---
title: "12-fix-gff"
author: "Steven Roberts"
date: "`r format(Sys.time(), '%d %B, %Y')`"  
analyses: 
  github_document:
    toc: true
    toc_depth: 3
    number_sections: true
    html_preview: true
  html_document:
    theme: readable
    highlight: zenburn
    toc: true
    toc_float: true
    number_sections: true
    code_folding: show
    code_download: true
editor_options: 
  markdown: 
    wrap: sentence
---

```{r setup, include=FALSE}
library(knitr)
library(tidyverse)
library(kableExtra)
library(DT)
library(Biostrings)
library(tm)
library(pheatmap)
library(DESeq2)
knitr::opts_chunk$set(
  echo = TRUE,         # Display code chunks
  eval = FALSE,         # Evaluate code chunks
  warning = FALSE,     # Hide warnings
  message = FALSE,     # Hide messages
  fig.width = 6,       # Set plot width in inches
  fig.height = 4,      # Set plot height in inches
  fig.align = "center", # Align plots to the center
  comment = ""         # Prevents appending '##' to beginning of lines in code analyses
)
```

Need to convert gtf to match genome fasta.. then will convert gtf to gff to use with hisat

```{r}
gtfbttr <- read.table("../data/augustus.hints.gtf", sep = "\t", quote = "")
```

```{r}
head(gtfbttr)
```




```{r}
save(gtfch, file = "../analyses/12-fix-gff/gtfch.RData")
save(ncbi, file = "../analyses/12-fix-gff/ncbi.RData")
```

```{r}
gtfch <- gtfbttr %>%
  mutate(Chromosome.name = str_extract(V1, "(?<=\\.)\\d+"),  # Extract the number after the dot
         Chromosome.name = str_remove_all(Chromosome.name, "^0+"))  # Remove leading zeros

```

```{r}
(gtfch)
```






```{r}
gtfch %>%
left_join(ncbi, by = "Chromosome.name")

```

```{r}
gtfch %>%
left_join(ncbi, by = "Chromosome.name") %>%
select(GenBank.seq.accession, V2, V3, V4, V5, V6, V7, V8, V9) %>% filter(!is.na(GenBank.seq.accession)) %>%
write.table(file = "../analyses/12-fix-gff/mod_augustus.gtf", sep = "\t", quote = FALSE, row.names = FALSE, col.names = FALSE)
```


```{bash}
head ../analyses/12-fix-gff/mod_augustus.gtf
```