单细胞数据集
最后发布时间 : 2023-01-11 11:54:35
浏览量 :
https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE60361
library(tidyverse)
library(Seurat)
library(Matrix)
exprMatrix <- read_delim("testData/singlecell/GSE60361_C1-3005-Expression.txt.gz") |>
distinct(cell_id, .keep_all = TRUE) |>
column_to_rownames("cell_id")
exprMatrix[1:5,1:5]
# rownames(My_data) <- My_data[,1]
# My_data <- My_data[,-1]
Matx <- as.matrix(exprMatrix)
Matx <- as(Matx,"sparseMatrix")
seurat_ob <- CreateSeuratObject(counts = Matx)
seurat_ob@assays$RNA@counts[1:5,1:5]
monocle lung 数据
原始位置: monocle-release/R/utils.R，monocle-release/inst/extdata/
测试数据: https://gitee.com/bioinfoFungi/monocle2/tree/master/monocle2_lung
表达矩阵
lung_exprs_data <- readr::read_tsv("https://gitee.com/bioinfoFungi/monocle2/raw/master/monocle2_lung/lung_exprs_data.tsv",show_col_types = FALSE) |>
column_to_rownames("symbol")
lung_exprs_data[1:5,1:5]
| # | SRR1033854_0 | SRR1033855_0 | SRR1033856_0 | SRR1033859_0 | SRR1033860_0 |
|---|---|---|---|---|---|
| ENSMUSG00000000031.9 | 0 | 0 | 0 | 10.7100207665015 | 0 |
| ENSMUSG00000000058.6 | 34.6354356143998 | 0 | 0 | 28.214174057558 | 3.18299366520609 |
| ENSMUSG00000000184.9 | 0.118705574924682 | 0.0267344012991981 | 0.00979288708446397 | 0 | 0.653084159748841 |
| ENSMUSG00000000216.8 | 0.442115291788066 | 0.0880425887744926 | 0.116616298212331 | 0.117774740716152 | 12.2427903522189 |
| ENSMUSG00000000402.2 | 43.4605452125962 | 43.8824386088398 | 3.33280333643549 | 0.877212657158511 | 0 |
样本信息
lung_phenotype_data <- readr::read_tsv("https://gitee.com/bioinfoFungi/monocle2/raw/master/monocle2_lung/lung_phenotype_data.tsv",show_col_types = FALSE) |>
column_to_rownames("sample")
lung_phenotype_data[1:5,1:5]
| # | file | total_mass | internal_scale | external_scale | median_transcript_frags |
|---|---|---|---|---|---|
| SRR1033854_0 | ./quantification/SRR1033854_clout/abundances.cxb | 2840200 | 2.16877 | 1 | 0.363568 |
| SRR1033855_0 | ./quantification/SRR1033855_clout/abundances.cxb | 2968830 | 4.20782 | 1 | 0.00141841 |
| SRR1033856_0 | ./quantification/SRR1033856_clout/abundances.cxb | 3396210 | 6.17393 | 1 | 0.403053 |
| SRR1033859_0 | ./quantification/SRR1033859_clout/abundances.cxb | 2846020 | 5.62105 | 1 | 0.0318467 |
| SRR1033860_0 | ./quantification/SRR1033860_clout/abundances.cxb | 3636420 | 11.0584 | 1 | 0.00151798 |
基因信息
lung_feature_data <- readr::read_tsv("https://gitee.com/bioinfoFungi/monocle2/raw/master/monocle2_lung/lung_feature_data.tsv",show_col_types = FALSE) |>
column_to_rownames("symbol")
lung_feature_data[1:5,1:5]
| # | class_code | nearest_ref_id | gene_id | gene_short_name | tss_id |
|---|---|---|---|---|---|
| ENSMUSG00000000031.9 | - | - | ENSMUSG00000000031.9 | H19 | - |
| ENSMUSG00000000058.6 | - | - | ENSMUSG00000000058.6 | Cav2 | - |
| ENSMUSG00000000184.9 | - | - | ENSMUSG00000000184.9 | Ccnd2 | - |
| ENSMUSG00000000216.8 | - | - | ENSMUSG00000000216.8 | Scnn1g | - |
| ENSMUSG00000000402.2 | - | - | ENSMUSG00000000402.2 | Egfl6 | - |
monocle HSMM（human skeletal muscle myoblasts） 数据
原始位置：monocle-release/tests/testthat/test.plot_cell_clusters.R，Single-cell RNA-Seq for differentiating human skeletal muscle myoblasts (HSMM)
library(HSMMSingleCell)
data(HSMM_expr_matrix)
data(HSMM_gene_annotation)
data(HSMM_sample_sheet)