Entering edit mode
4.6 years ago
michelle.piquet
▴
60
I want to upload an excel file sheet that has certain barcodes that I would like to show on my umap. How do I go about adding the file and linking it to the metadata?
Below is my following code.
# set up the working directory
wd = "/home/PTX_AAC656
setwd(wd)
# load counts
# SD-52-JZ33 patient sample but aligned to both mouse and human
SD_52_JZ33.data <- Read10X(data.dir = "../PTX_AAC656/metadata/patient_sample/SD-52-JZ33/outs/filtered_feature_bc_matrix/")
BNM_human_only.data <- Read10X(data.dir = "../PTX_AAC656/metadata/human_only_alignment/SD-52-JZ33_BNM_5K/outs/filtered_feature_bc_matrix/")
BNL_human_only.data <- Read10X(data.dir = "../PTX_AAC656/metadata/human_only_alignment/SD-52-JZ33_BNL_5K/outs/filtered_feature_bc_matrix/")
BNL_mouse_only.data <- Read10X(data.dir = "../PTX_AAC656/metadata/mouse_only_alignment/SD-52-JZ33_BNL_5K/outs/filtered_feature_bc_matrix/")
BNM_mouse_only.data <- Read10X(data.dir = "../PTX_AAC656/metadata/mouse_only_alignment/SD-52-JZ33_BNM_5K/outs/filtered_feature_bc_matrix/")
BNL_both.data <- Read10X(data.dir = "../AAC656/SD-52-JZ33_BNL_5K/outs/filtered_feature_bc_matrix/")
BNM_both.data <- Read10X(data.dir = "../AAC656/SD-52-JZ33_BNM_5K/outs/filtered_feature_bc_matrix/")
setwd(wd)
# create the Seurat objects
SD_52_JZ33 <- CreateSeuratObject(counts = SD_52_JZ33.data, min.cells = 0, project = "human")
BNL_human_only <- CreateSeuratObject(counts = BNL_human_only.data, min.cells = 0, project = "human_alignment_ptx")
BNM_human_only <- CreateSeuratObject(counts = BNM_human_only.data, min.cells = 0, project = "human_alignment_ptx")
BNM_both_ptx <- CreateSeuratObject(counts = BNM_both.data, min.cells = 0, project = "human_mouse_alignment_ptx")
BNL_both_ptx <- CreateSeuratObject(counts = BNL_both.data, min.cells = 0, project = "human_mouse_alignment_ptx")
BNL_both_ptx$model = "mouse_human_alignment_ptx"
BNM_both_ptx$model = "mouse_human_alignment_ptx"
SD_52_JZ33$model = "patient_aligned_mouse_human"
BNM_human_only$model = "human_alignment_only_ptx"
BNL_human_only$model = "human_alignment_only_ptx"
BNL_both_ptx$model = "mouse_human_alignment_ptx"
BNM_both_ptx$model = "mouse_human_alignment_ptx"
BNM_mouse_only <- CreateSeuratObject(counts = BNM_mouse_only.data, min.cells = 0, project = "mouse_alignment_ptx")
BNL_mouse_only <- CreateSeuratObject(counts = BNL_mouse_only.data, min.cells = 0, project = "mouse_alignment_ptx")
BNL_mouse_only$model = "mouse_alignment_only_ptx"
BNM_mouse_only$model = "mouse_alignment_only_ptx"
# merge samples
mouse_human_patient <- merge(BNL_mouse_only, y = c(BNM_mouse_only, SD_52_JZ33), add.cell.ids = c("A", "B", "C"), project = "HTB2876")
human_ptx_human_patient <- merge(BNL_human_only, y = c(BNM_human_only, SD_52_JZ33), add.cell.ids = c("D", "E", "F"), project = "HTB2876")
ptx_human_patient.1 <- merge(BNL_both_ptx, y = c(BNM_both_ptx, SD_52_JZ33), add.cell.ids = c("G", "H", "I"), project = "HTB2876")
# mouse ptx model with patient
# mark the mito genes
mito.genes <- grep(pattern = "^MT-", x = rownames(x = mouse_human_patient), value = TRUE)
