scRNA toturial
KJY
2022-05-31
Setup
Reference:
https://satijalab.org/seurat/articles/pbmc3k_tutorial.html
download data from here:
https://cf.10xgenomics.com/samples/cell/pbmc3k/pbmc3k_filtered_gene_bc_matrices.tar.gz
put it in my own folder
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(Seurat)## Attaching SeuratObject## Attaching splibrary(patchwork)The Read10X() function reads in the output of the cellranger pipeline from 10X, returning a unique molecular identified (UMI) count matrix.
The values in this matrix represent the number of molecules for each feature (i.e. gene; row) that are detected in each cell (column).
# Load the PBMC dataset
pbmc.data <- Read10X(data.dir = "../data/pbmc3k/filtered_gene_bc_matrices/hg19/")
# Initialize the Seurat object with the raw (non-normalized data).
pbmc <- CreateSeuratObject(counts = pbmc.data, project = "pbmc3k", min.cells = 3, min.features = 200)## Warning: Feature names cannot have underscores ('_'), replacing with dashes
## ('-')pbmc## An object of class Seurat
## 13714 features across 2700 samples within 1 assay
## Active assay: RNA (13714 features, 0 variable features)# Lets examine a few genes in the first thirty cells
pbmc.data[c("CD3D", "TCL1A", "MS4A1"), 1:30]## 3 x 30 sparse Matrix of class "dgCMatrix"## [[ suppressing 30 column names 'AAACATACAACCAC-1', 'AAACATTGAGCTAC-1', 'AAACATTGATCAGC-1' ... ]]##
## CD3D 4 . 10 . . 1 2 3 1 . . 2 7 1 . . 1 3 . 2 3 . . . . . 3 4 1 5
## TCL1A . . . . . . . . 1 . . . . . . . . . . . . 1 . . . . . . . .
## MS4A1 . 6 . . . . . . 1 1 1 . . . . . . . . . 36 1 2 . . 2 . . . .pre-processing workflow
# Show QC metrics for the first 5 cells
head(pbmc@meta.data, 5)## orig.ident nCount_RNA nFeature_RNA
## AAACATACAACCAC-1 pbmc3k 2419 779
## AAACATTGAGCTAC-1 pbmc3k 4903 1352
## AAACATTGATCAGC-1 pbmc3k 3147 1129
## AAACCGTGCTTCCG-1 pbmc3k 2639 960
## AAACCGTGTATGCG-1 pbmc3k 980 521# The [[ operator can add columns to object metadata. This is a great place to stash QC stats
pbmc[["percent.mt"]] <- PercentageFeatureSet(pbmc, pattern = "^MT-")# Visualize QC metrics as a violin plot
VlnPlot(pbmc, features = c("nFeature_RNA", "nCount_RNA", "percent.mt"), ncol = 3)
# filter cells that have unique feature counts over 2,500 or less than 200
# filter cells that have >5% mitochondrial counts
pbmc <- subset(pbmc, subset = nFeature_RNA > 200 & nFeature_RNA < 2500 & percent.mt < 5)# global-scaling normalization method “LogNormalize” that normalizes the feature expression measurements for each cell by the total expression, multiplies this by a scale factor (10,000 by default), and log-transforms the result. Normalized values are stored in pbmc[["RNA"]]@data.
pbmc <- NormalizeData(pbmc, normalization.method = "LogNormalize", scale.factor = 10000)pbmc <- FindVariableFeatures(pbmc, selection.method = "vst", nfeatures = 2000)
# Identify the 10 most highly variable genes
top10 <- head(VariableFeatures(pbmc), 10)
# plot variable features with and without labels
plot1 <- VariableFeaturePlot(pbmc)
plot2 <- LabelPoints(plot = plot1, points = top10, repel = TRUE)## When using repel, set xnudge and ynudge to 0 for optimal resultsplot1 + plot2## Warning: Transformation introduced infinite values in continuous x-axis## Warning: Removed 1 rows containing missing values (geom_point).## Warning: Transformation introduced infinite values in continuous x-axis## Warning: Removed 1 rows containing missing values (geom_point).
