---
title: "GOenrichment_listcreationforDAVID"
output: html_document
date: "2024-10-18"
---
### Library loading
```{r}
library(BiocManager)
library(tidyverse)
```

### Load files
```{r}
gene_count_matrix1 <- read_csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/gene_count_matrix_clean.csv")
g.spid <- read.table("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/g.spid.txt", header = TRUE)
colnames(g.spid) <- c("LOC_ID", "evalue", "uniprot_output", "transcript", "uniprot_acc")
```

### 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) #9476
                                  
```

### Extract LOC_ID from rownames
```{r}
filteredGCM1 <- filteredGCM %>%
  # Mutate to add the new column with part after the pipe (|) and place it after row names
  mutate(LOC_ID = str_extract(...1, "(?<=\\|).+")) %>%
  # Reorder columns to make the new column the first one after row names
  select(...1, LOC_ID, everything())
nrow(filteredGCM1)#9476
```

### left join g.spid file mapping LOC ID's to Uniprot accession ID's to filtered gene count matrix
```{r}
filteredGCM2 <- filteredGCM1 %>%
  left_join(g.spid %>% select(LOC_ID, uniprot_acc), by = "LOC_ID") %>%
  select(LOC_ID, uniprot_acc, everything())
nrow(filteredGCM2) #9964

filteredGCM2_unique <- filteredGCM2 %>%
  distinct(...1, .keep_all = TRUE)
nrow(filteredGCM2_unique) #9476
```

### Create BG for DAVID
```{r}
uniprot_BG_DAVID <- na.omit(filteredGCM2_unique$uniprot_acc)
head(uniprot_BG_DAVID)
length(uniprot_BG_DAVID) #6413 with UNIPROT id's 
uniprot_BG_DAVID_unique <- unique(uniprot_BG_DAVID)
length(uniprot_BG_DAVID_unique) #5581
writeLines(unlist(uniprot_BG_DAVID_unique), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/DAVID_lists/uniprot_BG_DAVID.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_uniprot <- na.omit(FOA_sigs_ID$uniprot_accession)
head(FOA_sigs_uniprot) 
length(FOA_sigs_uniprot) #72
FOA_sigs_uniprot_unique <- unique(FOA_sigs_uniprot)
length(FOA_sigs_uniprot_unique) #61
writeLines(unlist(FOA_sigs_uniprot_unique), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/DAVID_lists/FOA_ID_uniprot_DAVID.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_uniprot <- na.omit(GOA_sigs_ID$uniprot_accession)
head(GOA_sigs_uniprot)
length(GOA_sigs_uniprot) # 582
GOA_sigs_uniprot_unique <- unique(GOA_sigs_uniprot)
length(GOA_sigs_uniprot_unique) #364
writeLines(unlist(GOA_sigs_uniprot_unique), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/DAVID_lists/GOA_ID_uniprot_DAVID.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_uniprot <- na.omit(FOW_sigs_ID$uniprot_accession)
head(FOW_sigs_uniprot)
length(FOW_sigs_uniprot) # 152
FOW_sigs_uniprot_unique <- unique(FOW_sigs_uniprot)
length(FOW_sigs_uniprot_unique) #113
writeLines(unlist(FOW_sigs_uniprot_unique), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/DAVID_lists/FOW_ID_uniprot_DAVID.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_uniprot <- na.omit(GOW_sigs_ID$uniprot_accession)
head(GOW_sigs_uniprot)
length(GOW_sigs_uniprot) # 198
GOW_sigs_uniprot_unique <- unique(GOW_sigs_uniprot)
length(GOW_sigs_uniprot_unique) #139
writeLines(unlist(GOW_sigs_uniprot_unique), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/DAVID_lists/GOW_ID_uniprot_DAVID.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")
FDO_sigs_uniprot <- na.omit(FDO_sigs_ID$uniprot_accession)
head(FDO_sigs_uniprot)
length(FDO_sigs_uniprot) # 361
FDO_sigs_uniprot_unique <- unique(FDO_sigs_uniprot)
length(FDO_sigs_uniprot_unique) #275
writeLines(unlist(FDO_sigs_uniprot_unique), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/DAVID_lists/FDO_ID_uniprot_DAVID.txt")
```


### GDO list
```{r}
# Read in tab-delimited file
GDO_sigs_ID <- read.csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/GOterms_genome/GDO_sigs_ID.csv")
GDO_sigs_uniprot <- na.omit(GDO_sigs_ID$uniprot_accession)
head(GDO_sigs_uniprot)
length(GDO_sigs_uniprot) # 301
GDO_sigs_uniprot_unique <- unique(GDO_sigs_uniprot)
length(GDO_sigs_uniprot_unique) #217
writeLines(unlist(GDO_sigs_uniprot_unique), "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/DEG_lists/DAVID_lists/GDO_ID_uniprot_DAVID.txt")
```