---
title: "02-DGE-V2"
output: html_document
date: "2023-04-06"
---

#getting the data

#this is going to a public server with data and is downloading things that match the pattern (accept...)

```{bash}
cd ../data 
wget --recursive --no-parent --no-directories \
--no-check-certificate \
--accept '[DMN]*001.fastq.gz' \
https://gannet.fish.washington.edu/seashell/bu-github/nb-2023/Cgigas/data/nopp/
```
#Kallisto is already on Raven but if using Jupyter, would need to install

```{bash}
/home/shared/kallisto/kallisto
```

#Getting reference

```{bash}
cd ../data
curl --insecure -O https://gannet.fish.washington.edu/seashell/bu-github/nb-2023/Cgigas/data/rna.fna
```
```{bash}
/home/shared/kallisto/kallisto \
index -i \
../data/cgigas_roslin_rna.index \
../data/rna.fna
```
#Run Program

```{bash}
find ../data/*_L001_R1_001.fastq.gz \
| xargs basename -s _L001_R1_001.fastq.gz | xargs -I{} /home/shared/kallisto/kallisto \
quant -i ../data/cgigas_roslin_rna.index \
-o ../output/kallisto_01/{} \
-t 40 \
--single -l 100 -s 10 ../data/{}_L001_R1_001.fastq.gz
```


```{bash}
perl /home/shared/trinityrnaseq-v2.12.0/util/abundance_estimates_to_matrix.pl \
--est_method kallisto \
    --gene_trans_map none \
    --out_prefix ../output/kallisto_01 \
    --name_sample_by_basedir \
    ../output/kallisto_01/D54_S145/abundance.tsv \
    ../output/kallisto_01/D56_S136/abundance.tsv \
    ../output/kallisto_01/D58_S144/abundance.tsv \
    ../output/kallisto_01/M45_S140/abundance.tsv \
    ../output/kallisto_01/M48_S137/abundance.tsv \
    ../output/kallisto_01/M89_S138/abundance.tsv \
    ../output/kallisto_01/D55_S146/abundance.tsv \
    ../output/kallisto_01/D57_S143/abundance.tsv \
    ../output/kallisto_01/D59_S142/abundance.tsv \
    ../output/kallisto_01/M46_S141/abundance.tsv \
    ../output/kallisto_01/M49_S139/abundance.tsv \
    ../output/kallisto_01/M90_S147/abundance.tsv \
    ../output/kallisto_01/N48_S194/abundance.tsv \
    ../output/kallisto_01/N50_S187/abundance.tsv \
    ../output/kallisto_01/N52_S184/abundance.tsv \
    ../output/kallisto_01/N54_S193/abundance.tsv \
    ../output/kallisto_01/N56_S192/abundance.tsv \
    ../output/kallisto_01/N58_S195/abundance.tsv \
    ../output/kallisto_01/N49_S185/abundance.tsv \
    ../output/kallisto_01/N51_S186/abundance.tsv \
    ../output/kallisto_01/N53_S188/abundance.tsv \
    ../output/kallisto_01/N55_S190/abundance.tsv \
    ../output/kallisto_01/N57_S191/abundance.tsv \
    ../output/kallisto_01/N59_S189/abundance.tsv
```

#Load packages

```{r}
BiocManager::install("DESeq2")
```


```{r}
library(DESeq2)
library(tidyverse)
library(pheatmap)
library(RColorBrewer)
library(data.table)
```

#Read in Count matrix

```{r}
countmatrix <- read.delim("../output/kallisto_01.isoform.counts.matrix", header = TRUE, sep = '\t')
rownames(countmatrix) <- countmatrix$X
countmatrix <- countmatrix[,-1]
head(countmatrix)
```
#Round integers to whole numbers

```{r}
countmatrix <- round(countmatrix, 0)
str(countmatrix)
```

#Get DEGs based on Desication

```{r}
deseq2.colData <- data.frame(condition=factor(c(rep("control", 12), rep("desicated", 12))), 
                             type=factor(rep("single-read", 24)))
rownames(deseq2.colData) <- colnames(data)
deseq2.dds <- DESeqDataSetFromMatrix(countData = countmatrix,
                                     colData = deseq2.colData, 
                                     design = ~ condition)
```

```{r}
deseq2.dds <- DESeq(deseq2.dds)
deseq2.res <- results(deseq2.dds)
deseq2.res <- deseq2.res[order(rownames(deseq2.res)), ]
```

```{r}
head(deseq2.res)
```

```{r}
# Count number of hits with adjusted p-value less then 0.05
dim(deseq2.res[!is.na(deseq2.res$padj) & deseq2.res$padj <= 0.05, ])
```

```{r}
tmp <- deseq2.res
# The main plot
plot(tmp$baseMean, tmp$log2FoldChange, pch=20, cex=0.45, ylim=c(-3, 3), log="x", col="darkgray",
     main="DEG Dessication  (pval <= 0.05)",
     xlab="mean of normalized counts",
     ylab="Log2 Fold Change")
# Getting the significant points and plotting them again so they're a different color
tmp.sig <- deseq2.res[!is.na(deseq2.res$padj) & deseq2.res$padj <= 0.05, ]
points(tmp.sig$baseMean, tmp.sig$log2FoldChange, pch=20, cex=0.45, col="red")
# 2 FC lines
abline(h=c(-1,1), col="blue")
```

```{r}
write.table(tmp.sig, "../output/DEGlist.tab", row.names = T)
```

#Celebrate, it worked