# scaling step
# Shifts the expression of each gene, so that the mean expression across cells is 0
# Scales the expression of each gene, so that the variance across cells is 1
# This step gives equal weight in downstream analyses, so that highly-expressed genes do not dominate
all.genes <- rownames(pbmc)
head(all.genes)## [1] "AL627309.1" "AP006222.2" "RP11-206L10.2" "RP11-206L10.9"
## [5] "LINC00115" "NOC2L"pbmc <- ScaleData(pbmc, features = all.genes)## Centering and scaling data matrixpbmc <- RunPCA(pbmc, features = VariableFeatures(object = pbmc))## PC_ 1
## Positive: CST3, TYROBP, LST1, AIF1, FTL, FTH1, LYZ, FCN1, S100A9, TYMP
## FCER1G, CFD, LGALS1, S100A8, CTSS, LGALS2, SERPINA1, IFITM3, SPI1, CFP
## PSAP, IFI30, SAT1, COTL1, S100A11, NPC2, GRN, LGALS3, GSTP1, PYCARD
## Negative: MALAT1, LTB, IL32, IL7R, CD2, B2M, ACAP1, CD27, STK17A, CTSW
## CD247, GIMAP5, AQP3, CCL5, SELL, TRAF3IP3, GZMA, MAL, CST7, ITM2A
## MYC, GIMAP7, HOPX, BEX2, LDLRAP1, GZMK, ETS1, ZAP70, TNFAIP8, RIC3
## PC_ 2
## Positive: CD79A, MS4A1, TCL1A, HLA-DQA1, HLA-DQB1, HLA-DRA, LINC00926, CD79B, HLA-DRB1, CD74
## HLA-DMA, HLA-DPB1, HLA-DQA2, CD37, HLA-DRB5, HLA-DMB, HLA-DPA1, FCRLA, HVCN1, LTB
## BLNK, P2RX5, IGLL5, IRF8, SWAP70, ARHGAP24, FCGR2B, SMIM14, PPP1R14A, C16orf74
## Negative: NKG7, PRF1, CST7, GZMB, GZMA, FGFBP2, CTSW, GNLY, B2M, SPON2
## CCL4, GZMH, FCGR3A, CCL5, CD247, XCL2, CLIC3, AKR1C3, SRGN, HOPX
## TTC38, APMAP, CTSC, S100A4, IGFBP7, ANXA1, ID2, IL32, XCL1, RHOC
## PC_ 3
## Positive: HLA-DQA1, CD79A, CD79B, HLA-DQB1, HLA-DPB1, HLA-DPA1, CD74, MS4A1, HLA-DRB1, HLA-DRA
## HLA-DRB5, HLA-DQA2, TCL1A, LINC00926, HLA-DMB, HLA-DMA, CD37, HVCN1, FCRLA, IRF8
## PLAC8, BLNK, MALAT1, SMIM14, PLD4, LAT2, IGLL5, P2RX5, SWAP70, FCGR2B
## Negative: PPBP, PF4, SDPR, SPARC, GNG11, NRGN, GP9, RGS18, TUBB1, CLU
## HIST1H2AC, AP001189.4, ITGA2B, CD9, TMEM40, PTCRA, CA2, ACRBP, MMD, TREML1
## NGFRAP1, F13A1, SEPT5, RUFY1, TSC22D1, MPP1, CMTM5, RP11-367G6.3, MYL9, GP1BA
## PC_ 4
## Positive: HLA-DQA1, CD79B, CD79A, MS4A1, HLA-DQB1, CD74, HLA-DPB1, HIST1H2AC, PF4, TCL1A
## SDPR, HLA-DPA1, HLA-DRB1, HLA-DQA2, HLA-DRA, PPBP, LINC00926, GNG11, HLA-DRB5, SPARC
## GP9, AP001189.4, CA2, PTCRA, CD9, NRGN, RGS18, GZMB, CLU, TUBB1
## Negative: VIM, IL7R, S100A6, IL32, S100A8, S100A4, GIMAP7, S100A10, S100A9, MAL
## AQP3, CD2, CD14, FYB, LGALS2, GIMAP4, ANXA1, CD27, FCN1, RBP7
## LYZ, S100A11, GIMAP5, MS4A6A, S100A12, FOLR3, TRABD2A, AIF1, IL8, IFI6
## PC_ 5
