I added the manuscript's scripts

a78a5561 · Marco Monti · a78a5561 · a78a5561 · a78a5561 · a78a5561
Commit a78a5561 authored Mar 11, 2025 by Marco Monti
--- a/CB2025_figure_1_RNAseq.R
+++ b/CB2025_figure_1_RNAseq.R
+library("readxl")
+library("dplyr")
+
+#####Directories#####
+us <- "/Users/Squadrito/"
+us <-"C:/Users/bresesti.chiara/"
+wdir1509<-paste0(us,"/Dropbox (HSR Global)/SquadritoM_1509_RNASeq_QIAseq_UPX/QIAseqUltraplexRNA_181342/primary_analysis")
+wdir1510<-paste0(us,"/Dropbox (HSR Global)/SquadritoM_1510_RNA_miRNA_QIAseq_UPX")
+fdir <- paste0(us,"/Dropbox (HSR Global)/CancerGeneTherapy/Cancer Gene Therapy/MS/2024 Bresesti et al/Scripts/plots and tables used in figures")
+
+
+#### Figure 1B ####
+setwd(wdir1509)
+df1 <- as.data.frame(read_excel("QIAseqUltraplexRNA_181342.xlsx",sheet=3,col_names = T,skip = 1))#sheet: umis.genes.polyA-mouse
+df1 <-df1[,-c(1,3:6)] #keep only gene name and UMI counts
+df1[,-1] <-apply(df1[,-1],2,function(x){x/sum(x)*1000000}) #UMI normalized by CPM
+gene_vector <- c("Cd19", "Ms4a1", "Fcer2a", "Ighm", "Cd8a", "Xcr1", "Itgae", "Itgax", 
+                 "Ccr2", "Itgam", "Mgl2", "Cd68", "Vcam1", "Csf1r", "Adgre1", 
+                 "Siglec1", "Hmox1", "Timd4", "Vsig4", "Clec4f", "Marco", "Pecam1", 
+                 "Tek", "Lyve1", "Stab2")
+df2 <- df1[df1$gene%in%gene_vector,] %>% arrange(factor(gene, levels=gene_vector))
+rownames(df2) <- df2[,1]
+df2.scaled <- as.data.frame(t(scale(t(df2[-1])))) #Zscore normalization. Scaled only works on columns, so need to transform
+setwd(fdir)
+openxlsx::write.xlsx(df2.scaled,"Figure_1B_table.xlsx", rowNames=T)
+#the df was exported and used to create a heatmap using Graphpad
+
+#### Figure 1C ####
+# "edgeR_DGE_res_volcano.pdf" (in the 'wdir1509' folder) was imported in illustrator 
+# and merged with the plot generated by the code below
+setwd(wdir1510)
+df1 <- as.data.frame(read_excel("173308.all_samples.summary.xlsx",sheet=2,col_names = T))#sheet: miRNA_piRNA
+df1 <-df1[,1:7]#UMI 
+rownames(df1)<-df1$miRNA
+df2 <- apply(df1[,-1], 2, function(x) log(x)) #Log counts
+df2 <- as.data.frame(limma::normalizeCyclicLoess(df2, weights = NULL, span=0.7, iterations = 5, method = "pairs")) #Cyclic loess normalization
+colnames(df2)<-c("B cell","RPM","cDC1","cDC2","LSEC","KC") #Rename columns
+upper.panel<-function(x, y, ...){
+  points(((x+y)/2),(x-y), cex=0.6, pch=19, col="grey")
+  above <- (x-y-1)*((x+y)/2-5) > 5 & ((x+y)/2)>5
+  points(((x+y)/2)[above],(x-y)[above], col="red", cex=0.6, pch=19)
+  below <- (x-y+1)*((x+y)/2-5) < -5 & ((x+y)/2)>5
+  points(((x+y)/2)[below],(x-y)[below], col="blue", cex=0.6, pch=19)
+} #function for MA plot
+pairs(df2[,1:6], lower.panel = NULL, upper.panel = upper.panel, 
+      ylim=c(-8.5,8.5), xlim=c(2,14), cex.labels = 2) #pairwise plot
+
+#### Figure 1D ####
+setwd(wdir1510)
+df1 <- as.data.frame(read_excel("173308.all_samples.summary.xlsx",sheet=2,col_names = T))#sheet: miRNA_piRNA
+df1 <- df1[-which(grepl("piR",df1[,1])),1:7]#UMI and piRNA removing
+df1[,1] <- gsub("/.*","",df1[,1]) #leave only first miRNA for ambiguous entries
+df1[,-1] <- apply(df1[,-1],2,function(x){x/sum(x,na.rm=T)*1000000})#UMI normalized by CPM
+df.families <- as.data.frame(read_excel("Analysis CB/miRNA Family.xlsx",sheet=1,col_names = T))#miRNA families from miRBase
+df.families <- df.families[df.families[,3]==10090,c(4,1)] #select mouse entries
+df.families[,1] <- sub(pattern = "p.*",replacement ="p",x = df.families[,1])
+df2 <- merge(df.families,df1,by=1)
+df2 <- aggregate(df2[,-c(1:2)],by = df2["miR family"],FUN = sum,na.rm=T) #sum counts by family
+gene_vector <- c("miR-150-5p","miR-25-3p/32-5p/92-3p/363-3p/367-3p","miR-142-3p.1",
+                 "miR-17-5p/20-5p/93-5p/106-5p","miR-191-5p",
+                 "miR-15-5p/16-5p/195-5p/322-5p/497-5p","miR-26-5p","miR-138-5p",
+                 "miR-223-3p","miR-342-3p","miR-22-3p","miR-192-5p/215-5p",
+                 "miR-125-5p/351-5p","miR-126-3p.1","miR-199-3p")
+df3 <- subset(df2, df2$`miR family`%in% gene_vector) %>% arrange(factor(`miR family`, levels=gene_vector))
+rownames(df3) <- df3[,1]
+df3.scaled <- as.data.frame(t(scale(t(df3[-1])))) #Zscore normalization. Scaled only works on columns, so need to transform
+setwd(fdir)
+openxlsx::write.xlsx(df2.scaled,"Figure_1D_table.xlsx", rowNames=T)
+#the df was exported and used to create a heatmap using Graphpad
--- a/CB2025_figure_3_RNAseq.R
+++ b/CB2025_figure_3_RNAseq.R
+library(readxl)
+library(ggplot2)
+library(ggrepel)
+library(dplyr)
+library(fgsea)
+library(clusterProfiler)
+library(enrichplot)
+
+##### Directories #####
+#us <- "/Users/Squadrito/"
+us <-"C:/Users/bresesti.chiara/"
+wdir<-paste0(us,"/Dropbox (HSR Global)/90-857433247_RNAseq_Squadrito/05-DGE-NoOut-Corr")
+wdir_CB<-paste0(us, "/Dropbox (HSR Global)/90-857433247_RNAseq_Squadrito/Analysis CB_v2")
+fdir <- paste0(us,"/Dropbox (HSR Global)/CancerGeneTherapy/Cancer Gene Therapy/MS/2024 Bresesti et al/Scripts/plots and tables used in figures")
+
+#### Figure 3A&B ####
+
+#Import df
+setwd(wdir)
+miR_ctrl <- read_excel("edgeR_results.xlsx", sheet = "miR342-control")
+sponge_ctrl <- read_excel("edgeR_results.xlsx", sheet = "spongeBT-control")
+
+#Add DEG color and label for volcano plot
+miR_ctrl$DEG <- "NO"
+miR_ctrl$DEG[miR_ctrl$logFC > 1 & miR_ctrl$PValue < 0.05] <- "UP"
+miR_ctrl$DEG[miR_ctrl$logFC < (-1) & miR_ctrl$PValue < 0.05] <- "DOWN"
+miR_ctrl$DEG_label <- NA
+miR_ctrl$DEG_label[miR_ctrl$DEG != "NO"] <- miR_ctrl$...1[miR_ctrl$DEG != "NO"]
+
+sponge_ctrl$DEG <- "NO"
+sponge_ctrl$DEG[sponge_ctrl$logFC > 1 & sponge_ctrl$PValue < 0.05] <- "UP"
+sponge_ctrl$DEG[sponge_ctrl$logFC < (-1) & sponge_ctrl$PValue < 0.05] <- "DOWN"
+sponge_ctrl$DEG_label <- NA
+sponge_ctrl$DEG_label[sponge_ctrl$DEG != "NO"] <- sponge_ctrl$...1[sponge_ctrl$DEG != "NO"]
+
+#Volcano plot (left panel)
+data <- miR_ctrl
+ggplot(data=data, aes(x=logFC, y=-log10(PValue), col=DEG, label=DEG_label)) +
+  geom_point() + 
+  theme_minimal() +
+  geom_text_repel() +
+  scale_color_manual(values=c("blue", "grey", "red")) +
+  geom_vline(xintercept=c(-1, 1), col="black") +
+  geom_hline(yintercept=-log10(0.05), col="black") +
+  scale_x_continuous(limits = c(-4.1,4.1), breaks = seq(-4,4,1)) +
+  scale_y_continuous(limits = c(0,20)) +
+  xlab(bquote(Log[2](FC))) +
+  ylab(bquote(-Log[10](PVal)))
+
+data <- sponge_ctrl
+ggplot(data=data, aes(x=logFC, y=-log10(PValue), col=DEG, label=DEG_label)) +
+  geom_point() + 
+  theme_minimal() +
+  geom_text_repel() +
+  scale_color_manual(values=c("blue", "grey", "red")) +
+  geom_vline(xintercept=c(-1, 1), col="black") +
+  geom_hline(yintercept=-log10(0.05), col="black") +
+  scale_x_continuous(limits = c(-4.1,4.1), breaks = seq(-4,4,1)) +
+  scale_y_continuous(limits = c(0,20)) +
+  xlab(bquote(Log[2](FC))) +
+  ylab(bquote(-Log[10](PVal)))
+
+#Import miR-342-3p target list (from TargetScan)
+setwd(wdir_CB)
+miR342_targets <-  read_excel("TargetScan8.0__miR-342-3p.predicted_targets.xlsx")
+miR342_targets <-  filter(miR342_targets, miR342_targets$`Cumulative weighted context++ score`< (-0.3))
+
+#ecdf plot (right panel)
+data <- miR_ctrl
+test <-filter(data, data$...1 %in% miR342_targets$'Target gene')
+plot(ecdf(data$logFC), lwd = 2, do.points=F, verticals=T,
+     ylab = "Fraction of DEG",
+     xlab = bquote(Log[2](FC)),
+     xlim=c(-0.5,0.5),
+     ylim=c(0,1),
+     main="ECDF of gene expression: miR vs mut") +
+  lines(ecdf(test$logFC), col= "blue", do.points=F, lwd = 2, verticals=T) +
+  abline(v=0, col="black") + 
+  abline(h=0.5, col="black") +
+  legend("bottomright", c("All genes","miR-342-3p targets"),
+         col = c("black","blue"), lwd=2, cex = 0.7)
+ks.test(test$logFC, data$logFC, alternative = "g") #Kolmogorov-Smirnov test to calculate p-val of miR target distribution *not* greater than average data
+
+data <- sponge_ctrl
+test <-filter(data, data$...1 %in% miR342_targets$'Target gene')
+plot(ecdf(data$logFC), lwd = 2, do.points=F, verticals=T,
+     ylab = "Fraction of DEG",
+     xlab = bquote(Log[2](FC)),
+     xlim=c(-0.3,0.3),
+     ylim=c(0,1),
+     main="ECDF of gene expression: sponge vs scr") +
+  lines(ecdf(test$logFC), col= "red", do.points=F, lwd = 2, verticals=T) +
+  abline(v=0, col="black") + 
+  abline(h=0.5, col="black") +
+  legend("bottomright", c("All genes","miR-342-3p targets"),
+         col = c("black","red"), lwd=2, cex = 0.7)
+ks.test(test$logFC, data$logFC, alternative = "l") #Kolmogorov-Smirnov test to calculate p-val of miR target distribution *not* less than average data
