---
title: "23-Apul Amil lncRNA compare"
author: Steven Roberts
date: "`r format(Sys.time(), '%d %B, %Y')`"
format:
  gfm:
    toc: true
    number-sections: true
---

```{r setup, include=FALSE}
library(knitr)
library(tidyverse)
knitr::opts_chunk$set(
  echo = TRUE,         # Display code chunks
  eval = TRUE,         # 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
)
```


```{r, engine='bash'}
head ../output/05.33-lncRNA-discovery/Apul_lncRNA.bed
wc -l ../output/05.33-lncRNA-discovery/Apul_lncRNA.bed
```
```{r, engine='bash'}
grep -v -- '-[0-9]' ../output/05.33-lncRNA-discovery/Apul_lncRNA.bed > ../output/23-Apul-Amil-lncRNA-comp/Apul_lncRNA.no-negatives.bed
```

```{r, engine='bash'}
cat ../data/Amil/GCF_013753865.1_Amil_v2.1_genomic.gff | \
awk '$0 !~ /^#/ {count[$3]++} END {for (f in count) print f, count[f]}' | sort
```


```{r, engine='bash'}
grep -i "lnc_RNA" ../data/Amil/GCF_013753865.1_Amil_v2.1_genomic.gff > ../output/23-Apul-Amil-lncRNAlncRNA.gff
```


```{r, engine='bash'}
head ../output/23-Apul-Amil-lncRNA-comp/lncRNA.gff
wc -l ../output/23-Apul-Amil-lncRNA-comp/lncRNA.gff
```
```{r, engine='bash'}
wc -l ../output/23-Apul-Amil-lncRNA-comp/Apul_lncRNA.no-negatives.bed
```


```{r, engine='bash'}
bedtools intersect \
-a ../output/23-Apul-Amil-lncRNA-comp/Apul_lncRNA.no-negatives.bed \
-b ../output/23-Apul-Amil-lncRNA-comp/lncRNA.gff
```

```{r, engine='bash'}
bedtools intersect \
-a ../output/23-Apul-Amil-lncRNA-comp/Apul_lncRNA.no-negatives.bed \
-b ../output/23-Apul-Amil-lncRNA-comp/lncRNA.gff \
-u | wc -l
```



```{r, engine='bash'}
bedtools intersect \
-a ../output/23-Apul-Amil-lncRNA-comp/lncRNA.gff \
-b ../output/23-Apul-Amil-lncRNA-comp/Apul_lncRNA.no-negatives.bed \
-u | wc -l
```