## Positive: GZMB, NKG7, S100A8, FGFBP2, GNLY, CCL4, CST7, PRF1, GZMA, SPON2
## GZMH, S100A9, LGALS2, CCL3, CTSW, XCL2, CD14, CLIC3, S100A12, CCL5
## RBP7, MS4A6A, GSTP1, FOLR3, IGFBP7, TYROBP, TTC38, AKR1C3, XCL1, HOPX
## Negative: LTB, IL7R, CKB, VIM, MS4A7, AQP3, CYTIP, RP11-290F20.3, SIGLEC10, HMOX1
## PTGES3, LILRB2, MAL, CD27, HN1, CD2, GDI2, ANXA5, CORO1B, TUBA1B
## FAM110A, ATP1A1, TRADD, PPA1, CCDC109B, ABRACL, CTD-2006K23.1, WARS, VMO1, FYB# Examine and visualize PCA results a few different ways
print(pbmc[["pca"]], dims = 1:5, nfeatures = 5)## PC_ 1
## Positive: CST3, TYROBP, LST1, AIF1, FTL
## Negative: MALAT1, LTB, IL32, IL7R, CD2
## PC_ 2
## Positive: CD79A, MS4A1, TCL1A, HLA-DQA1, HLA-DQB1
## Negative: NKG7, PRF1, CST7, GZMB, GZMA
## PC_ 3
## Positive: HLA-DQA1, CD79A, CD79B, HLA-DQB1, HLA-DPB1
## Negative: PPBP, PF4, SDPR, SPARC, GNG11
## PC_ 4
## Positive: HLA-DQA1, CD79B, CD79A, MS4A1, HLA-DQB1
## Negative: VIM, IL7R, S100A6, IL32, S100A8
## PC_ 5
## Positive: GZMB, NKG7, S100A8, FGFBP2, GNLY
## Negative: LTB, IL7R, CKB, VIM, MS4A7VizDimLoadings(pbmc, dims = 1:2, reduction = "pca")
DimPlot(pbmc, reduction = "pca")
# total cell is 500
DimHeatmap(pbmc, dims = 1:15, cells = 500, balanced = TRUE)
JackStraw method: Randomly permutes a subset of data, and calculates projected PCA scores for these ‘random’ genes. Then compares the PCA scores for the ‘random’ genes with the observed PCA scores to determine statistical signifance. End result is a p-value for each gene’s association with each principal component.
# NOTE: This process can take a long time for big datasets, comment out for expediency. More
# approximate techniques such as those implemented in ElbowPlot() can be used to reduce
# computation time
pbmc <- JackStraw(pbmc, num.replicate = 100)
pbmc <- ScoreJackStraw(pbmc, dims = 1:20)JackStrawPlot(pbmc, dims = 1:15)## Warning: Removed 23496 rows containing missing values (geom_point).
‘Elbow plot’: a ranking of principle components based on the percentage of variance explained by each one
ElbowPlot(pbmc)
K-nearest neighbor (KNN) graph, with edges drawn between cells with similar feature expression patterns, and then attempt to partition this graph into highly interconnected ‘quasi-cliques’ or ‘communities’.
first construct a KNN graph based on the euclidean distance in PCA space, and refine the edge weights between any two cells based on the shared overlap in their local neighborhoods (Jaccard similarity).
