debug.Rmd

---
title: "debug"
author: "Yifan Duan"
date: "2024-10-03"
output: html_document
---

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


```{r}
BiocManager::install("clusterProfiler")
BiocManager::install("pathview")
BiocManager::install("enrichplot")
library(clusterProfiler)
library(enrichplot)
# we use ggplot2 to add x axis labels (ex: ridgeplot)
library(ggplot2)
```


```{r}
Idents(filtered_mature_neuron_obj) <- "Time.Point"
table(filtered_mature_neuron_obj$Time.Point)
naive_5_markers_dpi <- FindMarkers(filtered_mature_neuron_obj, 
                                   ident.1 = "Naive", 
                                   ident.2 = "5 dpi",
                                   slot = "data", 
                                   min.pct = 0,
                                   logfc.threshold = 0)

library(EnhancedVolcano)
pdf("DE_5dpi_naive.pdf")
EnhancedVolcano(naive_5_markers_dpi, 
                rownames(naive_5_markers_dpi),
                x ="avg_log2FC", 
                y ="p_val_adj")
dev.off()
naive_5_markers_dpi |> filter(abs(avg_log2FC) > 2 & p_val_adj < 0.01)
```


```{r}
# SET THE DESIRED ORGANISM HERE
organism = "org.Mm.eg.db"
BiocManager::install(organism, character.only = TRUE)
library(organism, character.only = TRUE)
```


```{r}
# reading in data from deseq2
df <- naive_5_markers_dpi

# we want the log2 fold change 
original_gene_list <- df$avg_log2FC

# name the vector
names(original_gene_list) <- rownames(df)

# omit any NA values 
gene_list<-na.omit(original_gene_list)

# sort the list in decreasing order (required for clusterProfiler)
gene_list = sort(gene_list, decreasing = TRUE)
```


```{r}
keytypes(org.Mm.eg.db)

gse <- gseGO(geneList=gene_list, 
             ont ="ALL", 
             keyType = "SYMBOL",
             minGSSize = 10, 
             maxGSSize = 500, 
             pvalueCutoff = 0.01,
             pAdjustMethod = "BH",
             verbose = TRUE, 
             OrgDb = organism)

dotplot(gse, showCategory = 10, title = "GSEA")
head(gse@result)
head(gse@result$NES)
```


```{r}
df <- naive_5_markers_dpi |> filter(abs(avg_log2FC) > 2 & p_val_adj < 0.01)

# we want the log2 fold change 
original_gene_list <- df$avg_log2FC

# name the vector
names(original_gene_list) <- rownames(df)

# omit any NA values 
gene_list <- na.omit(original_gene_list)

# sort the list in decreasing order (required for clusterProfiler)
gene_list = sort(gene_list, decreasing = TRUE)



go_enrich <- enrichGO(gene = names(gene_list),
                      OrgDb = organism, 
                      keyType = 'SYMBOL',
                      readable = T,
                      ont = "ALL",
                      pvalueCutoff = 0.05,
                      qvalueCutoff = 0.1)

barplot(go_enrich, 
        drop = TRUE, 
        showCategory = 10, 
        title = "GO analysis",
        font.size = 8)

DoHeatmap(filtered_mature_neuron_obj, features = rownames(df))
```