seurat to h5ad scanpy anndata对象转换20231004seurattoscanpyseuratscanpy

# 在R中把数据导出成scanpy可以读取的格式 geneinfo  cellinfo counts
# # 
# geneinfo=All.merge@[email protected]
# write.csv(geneinfo,file =  "/home/data/t040413/silicosis/geneinfo.csv")
# # [email protected]
# # write.csv(cell_info,file = "/home/data/t040413/silicosis/cell_info.csv",col.names = TRUE)
# # 
# # # Convert the counts data to a sparse matrix
# # counts_sparse <- Matrix::Matrix(as.matrix(GetAssayData(All.merge,slot = "counts")), sparse = TRUE)
# # # Save the sparse matrix in Matrix Market format (MM)
# # Matrix::writeMM(counts_sparse, file = "/home/data/t040413/silicosis/counts_sparse.mtx")
# 



import pandas as pd
cellinfo = pd.read_csv("./cell_info.csv",index_col=0)
geneinfo = pd.read_csv("./geneinfo.csv",index_col=0)

adata_ref=sc.read("./counts_sparse.mtx",index_col=0,header=None)
adata_ref=adata_ref.T  ########非常重要


adata_ref = sc.AnnData(adata_ref.X,obs=cellinfo,var = geneinfo)

adata_ref.var['SYMBOL'] = adata_ref.var.index

# find mitochondria-encoded (MT) genes
adata_ref.var['MT_gene'] = [gene.startswith('MT-') for gene in adata_ref.var['SYMBOL']]
adata_ref.var['mt_gene'] = [gene.startswith('mt-') for gene in adata_ref.var['SYMBOL']]

adata_ref.var.groupby('MT_gene').count()
adata_ref.var.groupby('mt_gene').count()


# remove MT genes for spatial mapping (keeping their counts in the object)
adata_ref.obsm['mt'] = adata_ref[:, adata_ref.var['mt_gene'].values].X.toarray()
adata_ref = adata_ref[:, ~adata_ref.var['mt_gene'].values]

convert seurat scrnaseq to annadata

library(Seurat, quietly = TRUE)
library(SeuratData, quietly = TRUE)
library(SeuratDisk, quietly = TRUE)
library(dplyr, quietly = TRUE)
library(ArchR, quietly = TRUE)

## load metadata
proj <- loadArchRProject(path = "../snATAC/DataIntegration/data/VisiumHeart", showLogo = FALSE)

## get a Seurat object for ATAC-seq
geneMatrix <- getMatrixFromProject(proj, useMatrix = "GeneScoreMatrix")
GeneScoreMatrix <- geneMatrix@assays@data$GeneScoreMatrix
rownames(GeneScoreMatrix) <- geneMatrix@elementMetadata$name

# load Seurat object
obj <- readRDS("../snATAC/DataIntegration/data/VisiumHeart/snATAC.annotated.Rds")

meta.data <- [email protected]
head(meta.data)

meta.data <- meta.data[, c("Sample", "cell_type")]

meta.data$cell_type <- as.character(meta.data$cell_type)

counts <- GeneScoreMatrix[, rownames(meta.data)]

dim(counts)

obj.atac <- CreateSeuratObject(counts = counts,
                               meta.data = meta.data,
                               assay = "RNA",
                              names.delim = "-") %>% 
            NormalizeData()

head([email protected])

umap_embedding <- Embeddings(obj, reduction = "umap_harmony_v2")
rownames(umap_embedding) <- colnames(obj.atac)
colnames(umap_embedding) <- c("UMAP_1", "UMAP_2")
head(umap_embedding)

obj.atac[["umap"]] <- CreateDimReducObject(embeddings = umap_embedding, key = "UMAP_", assay = DefaultAssay(obj.atac))

DimPlot(obj.atac, reduction = "umap", pt.size = 0.5, group.by = "cell_type", label = TRUE)

SaveH5Seurat(obj.atac, filename = "snATAC-seq.h5Seurat")

Convert("snATAC-seq.h5Seurat", dest = "h5ad")