GS_Pathway_analysis.Rmd

---
title: "GS + Pathway enrichment"
author: "AEKS"
date: "2023-11-08"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```


```{r packages}
library(DESeq2)
library(tidyverse)
library(fgsea)
library(qusage)
library(enrichR)
```


```{r GSEA}
#rank gene list
ranked_genes <- -log10(DESeq2_Output$FDR)*DESeq2_Output$logFC
names(ranked_genes) <- DESeq2_Output$gene_name

#import chosen gene set
pathway_gene_sets <- read.gmt("h.all.v7.5.1.symbols.gmt")

fgsea_results <- fgseaMultilevel(pathways = pathway_gene_sets, 
                       stats = ranked_genes)

#plot gene sets
ggplot(fgsea_results, aes(reorder(pathway, NES), NES)) + 
  geom_col(aes(fill = padj < 0.05)) +
  coord_flip() + 
  labs(x = "Pathway", y = "Normalized Enrichment Score (NES)")

```


```{r pathway enrichment}
#check database list
dbsList <- listEnrichrDbs()

#choose pathway databases
dbs <- c("Reactome_2022", "KEGG_2021_Human", "BioPlanet_2019", "GO_Biological_Process_2023", "GO_Cellular_Component_2023", "GO_Molecular_Function_2023", "MSigDB_Hallmark_2020", "GWAS_Catalog_2023")

#Filter FDR
DESeq2_Output_filtered <- DESeq2_Output[DESeq2_Output$FDR < 0.05, ]
enriched_pathways <- enrichr(DESeq2_Output_filtered$gene_name, dbs)

#Extract gene names
enriched_pathways_gene_names <- enriched_pathways[["Pathway name"]][c(), c(), drop = FALSE]

```