SCTransform tutorial

[NoaKarp]

Hi Seurat team and community,
I'm a new user learning Seurat by following the tutorials. I'm currently focusing on the SCTransform tutorial, and I’ve run into a problem. When I run the code exactly as shown in the tutorial, I get a different (but similar) DimPlot than what’s shown on the website.
I'm running this code:

# store mitochondrial percentage in object meta data
pbmc <- PercentageFeatureSet(pbmc, pattern = "^MT-", col.name = "percent.mt")

# run sctransform
pbmc <- SCTransform(pbmc, vars.to.regress = "percent.mt", verbose = FALSE)

pbmc <- RunPCA(pbmc, verbose = FALSE)
pbmc <- RunUMAP(pbmc, dims = 1:30, verbose = FALSE)

pbmc <- FindNeighbors(pbmc, dims = 1:30, verbose = FALSE)
pbmc <- FindClusters(pbmc, verbose = FALSE)

DimPlot(pbmc, label = TRUE)

This is the plot I'm getting:

and this is the plot on the website:

Seurat version: 5.3.0
R version: 4.5.0
Tutorial link: https://satijalab.org/seurat/articles/sctransform_vignette

I'm not sure what I'm doing wrong, and I would really appreciate any help or guidance.

Thanks so much.
Noa

[EZUY]

Your UMAP plot has the same clusters as the tutorial, but the axis is flipped — UMAP_1/2 is mirrored (positive vs negative).
UMAP orientation can rotate or flip because it only preserves relative distances.
I assume this is due to random seed