mouse_human_patient[["percent.mt"]] <- PercentageFeatureSet(mouse_human_patient, pattern = "^MT-")
mouse_human_patient[["log_nCount_RNA"]] <- log2(mouse_human_patient[["nCount_RNA"]]+1)
# remove cells with <200 RNA molecules, or >6000 molecules, or >30% mito
mouse_human_patient <- subset(mouse_human_patient, subset = nFeature_RNA > 200 & nFeature_RNA < 6000 & percent.mt < 30)
mouse_human_patient <- NormalizeData(mouse_human_patient, normalization.method = "LogNormalize", scale.factor = 10000)
mouse_human_patient <- FindVariableFeatures(mouse_human_patient, selection.method = "vst", nfeatures = 2000)
all.genes.mouse <- rownames(mouse_human_patient)
mouse_human_patient <- ScaleData(mouse_human_patient, features = VariableFeatures(object = mouse_human_patient), vars.to.regress = c("nCount_RNA"))
mouse_human_patient <- RunPCA(mouse_human_patient, features = VariableFeatures(object = mouse_human_patient))
mouse_human_patient <- FindNeighbors(mouse_human_patient, dims = 1:20)
mouse_human_patient <- FindClusters(mouse_human_patient, resolution = 0.4)
mouse_human_patient <- RunUMAP(mouse_human_patient, dims = 1:20)
DimPlot(mouse_human_patient, reduction = "umap", group.by = "model")
# human only alignment pix with patient
# mark the mito genes
mito.genes <- grep(pattern = "^MT-", x = rownames(x = human_ptx_human_patient), value = TRUE)
human_ptx_human_patient[["percent.mt"]] <- PercentageFeatureSet(human_ptx_human_patient, pattern = "^MT-")
human_ptx_human_patient[["log_nCount_RNA"]] <- log2(human_ptx_human_patient[["nCount_RNA"]]+1)
human_ptx_human_patient <- subset(human_ptx_human_patient, subset = nFeature_RNA > 200 & nFeature_RNA < 6000 & percent.mt < 30)
# remove cells with <200 RNA molecules, or >6000 molecules, or >30% mito
human_ptx_human_patient <- NormalizeData(human_ptx_human_patient, normalization.method = "LogNormalize", scale.factor = 10000)
human_ptx_human_patient <- FindVariableFeatures(human_ptx_human_patient, selection.method = "vst", nfeatures = 2000)
all.genes.human.ptx <- rownames(human_ptx_human_patient)
human_ptx_human_patient <- ScaleData(human_ptx_human_patient, features = VariableFeatures(object = human_ptx_human_patient), vars.to.regress = c("nCount_RNA"))
human_ptx_human_patient <- RunPCA(human_ptx_human_patient, features = VariableFeatures(object = human_ptx_human_patient))
DimPlot(human_ptx_human_patient, reduction = "pca")
human_ptx_human_patient <- FindNeighbors(human_ptx_human_patient, dims = 1:20)
human_ptx_human_patient <- FindClusters(human_ptx_human_patient, resolution = 0.4)
human_ptx_human_patient <- RunUMAP(human_ptx_human_patient, dims = 1:20)
DimPlot(human_ptx_human_patient, reduction = "umap", group.by = "model")
# ptx and human
# mark the mito genes
mito.genes.ptx_patient <- grep(pattern = "^MT-", x = rownames(x = ptx_human_patient.1), value = TRUE)
ptx_human_patient.1[["percent.mt"]] <- PercentageFeatureSet(ptx_human_patient.1, pattern = "^MT-")