+
+#### Figure 3C&D ####
+
+#Upload df
+setwd(wdir)
+df1<- read_excel("EdgeR_results.xlsx",, sheet = "miR342-control")
+setwd(wdir_CB)
+miDB_sig5 <- readRDS("miDB_sig5.MLS.rds") #GO terms db
+
+#Rename pathways of interest in miDB_sig5
+names(miDB_sig5)[names(miDB_sig5) == "HALLMARK_OXIDATIVE_PHOSPHORYLATION"] <- "Oxydative phosphorylation"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_REGULATION_OF_CHOLESTEROL_METABOLIC_PROCESS"] <- "Regulation of cholesterol metabolic process"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_RESPONSE_TO_INTERLEUKIN_12"] <- "Response to IL12"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_REGULATION_OF_LIPID_BIOSYNTHETIC_PROCESS"] <- "Regulation of lipid biosynthetic process"
+names(miDB_sig5)[names(miDB_sig5) == "GOMF_MHC_CLASS_I_PROTEIN_BINDING"] <- "MHC-I protein binding"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_TUMOR_NECROSIS_FACTOR_MEDIATED_SIGNALING_PATHWAY"] <- "TNFa mediated signalling pathway"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_NEGATIVE_REGULATION_OF_CELL_CYCLE_G2_M_PHASE_TRANSITION"] <- "Negative regulation of cell cycle progression"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_FATTY_ACYL_COA_BIOSYNTHETIC_PROCESS"] <- "Fatty acyl-CoA biosynthetic process"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_RESPONSE_TO_TUMOR_NECROSIS_FACTOR"] <- "Response to TNFa"
+names(miDB_sig5)[names(miDB_sig5) == "HALLMARK_G2M_CHECKPOINT"] <- "G2M checkpoint"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_RESPONSE_TO_TYPE_I_INTERFERON"] <- "Response to type I interferon"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_INTERLEUKIN_1_MEDIATED_SIGNALING_PATHWAY"] <- "IL1 mediated signalling pathway"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_RESPONSE_TO_INTERLEUKIN_1"] <- "Response to IL1"
+names(miDB_sig5)[names(miDB_sig5) == "LPS_RO"] <- "LPS response genes"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_CYTOKINE_MEDIATED_SIGNALING_PATHWAY"] <- "Cytokine mediated signalling pathway"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_MYELOID_CELL_DIFFERENTIATION"] <- "Myeloid cell differentiation"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_INTERLEUKIN_10_PRODUCTION"] <- "IL10 production"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_POSITIVE_REGULATION_OF_ENDOTHELIAL_CELL_PROLIFERATION"] <- "Regulation of endothelial cell proliferation"
+names(miDB_sig5)[names(miDB_sig5) == "GOBP_TUMOR_NECROSIS_FACTOR_SUPERFAMILY_CYTOKINE_PRODUCTION"] <- "TNFa superfamily cytokine production"
+names(miDB_sig5)[names(miDB_sig5) == "HALLMARK_ANGIOGENESIS"] <- "Angiogenesis"
+names(miDB_sig5)[names(miDB_sig5) == "GOMF_PATTERN_RECOGNITION_RECEPTOR_ACTIVITY"] <- "Pattern recognition receptor activity"
+names(miDB_sig5)[names(miDB_sig5) == "PGE2_RO"] <- "PGE2 response genes"
+
+#Filter low expression, NA and order by FC
+df1 <- filter(df1, df1$logCPM>5 & !is.na(df1$...1))
+df1<-df1[order(df1$logFC),]
+df2<-df1$logFC
+names(df2)<-df1$...1
+
+#Run GSEA with fgsea and filter by PVal
+sig <- miDB_sig5
+test1<-fgsea(sig, df2,minSize  = 7,maxSize  =500, nproc=1)
+PvalResult<-filter(test1, test1$padj<= 0.05)
+
+#DotPlot pathways of interest (Fig.3C)
+pathways <- c("Oxydative phosphorylation",
+              "Regulation of cholesterol metabolic process",
+              "Response to IL12",
+              "Regulation of lipid biosynthetic process",
+              "MHC-I protein binding",
+              "TNFa mediated signalling pathway",
+              "Negative regulation of cell cycle progression",
+              "Fatty acyl-CoA biosynthetic process",
+              "Response to TNFa",
+              "G2M checkpoint",
+              "Response to type I interferon",
+              "IL1 mediated signalling pathway",
+              "Response to IL1",
+              "LPS response genes",
+              "Cytokine mediated signalling pathway",
+              "Myeloid cell differentiation",
+              "IL10 production",
+              "Regulation of endothelial cell proliferation",
+              "TNFa superfamily cytokine production",
+              "Angiogenesis",
+              "Pattern recognition receptor activity",
+              "PGE2 response genes")
+
+genelist <- as.data.frame(PvalResult[PvalResult$pathway %in% pathways,])
+ggplot(genelist, aes(x=NES, y=reorder(pathway,NES), size=size ,color=padj)) + 
+  geom_point() +
+  scale_size_area(limits=c(10,450), max_size = 15) +
+  scale_colour_gradient(low="red",high="blue") +
+  labs(y='Pathway',x='NES')
+
+#Run GSEA with ClusterProfiler
+genelist <- data.frame(term = rep(names(miDB_sig5), sapply(miDB_sig5, length)),
+                       gene = unlist(miDB_sig5))
+df2 = sort(df2, decreasing = TRUE)
+test2 <- GSEA(df2,TERM2GENE = genelist)
+
+#Enrichment map (Fig.3D)
+test3 <- filter(test2, ID %in% pathways)
+test3 <- pairwise_termsim(test3)
+emapplot(test3, min_edge = 0.01, color = "NES", layout="fr", repel =T)+
+  scale_fill_gradient2(name=bquote(NES),low="blue", high="red") 
+#N.B. Produces slightly different plot every time, 
+#but connection between pathways stays the same
\ No newline at end of file
--- a/CB2025_figure_5_scRNAseq.R
+++ b/CB2025_figure_5_scRNAseq.R
+library(Seurat)
+library(openxlsx)
+library(readxl)
+library(ggplot2)
+library(dplyr)
+library(fgsea)
+library(pheatmap)
+library(scales)
+library(RColorBrewer)
+library(cetcolor)
+
+
+#username <- "/Users/Squadrito/"
+#username <- "/Users/bresesti.chiara/"
+#wdir <- paste0(username, "Dropbox (HSR Global)/90-935462466_scRNAseq_Bresesti/Analysis_MM/results2/CB1_CB3_CB4")
+#wdir_CB <- paste0(username, "Dropbox (HSR Global)/90-935462466_scRNAseq_Bresesti/CB_scripts/results2")
+#plot_dir <- paste0(username,"/Dropbox (HSR Global)/CancerGeneTherapy/Cancer Gene Therapy/MS/2024 Bresesti et al/Scripts/plots and tables used in figures") # fdir previously
+#dirCB <-paste0(username,"Dropbox (HSR Global)/90-935462466_scRNAseq_Bresesti/CB_scripts")
+#sig <- readRDS(paste0(wdir, "/miDB_sig5.MLS.rds")) #GO terms db
+
+wdir <- "/beegfs/scratch/ric.squadrito/ric.squadrito/90-935462466_scRNAseq_Bresesti/Analysis_MM/results2/CB1_CB3_CB4"
+wdir_CB <- "/beegfs/scratch/ric.squadrito/ric.squadrito/90-935462466_scRNAseq_Bresesti/Analysis_MM/CB_scripts/results2"
+plot_dir <- "/beegfs/scratch/ric.squadrito/ric.squadrito/90-935462466_scRNAseq_Bresesti/Analysis_MM/CB_scripts_final/plots and tables used in figures"
+dirCB <-"/beegfs/scratch/ric.squadrito/ric.squadrito/90-935462466_scRNAseq_Bresesti/Analysis_MM/CB_scripts"
+
+dir.create(plot_dir, showWarnings=F, recursive=T)
+
+# 16357 GO terms db. used for GSEA
+sig <- readRDS("/beegfs/scratch/ric.squadrito/ric.squadrito/90-935462466_scRNAseq_Bresesti/reference/miDB_sig5.MLS.rds")
+
+
+###############################################################################
+
+set.seed(42)
+
+obs1 <- readRDS(paste0(wdir, "/CB1_CB3_CB4_final.rds"))
+
+# Annotate each cell with a sample label based on its original identity (library) and hash ID
+obs1@meta.data$Sample <- "Undefined"
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB1"&obs1@meta.data$hash.ID=="Mouse1"] <- "Ctrl_01"   
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB1"&obs1@meta.data$hash.ID=="Mouse2"] <- "Ctrl_02" 
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB1"&obs1@meta.data$hash.ID=="Mouse3"] <- "Ctrl_03" 
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB3"&obs1@meta.data$hash.ID=="Mouse1"] <- "miR_01"
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB3"&obs1@meta.data$hash.ID=="Mouse2"] <- "miR_02"
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB3"&obs1@meta.data$hash.ID=="Mouse3"] <- "miR_03"
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB4"&obs1@meta.data$hash.ID=="Mouse1"] <- "miR_04"
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB4"&obs1@meta.data$hash.ID=="Mouse2"] <- "miR_02"
+obs1@meta.data$Sample[obs1@meta.data$orig.ident=="CB4"&obs1@meta.data$hash.ID=="Mouse3"] <- "miR_05"
+
+obs1<-FindClusters(obs1, graph.name="RNA_snn_h.orig.ident", resolution=4)
+
+# Manually annotate the clusters