resolution parameter that sets the ‘granularity’ of the downstream clustering, with increased values leading to a greater number of clusters
pbmc <- FindNeighbors(pbmc, dims = 1:10)## Computing nearest neighbor graph## Computing SNNpbmc <- FindClusters(pbmc, resolution = 0.5)## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
##
## Number of nodes: 2638
## Number of edges: 95965
##
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.8723
## Number of communities: 9
## Elapsed time: 1 seconds# Look at cluster IDs of the first 5 cells
head(Idents(pbmc), 5)## AAACATACAACCAC-1 AAACATTGAGCTAC-1 AAACATTGATCAGC-1 AAACCGTGCTTCCG-1
## 2 3 2 1
## AAACCGTGTATGCG-1
## 6
## Levels: 0 1 2 3 4 5 6 7 8non-linear dimensional reduction techniques, such as tSNE and UMAP, to visualize and explore these datasets. The goal of these algorithms is to learn the underlying manifold of the data in order to place similar cells together in low-dimensional space.
# If you haven't installed UMAP, you can do so via reticulate::py_install(packages =
# 'umap-learn')
pbmc <- RunUMAP(pbmc, dims = 1:10)## Warning: The default method for RunUMAP has changed from calling Python UMAP via reticulate to the R-native UWOT using the cosine metric
## To use Python UMAP via reticulate, set umap.method to 'umap-learn' and metric to 'correlation'
## This message will be shown once per session## 13:02:05 UMAP embedding parameters a = 0.9922 b = 1.112## 13:02:05 Read 2638 rows and found 10 numeric columns## 13:02:05 Using Annoy for neighbor search, n_neighbors = 30## 13:02:05 Building Annoy index with metric = cosine, n_trees = 50## 0% 10 20 30 40 50 60 70 80 90 100%## [----|----|----|----|----|----|----|----|----|----|## **************************************************|
## 13:02:06 Writing NN index file to temp file C:\Users\wd979071\AppData\Local\Temp\RtmpWQis3g\file1c1c29a69f3
## 13:02:06 Searching Annoy index using 1 thread, search_k = 3000
## 13:02:07 Annoy recall = 100%
## 13:02:09 Commencing smooth kNN distance calibration using 1 thread
## 13:02:10 Initializing from normalized Laplacian + noise
## 13:02:11 Commencing optimization for 500 epochs, with 105124 positive edges
## 13:02:22 Optimization finished# note that you can set `label = TRUE` or use the LabelClusters function to help label
# individual clusters
DimPlot(pbmc, reduction = "umap", label = TRUE)
saveRDS(pbmc, file = "../output/pbmc_tutorial.rds")Finding differentially expressed features (cluster biomarkers)
The min.pct argument requires a feature to be detected at a minimum percentage in either of the two groups of cells, and the thresh.test argument requires a feature to be differentially expressed (on average) by some amount between the two groups.
# find all markers of cluster 2
cluster2.markers <- FindMarkers(pbmc, ident.1 = 2, min.pct = 0.25)## For a more efficient implementation of the Wilcoxon Rank Sum Test,
