---
title: "09-GOenrichment_listcreation_REVIGO"
output: html_document
date: "2024-10-29"
---

### Library loading
```{r}
library(BiocManager)
library(tidyverse)
```

### Load files
```{r}
gene_count_matrix1 <- read.table("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/gene_count_matrix_clean",row.names = 1 )
masterID <- read.delim("output/LOC_GO_list.txt", sep= "\t", header = TRUE)
#Cut out extras
masterID <- masterID[, -((ncol(masterID)-2):ncol(masterID))]

# Rename remaining columns

colnames(masterID)  <- c("transcript", "database","uniprot_accession","geneID","species", "pident", "length", "mismatch", "gapopen", "qstart", "qend", "sstart", "send", "evalue", "bitscore", "reviewed", "entryname", "protein_name", "gene_name", "organism", "prot_length", "GO_ID", "GO_BP", "GO_MF", "GO_CC", "Genename_orderedlocus", "Induction", "Pathwaycommons", "Reactome", "Unipathway", "Interacts_with", "LOC_column")
```

### Filter for genes that have counts of at least 10 in >= 1/3 of gene count matrix
```{r}
nrow(gene_count_matrix1) #47806
filteredGCM <- gene_count_matrix1[rowSums(gene_count_matrix1 >= 10) >= ceiling(ncol(gene_count_matrix1)/ 3),]
nrow(filteredGCM) #9386
                                  
```

### Extract LOC_ID from rownames
```{r}
filteredGCM1 <- filteredGCM %>%
  rownames_to_column(var = "row_name") %>%
  # Mutate to add the new column with part after the pipe (|) and place it after row names
  mutate(LOC_ID = str_extract(row_name, "(?<=\\|).+")) %>%
  # Reorder columns to make the new column the first one after row names
  select(row_name, LOC_ID, everything())
nrow(filteredGCM1)#9386
```

### left join masterID file mapping LOC ID's to GO ID's to filtered gene count matrix
```{r}
filteredGCM2 <- filteredGCM1 %>%
  left_join(masterID %>% select(LOC_ID,GO_ID ), by = "LOC_ID") %>%
  select(LOC_ID, GO_ID, everything())
nrow(filteredGCM2) #9873

filteredGCM3 <- separate_rows(filteredGCM2, GO_ID, sep = ";")
filteredGCM3$GO_ID <- trimws(filteredGCM3$GO_ID)

filteredGCM3_unique <- filteredGCM3 %>%
  distinct(GO_ID, .keep_all = TRUE)
nrow(filteredGCM2_unique) #9386
```

### Create BG for DAVID
```{r}
uniprot_BG_REVIGO <- na.omit(filteredGCM3$GO_ID)
head(uniprot_BG_REVIGO)
length(uniprot_BG_REVIGO ) #2342567 GO id's (not all unique) 
writeLines(unlist(uniprot_BG_REVIGO), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/REVIGO_lists/uniprot_BG_REVIGO.txt")
```

### FOA list
```{r}
FOA_sigs_ID <-  read.csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/GOterms_genome/FOA_sigs_ID.csv",
                      sep = " ")
FOA_sigs_ID <- separate_rows(FOA_sigs_ID, GO_ID, sep = ";")
FOA_sigs_ID$GO_ID <- trimws(FOA_sigs_ID$GO_ID)
FOA_sigs_REVIGO <- na.omit(FOA_sigs_ID$GO_ID)
head(FOA_sigs_REVIGO) 
length(FOA_sigs_REVIGO) #995
writeLines(unlist(FOA_sigs_REVIGO), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/REVIGO_lists/FOA_ID_REVIGO.txt")


```


### GOA list
```{r}


GOA_sigs_ID <-  read.csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/GOterms_genome/GOA_sigs_ID.csv",
                      sep = " ")
GOA_sigs_ID <- separate_rows(GOA_sigs_ID, GO_ID, sep = ";")
GOA_sigs_ID$GO_ID <- trimws(GOA_sigs_ID$GO_ID)
GOA_sigs_REVIGO <- na.omit(GOA_sigs_ID$GO_ID)
head(GOA_sigs_REVIGO) 
length(GOA_sigs_REVIGO) #7379
writeLines(unlist(GOA_sigs_REVIGO), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/REVIGO_lists/GOA_ID_REVIGO.txt")

```


### FOW list
```{r}
FOW_sigs_ID <-  read.csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/GOterms_genome/FOW_sigs_ID.csv",
                      sep = " ")
FOW_sigs_ID <- separate_rows(FOW_sigs_ID, GO_ID, sep = ";")
FOW_sigs_ID$GO_ID <- trimws(FOW_sigs_ID$GO_ID)
FOW_sigs_REVIGO <- na.omit(FOW_sigs_ID$GO_ID)
head(FOW_sigs_REVIGO) 
length(FOW_sigs_REVIGO) #1920
writeLines(unlist(FOW_sigs_REVIGO), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/REVIGO_lists/FOW_ID_REVIGO.txt")
```


### GOW list
```{r}
GOW_sigs_ID <-  read.csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/GOterms_genome/GOW_sigs_ID.csv",
                      sep = " ")
GOW_sigs_ID <- separate_rows(GOW_sigs_ID, GO_ID, sep = ";")
GOW_sigs_ID$GO_ID <- trimws(GOW_sigs_ID$GO_ID)
GOW_sigs_REVIGO <- na.omit(GOW_sigs_ID$GO_ID)
head(GOW_sigs_REVIGO) 
length(GOW_sigs_REVIGO) #3180
writeLines(unlist(GOW_sigs_REVIGO), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/REVIGO_lists/GOW_ID_REVIGO.txt")
```


### FDO list
```{r}
FDO_sigs_ID <-  read.csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/GOterms_genome/FDO_sigs_ID.csv",
                      sep = " ")
FDO_sigs_ID <- separate_rows(FDO_sigs_ID, GO_ID, sep = ";")
FDO_sigs_ID$GO_ID <- trimws(FDO_sigs_ID$GO_ID)
FDO_sigs_REVIGO <- na.omit(FDO_sigs_ID$GO_ID)
head(FDO_sigs_REVIGO) 
length(FDO_sigs_REVIGO) #3462
writeLines(unlist(FDO_sigs_REVIGO), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/REVIGO_lists/FDO_ID_REVIGO.txt")
```


### GDO list
```{r}
GDO_sigs_ID <-  read.csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/GOterms_genome/GDO_sigs_ID.csv",
                      sep = " ")
GDO_sigs_ID <- separate_rows(GDO_sigs_ID, GO_ID, sep = ";")
GDO_sigs_ID$GO_ID <- trimws(GDO_sigs_ID$GO_ID)
GDO_sigs_REVIGO <- na.omit(GDO_sigs_ID$GO_ID)
head(GDO_sigs_REVIGO) 
length(GDO_sigs_REVIGO) #2460
writeLines(unlist(GDO_sigs_REVIGO), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/REVIGO_lists/GDO_ID_REVIGO.txt")
```