+obs1@meta.data$Annotation.final.CB<-"Undefined"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==0]<- "Monocytes"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==1]<- "TAMs_3"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==2]<- "TAMs_4"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==3]<- "LSECs"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==4]<- "TAMs_1"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==5]<- "Cancer cells"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==6]<- "cDC2_MoDCs"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==7]<- "TAMs_2"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==8]<- "T and NK cells"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==9]<- "Neutrophils"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==10]<- "pre DCs"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==11]<- "KCs"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==12]<- "TAMs_5"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==13]<- "B cells"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==14]<- "Hepatocytes"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==15]<- "Mig cDCs"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==16]<- "Cholangiocytes"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==17]<- "cDC1"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==18]<- "Macrophages"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.0.6==19]<- "pDCs"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.1.2==8]<-"KC-LSEC doublet"
+obs1@meta.data$Annotation.final.CB[obs1@meta.data$RNA_snn_h.orig.ident_res.4==51]<-"Basophils"
+
+
+# Visualize final annotation in Umap (Fig.5A)
+obs1 <- SetIdent(obs1,value="Annotation.final.CB")
+pdf(file = paste(plot_dir, "CB_Annotation.final.CB_Fig.5A.pdf", sep = "/"), width=9, height=7)
+DimPlot(obs1, reduction="umap.harmony.orig.ident", group.by="Annotation.final.CB", label=T, repel=T)
+dev.off()
+
+# Adding a simplified annotation
+obs1@meta.data$Shortlables<-obs1@meta.data$Annotation.final.CB
+DCs<-c("Mig cDCs","pDCs","pre DCs", "cDC1", "cDC2_MoDCs")
+obs1@meta.data$Shortlables[obs1@meta.data$Annotation.final.CB%in%DCs]<- "DCs"
+granu<-c("Neutrophils","Basophils")
+obs1@meta.data$Shortlables[obs1@meta.data$Annotation.final.CB%in%granu]<- "Granulocytes"
+TAMs<-c("TAMs_1", "TAMs_2", "TAMs_3", "TAMs_4", "TAMs_5")
+obs1@meta.data$Shortlables[obs1@meta.data$Annotation.final.CB%in%TAMs]<- "TAMs"
+
+# Dotplot with markers for population (Suppl.Fig.5A)
+obs1 <- SetIdent(obs1,value="Shortlables")
+obs1$Shortlables <- factor(x = obs1$Shortlables, 
+                           levels = c("Cancer cells","Cholangiocytes",
+                                      "Hepatocytes", "LSECs", "KC-LSEC doublet", 
+                                      "KCs", "Macrophages","TAMs", "Monocytes", 
+                                      "Granulocytes","DCs", "B cells", "T and NK cells"))
+gene <- c("Vil1", "Cdx2","Cldn4","Cldn7","Epcam", 
+          "Krt19", "Sox9", "Cftr", "Hnf1b",
+          "Alb", "Ttr", "Hnf4a", "Cyp3a11",
+          "Lyve1", "Stab2", "Fcgr2b", "Tek", 
+          "Vsig4", "Clec4f", "Timd4", 
+          "Cd5l", "Mertk", "Timd4", "Adgre1","Cd68","Marco", 
+          "Itgam", "Cd14","Arg1", "Ccl2", 
+          "Ccr2",  "Itgam", "Cx3cr1",
+          "Ly6g", "S100a8", "S100a9","Mcpt8", "Cpa3",
+          "Cd209a","Itgax", "Flt3","H2-Aa","Xcr1", "Clec9a",
+          "Cd19", "Cd22", "Cd79a", "Ms4a1", "Pax5",
+          "Cd3e", "Cd4", "Cd8a", "Ncr1", "Gzmb")
+pdf(file = paste(plot_dir, "CB_DotPlot_Shortlables_Fig.S5A.pdf", sep="/"), width=12, height=6)
+DotPlot(obs1,features = unique(gene), cols = "RdBu") + 
+  theme(axis.text.x = element_text(angle=45, vjust=1, hjust=1))
+dev.off()
+
+
+# Generate table with distribution clusters by Mouse 
+# Table saved in excel and used to generate a barplot with GraphPad Prism (Suppl.Fig.5B)
+cells_labels <- table(obs1@meta.data$Annotation.final.CB, obs1@meta.data$Sample)
+cells_labels_p <- round(prop.table(table(obs1@meta.data$Annotation.final.CB, obs1@meta.data$Sample), 2) * 100, 1)
+
+write.csv(cells_labels, paste0(plot_dir, "/number_cells_sample_Annotation.final.CB_Fig.S5B.csv"), row.names=T)
+write.csv(cells_labels_p, paste0(plot_dir, "/number_cells_sample_Annotation.final.CB_percentage_Fig.S5B.csv"), row.names=T)
+
+
+#### Analysis of mOrange+ fraction (Fig.5B, Suppl.Fig.5C,D) ####
+
+# The metadata indicating mOrange positivity are: positive_cells (generated with the mapping), mOrange_label (generated with CellRanger), mOrange_union (union of the previous two labels)
+
+# Generate table with mOrange+ cells distribution by cluster
+# Table saved in excel and used to generate a barplot with GraphPad Prism (Suppl.Fig.5C)
+# Suppl.Fig.5D was subsequently generated dividing data from Suppl.Fig.5C and B
+obs2 <- subset(obs1, subset = mOrange_union == "mOrange+")
+cells_labels_orange <- table(obs2@meta.data$Annotation.final.CB, obs2@meta.data$Sample)
+cells_labels_orange_p <- round(prop.table(table(obs2@meta.data$Annotation.final.CB, obs2@meta.data$Sample), 2) * 100, 1)
+
+write.csv(cells_labels_orange, paste0(plot_dir, "/number_cells_sample_Annotation.final.CB_mOrange_fraction_Fig.S5C.csv"), row.names=T)
+write.csv(cells_labels_orange_p, paste0(plot_dir, "/number_cells_sample_Annotation.final.CB_percentage_mOrange_fraction_Fig.S5C.csv"), row.names=T)
+
+
+# DimPlot with overlayed mOrange density (Fig.5B)
+data <- Embeddings(object = obs2[["umap.harmony.orig.ident"]])[(colnames(obs2)), c(1,2)]
+data <- as.data.frame(data)
+
+obs1 <- SetIdent(obs1, value="cells")
+pdf(file = paste(plot_dir, "UMAP_mOrange_cells_Fig.5B.pdf", sep = "/"), width=9, height=7)
+DimPlot(obs1, reduction = "umap.harmony.orig.ident", pt.size = 0.1, cols = "azure3")  + 
+  stat_density_2d(aes_string(x = "UMAPh_1", y = "UMAPh_2", fill = "after_stat(level)"), data=data,
+                  linewidth = 0.4, geom = "density_2d_filled", 
+                  colour = "black", alpha = 0.2, n = 150, h = c(2,2))+
+  scale_fill_gradientn(colours = cet_pal(16, name = "fire"))
+dev.off()
+
+
+#### GSEA (Fig.5C-E) ####
+
+# Subset populations of interest (to plot)
+selected_pop <- c("DCs", "KCs", "TAMs", "Monocytes", "Cancer cells", "LSECs")
+obs3 <- subset(obs1, subset = Shortlables %in% selected_pop)
+
+# Dotplot of Slc7a11 expression by cluster and experimental group (Fig.5C, groups divided in Illustrator)
+obs3 <- SetIdent(obs3, value="Shortlables")
+obs3$Shortlables <- factor(x = obs3$Shortlables, levels = c("LSECs", "Cancer cells", "Monocytes", "TAMs", "KCs", "DCs"))
+pdf(file = paste(plot_dir, "CB_DotPlot_Shortlables_Slc7a11_Fig.5C.pdf", sep = "/"), width=9, height=5)
+DotPlot(obs3, features = "Slc7a11", dot.scale=20, cols = "RdBu", split.by = "PROP.Group") + 
+  theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1)) +
+  coord_flip()
+dev.off()
+
+# Run DEG between groups in each pop
+simpl_DEG <- createWorkbook()
+deg_results <- list()
+for(i in selected_pop){
+  obs3 <- SetIdent(obs3, value="Shortlables")
+  # We want to calculate DGE between miR342 vs miRmut in each cell population in Shortlables
+  markers <- FindMarkers(obs3, ident.1 = "miR342", group.by = "PROP.Group", subset.ident = i, min.pct=0.01, logfc.threshold=0, min.cells.feature=3, min.cells.group=3) # added min.pct=0.01, logfc.threshold=0, min.cells.feature=3, min.cells.group=3
+  markers$diff_pct <- abs(markers$pct.1-markers$pct.2)
+  name <-paste("DEG_simpl", i, sep = "_")
+  deg_results[[name]] <- markers
+  assign(name, markers)
+  addWorksheet(simpl_DEG, name)
+  writeData(simpl_DEG, name, markers, rowNames = T)
+}
+saveWorkbook(simpl_DEG, file = paste0(plot_dir, "/DEG_simpl_Shortlables.xlsx"), overwrite = T)
+
+# Run GSEA for each population
+GSEA_simpl <- data.frame(matrix(nrow = 0, ncol = 9))
+for(i in selected_pop){
+  df1 <- deg_results[[paste0("DEG_simpl_", i)]]
+  df1 <- df1[order(df1$avg_log2FC),]
+  ranks<-df1$avg_log2FC
+  names(ranks)<-rownames(df1)
+  test<-fgsea(pathways = sig, stats = ranks, minSize=5, maxSize=1000, nproc=1, nPermSimple=10000)
+  test$cluster <- i
+  colnames(GSEA_simpl) <- colnames(test)
+  GSEA_simpl <- rbind(GSEA_simpl, test)
+}
+write.xlsx(GSEA_simpl, file = paste0(plot_dir, "/GSEA_simpl_Shortlables.xlsx"))
+
+# Plot barplot for selected gene sets (Fig.5D, names and colors edited on illustrator)
+gene_sets <- c("HALLMARK_TNFA_SIGNALING_VIA_NFKB",
+               "HALLMARK_INFLAMMATORY_RESPONSE",
+               "GOMF_CHEMOKINE_ACTIVITY",
+               "GOBP_RESPONSE_TO_CYTOKINE",
+               "GOBP_CYTOKINE_MEDIATED_SIGNALING_PATHWAY",
+               "HALLMARK_INTERFERON_GAMMA_RESPONSE",
+               "HALLMARK_INTERFERON_ALPHA_RESPONSE",
+               "GOBP_RESPONSE_TO_TYPE_I_INTERFERON",
+               "GOMF_ANTIOXIDANT_ACTIVITY",
+               "GOBP_CELLULAR_OXIDANT_DETOXIFICATION",
+               "GOMF_GLUTATHIONE_PEROXIDASE_ACTIVITY",
+               "GOMF_GLUTATHIONE_TRANSFERASE_ACTIVITY",
