Back

Spatially Resolved Gene Expression is Not Necessary for Identifying Spatial Domains

Lin, S.; Zhao, Y.; Yuan, Z.

2023-10-18 bioinformatics
10.1101/2023.10.15.562443 bioRxiv
Show abstract

The development of Spatially Resolved Transcriptomics (SRT) technologies has revolutionized the study of tissue organization. We introduce a graph convolutional network with an attention and positive emphasis mechanism, named "BINARY," relying exclusively on binarized SRT data to delineate spatial domains. BINARY outperforms existing methods across various SRT data types while using significantly less input information. Our study suggests that precise gene expression quantification may not always be essential, inspiring further exploration of the broader applications of spatially resolved binarized gene expression data.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 8%
19.0%
Similar papers in this journal
2
Bioinformatics
◐ 1204 papers in training set
Top 2%
13.3%
Similar papers in this journal
3
Nature Methods
○ 385 papers in training set
Top 0.7%
12.8%
Similar papers in this journal
4
Briefings in Bioinformatics
◐ 354 papers in training set
Top 0.6%
10.1%
Similar papers in this journal
50% of probability mass above
5
Nucleic Acids Research
◐ 1281 papers in training set
Top 2%
8.1%
Similar papers in this journal
6
Genome Biology
○ 637 papers in training set
Top 2%
6.4%
7
Cell Reports Methods
○ 165 papers in training set
Top 0.9%
2.5%
8
Patterns
○ 78 papers in training set
Top 0.9%
2.2%
9
Nature Machine Intelligence
○ 70 papers in training set
Top 1%
2.2%
10
Cell Systems
○ 201 papers in training set
Top 2%
2.2%
11
PLOS Computational Biology
● 1863 papers in training set
Top 14%
1.8%
12
Advanced Science
○ 286 papers in training set
Top 4%
1.8%
13
Communications Biology
○ 993 papers in training set
Top 16%
1.5%
14
Genome Research
● 468 papers in training set
Top 4%
1.5%
15
Bioinformatics Advances
◐ 203 papers in training set
Top 3%
1.5%
16
Nature Biotechnology
○ 172 papers in training set
Top 3%
1.2%
17
Nature Computational Science
○ 55 papers in training set
Top 1.0%
1.2%
18
iScience
○ 1154 papers in training set
Top 29%
1.1%
19
Scientific Reports
○ 3612 papers in training set
Top 68%
1.0%
20
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 4%
1.0%
21
GigaScience
◐ 212 papers in training set
Top 4%
0.9%

"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.