scRNAseq realted scripts

scRNAseq/Figure_S7ABC_c.R

+library(Seurat)
+library(ggplot2)
+library(gridExtra)
+library(reshape2)
+library(pheatmap)
+library(RColorBrewer)
+
+# script for discrimination of AML mut or not.
+
+obj <- readRDS(file = "PT19_final.rds")
+
+png(filename = "PT19_res.3.0.png", width = 9, height = 6, units = "in", res = 300)
+a <- DimPlot(object = obj, group.by = "RNA_snn_res.3", pt.size = 0.01, label = T)
+a
+dev.off()
+
+# Adding NPM1 classification
+
+npm1 <- read.table(file = "NPM1_PT19_data.txt", header = T)
+rownames(npm1) <- paste0(npm1$CB,"-1")
+npm1$CB <- NULL
+obj <- AddMetaData(object = obj, metadata = npm1)
+
+png(filename = "PT19_classification_by_Timepoint.png", width = 9, height = 6, units = "in", res = 300)
+DimPlot(object = obj, split.by  = "RNA_Timepoint", group.by = "Classification", pt.size = 0.01)
+dev.off()
+
+# Table creation
+
+res3_classification <- as.data.frame(round(prop.table(table(obj$RNA_snn_res.3, obj$Classification, useNA = 'ifany'), margin = 1)*100,0))
+res3_bpe <- as.data.frame(round(prop.table(table(obj$RNA_snn_res.3, obj$SingleR_BlueprintEncodeData_labels, useNA = 'ifany'), margin = 1)*100,0))
+
+res3_classification_cast <- dcast(res3_classification, formula = Var1 ~ Var2)
+rownames(res3_classification_cast) <- res3_classification_cast$Var1
+res3_classification_cast$Var1 <- NULL
+colnames(res3_classification_cast)[4] <- "NoCall"
+res3_bpe_cast <- dcast(res3_bpe, formula = Var1 ~ Var2)
+rownames(res3_bpe_cast) <- res3_bpe_cast$Var1
+res3_bpe_cast$Var1 <- NULL
+
+# ann.rows
+
+ann.rows <- read.table(file = "PT19_Annotation_row.txt", header = T)
+rownames(ann.rows) <- ann.rows$Cluster
+ann.rows$Cluster <- NULL
+ann.rows$AML <- as.factor(ann.rows$AML)
+ann.rows.colors <- list(
+  AML = c(YES = "red", NO = "grey")
+)
+
+b <- pheatmap(res3_classification_cast[,c(1,2,4,3)], 
+              scale = "none",annotation_names_row = F,
+              cluster_rows = T, 
+              cluster_cols = F, 
+              color = brewer.pal(9, "Reds"), 
+              cellheight = 10, number_color = "black",
+              cellwidth = 30, 
+              angle_col = 0, 
+              annotation_row = ann.rows, 
