Back

Unsupervised Spatial Embedded Deep Representation of Spatial Transcriptomics

Fu, H.; Xu, H.; Chong, K.; Li, M.; Ang, K. S.; Lee, H. K.; Lin, J.; Chen, A.; Shao, L.; Liu, L.; Chen, J.

2021-07-02 bioinformatics
10.1101/2021.06.15.448542 bioRxiv
Show abstract

Spatial transcriptomics enable us to dissect tissue heterogeneity and map out inter-cellular communications. Optimal integration of transcriptomics data and associated spatial information is essential towards fully exploiting the data. We present SEDR, an unsupervised spatially embedded deep representation of both transcript and spatial information. The SEDR pipeline uses a deep autoencoder to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder. We applied SEDR on human dorsolateral prefrontal cortex data and achieved better clustering accuracy, and correctly retraced the prenatal cortex development order with trajectory analysis. We also found the SEDR representation to be eminently suited for batch integration. Applying SEDR to human breast cancer data, we discerned heterogeneous sub-regions within a visually homogenous tumor region, identifying a tumor core with pro-inflammatory microenvironment and an outer ring region enriched with tumor associated macrophages which drives an immune suppressive microenvironment.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 3%
30.1%
Similar papers in this journal
2
Nature Methods
○ 385 papers in training set
Top 0.6%
14.6%
Similar papers in this journal
3
Genome Biology
○ 637 papers in training set
Top 3%
5.0%
Similar papers in this journal
4
Communications Biology
○ 993 papers in training set
Top 3%
4.2%
Similar papers in this journal
50% of probability mass above
5
Briefings in Bioinformatics
◐ 354 papers in training set
Top 2%
3.9%
Similar papers in this journal
6
Advanced Science
○ 286 papers in training set
Top 2%
3.9%
7
Bioinformatics
◐ 1204 papers in training set
Top 5%
3.1%
8
Nature Biotechnology
○ 172 papers in training set
Top 1%
3.1%
9
Cell Systems
○ 201 papers in training set
Top 2%
2.6%
10
Patterns
○ 78 papers in training set
Top 0.9%
2.3%
11
iScience
○ 1154 papers in training set
Top 12%
2.3%
12
Cell Reports Methods
○ 165 papers in training set
Top 1%
2.3%
13
Scientific Reports
○ 3612 papers in training set
Top 50%
1.8%
14
Nucleic Acids Research
◐ 1281 papers in training set
Top 9%
1.7%
15
Cell Reports
○ 1498 papers in training set
Top 19%
1.7%
16
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 33%
1.3%
17
Science Advances
● 1243 papers in training set
Top 26%
1.1%
18
PLOS Computational Biology
● 1863 papers in training set
Top 17%
1.1%
19
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
1.1%
20
npj Systems Biology and Applications
○ 125 papers in training set
Top 2%
1.0%
21
GigaScience
◐ 212 papers in training set
Top 5%
0.8%
22
Cell Genomics
○ 172 papers in training set
Top 5%
0.8%
23
Genome Research
● 468 papers in training set
Top 7%
0.8%
24
Molecular Systems Biology
○ 162 papers in training set
Top 4%
0.6%
25
eLife
● 5828 papers in training set
Top 72%
0.6%
26
Cell
○ 431 papers in training set
Top 12%
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.