RNA-seq

1 Kallisto Alignment

1.1 Getting sequencing reads

cd ../data 
wget --recursive --no-parent --no-directories \
--accept '*001.fastq.gz' \
https://gannet.fish.washington.edu/seashell/bu-github/nb-2023/Cgigas/data/nopp/

cd ../data 
/home/shared/FastQC/fastqc *fastq.gz -o ../output

eval "$(/opt/anaconda/anaconda3/bin/conda shell.bash hook)"
conda activate
which multiqc

cd ../output

multiqc .

1.2 Obtain the reference

cd ../data
curl -O https://gannet.fish.washington.edu/seashell/bu-github/nb-2023/Cgigas/data/rna.fna

1.3 Index Reference

#!/bin/bash

# run kallisto to index the transcriptome
/home/shared/kallisto/kallisto \

# index the transcriptome
index -i \

# specify the output file name
../data/cgigas_roslin_rna.index \

# specify the input file name
../data/rna.fna

1.4 Align reads

mkdir ../output/kallisto_01

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

1.5 Merge quant data

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

2 DESeq2

countmatrix <- read.delim("../output/kallisto_01.isoform.counts.matrix", header = TRUE, sep = '\t')
rownames(countmatrix) <- countmatrix$X
countmatrix <- countmatrix[,-1]
head(countmatrix)

countmatrix <- round(countmatrix, 0)
str(countmatrix)

dim(countmatrix)
dim(deseq2.colData)

length(colnames(data))

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

deseq2.dds <- DESeq(deseq2.dds)
deseq2.res <- results(deseq2.dds)
deseq2.res <- deseq2.res[order(rownames(deseq2.res)), ]

vsd <- vst(deseq2.dds, blind = FALSE)
plotPCA(vsd, intgroup = "condition")

# Select top 50 differentially expressed genes
res <- results(deseq2.dds)
res_ordered <- res[order(res$padj), ]
top_genes <- row.names(res_ordered)[1:50]

# Extract counts and normalize
counts <- counts(deseq2.dds, normalized = TRUE)
counts_top <- counts[top_genes, ]

# Log-transform counts
log_counts_top <- log2(counts_top + 1)

# Generate heatmap
pheatmap(log_counts_top, scale = "row")

head(deseq2.res)

# 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, ])

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")

# Prepare the data for plotting
res_df <- as.data.frame(deseq2.res)
res_df$gene <- row.names(res_df)

# Create volcano plot
volcano_plot <- ggplot(res_df, aes(x = log2FoldChange, y = -log10(padj), color = padj < 0.05)) +
  geom_point(alpha = 0.6, size = 1.5) +
  scale_color_manual(values = c("grey", "red")) +
  labs(title = "Volcano Plot",
       x = "Log2 Fold Change",
       y = "-Log10 Adjusted P-value",
       color = "Significantly\nDifferentially Expressed") +
  theme_minimal() +
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        legend.position = "top")

print(volcano_plot)

write.table(tmp.sig, "../output/DEGlist.tab", sep = '\t', row.names = T)

deglist <- read.csv("../output/DEGlist.tab", sep = '\t', header = TRUE)
deglist$RowName <- rownames(deglist)
deglist2 <- deglist[, c("RowName", "pvalue")] # Optionally, reorder the columns

datatable(deglist)

3 Annotation?

cg_sp <- read.csv("https://raw.githubusercontent.com/sr320/nb-2022/main/C_gigas/analyses/CgR-blastp-sp.tab", header = FALSE, sep="\t")  %>%
  distinct(V1, .keep_all = TRUE)

loc <- read.csv("https://raw.githubusercontent.com/sr320/nb-2022/main/C_gigas/analyses/LOC_Acc.tab", sep = " ", header = FALSE)

comb <- left_join(loc, cg_sp, by = c("V2" = "V1")) %>%
  left_join(deglist, by = c("V1" = "RowName"))

4 Gene Enrichment Analysis

gene_deg_status <- res_df %>%
  mutate(degstaus = ifelse(padj < 0.05, 1, 0)) 

# Read the FASTA file
fasta_data <- readDNAStringSet("../data/rna.fna")

# Calculate gene lengths
gene_lengths <- width(fasta_data)


# Extract gene names/IDs from sequence IDs
gene_names <- sapply(names(fasta_data), function(x) strsplit(x, " ")[[1]][1])

# Create a data frame with gene IDs and lengths
gene_lengths_df <- data.frame(geneID = gene_names, length = gene_lengths)

4.1 Need GO Mappings

pwf <- nullp(gene_data, bias.data = gene_lengths)

GO_analysis <- goseq(pwf, gene2cat = "your_organism_GO_mapping")