Using a publicly available breast cancer imaging mass cytometry dataset, InterSTELLAR allows simultaneous tissue type prediction and interested community detection, with improved performance over conventional methods. Downstream analyses demonstrate InterSTELLAR is able to capture specific pathological features from different clinical cancer subtypes. The method is able to reveal potential relationships between these regions and patient prognosis. InterSTELLAR represents an application of geometric deep learning with direct benefits for extracting enhanced microenvironment characterization for multiplexed imaging of patient samples.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 5%
26.1%
Similar papers in this journal
2
Advanced Science
○ 286 papers in training set
Top 0.1%
14.8%
Similar papers in this journal
3
Briefings in Bioinformatics
◐ 354 papers in training set
Top 2%
5.4%
Similar papers in this journal
4
Communications Biology
○ 993 papers in training set
Top 2%
4.8%
Similar papers in this journal
50% of probability mass above
5
Cell Systems
○ 201 papers in training set
Top 2%
3.2%
6
Bioinformatics
◐ 1204 papers in training set
Top 5%
3.2%
Similar papers in this journal
7
Nature Methods
○ 385 papers in training set
Top 3%
2.6%
8
Science Advances
● 1243 papers in training set
Top 16%
2.3%
9
npj Precision Oncology
○ 53 papers in training set
Top 0.7%
2.3%
10
Genome Biology
○ 637 papers in training set
Top 5%
2.3%
11
PLOS Computational Biology
● 1863 papers in training set
Top 13%
2.1%
12
iScience
○ 1154 papers in training set
Top 15%
1.9%
13
Small Methods
○ 29 papers in training set
Top 0.2%
1.9%
14
Patterns
○ 78 papers in training set
Top 1%
1.9%
15
Genome Medicine
○ 183 papers in training set
Top 3%
1.7%
16
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 29%
1.7%
17
Scientific Reports
○ 3612 papers in training set
Top 57%
1.5%
18
Genomics, Proteomics & Bioinformatics
188 papers in training set
Top 1%
1.3%
19
PNAS Nexus
◐ 159 papers in training set
Top 2%
1.1%
20
eLife
● 5828 papers in training set
Top 60%
1.1%
21
Cell Reports Methods
○ 165 papers in training set
Top 3%
1.0%
22
Nature Biomedical Engineering
○ 47 papers in training set
Top 2%
1.0%
23
Nucleic Acids Research
◐ 1281 papers in training set
Top 13%
0.9%
24
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
0.9%
25
Nature Biotechnology
○ 172 papers in training set
Top 4%
0.8%
26
Cell Reports
○ 1498 papers in training set
Top 27%
0.8%
27
PLOS ONE
● 5266 papers in training set
Top 63%
0.6%
28
GigaScience
◐ 212 papers in training set
Top 5%
0.6%
29
npj Systems Biology and Applications
○ 125 papers in training set
Top 2%
0.6%
30
Biomaterials
○ 84 papers in training set
Top 2%
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.