ptx_human_patient.1[["log_nCount_RNA"]] <- log2(ptx_human_patient.1[["nCount_RNA"]]+1)
# remove cells with <200 RNA molecules, or >6000 molecules, or >30% mito
ptx_human_patient.1 <- subset(ptx_human_patient.1, subset = nFeature_RNA > 200 & nFeature_RNA < 6000 & percent.mt < 30)
ptx_human_patient.1 <- NormalizeData(ptx_human_patient.1, normalization.method = "LogNormalize", scale.factor = 10000)
ptx_human_patient.1 <- FindVariableFeatures(ptx_human_patient.1, selection.method = "vst", nfeatures = 2000)
all.genes.both.patient.1 <- rownames(ptx_human_patient.1)
ptx_human_patient.1 <- ScaleData(ptx_human_patient.1, features = VariableFeatures(object = ptx_human_patient.1), vars.to.regress = c("nCount_RNA"))
ptx_human_patient.1 <- RunPCA(ptx_human_patient.1, features = VariableFeatures(object = ptx_human_patient.1))
ptx_human_patient.1 <- FindNeighbors(ptx_human_patient.1, dims = 1:20)
ptx_human_patient.1 <- FindClusters(ptx_human_patient.1, resolution = 0.4)
ptx_human_patient.1 <- RunUMAP(ptx_human_patient.1, dims = 1:20)
#run plots
DimPlot(ptx_human_patient.1, reduction = "umap", group.by = "model")
DimPlot(ptx_human_patient.1, reduction = "umap", label = "TRUE")
saveRDS(ptx_human_patient.1, file = "derived_data/PTX_human_2876_res04_6000g.rds")
DimPlot(ptx_human_patient.1, reduction = "umap", group.by = "model")
DimPlot(ptx_human_patient.1, reduction = "umap", label = TRUE, pt.size = 0.5) + NoLegend()
ptx_human_patient.1$clustering.idents <- Idents(object = ptx_human_patient.1)
Idents(ptx_human_patient.1) <- "clustering.idents"
new.cluster.ids <- c("Human PTX Tumor", "PTX Fibroblast", "Human Fibroblast", "PTX Macrophage", "Human PTX Tumor", "Human Mitochondrial", "Human Macrophage", "Human Endothelial", "Human T-cells", "Human PTX Tumor","Human Fibroblast", "PTX Fibroblast", "Human Tumor Ductal", "Human Acinar", "PTX Macrophage", "PTX Stellate", "PTX Endothelial")
names(new.cluster.ids) <- levels(ptx_human_patient.1)
ptx_human_patient.1 <- RenameIdents(ptx_human_patient.1, new.cluster.ids)
saveRDS(ptx_human_patient.1, file = "derived_data/PTX_human_2876_res04_6000g.rds")
p1 = DimPlot(ptx_human_patient.1, reduction = "umap", label = TRUE, pt.size = 0.5, group.by = "clustering.idents") + NoLegend()
p2 = DimPlot(ptx_human_patient.1, reduction = "umap", label = TRUE, pt.size = 0.5) + NoLegend()
print(CombinePlots(plots = list(p1, p2)))
markers2 <- FindAllMarkers(ptx_human_patient.1, min.pct = 0.25, logfc.threshold = 0.25)
markers2 %>% group_by(cluster) %>% top_n(n = 2, wt = avg_logFC)
saveRDS(markers, file="derived_data/markers_HTB2876_PC20_res04_6000g.rds")
Part of my excel sheet
barcode muTaTionsTaTus
GAGATGGCACTAGGCC-1 G12V
CTGAGCGAGACTCAAA-1 G12V
TACCGGGGTCCGAAGA-1 G12V
TATACCTCATAGGCGA-1 G12V
CTGCCATGTATTGGCT-1 G12V
AGTGTTGTCAGGAGAC-1 G12V
AATGCCAAGCAGTACG-1 G12V
TTTGTTGAGGCTTCCG-1 G12V
ACAGAAATCCATTCGC-1 G12V
GTCATTTCAACTAGAA-1 G12V
GAGTGTTGTGAGATTA-1 G12V
TCTTGCGCATAACGGG-1 G12V
ACATCGATCGGCATCG-1 G12V
CATCCCACACACAGCC-1 G12V
GACAGCCGTAGCTGTT-1 G12V
CACAGATGTTAGGCCC-1 G12V
AACGGGATCACAACCA-1 G12V