+               "GOBP_GLUTATHIONE_DERIVATIVE_METABOLIC_PROCESS",
+               "GOBP_GLUTATHIONE_METABOLIC_PROCESS",
+               "GOBP_ANTIGEN_PROCESSING_AND_PRESENTATION",
+               "GOMF_ANTIGEN_BINDING",
+               "GOMF_MHC_CLASS_II_PROTEIN_COMPLEX_BINDING",
+               "GOMF_MHC_PROTEIN_COMPLEX_BINDING",
+               "GOCC_MHC_CLASS_II_PROTEIN_COMPLEX",
+               "GOCC_MHC_PROTEIN_COMPLEX",
+               "GOBP_LEUKOCYTE_MIGRATION_INVOLVED_IN_INFLAMMATORY_RESPONSE",
+               "GOBP_CYTOKINESIS",
+               "GOBP_MICROTUBULE_CYTOSKELETON_ORGANIZATION",
+               "GOBP_MICROTUBULE_BASED_PROCESS",
+               "GOBP_POSITIVE_REGULATION_OF_CELL_CYCLE_PROCESS",
+               "GOBP_CELL_DIVISION",
+               "HALLMARK_G2M_CHECKPOINT",
+               "GOBP_MITOTIC_CELL_CYCLE",
+               "GOBP_CELL_CYCLE_PHASE_TRANSITION")
+
+plot <- filter(GSEA_simpl, pathway %in% gene_sets)
+plot$cluster <- factor(plot$cluster, levels = c("LSECs", "Cancer cells", "TAMs", "Monocytes","KCs","DCs"))
+
+# Remove the 'HALLMARK_' prefix and other prefixes from the 'pathway' column
+plot$pathway <- gsub(x=plot$pathway, pattern="HALLMARK_|GOBP_|GOMF_|GOCC_", replacement="")
+plot$pathway <- gsub(x=plot$pathway, pattern="_", replacement=" ")
+
+gene_sets <- gsub(x=gene_sets, pattern="HALLMARK_|GOBP_|GOMF_|GOCC_", replacement="")
+gene_sets <- gsub(x=gene_sets, pattern="_", replacement=" ")
+# Reorder the terms
+plot$pathway <- factor(plot$pathway, levels = gene_sets)
+
+write.xlsx(plot, file = paste0(plot_dir, "/GSEA_plotted.xlsx"))
+
+# Plot the GSEA results (Fig5D)
+p <- ggplot(data=plot, aes(x=NES, y=pathway, fill=log10(pval))) + 
+  geom_bar(stat="identity", color="black")+
+  scale_fill_gradientn(
+    colors=c("red","white","blue"),
+    values=rescale(c(-8,log10(0.05),0)),
+    limits=c(-8,0),
+    na.value = "red") +
+  labs(y='Pathway', x='NES')+
+  theme(strip.text = element_text(face = "bold"),
+        axis.text.x = element_text(colour = "black"),
+        axis.text.y = element_text(colour = "black"))+
+  geom_vline(xintercept=0)+
+  facet_wrap(~cluster, ncol = length(unique(plot$cluster)))
+ggsave(filename = paste0(plot_dir, "/GSEA_Fig5D.pdf"), plot=p, width=12, height=7)
+
+
+
+# Create signature file with only signature cytokines for the more stringent GSEA in Fig.5E
+sig.cyto <- sig[15061:16357]
+
+# Define the populations we want to use for this GSEA
+selected_pop2 <- c("B cells","cDC1","cDC2_MoDCs","KCs","Macrophages","Mig cDCs","Monocytes","Neutrophils","pDCs","T and NK cells", "TAMs_1","TAMs_2","TAMs_3","TAMs_4","TAMs_5")
+# Run DEG between groups in each population
+simpl_DEG2 <- createWorkbook()
+deg_results <- list()
+for(i in selected_pop2){
+  obs1 <- SetIdent(obs1, value="Annotation.final.CB")
+  # We want to calculate DGE between miR342 vs miRmut in each cell population in Annotation.final.CB
+  markers <- FindMarkers(obs1, ident.1="miR342", group.by="PROP.Group", subset.ident=i, min.pct=0.01, logfc.threshold=0, min.cells.feature=3, min.cells.group=3) # added min.pct=0.01, logfc.threshold=0, min.cells.feature=3, min.cells.group=3
+  markers$diff_pct <- abs(markers$pct.1-markers$pct.2)
+  name <-paste("DEG_simpl", i, sep = "_")
+  deg_results[[name]] <- markers
+  assign(name, markers)
+  addWorksheet(simpl_DEG2, name)
+  writeData(simpl_DEG2, name, markers, rowNames = T)
+}
+saveWorkbook(simpl_DEG2, file = paste0(plot_dir, "/DEG_Annotation.final.CB.xlsx"), overwrite = T)
+
+
+# Repeat GSEA for cytokines signatures only
+GSEA_cyto <- data.frame(matrix(nrow=0, ncol=9))
+for(i in selected_pop2){
+  df1 <- deg_results[[paste0("DEG_simpl_", i)]]
+  df1<-df1[order(df1$avg_log2FC),]
+  ranks<-df1$avg_log2FC
+  names(ranks)<-rownames(df1)
+  test<-fgsea(pathways = sig.cyto, stats = ranks, minSize=2, maxSize=1000, nproc=1, nPermSimple=30000)
+  test$cluster <- i
+  colnames(GSEA_cyto) <- colnames(test)
+  GSEA_cyto <- rbind(GSEA_cyto,test)
+}
+write.xlsx(GSEA_cyto, file = paste0(plot_dir, "/GSEA_cyto.xlsx"))
+
+# Subset the GSEA_cyto to match the cytokine signature calculated in the populations with the same populations that we have in our scRNAseq.
+# This is necessary because each cytokine was tested and the effect in each population was saved as a different signature.
+df <- GSEA_cyto
+df_Bcells <- df[grepl("B_cell", df$pathway) & df$cluster=="B cells",]
+df_cDC1 <- df[grepl("cDC1", df$pathway) & df$cluster=="cDC1",]
+df_cDC2 <- df[grepl("cDC2", df$pathway) & df$cluster=="cDC2_MoDCs",]
+df_macrophage <- df[grepl("Macrophage", df$pathway) & grepl("TAMs|KCs|Macrophages", df$cluster),]
+df_MigDC <- df[grepl("MigDC", df$pathway) & df$cluster=="Mig cDCs",]
+df_Monocyte <- df[grepl("Monocyte", df$pathway) & df$cluster=="Monocytes",]
+df_Neutrophil <- df[grepl("Neutrophil", df$pathway) & df$cluster=="Neutrophils",]
+df_pDC <- df[grepl("pDC", df$pathway) & df$cluster=="pDCs",]
+df_Tcells <- df[grepl("T_cell_CD8", df$pathway) & df$cluster=="T and NK cells",]
+
+# Combine again all the generated subsets
+df <- rbind(df_Bcells, df_cDC1, df_cDC2, df_macrophage, df_MigDC, df_Monocyte, df_Neutrophil, df_pDC, df_Tcells)
+# Remove the redundant data frames
+rm(df_Bcells, df_cDC1, df_cDC2, df_macrophage, df_MigDC, df_Monocyte, df_Neutrophil, df_pDC, df_Tcells)
+
+# Generate a column indicating the cytokine analysed.
+df$cytokine <- gsub(".*_","",df$pathway)
+df$padj[is.na(df$padj)] <- 1 # Convert the NA into padj=1
+# Assing marks for the significance: *=padj<0.05; **=padj<0.01; ***=padj<0.001.
+df$label <- ""
+df <- df %>% mutate(label = cut(
+  padj,
+  breaks = c(0, 0.001, 0.01, 0.05, 1),
+  label = c("***", "**", "*", "")))
+
+paletteLength <- 100
+myColor <- colorRampPalette(rev(brewer.pal(5, "RdBu")))(paletteLength)
+# Define breaks to set the zero to the center
+df$NES[is.na(df$NES)] <- 0 # Convert the NA into NAS=0
+MIN <- min(df$NES)
+MAX <- max(df$NES)
+myBreaks <- c(seq(MIN, 0, length.out=ceiling(paletteLength/2) + 1), 
+              seq(MAX/paletteLength, MAX, length.out=floor(paletteLength/2)))
+
+# Plot heatmap cytokine signatures (Fig.5E, removed dendrograms in illustrator)
+mat.df <- with(df, tapply(NES, list(cluster, cytokine), FUN = mean))
+mat.label <- with(df, tapply(label, list(cluster, cytokine), FUN = paste))
+
+pheatmap(mat.df, scale = "none", display_numbers = mat.label,
+         clustering_method = "ward.D2",
+         cutree_rows = 2, cutree_cols = 3,
+         col=myColor, breaks = myBreaks, na_col = "grey",
+         filename = paste0(plot_dir, "/Heatmap_cytokine_sig_Fig.5E_new.pdf"), cellwidth=10, cellheight=10) # width=12, height=7
--- a/README.md
+++ b/README.md
+# Bresesti_Cell_Reports_2025
+
+**Reprogramming liver metastasis-associated macrophages towards an anti-tumoral phenotype through enforced miR-342 expression**
+
+Bresesti C, Monti M, Beretta S, Merelli I, Squadrito M, _et al._; 2025
+
+Corresponding Author: Mario Leonardo Squadrito. Email: squadrito.mario@hsr.it.  [![Twitter URL](https://img.shields.io/twitter/url/https/twitter.com/wouter_decoster.svg?style=social&label=Follow%20%40Mariosqua)](https://x.com/Mariosqua)
+
+GEO:  
+[GSE274043](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274043) (single-cell RNA-seq)  
+[GSE274044](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274044) (RNA-seq on iKCs)  
+[GSE274045](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274045) (small RNA-seq on splenic and hepatic cell populations)  
+[GSE274046](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274046) (bulk RNA-seq on splenic and hepatic cell populations)  
+
+
+## Directories and Files
+
+- environment_singlecell5.yml: contains the conda virtual environment that can be used to install all the dependencies.
+- scripts: folder with R scripts used for the analyses
+    - CB2025_figure_1_RNAseq.R
+    - CB2025_figure_3_RNAseq.R
+    - CB2025_figure_5_scRNAseq.R
+    - TCGA_analysis.R
+- data: results of the analyses
+    - plots
+    - tables
+- reference
+    - regev_lab_cell_cycle_mouse.rds: contains the genes involved in the cell cycle in mouse
+    - miDB_sig5.MLS.rds: reference files for GSEA analysis
+    - miDB_sig5.MLS_cytokines.rds: reference files for GSEA analysis
+
+## scRNAseq analysis
+The initial preprocessing of the data, including mapping against the _Mus musculus_ GRCm38 reference genome and gene counting, was done using the 10x Genomics Cell Ranger Software (v7.2.0) using default parameters. The resulting data were imported into R and analyzed with the Seurat package (v5.0.1).
