R Notebook Figure 5b

Please use the same folder as work directory as the data files. 1. Remove anything left in the datafiles

If necesearry please install the following packages:2
if (!requireNamespace("BiocManager", quietly = TRUE))
    install.packages("BiocManager")
BiocManager::install("clusterProfiler")
BiocManager::install("ReactomePA") 
BiocManager::install("rrvgo")
BiocManager::install("enrichplot")
BiocManager::install("msigdbr")
BiocManager::install("org.Hs.eg.db")
BiocManager::install("AnnotationDbi")
install.packages("ggplot2")
install.packages("glue")
BiocManager::install("fgsea")
install.packages("mulea")

2. Reading in necesearry packages

3. Data input and prepearation for enrtichment analysis THe working directory to be ecpected to be the folder of the Rmd file

PPI network propagation output

outcome_uc <- read.csv("uc_only_ppi_10k.txt", sep="\t", row.names = 1)
head(outcome_uc)

Reactome gene annotation file

reactome_ontology <- read_gmt("ReactomePathways.gmt")

reactome_ontology <- reactome_ontology %>% 
rename(ontology_id = "ontology_id",
    ontology_name = "ontology_name",
    list_of_values = "list_of_values")
head(reactome_ontology)      

Filtering onytology for minimum 5 and maximmum 400 elments - excluding really large and really small patheways. We can change theese settings later.

reactome_ontology_filtered <- filter_ontology(gmt = reactome_ontology,
                                        min_nr_of_elements = 5,
                                        max_nr_of_elements = 500)

OmniPath newtwork file

op <- read.csv("OmniPath_27_10_2021_directed.ncol", sep=" ", header = FALSE, row.names = NULL)
head(op)

head(outcome_uc)

filtered_outcome_uc <- outcome_uc[outcome_uc$Z_Count>0,]
head(filtered_outcome_uc)

bg <- unique(c(op$V1,op$V2))

# Translating genes in the background and outcome data to gene symbols

# Translate background genes
bg_symbols <- mapIds(org.Hs.eg.db, keys = bg, column = "SYMBOL", keytype = "UNIPROT", multiVals = "first")

4. Creating Figure 4/b

histogramplot_uc <- ggplot(filtered_outcome_uc, aes(x=Z_Count)) + 
    geom_histogram(colour="white", fill="orange", binwidth = 50)+
    ylab("Number of individual proteins") + xlab("Number of patients") +
    geom_vline(aes(xintercept=100),
            color="black", linetype="dashed", size=1) + 
    scale_x_continuous(breaks=seq(0,1400,200)) + theme_light()
    theme(panel.background = element_rect(fill = "black")) +
    theme(plot.background = element_rect(fill = "white", colour = "white")) +
    theme(axis.title.x = element_text(colour = "black", size = 10)) +
    theme(axis.title.y = element_text(colour = "black", size = 10)) +
    theme(axis.text = element_text(color= "black", size = 10)) +
    theme(axis.line = element_line(color = "black")) +
    theme(panel.grid.minor = element_blank())
histogramplot_uc

5. Enrichmnet and creating Figure 2c

commonly_afffected_genes_uc <- filtered_outcome_uc[filtered_outcome_uc$Z_Count>100,] 

dim(commonly_afffected_genes_uc)

commonly_afffected_uc_genes_symbols <- mapIds(org.Hs.eg.db, keys = row.names(commonly_afffected_genes_uc), 
column = "SYMBOL", keytype = "UNIPROT", multiVals = "first")

ora_model <- ora(gmt = reactome_ontology_filtered, 
                 # Test set variable
                 element_names = commonly_afffected_uc_genes_symbols, 
                 # Background set variable
                 background_element_names = bg_symbols, 
                 # p-value adjustment method
                 p_value_adjustment_method = "eFDR", 
                 # Number of permutations
                 number_of_permutations = 10000,
                 # Number of processor threads to use
                 nthreads = 2, 
                 # Setting a random seed for reproducibility
                 random_seed = 42) 

reactome_results_uc_ppi <- run_test(ora_model)

reactome_results_uc_ppi$GeneRatio <- reactome_results_uc_ppi$nr_common_with_tested_elements / length(commonly_afffected_uc_genes_symbols)
sig_results_uc_ppi <- reactome_results_uc_ppi %>%
    # Rows where the eFDR < 0.05
    filter(eFDR < 0.1) %>%
    # Arrange the rows by the gene ratio for plotting
    arrange(desc(GeneRatio))
sig_results_uc_ppi$ontology_id <- factor(sig_results_uc_ppi$ontology_id,
levels = sig_results_uc_ppi[order(sig_results_uc_ppi$GeneRatio, decreasing = FALSE), "ontology_id"])
sig_results_uc_ppi

write.csv(reactome_results_uc_ppi, glue("Reactome_UC_PPI_100_cutoff_ora_results.csv"), row.names = FALSE)

Label formatting

sig_results_uc_ppi$formed_id <- gsub("_", " ", sig_results_uc_ppi$ontology_id)
sig_results_uc_ppi$formed_id <- factor(sig_results_uc_ppi$formed_id,
                                    levels = sig_results_uc_ppi[order(sig_results_uc_ppi$GeneRatio,
                                    decreasing = FALSE), "formed_id"])

Adding a small amount for the fDR calcuation based on the MULEA calcautions.

sig_results_uc_ppi$eFDR = sig_results_uc_ppi$eFDR +10^-12

dotplot_reactome_uc_ppi <- ggplot(sig_results_uc_ppi[1:20,], aes(x=GeneRatio, y=formed_id)) +
    geom_point(aes(size=nr_common_with_tested_elements, colour=eFDR)) +
    scale_y_discrete(labels = label_wrap(50)) + 
    scale_color_continuous(low="red", high="blue", 
                           limits=c(10^-5, 0.1),
                           trans = "log10", name="Emprical FDR")
                

dotplot_reactome_uc_ppi <- dotplot_reactome_uc_ppi +
    scale_size(limits = c(2,20), range = c(2,15), name = "Number of genes") + 
    xlim(0, 0.23) +
    xlab("Gene Ratio") +
    ylab("Reactome pathways") +
    theme_light() +
    theme(rect=element_rect(fill="white")) +
    theme(panel.background = element_rect(fill = "white")) +
    theme(plot.background = element_rect(fill = "white")) +
    theme(plot.background = element_rect(colour = "white"))+
    theme(axis.title.x = element_text(colour = "black", size = 10)) +
    theme(axis.title.y = element_text(colour = "black", size = 10)) +
    theme(axis.text = element_text(color= "black", size = 10)) +
    theme(axis.line = element_line(color = "black")) +
    theme(legend.background = element_rect(fill ="white")) +
    theme(legend.text = element_text(color="black", size = 10)) +
    theme(legend.title = element_text(color= "black", size = 10)) 

dotplot_reactome_uc_ppi

png(file=glue("Histogram_UC_PPI_v4.png"),width=8, height=4, units="in", res=600)
histogramplot_uc
dev.off()
png(file=glue("Hallmarks_UC_PPItop100_v3_top20.png"),width=8, height=8, units="in", res=600)
dotplot_reactome_uc_ppi
dev.off()