+              annotation_colors = ann.rows.colors,
+              legend = F, border_color = NA,
+              display_numbers = T, fontsize_number = 8, 
+              fontsize_col = 9, fontsize_row = 9,
+              number_format = "%.0f") 
+
+c <- pheatmap(res3_bpe_cast, 
+         scale = "none",annotation_names_row = F,
+         cluster_rows = T, 
+         cluster_cols = F, 
+         color = brewer.pal(9, "Blues"), 
+         cellheight = 10, number_color = "black",
+         cellwidth = 20, 
+         angle_col = 90, 
+         annotation_row = ann.rows, 
+         annotation_colors = ann.rows.colors,
+         legend = F, border_color = NA,
+         display_numbers = T, fontsize_number = 8, 
+         fontsize_col = 9, fontsize_row = 9,
+         number_format = "%.0f") 
+
+library(gridExtra)
+
+pdf(file = "PT19_NatComm_Supp_Fig7_partD.pdf", width = 18, height = 6)
+grid.arrange(a,b[[4]],c[[4]], ncol = 3, widths=c(1.2, 0.9, 0.9))
+dev.off()
+
+# subset minimal and create clean AML and HEALTHY subsets
+
+minimal <- readRDS(file = "PT19_minimal.rds")
+obj <- SetIdent(object = obj, value = "RNA_snn_res.3")
+AML_cells <- WhichCells(object = obj, idents = c("24","25","30"), invert = T)
+obj <- SetIdent(object = obj, value = "Classification")
+MUT_cells <- WhichCells(object = obj, idents = c("MUT"))
+WT_cells <- WhichCells(object = obj, idents = c("WT"))
+
+AML_cells_refined <- setdiff(union(x = MUT_cells, y = AML_cells), y = WT_cells)
+obj <- SetIdent(object = obj, value = "RNA_snn_res.3")
+HEALTHY_cells <- setdiff(x = Cells(obj), y = AML_cells_refined)
+
+# create minimals AML and HEALTHY
+
+minimals.AML <- subset(x = minimal, cells = AML_cells_refined)
+minimals.HEALTHY <- subset(x = minimal, cells = HEALTHY_cells)
+
+saveRDS(minimals.AML, "PT19_AML_minimal.rds")
+saveRDS(minimals.HEALTHY, "PT19_HEALTHY_minimal.rds")
+
+
+
+
+

scRNAseq/Figure_S7ABC_indexes.txt

+SI-GA-A1,GGTTTACT,CTAAACGG,TCGGCGTC,AACCGTAA
+SI-GA-A2,TTTCATGA,ACGTCCCT,CGCATGTG,GAAGGAAC
+SI-GA-A3,CAGTACTG,AGTAGTCT,GCAGTAGA,TTCCCGAC
+SI-GA-A4,TATGATTC,CCCACAGT,ATGCTGAA,GGATGCCG
+SI-GA-A5,CTAGGTGA,TCGTTCAG,AGCCAATT,GATACGCC
