---
title: "02-foot_TC_DGE_viz_genome"
output: html_document
date: "2024-06-05"
---
## Make genome counts matrix
```{r, eval = TRUE}
gene_count_matrix1 <- read_csv("/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/gene_count_matrix.csv")
gene_count_matrix1 <- data.frame(gene_count_matrix)

```
## Load in treatment info for DESeq
```{r}
#Load in the metadata
library(dplyr)
treatmentinfo.2 <- read.csv("data/PSMFC-mytilus-byssus-pilot-RNA-tagseq_raw.csv", header = TRUE, sep = ",")
treatmentinfo.2

### NEED TO ADD IN CODE FROM OTHER CODE FILE TO CLEAN UP THIS FILE
```

## Clean up genome countmatrix
```{r}
rownames(gene_count_matrix) <- gene_count_matrix$gene_id
rownames <- rownames(gene_count_matrix)
gene_count_matrix <- gene_count_matrix[,-1]
rownames(gene_count_matrix) <- rownames

#Change column names in count matrix to adjust to sample name in treatment info
new_column_names <- substr(names(gene_count_matrix), 4, nchar(names(gene_count_matrix)) - 5)
names(gene_count_matrix) <- new_column_names

#Remove remaining periods that are at the front of column names
remove_dash <- function(col_name) {
  if (grepl("^\\-", col_name)) {
    # Remove period from the beginning of the column name
    return(sub("^\\-", "", col_name))
  } else {
    # Keep the column name unchanged
    return(col_name)
  }
}

# Apply the function to all column names
new_column_names <- sapply(names(gene_count_matrix), remove_dash)

# Assign the modified column names to the data frame
names(gene_count_matrix) <- new_column_names

remove_periods <- function(col_name) {
  if (grepl("^\\.", col_name)) {
    # Remove period from the beginning of the column name
    return(sub("^\\.", "", col_name))
  } else {
    # Keep the column name unchanged
    return(col_name)
  }
}

# Apply the function to all column names
new_column_names <- sapply(names(gene_count_matrix), remove_periods)

# Assign the modified column names to the data frame
names(gene_count_matrix) <- new_column_names

#clean up data, get rid of NA's and blank cells, and put samples in order 
gene_count_matrix <- gene_count_matrix[, order(names(gene_count_matrix))]
treatmentinfo.2 <- treatmentinfo.2[order(treatmentinfo.2),]
treatmentinfo.2 <- treatmentinfo.2[complete.cases(treatmentinfo.2), ]

#Remove sample IDS that match the FX samples
# gene_count_matrix <- gene_count_matrix[, !names(gene_count_matrix) %in% fX_ids, drop = FALSE]
# treatmentinfo.2 <- treatmentinfo.2 %>%
#   filter(!sample.1 %in% fX_ids)

rownames(treatmentinfo.2) <- treatmentinfo.2$sample.1

#Removing T047 from treatment info because there isn't data for that
removal <- which(rownames(treatmentinfo.2) %in% c("T047F", "T051F", "T051G"))
treatmentinfo.2 <- treatmentinfo.2[-removal,]
removal2 <- which(names(gene_count_matrix) %in% c("T051F", "T051G"))
gene_count_matrix <- gene_count_matrix[,-removal2]

#remove loc identifier temporarily
gene_count_matrix3 <- subset(gene_count_matrix, select=-(loc_id))

#Check that columns and row names match
all(rownames(treatmentinfo.2) == colnames(gene_count_matrix3))

write.csv(gene_count_matrix3, file = "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/gene_count_matrix_clean.csv", row.names = TRUE)
write.csv(treatmentinfo.2, file = "/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/treatmentinfo_clean.csv", row.names = TRUE)
```


```{r}
list <- c(treatmentinfo.2$sample.1, colnames(gene_count_matrix)) 
```