## ----setup, include = FALSE----------------------------------------------------------------------- knitr::opts_chunk$set( collapse = TRUE, comment = "#>", error = FALSE, warning = FALSE, eval = TRUE, message = FALSE, fig.width = 8 ) options(width = 100) ## ----install, eval=FALSE-------------------------------------------------------------------------- # if (!requireNamespace("BiocManager", quietly = TRUE)) { # install.packages("BiocManager") # } # # BiocManager::install("GeDi") ## ----loadlib-------------------------------------------------------------------------------------- library("GeDi") ## ----launchapp, eval=FALSE------------------------------------------------------------------------ # GeDi() ## ----launchappwithData, eval=FALSE---------------------------------------------------------------- # GeDi( # genesets = geneset_df, # ppi = ppi_df, # distance_scores = distance_scores_df # ) ## ----examplerun, eval=FALSE----------------------------------------------------------------------- # GeDi() ## ----create_dds----------------------------------------------------------------------------------- # Load required libraries library("macrophage") library("DESeq2") # Load the example dataset "gse" from the "macrophage" package data("gse", package = "macrophage") # Create a DESeqDataSet object using the "gse" dataset and define the # experimental design. # We use the condition as part of the experimental design, because we are # interested in the differentially expressed genes between treatments. We also # add the line to the design to account for the inherent differences between # the donors. dds_macrophage <- DESeqDataSet(gse, design = ~ line + condition) # Change the row names of the DESeqDataSet object to Ensembl IDs rownames(dds_macrophage) <- gsub("\\..*", "", rownames(dds_macrophage)) # Have a look at the resulting DESeqDataSet object dds_macrophage ## ----create_resde1-------------------------------------------------------------------------------- # Filter genes based on read counts # Calculate the number of genes with at least 10 counts in at least 6 samples keep <- rowSums(counts(dds_macrophage) >= 10) >= 6 # Subset the DESeqDataSet object to keep only the selected genes dds_macrophage <- dds_macrophage[keep, ] # Have a look at the resulting DESeqDataSet object dds_macrophage ## ----create_resde2-------------------------------------------------------------------------------- # Perform differential expression analysis using DESeq2 dds_macrophage <- DESeq(dds_macrophage) # Extract differentially expressed genes # Perform contrast analysis comparing "IFNg" condition to "naive" condition # Set a log2 fold change threshold of 1 and a significance level (alpha) of 0.05 res_macrophage_IFNg_vs_naive <- results(dds_macrophage, contrast = c("condition", "IFNg", "naive"), lfcThreshold = 1, alpha = 0.05 ) # Add gene symbols to the results in a column "SYMBOL" res_macrophage_IFNg_vs_naive$SYMBOL <- rowData(dds_macrophage)$SYMBOL ## ----create_resenrich1, eval=TRUE----------------------------------------------------------------- # Load required packages for analysis library("mosdef") library("AnnotationDbi") # Extract gene symbols from the DESeq2 results object where FDR is below 0.05 # The function deseqresult2df is used to convert the DESeq2 results to a # dataframe format # FDR is set to 0.05 to filter significant results de_symbols_IFNg_vs_naive <- mosdef::deresult_to_df(res_macrophage_IFNg_vs_naive, FDR = 0.05)$SYMBOL # Extract gene symbols for background using the DESeq2 results object # Filter genes that have nonzero counts bg_ids <- rowData(dds_macrophage)$SYMBOL[rowSums(counts(dds_macrophage)) > 0] ## ----create_resenrich2, eval=TRUE----------------------------------------------------------------- # Load required package for analysis library("topGO") library("org.Hs.eg.db") # Perform Gene Ontology enrichment analysis using the run_topGO function from # the "mosdef" package macrophage_topGO_example <- mosdef::run_topGO( de_genes = de_symbols_IFNg_vs_naive, bg_genes = bg_ids, ontology = "BP", mapping = "org.Hs.eg.db", gene_id = "symbol" ) ## ----renamecolumns, eval=TRUE--------------------------------------------------------------------- # Rename