---
title: "deg figure"
author: "Megan Ewing"
date: "2024-05-28"
output: html_document
---

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

```{r}
library(readr)
library(dplyr)
```

```{r}
# read in log count data: matrix of LOC x Sample with log count as value
log_counts_top <- read.csv("../output/log_counts_top.csv", row.names = NULL)
names(log_counts_top)[1] <- "LOC"


# read in blast output with LOC and accession info (maybe just get the go terms?)
blastout <- read.csv("../output/clam_GO_annotations_cds_0514.csv", row.names=1)

```

```{r}
# join by common LOC

top_counts_GO <- left_join(log_counts_top, blastout, by = "LOC")
head(top_counts_GO)

write.csv(top_counts_GO, "../output/top_counts_GO.csv")

```


```{r}

df2 <- top_counts_GO
df1 <- read.csv("../output/goterm_annot_id.csv", row.names = NULL)



# Define a function to find the matching value
get_matching_col1 <- function(row, df2) {
  match_found <- df2 %>%
    filter(row["uniprot_id"] %in% colnames()) %>%
    select(col1) %>%
    unlist() %>%
    unique()
  if (length(match_found) == 0) return(NA)
  return(match_found[1])
}

# Apply the function to df1
df1$col1_match <- apply(df1, 1, get_matching_col1, df2 = df2)

# View the updated df1
print(df1)


```