## (default method for FindMarkers) please install the limma package
## --------------------------------------------
## install.packages('BiocManager')
## BiocManager::install('limma')
## --------------------------------------------
## After installation of limma, Seurat will automatically use the more
## efficient implementation (no further action necessary).
## This message will be shown once per sessionhead(cluster2.markers, n = 5)## p_val avg_log2FC pct.1 pct.2 p_val_adj
## IL32 2.593535e-91 1.2154360 0.949 0.466 3.556774e-87
## LTB 7.994465e-87 1.2828597 0.981 0.644 1.096361e-82
## CD3D 3.922451e-70 0.9359210 0.922 0.433 5.379250e-66
## IL7R 1.130870e-66 1.1776027 0.748 0.327 1.550876e-62
## LDHB 4.082189e-65 0.8837324 0.953 0.614 5.598314e-61# find all markers distinguishing cluster 5 from clusters 0 and 3
cluster5.markers <- FindMarkers(pbmc, ident.1 = 5, ident.2 = c(0, 3), min.pct = 0.25)
head(cluster5.markers, n = 5)## p_val avg_log2FC pct.1 pct.2 p_val_adj
## FCGR3A 2.150929e-209 4.267579 0.975 0.039 2.949784e-205
## IFITM3 6.103366e-199 3.877105 0.975 0.048 8.370156e-195
## CFD 8.891428e-198 3.411039 0.938 0.037 1.219370e-193
## CD68 2.374425e-194 3.014535 0.926 0.035 3.256286e-190
## RP11-290F20.3 9.308287e-191 2.722684 0.840 0.016 1.276538e-186# find markers for every cluster compared to all remaining cells, report only the positive
# ones
pbmc.markers <- FindAllMarkers(pbmc, only.pos = TRUE, min.pct = 0.25, logfc.threshold = 0.25)## Calculating cluster 0## Calculating cluster 1## Calculating cluster 2## Calculating cluster 3## Calculating cluster 4## Calculating cluster 5## Calculating cluster 6## Calculating cluster 7## Calculating cluster 8pbmc.markers %>%
group_by(cluster) %>%
slice_max(n = 2, order_by = avg_log2FC)## # A tibble: 18 × 7
## # Groups: cluster [9]
## p_val avg_log2FC pct.1 pct.2 p_val_adj cluster gene
## <dbl> <dbl> <dbl> <dbl> <dbl> <fct> <chr>
## 1 1.17e- 83 1.33 0.435 0.108 1.60e- 79 0 CCR7
## 2 1.74e-109 1.07 0.897 0.593 2.39e-105 0 LDHB
## 3 0 5.57 0.996 0.215 0 1 S100A9
## 4 0 5.48 0.975 0.121 0 1 S100A8
## 5 7.99e- 87 1.28 0.981 0.644 1.10e- 82 2 LTB
## 6 2.61e- 59 1.24 0.424 0.111 3.58e- 55 2 AQP3
## 7 0 4.31 0.936 0.041 0 3 CD79A
## 8 9.48e-271 3.59 0.622 0.022 1.30e-266 3 TCL1A
## 9 4.93e-169 3.01 0.595 0.056 6.76e-165 4 GZMK
## 10 1.17e-178 2.97 0.957 0.241 1.60e-174 4 CCL5
## 11 3.51e-184 3.31 0.975 0.134 4.82e-180 5 FCGR3A
## 12 2.03e-125 3.09 1 0.315 2.78e-121 5 LST1
## 13 6.82e-175 4.92 0.958 0.135 9.36e-171 6 GNLY
## 14 1.05e-265 4.89 0.986 0.071 1.44e-261 6 GZMB
## 15 1.48e-220 3.87 0.812 0.011 2.03e-216 7 FCER1A
## 16 1.67e- 21 2.87 1 0.513 2.28e- 17 7 HLA-DPB1
## 17 3.68e-110 8.58 1 0.024 5.05e-106 8 PPBP
## 18 7.73e-200 7.24 1 0.01 1.06e-195 8 PF4VlnPlot(pbmc, features = c("MS4A1", "CD79A"))
# you can plot raw counts as well
VlnPlot(pbmc, features = c("NKG7", "PF4"), slot = "counts", log = TRUE)
FeaturePlot(pbmc, features = c("MS4A1", "GNLY", "CD3E", "CD14", "FCER1A", "FCGR3A", "LYZ", "PPBP",
"CD8A"))
levels(pbmc)## [1] "0" "1" "2" "3" "4" "5" "6" "7" "8"new.cluster.ids <- c("Naive CD4 T", "CD14+ Mono", "Memory CD4 T", "B", "CD8 T", "FCGR3A+ Mono",
"NK", "DC", "Platelet")
names(new.cluster.ids) <- levels(pbmc)
pbmc <- RenameIdents(pbmc, new.cluster.ids)
DimPlot(pbmc, reduction = "umap", label = TRUE, pt.size = 0.5) + NoLegend()
最后一次修改于 2022-06-03