stew

Uncover spatially informed variations underlying single-cell spatial transcriptomics with STew.

https://github.com/fanzhanglab/stew

Repository

Uncover spatially informed variations underlying single-cell spatial transcriptomics with STew.

README.Rmd

---
output: github_document
---



```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
```

# STew 

[![R-CMD-check](https://github.com/fanzhanglab/STew/actions/workflows/check-standard.yaml/badge.svg)](https://github.com/fanzhanglab/STew/actions/workflows/check-standard.yaml)
![](https://komarev.com/ghpvc/?username=fanzhanglab&style=flat-square&color=green)




We introduce STew, a Spatial Transcriptomic multi-viEW representation learning method, or STew, to jointly characterize the gene expression variation and spatial information in the shared low-dimenion space in a scalable manner. STew will output distinct spatially informed cell gradients, robust clusters, and statistical goodness of model fit to reveal significant genes that reflect subtle spatial niches in complex tissues.








## Installation

You can install the STew Package from
[GitHub](https://github.com/fanzhanglab/STew/) using the devtools as
follows:

``` r
# install.packages("devtools")
devtools::install_github("fanzhanglab/STew")
```
(OR)

``` r
remotes::install_github("fanzhanglab/STew")
```



### Dependencies / Other required packages

- R (\>= 4.2)
- MERINGUE (\>= 1.0)
- loe (\>= 1.1)
- Matrix (\>= 1.5.4)
- ggplot2 (\>= 3.4.2)
- ggpubr (\>= 0.6.0)
- Seurat (\>= 4.3.0)
- future.apply (\>= 1.10.0)
- RANN (\>= 2.6.1)
- sctransform
- tibble




## Tutorials

**Step-by-step notebook** of applying STew on identifying spatially informed low-dimensional embeddings and spatially aware clusters on the 10X Visium Human Brain Data (DLPFC):

-  Tutorial of applying STew on DLPFC data 
-  Tutorial of count data modelling 




#### Below are several major steps of running STew:

``` r
# Create a new STew object for the loaded spatial transcriptomic data
STew = STew_Obj(count = dlpfc$count_exp,
                  spatial = dlpfc$spatial)
```
... (skip several preprocessing steps) ...

``` r
# permute optimal penalty parameters
STew <- parallel_cca_permute(x = STew$exp_adj_matrix, z = STew$adj_matrix, obj = STew, nperms=50, niter=3)
```

``` r
# Perform sparse CCA based on the optimal penalty parameters
STew <- cca_main(x = STew$exp_adj_matrix, z = STew$adj_matrix, obj = STew, K=20, penaltyx=STew$bestpenaltyx, penaltyz=STew$bestpenaltyz, v=STew$v.init)
```

``` r
gradient_plot <- spatial_gradient(STew)
gradient_plot[1:5]
```




 

``` r
cluster_plot <- plot_cluster(coordis = spatial, label = cluster$res_0.30, colors = colors, t="Cell clusters based on STew")
cluster_plot
```






``` r
# Save the main results into the STew object
saveRDS(STew, file="STew_10x_human_dlpfc_no.rds")
```





#### Benchmarcking STew with other algorithms:







## Citations

Guo, N., Vargas, J., Fritz, D., Krishna, R., Zhang, F. Uncover spatially informed shared variations underlying single-cell spatial transcriptomics with STew, [*bioRxiv*](link), 2023




## Help, Suggestion and Contribution

Using github [**issues**](https://github.com/fanzhanglab/STew/issues)
section, if you have any question, comments, suggestions, or to report
coding related issues of STew is highly encouranged than sending
emails.

- Please **check the GitHub
  [issues](https://github.com/fanzhanglab/STew/issues)** for similar
  issues that has been reported and resolved. This helps the team to
  focus on adding new features and working on cool projects instead of
  resolving the same issues!
- **Examples** are required when filing a GitHub issue. In certain
  cases, please share your STew object and related codes to understand
  the issues.
  



## Contact 

Please contact [fanzhanglab@gmail.com](fanzhanglab@gmail.com) for further questions or protential collaborative opportunities!

Owner

Citation (citation.cff)

cff-version: 1.0.3
message: "If you use this software, please cite it using the following reference."
authors:
  - family-names: Guo
    given-names: N.
  - family-names: Vargas
    given-names: J.
  - family-names: Reynoso
    given-names: S.
  - family-names: Fritz
    given-names: D.
  - family-names: Krishna
    given-names: R.
  - family-names: Wang
    given-names: C.
  - family-names: Zhang
    given-names: F.
title: "Uncover spatially informed variations for single-cell spatial transcriptomics with STew"
date-released: 2024
url: "https://doi.org/10.1093/bioadv/vbae064"
journal: "Bioinformatics Advances"
doi: "10.1093/bioadv/vbae064"

GitHub Events