+
--- a/TCGA_analysis.R
+++ b/TCGA_analysis.R
+library(data.table)
+library(survival)
+library(dplyr)
+library(babelgene)
+library(openxlsx)
+library(readxl)
+library(survminer)
+library(gridExtra)
+library(ggplot2)
+##Load dataset
+#username <- "C:/Users/notaro.marco/"
+username <- "/Users/bresesti.chiara/"
+wdir<- paste0(username, "/Dropbox (HSR Global)/CancerGeneTherapy/Cancer Gene Therapy/MS/2024 Bresesti et al Cell Reports/TCGA_analysis")
+setwd(wdir)
+metaD<-data.frame(fread("TCGA_phenotype_denseDataOnlyDownload.tsv.gz", sep='\t',colClasses=c("character"),data.table=FALSE))
+Surv01<-data.frame(fread("Survival_SupplementalTable_S1_20171025_xena_sp", sep='\t',colClasses=c("character"),data.table=FALSE))
+# FPKM01<-fread("tcga_RSEM_Hugo_norm_count")
+FPKM01<-fread("pancanMiRs_EBadjOnProtocolPlatformWithoutRepsWithUnCorrectMiRs_08_04_16.xena.gz")
+FPKM01<-as.data.frame(FPKM01)
+# Annot<-data.frame(fread("probeMap_gencode.v23.annotation.gene.probemap", sep='\t',colClasses=c("character"),data.table=FALSE))
+allGenes <- FPKM01[,1]
+
+
+
+
+#######################################################################
+#####PLOT HR Score of signature for multiple tumor types###############
+#####################################################################
+humanGenes<-list(c("hsa-miR-342-3p"))
+
+
+####create xlsx file with genes, patients and tumor types
+Pan.data3 <- metaD[,]
+Pan.data4 <- merge(Surv01,Pan.data3,by=1)
+Genes_selected <- FPKM01[FPKM01[,1]%in%humanGenes,]
+
+
+rownames(Genes_selected)<-Genes_selected[,1]
+Genes_selected<-Genes_selected[,-1]
+Genes_selected <- data.frame(t(Genes_selected))
+
+
+Genes_selected$sample<-rownames(Genes_selected)
+Pan.data5 <- merge(Genes_selected,Pan.data4,by.y="sample")
+colnames(Pan.data5)
+#setwd(wdir)
+#write.xlsx(Pan.data5, "miR342_patients_survival.xlsx")
+
+
+#############Regression with defined k2
+k2<-0.5 #define quartile for selecting low/high score
+df2 <- NULL
+for (i in unique(Pan.data5$cancer.type.abbreviation)){
+  Pan.data6 <- Pan.data5[Pan.data5$cancer.type.abbreviation%in%i,]
+  if(nrow(Pan.data6)>2){
+    P.OS <- Surv(as.numeric(Pan.data6$OS.time), as.numeric(Pan.data6$OS))
+    cohort.score<-rep(0,nrow(P.OS))
+    M1 <- quantile(Pan.data6$hsa.miR.342.3p,k2)
+    cohort.score[Pan.data6$hsa.miR.342.3p>=M1]<-1
+    a1<-coxph(P.OS ~ as.numeric(cohort.score))
+    df1 <- data.frame(Tumor = unique(Pan.data6$cancer.type.abbreviation),npatients=length(Pan.data6$X_PATIENT), HR = summary(a1)$coefficients[2], SE=summary(a1)$coefficients[3],
+                      p = summary(a1)$coefficients[5] )
+    df2 <- rbind(df2,df1)
+    df2<-df2[(order(df2$p)),]
+  }else{}}
+#write.xlsx(df2, "miR342_HR_by_tumortype.xlsx")
+
+
+###Filters selected tumors
+df3<-df2
+df3<-df3[df3$p<0.1,]
+df3<-df3[df3$npatients>100,]
+df3$significance <- ifelse(df3$p < 0.05, "p<0.05", "NS")
+a<-ggplot(df3, aes(x = reorder(Tumor, HR), y = HR, color = significance, label = significance)) +
+  geom_point(size = 4) +
+  geom_errorbar(aes(ymin = pmax(HR-SE, 0), ymax = HR + SE), width = 0.2) +
+  scale_color_manual(name = "Color", values = c("red", "blue")) +
+  labs(title = "HR by tumor type",
+       x = "Tumor Type",
+       y = "HR") +
+  geom_rect(aes(xmin = -Inf, xmax = Inf, ymin = -Inf, ymax = 1), fill = "lightblue", alpha = 0.01) +
+  geom_rect(aes(xmin = -Inf, xmax = Inf, ymin = 1, ymax = Inf), fill = "pink", alpha = 0.01)+
+  theme_minimal() +
+  theme(axis.text.x = element_text(angle = 45, hjust= 1, color = "Black")) +
+  geom_hline(yintercept = 1, linetype = "dashed", color = "gray") 
+
+
+# pdf("HR_alltumors_342.pdf",width=9,height = 4)
+a
+# dev.off()
+
+
+
+
+####Plot survival of chosen tumors
+###Select type of tumor
+df3<-df3[order(df3$HR),]
+df3<-df3[df3$p<0.05,]
+
+
+# pdf("Survival_***_342",width=10,height = 6)
+par(mfrow = c(2,4))
+survival<-list()
+for (i in df3$Tumor){
+  tumor.type<-i
+  Pan.data6 <- Pan.data5[Pan.data5$cancer.type.abbreviation%in%i,]
+  P.OS <- Surv(as.numeric(Pan.data6$OS.time), as.numeric(Pan.data6$OS))
+  cohort.score<-rep(0,nrow(P.OS))
+  M1 <- quantile(Pan.data6$hsa.miR.342.3p,k2)
+  cohort.score[Pan.data6$hsa.miR.342.3p>=M1]<-1
+  ##plotting survival
+  fit.score <- survfit(P.OS ~ cohort.score)
+  cox_model <- coxph(P.OS ~ as.numeric(cohort.score))
+  p_value <- summary(cox_model)$coefficients["as.numeric(cohort.score)", "Pr(>|z|)"]
+  formatted_p_value <- ifelse(p_value < 0.0001, "<0.0001",  as.numeric(round(p_value,5)))
+  par(las = 0)
+  plot(fit.score, lty = c(1, 1), col = c("blue", "red"), xlab = "Time (d)", ylab = "Overall Survival", lwd = 2, bty = "n",
+       main = paste0("Survival in ", i)) 
+  # Add legend
+  legend(x = max(fit.score$time)/2, y = 1, legend = c("miRNA high", "miRNA low"), lty = c(1, 1), col = c("red", "blue"), lwd = 2,bty = "n")
+  text(x = max(fit.score$time)/1.8, y = 0.70, label = paste("p=", (formatted_p_value)), adj = c(0, 1))
+  text(x = 10, y = 0.05, label = paste("n =", length(cohort.score)), adj = c(0, 1))
+  survival[[i]] <- recordPlot()
+}
+# dev.off()
+
+
+
+###Plot survival of metastastic/primary cancers
+#k2<-0.5
+Pan.data7 <- Pan.data5[Pan.data5$sample_type == "Metastatic",]
+#Pan.data7 <- Pan.data5[Pan.data5$sample_type == "Primary Tumor",]
+P.OS <- Surv(as.numeric(Pan.data7$OS.time), as.numeric(Pan.data7$OS))
+cohort.score<-rep(0,nrow(P.OS))
+M1 <- quantile(Pan.data7$hsa.miR.342.3p,k2)
+cohort.score[Pan.data7$hsa.miR.342.3p>M1]<-1
+fit.score <- survfit(P.OS ~ cohort.score)
+cox_model <- coxph(P.OS ~ as.numeric(cohort.score))
+p_value <- summary(cox_model)$coefficients["as.numeric(cohort.score)", "Pr(>|z|)"]
+formatted_p_value <- ifelse(p_value < 0.0001, "<0.0001",  as.numeric(round(p_value,5)))
+par(las = 0)
+
+
+pdf("Survival_metastatic_342.pdf",width=5,height =5)
+plot(fit.score, lty = c(1, 1), col = c("blue", "red"), xlab = "Time (d)", ylab = "Overall Survival", lwd = 2, bty = "n",
+     main = "Metastatic tumors") 
+#Add legend
+legend(x = max(fit.score$time)/2, y = 1, legend = c("miRNA high", "miRNA low"), lty = c(1, 1), col = c("red", "blue"), lwd = 2,bty = "n")
+text(x = max(fit.score$time)/1.8, y = 0.70, label = paste("p=", (formatted_p_value)), adj = c(0, 1))
+text(x = 10, y = 0.05, label = paste("n =", length(cohort.score)), adj = c(0, 1))
+dev.off()
--- a/environment_singlecell5.yml
+++ b/environment_singlecell5.yml
+name: singlecell5
+channels:
+  - defaults
+  - bioconda
+  - conda-forge
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - _r-mutex=1.0.1=anacondar_1
+  - aioeasywebdav=2.4.0=pyha770c72_0
+  - aiohttp=3.9.1=py311h459d7ec_0
+  - aiosignal=1.3.1=pyhd8ed1ab_0
+  - amply=0.1.6=pyhd8ed1ab_0
+  - anyio=4.8.0=pyhd8ed1ab_0
+  - aom=3.9.1=hac33072_0
+  - appdirs=1.4.4=pyh9f0ad1d_0
+  - argon2-cffi=23.1.0=pyhd8ed1ab_1
+  - argon2-cffi-bindings=21.2.0=py311h9ecbd09_5
+  - arrow=1.3.0=pyhd8ed1ab_1
+  - asttokens=2.4.1=pyhd8ed1ab_0
+  - async-lru=2.0.4=pyhd8ed1ab_1
+  - atk-1.0=2.38.0=h04ea711_2
+  - attmap=0.13.2=pyhd8ed1ab_0
+  - attrs=23.1.0=pyh71513ae_1
+  - aws-c-auth=0.8.0=h205f482_16
+  - aws-c-cal=0.8.1=h1a47875_3
+  - aws-c-common=0.10.6=hb9d3cd8_0
+  - aws-c-compression=0.3.0=h4e1184b_5
+  - aws-c-event-stream=0.5.0=h7959bf6_11