columns in the macrophage_topGO_example dataframe # Change the column name "GO.ID" to "Genesets" macrophage_topGO_example <- path_to_GeDi(macrophage_topGO_example, enrichment_package = "topGO") ## ----dryrun, eval=FALSE--------------------------------------------------------------------------- # GeDi() # # GeDi(genesets = macrophage_topGO_example) ## ----welcome-page2, fig.align = "center", fig.cap = "The Welcome panel of GeDi", echo = FALSE----- knitr::include_graphics("Welcome_page.png") ## ----data-input-step1, fig.align = "center", fig.cap = "The Data input panel - Step 1", echo = FALSE---- knitr::include_graphics("Data_Input_panel_Step1.png") ## ----optional-filtering, fig.align = "center", fig.cap = "Optional Filtering Step", echo = FALSE---- knitr::include_graphics("Optional_Filtering.png") ## ----species-selection, fig.align = "center", fig.cap = "Species Selection", echo = FALSE--------- knitr::include_graphics("Species_Selection.png") ## ----download-ppi, fig.align = "center", fig.cap = "Downloading the PPI", echo = FALSE------------ knitr::include_graphics("Downloading_PPI.png") ## ----distance-score, fig.align = "center", fig.cap = "The Distance Score panel", echo = FALSE----- knitr::include_graphics("Distance_Score_panel.png") ## ----clustering-graph, fig.align = "center", fig.cap = "The Clustering Graph panel", echo = FALSE---- knitr::include_graphics("Clustering_Graph_Panel.png") ## ----report-panel, fig.align = "center", fig.cap = "The Report panel", echo = FALSE--------------- knitr::include_graphics("Report_panel.png") ## ----withbiomart, eval = FALSE-------------------------------------------------------------------- # # Load the "biomaRt" package to access the BioMart database # library("biomaRt") # # # Set up a connection to the ENSEMBL BioMart database for human genes # mart <- # useMart(biomart = "ENSEMBL_MART_ENSEMBL", dataset = "hsapiens_gene_ensembl") # # # Retrieve gene annotations using the BioMart database # anns <- getBM( # attributes = c( # "ensembl_gene_id", # "external_gene_name", # "entrezgene_id", # "description" # ), # filters = "ensembl_gene_id", # values = rownames(dds_macrophage), # mart = mart # ) # # # Match the retrieved annotations to the genes in dds_macrophage # anns <- anns[match(rownames(dds_macrophage), anns[, 1]), ] ## ----enrichKegg, eval = FALSE--------------------------------------------------------------------- # # Load the "clusterProfiler" package for functional enrichment analysis # library("clusterProfiler") # # # Retrieve Entrez gene IDs from the annotations data frame based on matching # # Ensembl gene IDs from the DE results # genes <- anns$entrezgene_id[match(rownames(res_macrophage_IFNg_vs_naive), # anns$ensembl_gene_id)] # # # Perform KEGG pathway enrichment analysis using the retrieved gene IDs # res_enrich <- enrichKEGG(genes, # organism = "hsa", # pvalueCutoff = 0.05 # ) ## ----GeDi_Kegg, eval = FALSE---------------------------------------------------------------------- # # Load the "macrophage_KEGG_example" dataset from the "GeDi" package # data("macrophage_KEGG_example", package = "GeDi") # # # Start the GeDi app with the loaded data # # The "genesets" parameter is set to the loaded "macrophage_KEGG_example" # # dataset # GeDi(genesets = macrophage_KEGG_example) ## ----enrichReactome, eval = FALSE----------------------------------------------------------------- # # Load the "ReactomePA" package for pathway enrichment analysis # library("ReactomePA") # # # Perform pathway enrichment analysis using the "enrichPathway" function # reactome <- enrichPathway(genes, # organism = "human", # pvalueCutoff = 0.05, # readable = TRUE # ) ## ----GeDi_Reactome, eval = FALSE------------------------------------------------------------------ # # Load the "macrophage_Reactome_example" dataset from the "GeDi" package # data("macrophage_Reactome_example", package = "GeDi") # # # Start the GeDi app with the loaded data # # The "genesets" parameter is set to the loaded "macrophage_Reactome_example" # # dataset # GeDi(genesets = macrophage_Reactome_example) ## ----sessioninfo---------------------------------------------------------------------------------- utils::sessionInfo()