+SI-GA-A6,CGCTATGT,GCTGTCCA,TTGAGATC,AAACCGAG
+SI-GA-A7,ACAGAGGT,TATAGTTG,CGGTCCCA,GTCCTAAC
+SI-GA-A8,GCATCTCC,TGTAAGGT,CTGCGATG,AACGTCAA
+SI-GA-A9,TCTTAAAG,CGAGGCTC,GTCCTTCT,AAGACGGA
+SI-GA-A10,GAAACCCT,TTTCTGTC,CCGTGTGA,AGCGAAAG
+SI-GA-A11,GTCCGGTC,AAGATCAT,CCTGAAGG,TGATCTCA
+SI-GA-A12,AGTGGAAC,GTCTCCTT,TCACATCA,CAGATGGG
+SI-GA-B1,GTAATCTT,TCCGGAAG,AGTTCGGC,CAGCATCA
+SI-GA-B2,TACTCTTC,CCTGTGCG,GGACACGT,ATGAGAAA
+SI-GA-B3,GTGTATTA,TGTGCGGG,ACCATAAC,CAACGCCT
+SI-GA-B4,ACTTCATA,GAGATGAC,TGCCGTGG,CTAGACCT
+SI-GA-B5,AATAATGG,CCAGGGCA,TGCCTCAT,GTGTCATC
+SI-GA-B6,CGTTAATC,GCCACGCT,TTACTCAG,AAGGGTGA
+SI-GA-B7,AAACCTCA,GCCTTGGT,CTGGACTC,TGTAGAAG
+SI-GA-B8,AAAGTGCT,GCTACCTG,TGCTGTAA,CTGCAAGC
+SI-GA-B9,CTGTAACT,TCTAGCGA,AGAGTGTG,GACCCTAC
+SI-GA-B10,ACCGTATG,GATTAGAT,CTGACTGA,TGACGCCC
+SI-GA-B11,GTTCCTCA,AGGTACGC,TAAGTATG,CCCAGGAT
+SI-GA-B12,TACCACCA,CTAAGTTT,GGGTCAAG,ACTGTGGC
+SI-GA-C1,CCACTTAT,AACTGGCG,TTGGCATA,GGTAACGC
+SI-GA-C2,CCTAGACC,ATCTCTGT,TAGCTCTA,GGAGAGAG
+SI-GA-C3,TCAGCCGT,CAGAGGCC,GGTCAATA,ATCTTTAG
+SI-GA-C4,ACAATTCA,TGCGCAGC,CATCACTT,GTGTGGAG
+SI-GA-C5,CGACTTGA,TACAGACT,ATTGCGTG,GCGTACAC
+SI-GA-C6,ATTACTTC,TGCGAACT,GCATTCGG,CAGCGGAA
+SI-GA-C7,GTCTCTCG,AATCTCTC,CGGAGGGA,TCAGAAAT
+SI-GA-C8,GTTGAGAA,AGATCTGG,TCGATACT,CACCGCTC
+SI-GA-C9,GCGCAGAA,ATCTTACC,TATGGTGT,CGAACCTG
+SI-GA-C10,TCTCAGTG,GAGACTAT,CGCTTAGC,ATAGGCCA
+SI-GA-C11,GAGGATCT,AGACCATA,TCCTGCGC,CTTATGAG
+SI-GA-C12,TCTCGTTT,GGCTAGCG,ATGACCGC,CAAGTAAA
+SI-GA-D1,CACTCGGA,GCTGAATT,TGAAGTAC,ATGCTCCG
+SI-GA-D2,TAACAAGG,GGTTCCTC,ATCATGCA,CCGGGTAT
+SI-GA-D3,ACATTACT,TTTGGGTA,CAGCCCAC,GGCAATGG
+SI-GA-D4,CCCTAACA,ATTCCGAT,TGGATTGC,GAAGGCTG
+SI-GA-D5,CTCGTCAC,GATCAGCA,ACAACAGG,TGGTGTTT
+SI-GA-D6,CATGCGAT,TGATATTC,GTGATCGA,ACCCGACG
+SI-GA-D7,ATTTGCTA,TAGACACC,CCACAGGG,GGCGTTAT
+SI-GA-D8,GCAACAAA,TAGTTGTC,CGCCATCG,ATTGGCGT
+SI-GA-D9,AGGAGATG,GATGTGGT,CTACATCC,TCCTCCAA
+SI-GA-D10,CAATACCC,TGTCTATG,ACCACGAA,GTGGGTGT
+SI-GA-D11,CTTTGCGG,TGCACAAA,AAGCAGTC,GCAGTTCT
+SI-GA-D12,GCACAATG,CTTGGTAC,TGCACCGT,AAGTTGCA
+SI-GA-E1,TGGTAAAC,GAAAGGGT,ACTGCTCG,CTCCTCTA
+SI-GA-E2,GTGGTACC,TACTATAG,ACAAGGTA,CGTCCCGT
+SI-GA-E3,AGGTATTG,CTCCTAGT,TCAAGGCC,GATGCCAA
+SI-GA-E4,TTCGCCCT,GGATGGGC,AATCAATG,CCGATTAA