+  - aws-c-http=0.9.2=hefd7a92_4
+  - aws-c-io=0.15.3=h173a860_6
+  - aws-c-mqtt=0.11.0=h11f4f37_12
+  - aws-c-s3=0.7.9=hf454442_0
+  - aws-c-sdkutils=0.2.2=h4e1184b_0
+  - aws-checksums=0.2.2=h4e1184b_4
+  - aws-crt-cpp=0.29.9=hbbd73d0_1
+  - aws-sdk-cpp=1.11.488=h4d475cb_0
+  - azure-core-cpp=1.14.0=h5cfcd09_0
+  - azure-identity-cpp=1.10.0=h113e628_0
+  - azure-storage-blobs-cpp=12.13.0=h3cf044e_1
+  - azure-storage-common-cpp=12.8.0=h736e048_1
+  - azure-storage-files-datalake-cpp=12.12.0=ha633028_1
+  - babel=2.16.0=pyhd8ed1ab_1
+  - backports=1.0=pyhd8ed1ab_3
+  - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
+  - bcrypt=4.1.1=py311h46250e7_0
+  - beautifulsoup4=4.12.3=pyha770c72_1
+  - bedtools=2.31.1=h13024bc_3
+  - binutils_impl_linux-64=2.40=hf600244_0
+  - bleach=6.2.0=pyh29332c3_4
+  - bleach-with-css=6.2.0=h82add2a_4
+  - boto3=1.28.81=pyhd8ed1ab_0
+  - botocore=1.31.82=pyhd8ed1ab_0
+  - brotli=1.1.0=hd590300_1
+  - brotli-bin=1.1.0=hd590300_1
+  - brotli-python=1.1.0=py311hb755f60_1
+  - bwidget=1.9.14=ha770c72_1
+  - bzip2=1.0.8=hd590300_5
+  - c-ares=1.34.4=hb9d3cd8_0
+  - ca-certificates=2025.1.31=hbcca054_0
+  - cached-property=1.5.2=hd8ed1ab_1
+  - cached_property=1.5.2=pyha770c72_1
+  - cachetools=5.3.2=pyhd8ed1ab_0
+  - cairo=1.18.2=h3394656_1
+  - certifi=2025.1.31=pyhd8ed1ab_0
+  - cffi=1.16.0=py311hb3a22ac_0
+  - charset-normalizer=3.3.2=pyhd8ed1ab_0
+  - cmake=3.31.4=h74e3db0_0
+  - coin-or-cbc=2.10.10=h9002f0b_0
+  - coin-or-cgl=0.60.9=h1d3f3f2_0
+  - coin-or-clp=1.17.10=h07f2a63_0
+  - coin-or-osi=0.108.11=h6514dde_1
+  - coin-or-utils=2.11.12=h99da652_1
+  - coincbc=2.10.10=0_metapackage
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - comm=0.1.4=pyhd8ed1ab_0
+  - configargparse=1.7=pyhd8ed1ab_0
+  - connection_pool=0.0.3=pyhd3deb0d_0
+  - cryptography=41.0.7=py311hcb13ee4_1
+  - curl=8.11.1=h332b0f4_0
+  - cycler=0.12.1=pyhd8ed1ab_1
+  - dart-sass=1.58.3=ha770c72_1
+  - datrie=0.8.2=py311h459d7ec_7
+  - dav1d=1.2.1=hd590300_0
+  - debugpy=1.8.0=py311hb755f60_1
+  - decorator=5.1.1=pyhd8ed1ab_0
+  - defusedxml=0.7.1=pyhd8ed1ab_0
+  - deno=1.46.3=hcab8b69_0
+  - deno-dom=0.1.41=h4768de7_0
+  - docutils=0.20.1=py311h38be061_3
+  - dpath=2.1.6=pyha770c72_0
+  - dropbox=11.36.2=pyhd8ed1ab_0
+  - eido=0.2.1=pyhd8ed1ab_0
+  - esbuild=0.19.2=ha770c72_0
+  - exceptiongroup=1.1.3=pyhd8ed1ab_0
+  - executing=2.0.1=pyhd8ed1ab_0
+  - expat=2.6.4=h5888daf_0
+  - fftw=3.3.10=nompi_hf1063bd_110
+  - filechunkio=1.8=py_2
+  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+  - font-ttf-inconsolata=3.000=h77eed37_0
+  - font-ttf-source-code-pro=2.038=h77eed37_0
+  - font-ttf-ubuntu=0.83=hab24e00_0
+  - fontconfig=2.15.0=h7e30c49_1
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - fqdn=1.5.1=pyhd8ed1ab_1
+  - freetype=2.12.1=h267a509_2
+  - fribidi=1.0.10=h36c2ea0_0
+  - frozenlist=1.4.0=py311h459d7ec_1
+  - ftputil=5.0.4=pyhd8ed1ab_0
+  - future=1.0.0=pyhd8ed1ab_1
+  - gcc_impl_linux-64=13.2.0=h338b0a0_2
+  - gdk-pixbuf=2.42.12=hb9ae30d_0
+  - gettext=0.21.1=h27087fc_0
+  - gflags=2.2.2=he1b5a44_1004
+  - gfortran_impl_linux-64=13.2.0=h76e1118_2
+  - ghostscript=10.04.0=h5888daf_0
+  - giflib=5.2.2=hd590300_0
+  - gitdb=4.0.11=pyhd8ed1ab_0
+  - gitpython=3.1.40=pyhd8ed1ab_0
+  - glog=0.7.1=hbabe93e_0
+  - google-api-core=2.24.0=pyhd8ed1ab_0
+  - google-api-python-client=2.107.0=pyhd8ed1ab_0
+  - google-auth=2.23.4=pyhca7485f_0
+  - google-auth-httplib2=0.1.1=pyhd8ed1ab_0
+  - google-cloud-core=2.3.3=pyhd8ed1ab_0
+  - google-cloud-storage=2.3.0=pyh6c4a22f_0
+  - google-crc32c=1.1.2=py311h9b08b9c_5
+  - google-resumable-media=2.6.0=pyhd8ed1ab_0
+  - googleapis-common-protos=1.66.0=pyhff2d567_0
+  - graphite2=1.3.13=h58526e2_1001
+  - graphviz=12.0.0=hba01fac_0
+  - grpcio=1.67.1=py311h9789449_1
+  - gsl=2.7=he838d99_0
+  - gtk2=2.24.33=h6470451_5
+  - gts=0.7.6=h977cf35_4
+  - gxx_impl_linux-64=13.2.0=h338b0a0_2
+  - h11=0.14.0=pyhd8ed1ab_1
+  - h2=4.1.0=pyhd8ed1ab_1
+  - harfbuzz=9.0.0=hda332d3_1
+  - hdf5=1.14.4=nompi_h2d575fe_105
+  - hpack=4.1.0=pyhd8ed1ab_0
+  - htslib=1.21=h566b1c6_1
+  - httpcore=1.0.7=pyh29332c3_1
+  - httplib2=0.22.0=pyhd8ed1ab_0
+  - httpx=0.28.1=pyhd8ed1ab_0
+  - humanfriendly=10.0=pyhd8ed1ab_6
+  - hyperframe=6.1.0=pyhd8ed1ab_0
+  - icu=75.1=he02047a_0
+  - idna=3.4=pyhd8ed1ab_0
+  - imagemagick=7.1.1_41=imagemagick_hcfc5581_0
+  - importlib-metadata=6.8.0=pyha770c72_0
+  - importlib_metadata=6.8.0=hd8ed1ab_0
+  - importlib_resources=6.1.1=pyhd8ed1ab_0
+  - iniconfig=2.0.0=pyhd8ed1ab_0
+  - ipykernel=6.26.0=pyhf8b6a83_0
+  - ipython=8.17.2=pyh41d4057_0
+  - isoduration=20.11.0=pyhd8ed1ab_1
+  - jags=4.3.2=h647a790_1
+  - jbig=2.1=h7f98852_2003
+  - jedi=0.19.1=pyhd8ed1ab_0
+  - jinja2=3.1.2=pyhd8ed1ab_1
+  - jmespath=1.0.1=pyhd8ed1ab_0
+  - json5=0.10.0=pyhd8ed1ab_1
+  - jsonpointer=3.0.0=py311h38be061_1
+  - jsonschema=4.19.2=pyhd8ed1ab_0
+  - jsonschema-specifications=2023.7.1=pyhd8ed1ab_0
+  - jsonschema-with-format-nongpl=4.19.2=pyhd8ed1ab_0
+  - jupyter-lsp=2.2.5=pyhd8ed1ab_1
+  - jupyter_client=8.6.0=pyhd8ed1ab_0
+  - jupyter_core=5.5.0=py311h38be061_0
+  - jupyter_events=0.11.0=pyhd8ed1ab_0
+  - jupyter_server=2.15.0=pyhd8ed1ab_0
+  - jupyter_server_terminals=0.5.3=pyhd8ed1ab_1
+  - jupyterlab=4.3.5=pyhd8ed1ab_0
+  - jupyterlab_pygments=0.3.0=pyhd8ed1ab_2
+  - jupyterlab_server=2.27.3=pyhd8ed1ab_1
+  - kernel-headers_linux-64=2.6.32=he073ed8_16
+  - keyutils=1.6.1=h166bdaf_0
+  - krb5=1.21.3=h659f571_0
+  - lcms2=2.16=hb7c19ff_0
+  - ld_impl_linux-64=2.40=h41732ed_0
+  - lerc=4.0.0=h27087fc_0
+  - lftp=4.9.3=h63b36a4_1
+  - libabseil=20240722.0=cxx17_hbbce691_4
+  - libaec=1.1.3=h59595ed_0
+  - libarrow=19.0.0=hb1bf10f_2_cuda
+  - libarrow-acero=19.0.0=hb826db4_2_cuda
+  - libarrow-dataset=19.0.0=hb826db4_2_cuda
+  - libarrow-substrait=19.0.0=hbf482d9_2_cuda
+  - libavif16=1.1.1=h1909e37_2
+  - libblas=3.9.0=19_linux64_openblas
+  - libbrotlicommon=1.1.0=hd590300_1
+  - libbrotlidec=1.1.0=hd590300_1
+  - libbrotlienc=1.1.0=hd590300_1
+  - libcblas=3.9.0=19_linux64_openblas
+  - libcrc32c=1.1.2=h9c3ff4c_0
+  - libcurl=8.11.1=h332b0f4_0
+  - libde265=1.0.15=h00ab1b0_0
+  - libdeflate=1.23=h4ddbbb0_0
+  - libedit=3.1.20191231=he28a2e2_2
+  - libev=4.33=h516909a_1
+  - libevent=2.1.12=hf998b51_1
+  - libexpat=2.6.4=h5888daf_0
+  - libffi=3.4.2=h7f98852_5
+  - libgcc=14.2.0=h77fa898_1
+  - libgcc-devel_linux-64=13.2.0=ha9c7c90_2
+  - libgcc-ng=14.2.0=h69a702a_1
+  - libgd=2.3.3=h6f5c62b_11
+  - libgfortran=14.2.0=h69a702a_1
+  - libgfortran-ng=14.2.0=h69a702a_1
+  - libgfortran5=14.2.0=hd5240d6_1
+  - libgit2=1.8.4=hd24f944_1
+  - libglib=2.82.2=h2ff4ddf_1
+  - libgomp=14.2.0=h77fa898_1
+  - libgoogle-cloud=2.33.0=h2b5623c_1
+  - libgoogle-cloud-storage=2.33.0=h0121fbd_1
+  - libgrpc=1.67.1=h25350d4_1
+  - libheif=1.18.2=gpl_hffcb242_100
+  - libiconv=1.17=h166bdaf_0
+  - libjpeg-turbo=3.0.0=hd590300_1
+  - liblapack=3.9.0=19_linux64_openblas
+  - liblapacke=3.9.0=19_linux64_openblas
+  - liblzma=5.6.3=hb9d3cd8_1
+  - libnghttp2=1.64.0=h161d5f1_0
+  - libnsl=2.0.1=hd590300_0
+  - libopenblas=0.3.24=pthreads_h413a1c8_0
+  - libparquet=19.0.0=h3f30f2e_2_cuda
+  - libpng=1.6.45=h943b412_0
+  - libprotobuf=5.28.3=h6128344_1
+  - libre2-11=2024.07.02=hbbce691_2
+  - librsvg=2.58.4=hc0ffecb_0
+  - libsanitizer=13.2.0=h7e041cc_2
+  - libsodium=1.0.18=h36c2ea0_1
+  - libsqlite=3.48.0=hee588c1_0
+  - libssh2=1.11.1=hf672d98_0
+  - libstdcxx=14.2.0=hc0a3c3a_1
+  - libstdcxx-devel_linux-64=13.2.0=ha9c7c90_2
+  - libstdcxx-ng=13.2.0=h7e041cc_2
+  - libthrift=0.21.0=h0e7cc3e_0
+  - libtiff=4.7.0=hd9ff511_3
+  - libutf8proc=2.9.0=hb9d3cd8_1
+  - libuuid=2.38.1=h0b41bf4_0
+  - libuv=1.50.0=hb9d3cd8_0
+  - libwebp=1.5.0=hae8dbeb_0
+  - libwebp-base=1.5.0=h851e524_0
+  - libxcb=1.17.0=h8a09558_0
+  - libxcrypt=4.4.36=hd590300_1
+  - libxml2=2.13.5=h8d12d68_1
+  - libzlib=1.3.1=hb9d3cd8_2
+  - logmuse=0.2.6=pyh8c360ce_0
+  - lz4-c=1.10.0=h5888daf_1
+  - make=4.3=hd18ef5c_1
+  - markdown-it-py=3.0.0=pyhd8ed1ab_0
+  - markupsafe=2.1.3=py311h459d7ec_1
+  - matplotlib-base=3.10.0=py311h2b939e6_0
+  - matplotlib-inline=0.1.6=pyhd8ed1ab_0
+  - mdurl=0.1.0=pyhd8ed1ab_0
+  - mistune=3.1.1=pyhd8ed1ab_0
+  - multidict=6.0.4=py311h459d7ec_1
+  - munkres=1.0.7=py_1
+  - nbconvert-core=7.16.6=pyh29332c3_0
+  - nbformat=5.9.2=pyhd8ed1ab_0
+  - ncbi-vdb=3.0.8=hdbdd923_0
+  - ncurses=6.5=h2d0b736_2
+  - nest-asyncio=1.5.8=pyhd8ed1ab_0
+  - notebook-shim=0.2.4=pyhd8ed1ab_1
+  - numpy=1.26.2=py311h64a7726_0
+  - oauth2client=4.1.3=py_0
+  - openjpeg=2.5.2=he7f1fd0_0
+  - openssl=3.4.1=h7b32b05_0
+  - orc=2.0.3=h12ee42a_2
+  - ossuuid=1.6.2=hf484d3e_1000
+  - overrides=7.7.0=pyhd8ed1ab_1
+  - packaging=23.2=pyhd8ed1ab_0
+  - pandas=2.1.4=py311h320fe9a_0
+  - pandoc=3.4=ha770c72_0
+  - pandocfilters=1.5.0=pyhd8ed1ab_0
+  - pango=1.54.0=h3a902e7_3
+  - paramiko=3.3.1=pyhd8ed1ab_0
+  - parso=0.8.3=pyhd8ed1ab_0
+  - pcre2=10.44=hba22ea6_2
+  - peppy=0.35.7=pyhd8ed1ab_0
+  - perl=5.32.1=7_hd590300_perl5
+  - perl-alien-build=2.84=pl5321h7b50bb2_0
+  - perl-alien-libxml2=0.17=pl5321h577a1d6_1
+  - perl-app-cpanminus=1.7048=pl5321hd8ed1ab_0
+  - perl-business-isbn=3.007=pl5321hd8ed1ab_0
+  - perl-business-isbn-data=20210112.006=pl5321hd8ed1ab_0
+  - perl-capture-tiny=0.48=pl5321ha770c72_1
+  - perl-carp=1.50=pl5321hd8ed1ab_0
+  - perl-constant=1.33=pl5321hd8ed1ab_0
+  - perl-data-dumper=2.183=pl5321hd590300_0
+  - perl-encode=3.21=pl5321hb9d3cd8_1
+  - perl-exporter=5.74=pl5321hd8ed1ab_0
+  - perl-extutils-makemaker=7.70=pl5321hd8ed1ab_0
+  - perl-ffi-checklib=0.28=pl5321hdfd78af_0
+  - perl-file-chdir=0.1011=pl5321hd8ed1ab_0
+  - perl-file-path=2.18=pl5321hd8ed1ab_0
+  - perl-file-temp=0.2304=pl5321hd8ed1ab_0
+  - perl-file-which=1.24=pl5321hd8ed1ab_0
+  - perl-importer=0.026=pl5321hd8ed1ab_0
+  - perl-mime-base64=3.16=pl5321hb9d3cd8_2
+  - perl-parent=0.243=pl5321hd8ed1ab_0
+  - perl-path-tiny=0.124=pl5321hd8ed1ab_0
+  - perl-pathtools=3.75=pl5321hb9d3cd8_1
+  - perl-scope-guard=0.21=pl5321hd8ed1ab_0
+  - perl-storable=3.15=pl5321hb9d3cd8_0
+  - perl-sub-info=0.002=pl5321hd8ed1ab_0
+  - perl-term-table=0.024=pl5321hdfd78af_0
+  - perl-test-fatal=0.016=pl5321ha770c72_0
+  - perl-test-warnings=0.031=pl5321ha770c72_0
+  - perl-test2-suite=0.000163=pl5321hdfd78af_0
+  - perl-try-tiny=0.31=pl5321ha770c72_0
+  - perl-uri=5.17=pl5321ha770c72_0
+  - perl-xml-libxml=2.0210=pl5321hf886d80_0
+  - perl-xml-namespacesupport=1.12=pl5321hd8ed1ab_0
+  - perl-xml-sax=1.02=pl5321hd8ed1ab_0
+  - perl-xml-sax-base=1.09=pl5321hd8ed1ab_0
+  - perl-xsloader=0.24=pl5321hd8ed1ab_0
+  - pexpect=4.8.0=pyh1a96a4e_2
+  - pickleshare=0.7.5=py_1003
+  - pip=23.3.1=pyhd8ed1ab_0
+  - pixman=0.44.2=h29eaf8c_0
+  - pkg-config=0.29.2=h4bc722e_1009
+  - pkgutil-resolve-name=1.3.10=pyhd8ed1ab_1
+  - plac=1.4.1=pyhd8ed1ab_1
+  - platformdirs=3.11.0=pyhd8ed1ab_0
+  - pluggy=1.3.0=pyhd8ed1ab_0
+  - ply=3.11=py_1
+  - prettytable=3.9.0=pyhd8ed1ab_0
+  - prometheus_client=0.21.1=pyhd8ed1ab_0
+  - prompt-toolkit=3.0.39=pyha770c72_0
+  - prompt_toolkit=3.0.39=hd8ed1ab_0
+  - proto-plus=1.25.0=pyhd8ed1ab_1
+  - protobuf=5.28.3=py311hfdbb021_0
+  - psutil=5.9.5=py311h459d7ec_1
+  - pthread-stubs=0.4=h36c2ea0_1001
+  - ptyprocess=0.7.0=pyhd3deb0d_0
+  - pulp=2.7.0=py311h38be061_1
+  - pure_eval=0.2.2=pyhd8ed1ab_0
+  - pyasn1=0.5.0=pyhd8ed1ab_0
+  - pyasn1-modules=0.3.0=pyhd8ed1ab_0
+  - pybktree=1.1=pyh9f0ad1d_0
+  - pycparser=2.21=pyhd8ed1ab_0
+  - pygments=2.16.1=pyhd8ed1ab_0
+  - pynacl=1.5.0=py311h459d7ec_3
+  - pyopenssl=23.3.0=pyhd8ed1ab_0
+  - pyparsing=3.1.1=pyhd8ed1ab_0
+  - pysam=0.22.1=py311h1f0e11c_2
+  - pysftp=0.2.9=py_1
+  - pysocks=1.7.1=pyha2e5f31_6
+  - pytest=7.4.3=pyhd8ed1ab_0
+  - python=3.11.11=h9e4cc4f_1_cpython
+  - python-dateutil=2.8.2=pyhd8ed1ab_0
+  - python-fastjsonschema=2.18.1=pyhd8ed1ab_0
+  - python-irodsclient=1.1.9=pyhd8ed1ab_0
+  - python-json-logger=2.0.7=pyhd8ed1ab_0
+  - python-tzdata=2023.3=pyhd8ed1ab_0
+  - python_abi=3.11=4_cp311
+  - pytz=2023.3.post1=pyhd8ed1ab_0
+  - pyu2f=0.1.5=pyhd8ed1ab_0
+  - pyyaml=6.0.1=py311h459d7ec_1
+  - pyzmq=25.1.2=py311h34ded2d_0
+  - qhull=2020.2=h434a139_5
+  - r-arrow=19.0.0=r44h5888daf_0
+  - r-askpass=1.2.1=r44h2b5f3a1_0
+  - r-assertthat=0.2.1=r44hc72bb7e_5
+  - r-base=4.4.2=hc737e89_2
+  - r-base64enc=0.1_3=r44hb1dbf0f_1007
+  - r-bit=4.5.0.1=r44h2b5f3a1_0
+  - r-bit64=4.5.2=r44h2b5f3a1_0
+  - r-bslib=0.8.0=r44hc72bb7e_0
+  - r-cachem=1.1.0=r44hb1dbf0f_1
+  - r-cairo=1.6_2=r44h232ff4d_2
+  - r-cli=3.6.3=r44h0d4f4ea_1
+  - r-coda=0.19_4.1=r44hc72bb7e_1
+  - r-codetools=0.2_20=r44hc72bb7e_1
+  - r-colorspace=2.1_1=r44hdb488b9_0
+  - r-cpp11=0.5.1=r44hc72bb7e_0
+  - r-crayon=1.5.3=r44hc72bb7e_1
+  - r-credentials=2.0.2=r44hc72bb7e_0
+  - r-curl=6.0.1=r44h2700575_0
+  - r-digest=0.6.37=r44h0d4f4ea_0
+  - r-dplyr=1.1.4=r44h0d4f4ea_1
+  - r-ellipsis=0.3.2=r44hb1dbf0f_3
+  - r-evaluate=1.0.3=r44hc72bb7e_0
+  - r-fansi=1.0.6=r44hb1dbf0f_1
+  - r-farver=2.1.2=r44ha18555a_1
+  - r-fastmap=1.2.0=r44ha18555a_1
+  - r-fontawesome=0.5.3=r44hc72bb7e_0
+  - r-fs=1.6.5=r44h93ab643_0
+  - r-future=1.34.0=r44h785f33e_0
+  - r-future.apply=1.11.3=r44hc72bb7e_0
+  - r-generics=0.1.3=r44hc72bb7e_3
+  - r-gert=2.1.4=r44h017ce79_0
+  - r-ggplot2=3.5.1=r44hc72bb7e_1
+  - r-globals=0.16.3=r44hc72bb7e_1
+  - r-glue=1.8.0=r44h2b5f3a1_0
+  - r-gridextra=2.3=r44hc72bb7e_1006
+  - r-gtable=0.3.6=r44hc72bb7e_0
+  - r-highr=0.11=r44hc72bb7e_1
+  - r-htmltools=0.5.8.1=r44ha18555a_1
+  - r-isoband=0.2.7=r44ha18555a_3
+  - r-jquerylib=0.1.4=r44hc72bb7e_3
+  - r-jsonlite=1.8.9=r44h2b5f3a1_0
+  - r-knitr=1.49=r44hc72bb7e_0
+  - r-labeling=0.4.3=r44hc72bb7e_1
+  - r-later=1.4.1=r44h93ab643_0
+  - r-lattice=0.22_6=r44hb1dbf0f_1
+  - r-lifecycle=1.0.4=r44hc72bb7e_1
+  - r-listenv=0.9.1=r44hc72bb7e_1
+  - r-magick=2.8.5=r44h93ab643_0
+  - r-magrittr=2.0.3=r44hb1dbf0f_3
+  - r-mass=7.3_64=r44h2b5f3a1_0
+  - r-matrix=1.6_5=r44he966344_1
+  - r-matrixstats=1.5.0=r44h2b5f3a1_0
+  - r-memoise=2.0.1=r44hc72bb7e_3
+  - r-mgcv=1.9_1=r44h0d28552_1
+  - r-mime=0.12=r44hb1dbf0f_3
+  - r-munsell=0.5.1=r44hc72bb7e_1
+  - r-nlme=3.1_165=r44hbcb9c34_1
+  - r-openssl=2.2.2=r44he8289e2_0
+  - r-packrat=0.9.2=r44hc72bb7e_1
+  - r-parallelly=1.41.0=r44h2b5f3a1_0
+  - r-pillar=1.10.1=r44hc72bb7e_0
+  - r-pkgconfig=2.0.3=r44hc72bb7e_4
+  - r-pki=0.1_14=r44he8289e2_2
+  - r-plyr=1.8.9=r44ha18555a_1