+SI-GA-E5,CATTAGCG,TTCGCTGA,ACAAGAAT,GGGCTCTC
+SI-GA-E6,CTGCGGCT,GACTCAAA,AGAAACTC,TCTGTTGG
+SI-GA-E7,CACGCCTT,GTATATAG,TCTCGGGC,AGGATACA
+SI-GA-E8,ATAGTTAC,TGCTGAGT,CCTACGTA,GAGCACCG
+SI-GA-E9,TTGTTTCC,GGAGGAGG,CCTAACAA,AACCCGTT
+SI-GA-E10,AAATGTGC,GGGCAAAT,TCTATCCG,CTCGCGTA
+SI-GA-E11,AAGCGCTG,CGTTTGAT,GTAGCACA,TCCAATGC
+SI-GA-E12,ACCGGCTC,GAGTTAGT,CGTCCTAG,TTAAAGCA
+SI-GA-F1,GTTGCAGC,TGGAATTA,CAATGGAG,ACCCTCCT
+SI-GA-F2,TTTACATG,CGCGATAC,ACGCGGGT,GAATTCCA
+SI-GA-F3,TTCAGGTG,ACGGACAT,GATCTTGA,CGATCACC
+SI-GA-F4,CCCAATAG,GTGTCGCT,AGAGTCGC,TATCGATA
+SI-GA-F5,GACTACGT,CTAGCGAG,TCTATATC,AGGCGTCA
+SI-GA-F6,CGGAGCAC,GACCTATT,ACTTAGGA,TTAGCTCG
+SI-GA-F7,CGTGCAGA,AACAAGAT,TCGCTTCG,GTATGCTC
+SI-GA-F8,CATGAACA,TCACTCGC,AGCTGGAT,GTGACTTG
+SI-GA-F9,CAAGCTCC,GTTCACTG,TCGTGAAA,AGCATGGT
+SI-GA-F10,GCTTGGCT,AAACAAAC,CGGGCTTA,TTCATCGG
+SI-GA-F11,GCGAGAGT,TACGTTCA,AGTCCCAC,CTATAGTG
+SI-GA-F12,TGATGCAT,GCTACTGA,CACCTGCC,ATGGAATG
+SI-GA-G1,ATGAATCT,GATCTCAG,CCAGGAGC,TGCTCGTA
+SI-GA-G2,TGATTCTA,ACTAGGAG,CAGCCACT,GTCGATGC
+SI-GA-G3,CCTCATTC,AGCATCCG,GTGGCAAT,TAATGGGA
+SI-GA-G4,GCGATGTG,AGATACAA,TTTCCACT,CACGGTGC
+SI-GA-G5,GAGCAAGA,TCTGTGAT,CGCAGTTC,ATATCCCG
+SI-GA-G6,CTGACGCG,GGTCGTAC,TCCTTCTT,AAAGAAGA
+SI-GA-G7,GGTATGCA,CTCGAAAT,ACACCTTC,TAGTGCGG
+SI-GA-G8,TATGAGCT,CCGATAGC,ATACCCAA,GGCTGTTG
+SI-GA-G9,TAGGACGT,ATCCCACA,GGAATGTC,CCTTGTAG
+SI-GA-G10,TCGCCAGC,AATGTTAG,CGATAGCT,GTCAGCTA
+SI-GA-G11,TTATCGTT,AGCAGAGC,CATCTCCA,GCGGATAG
+SI-GA-G12,ATTCTAAG,CCCGATTA,TGGAGGCT,GAATCCGC
+SI-GA-H1,GTATGTCA,TGTCAGAC,CACGTCGG,ACGACATT
+SI-GA-H2,TAATGACC,ATGCCTTA,GCCGAGAT,CGTATCGG
+SI-GA-H3,CCAAGATG,AGGCCCGA,TACGTGAC,GTTTATCT
+SI-GA-H4,GCCATTCC,CAAGAATT,TTGCCGGA,AGTTGCAG
+SI-GA-H5,CCACTACA,GATTCTGG,TGCGGCTT,ATGAAGAC
+SI-GA-H6,TAGGATAA,CCTTTGTC,GTACGCGG,AGCACACT
+SI-GA-H7,AGCTATCA,CATATAAC,TCAGGGTG,GTGCCCGT
+SI-GA-H8,TTGTTGAT,GCTCAACC,CAAAGTGG,AGCGCCTA
+SI-GA-H9,ACACTGTT,CAGGATGG,GGCTGAAC,TTTACCCA
+SI-GA-H10,GTAATTGC,AGTCGCTT,CACGAGAA,TCGTCACG
+SI-GA-H11,GGCGAGTA,ACTTCTAT,CAAATACG,TTGCGCGC
+SI-GA-H12,GACAGCAT,TTTGTACA,AGGCCGTG,CCATATGC

scRNAseq/Figure_S7D.R

+# Aim: plotting mod score distribution in the 3 different patients
+# Plotting according classification on full dataset del7.
+
+library(Seurat)
+library(ggplot2)
+
+modscores <- list()
+
+for (id in c("PT11","PT17","PT18")) {
+  modscores[[id]] <- readRDS(file = paste0("Figure_S7D_",id,"_data.rds"))
+}
+
+modscores[["PT11"]]$RNA_Timepoint <- factor(modscores[["PT11"]]$RNA_Timepoint, levels = c("DX","D30"))
+modscores[["PT17"]]$RNA_Timepoint <- factor(modscores[["PT17"]]$RNA_Timepoint, levels = c("DX","D14","D30"))
+modscores[["PT18"]]$RNA_Timepoint <- factor(modscores[["PT18"]]$RNA_Timepoint, levels = c("DX","D14","D30"))
+
+modscores$PT11$Classification <- factor(kmeans(modscores$PT11$Cluster1, centers = 2, iter.max = 1000)$cluster, levels = c("1","2"))
+modscores$PT17$Classification <- factor(kmeans(modscores$PT17$Cluster1, centers = 2, iter.max = 1000)$cluster, levels = c("1","2"))
+modscores$PT18$Classification <- factor(kmeans(modscores$PT18$Cluster1, centers = 2, iter.max = 1000)$cluster, levels = c("1","2"))
+
+modscores$PT11$Classification <- gsub(modscores$PT11$Classification, pattern = "1", replacement = "AML")
+modscores$PT11$Classification <- gsub(modscores$PT11$Classification, pattern = "2", replacement = "noAML")
+
+modscores$PT17$Classification <- gsub(modscores$PT17$Classification, pattern = "2", replacement = "AML")
+modscores$PT17$Classification <- gsub(modscores$PT17$Classification, pattern = "1", replacement = "noAML")
+
+modscores$PT18$Classification <- gsub(modscores$PT18$Classification, pattern = "1", replacement = "AML")
+modscores$PT18$Classification <- gsub(modscores$PT18$Classification, pattern = "2", replacement = "noAML")
+
+
+png(filename = "Figure_7D_top.png", width = 8, height = 3, units = "in", res = 300)
+ggplot(data = modscores$PT11, mapping = aes(x = Cluster1, fill = Classification)) + 
+  geom_histogram(binwidth = 0.0001) + 
+  facet_wrap(. ~ RNA_Timepoint, nrow = 1) + 
+  theme(legend.position = "right", panel.background = element_rect(fill = "white"),
+        strip.text.x = element_text(size = 12),
+        axis.title = element_blank())
+dev.off()
+
+png(filename = "Figure_7D_middle.png", width = 8, height = 3, units = "in", res = 300)
+ggplot(data = modscores$PT17, mapping = aes(x = Cluster1, fill = Classification)) + 
+  geom_histogram(binwidth = 0.0001) + 
+  facet_wrap(. ~ RNA_Timepoint, nrow = 1) + 
+  theme(legend.position = "right", panel.background = element_rect(fill = "white"),
+        strip.text.x = element_text(size = 12),
+        axis.title = element_blank())
+dev.off()
+
+png(filename = "Figure_7D_bottom.png", width = 8, height = 3, units = "in", res = 300)
+ggplot(data = modscores$PT18, mapping = aes(x = Cluster1, fill = Classification)) + 
+  geom_histogram(binwidth = 0.0001) + 
+  facet_wrap(. ~ RNA_Timepoint, nrow = 1) + 
+  theme(legend.position = "right", panel.background = element_rect(fill = "white"),
+        strip.text.x = element_text(size = 12),
+        axis.title = element_blank())
+dev.off()
+
+