+  - r-processx=3.8.5=r44h2b5f3a1_0
+  - r-ps=1.8.1=r44h2b5f3a1_0
+  - r-purrr=1.0.2=r44hdb488b9_1
+  - r-quarto=1.4.4=r44hc72bb7e_1
+  - r-r6=2.5.1=r44hc72bb7e_3
+  - r-rappdirs=0.3.3=r44hb1dbf0f_3
+  - r-rcolorbrewer=1.1_3=r44h785f33e_3
+  - r-rcpp=1.0.14=r44h93ab643_0
+  - r-rcppannoy=0.0.22=r44ha18555a_1
+  - r-rcpparmadillo=14.2.2_1=r44hb79369c_0
+  - r-rcpptoml=0.2.2=r44ha18555a_2
+  - r-renv=1.0.11=r44hc72bb7e_0
+  - r-reshape2=1.4.4=r44h0d4f4ea_4
+  - r-rjags=4_16=r44h93ab643_1
+  - r-rlang=1.1.5=r44h93ab643_0
+  - r-rmarkdown=2.29=r44hc72bb7e_0
+  - r-rsconnect=1.3.3=r44hc72bb7e_0
+  - r-rstudioapi=0.17.1=r44hc72bb7e_0
+  - r-sass=0.4.9=r44ha18555a_1
+  - r-scales=1.3.0=r44hc72bb7e_1
+  - r-sctransform=0.4.1=r44hb424bfc_1
+  - r-stringi=1.8.4=r44h33cde33_3
+  - r-stringr=1.5.1=r44h785f33e_1
+  - r-sys=3.4.3=r44h2b5f3a1_0
+  - r-systemfonts=1.1.0=r44h38d38ca_1
+  - r-textshaping=0.4.0=r44ha47bcaa_2
+  - r-tibble=3.2.1=r44hdb488b9_3
+  - r-tidyselect=1.2.1=r44hc72bb7e_1
+  - r-tinytex=0.54=r44hc72bb7e_0
+  - r-utf8=1.2.4=r44hb1dbf0f_1
+  - r-vctrs=0.6.5=r44h0d4f4ea_1
+  - r-viridislite=0.4.2=r44hc72bb7e_2
+  - r-withr=3.0.2=r44hc72bb7e_0
+  - r-xfun=0.50=r44h93ab643_0
+  - r-yaml=2.3.10=r44hdb488b9_0
+  - r-zip=2.3.1=r44hb1dbf0f_1
+  - rav1e=0.6.6=he8a937b_2
+  - re2=2024.07.02=h9925aae_2
+  - readline=8.2=h8228510_1
+  - referencing=0.30.2=pyhd8ed1ab_0
+  - regex=2024.11.6=py311h9ecbd09_0
+  - requests=2.31.0=pyhd8ed1ab_0
+  - reretry=0.11.8=pyhd8ed1ab_0
+  - rfc3339-validator=0.1.4=pyhd8ed1ab_1
+  - rfc3986-validator=0.1.1=pyh9f0ad1d_0
+  - rhash=1.4.5=hb9d3cd8_0
+  - rich=13.6.0=pyhd8ed1ab_0
+  - rpds-py=0.13.2=py311h46250e7_0
+  - rsa=4.9=pyhd8ed1ab_0
+  - s2n=1.5.11=h072c03f_0
+  - s3transfer=0.7.0=pyhd8ed1ab_0
+  - samtools=1.21=h96c455f_1
+  - sed=4.8=he412f7d_0
+  - send2trash=1.8.3=pyh0d859eb_1
+  - setuptools=68.2.2=pyhd8ed1ab_0
+  - setuptools-scm=8.0.4=pyhd8ed1ab_0
+  - six=1.16.0=pyh6c4a22f_0
+  - slacker=0.14.0=py_0
+  - smart_open=6.4.0=pyhd8ed1ab_0
+  - smmap=5.0.0=pyhd8ed1ab_0
+  - snakemake=7.32.4=hdfd78af_1
+  - snakemake-minimal=7.32.4=pyhdfd78af_0
+  - snappy=1.2.1=h8bd8927_1
+  - sniffio=1.3.1=pyhd8ed1ab_1
+  - soupsieve=2.5=pyhd8ed1ab_1
+  - sra-tools=3.0.8=h9f5acd7_0
+  - stack_data=0.6.2=pyhd8ed1ab_0
+  - star=2.7.11b=h5ca1c30_5
+  - stone=3.3.1=pyhd8ed1ab_0
+  - stopit=1.1.2=py_0
+  - stress-ng=0.17.03=h2797004_0
+  - svt-av1=2.3.0=h5888daf_0
+  - sysroot_linux-64=2.12=he073ed8_16
+  - tabulate=0.9.0=pyhd8ed1ab_1
+  - terminado=0.18.1=pyh0d859eb_0
+  - throttler=1.2.2=pyhd8ed1ab_0
+  - tinycss2=1.4.0=pyhd8ed1ab_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - tktable=2.10=h0c5db8f_5
+  - tomli=2.0.1=pyhd8ed1ab_0
+  - toposort=1.10=pyhd8ed1ab_0
+  - tornado=6.3.3=py311h459d7ec_1
+  - traitlets=5.13.0=pyhd8ed1ab_0
+  - types-python-dateutil=2.9.0.20241206=pyhd8ed1ab_0
+  - typing-extensions=4.8.0=hd8ed1ab_0
+  - typing_extensions=4.8.0=pyha770c72_0
+  - typing_utils=0.1.0=pyhd8ed1ab_1
+  - typst=0.11.0=he8a937b_0
+  - tzdata=2025a=h78e105d_0
+  - ubiquerg=0.6.3=pyhd8ed1ab_0
+  - umi_tools=1.1.6=py311haab0aaa_0
+  - unicodedata2=16.0.0=py311h9ecbd09_0
+  - uri-template=1.3.0=pyhd8ed1ab_1
+  - uritemplate=4.1.1=pyhd8ed1ab_0
+  - urllib3=1.26.18=pyhd8ed1ab_0
+  - veracitools=0.1.3=py_0
+  - wcwidth=0.2.9=pyhd8ed1ab_0
+  - webcolors=24.11.1=pyhd8ed1ab_0
+  - webencodings=0.5.1=pyhd8ed1ab_3
+  - websocket-client=1.8.0=pyhd8ed1ab_1
+  - wheel=0.41.3=pyhd8ed1ab_0
+  - wrapt=1.16.0=py311h459d7ec_0
+  - x265=3.5=h924138e_3
+  - xorg-kbproto=1.0.7=h7f98852_1002
+  - xorg-libice=1.1.1=hd590300_0
+  - xorg-libsm=1.2.4=h7391055_0
+  - xorg-libx11=1.8.10=h4f16b4b_1
+  - xorg-libxau=1.0.11=hd590300_0
+  - xorg-libxdmcp=1.1.3=h7f98852_0
+  - xorg-libxext=1.3.6=hb9d3cd8_0
+  - xorg-libxrender=0.9.11=hd590300_0
+  - xorg-libxt=1.3.0=hd590300_1
+  - xorg-renderproto=0.11.1=h7f98852_1002
+  - xorg-xextproto=7.3.0=h0b41bf4_1003
+  - xorg-xproto=7.0.31=h7f98852_1007
+  - xz=5.2.6=h166bdaf_0
+  - yaml=0.2.5=h7f98852_2
+  - yarl=1.9.3=py311h459d7ec_0
+  - yte=1.5.1=pyha770c72_2
+  - zeromq=4.3.5=h59595ed_0
+  - zipp=3.17.0=pyhd8ed1ab_0
+  - zlib=1.3.1=hb9d3cd8_2
+  - zstd=1.5.6=ha6fb4c9_0
+  - pip:
+      - absl-py==2.1.0
+      - anndata==0.8.0
+      - arboreto==0.1.6
+      - array-api-compat==1.6
+      - bokeh==3.3.2
+      - boltons==23.1.1
+      - chex==0.1.86
+      - click==8.1.7
+      - cloudpickle==3.0.0
+      - contextlib2==21.6.0
+      - contourpy==1.2.0
+      - ctxcore==0.2.0
+      - cytoolz==0.12.2
+      - dask==2023.12.0
+      - dill==0.3.7
+      - distributed==2023.12.0
+      - dnspython==2.6.1
+      - docrep==0.3.2
+      - et-xmlfile==1.1.0
+      - etils==1.8.0
+      - filelock==3.13.4
+      - flax==0.8.2
+      - fonttools==4.51.0
+      - frozendict==2.3.10
+      - fsspec==2023.12.2
+      - h5py==3.10.0
+      - hyperopt==0.1.2
+      - igraph==0.10.8
+      - interlap==0.2.7
+      - jax==0.4.26
+      - jaxlib==0.4.26
+      - joblib==1.3.2
+      - kiwisolver==1.4.5
+      - legacy-api-wrap==1.4
+      - leidenalg==0.10.1
+      - lightning==2.1.4
+      - lightning-utilities==0.11.2
+      - llvmlite==0.41.1
+      - locket==1.0.0
+      - loompy==3.0.7
+      - lz4==4.3.2
+      - matplotlib==3.8.4
+      - ml-collections==0.1.1
+      - ml-dtypes==0.4.0
+      - mpmath==1.3.0
+      - msgpack==1.0.7
+      - mudata==0.2.3
+      - multipledispatch==1.0.0
+      - multiprocessing-on-dill==3.5.0a4
+      - natsort==8.4.0
+      - nbclient==0.9.0
+      - networkx==3.2.1
+      - numba==0.58.1
+      - numexpr==2.8.8
+      - numpy-groupies==0.10.2
+      - numpyro==0.14.0
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==8.9.2.26
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-nccl-cu12==2.19.3
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.1.105
+      - openpyxl==3.1.5
+      - opt-einsum==3.3.0
+      - optax==0.2.2
+      - orbax-checkpoint==0.5.10
+      - partd==1.4.1
+      - patsy==0.5.6
+      - pillow==10.1.0
+      - pyarrow==14.0.1
+      - pyarrow-hotfix==0.6
+      - pymongo==4.6.3
+      - pynndescent==0.5.11
+      - pyro-api==0.1.2
+      - pyro-ppl==1.9.0
+      - pyscenic==0.12.1
+      - pytorch-lightning==2.2.3
+      - quarto==0.1.0
+      - scanpy==1.10.1
+      - scikit-learn==1.3.2
+      - scikit-misc==0.3.1
+      - scipy==1.11.4
+      - scvi-tools==1.1.2
+      - seaborn==0.13.2
+      - session-info==1.0.0
+      - sortedcontainers==2.4.0
+      - statsmodels==0.14.2
+      - stdlib-list==0.10.0
+      - sympy==1.12
+      - tblib==3.0.0
+      - tensorstore==0.1.56
+      - texttable==1.7.0
+      - threadpoolctl==3.2.0
+      - toolz==0.12.0
+      - torch==2.2.2
+      - torchmetrics==1.3.2
+      - tqdm==4.66.1
+      - triton==2.2.0
+      - umap-learn==0.5.5
+      - xlrd==2.0.1
+      - xyzservices==2023.10.1
+      - zict==3.0.0
+prefix: /opt/common/tools/ric.tiget/mambaforge/envs/singlecell5
--- a/reference/miDB_sig5.MLS.rds
+++ b/reference/miDB_sig5.MLS.rds
--- a/reference/miDB_sig5.MLS_cytokines.rds
+++ b/reference/miDB_sig5.MLS_cytokines.rds
--- a/reference/regev_lab_cell_cycle_mouse.rds
+++ b/reference/regev_lab_cell_cycle_mouse.rds