Salmon快速转录本定量

1

salmon index -t athal.fa.gz -i athal_index --type quasi -k 31

1

salmon quant -i transcripts_index  -l A -1 reads_1.fastq.gz -2 reads_2.fastq.gz -o transcripts_valid -p 16 --validateMappings

1
2

library(tximport)
txi.salmon <- tximport('quant.sf', type = "salmon", tx2gene = tx2gene)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

#!/bin/bash
for fn in ERR1698{194..209};
do    samp=`basename ${fn}`    
echo "Processin sample ${sampe}"   
salmon quant -i athal_index -l A \
        -1 ${samp}_1.fastq.gz \
        -2 ${samp}_2.fastq.gz \
        -p 8 -o quants/${samp}_valid \
        --validateMappings
done

1
2
3
4
5
6

dir <- "C:/Users/Xu/Desktop/"
list.files(dir)
sample <- paste0("ERR1698",seq(194,209),"_valid")
files <- file.path(dir,"quants",sample,"quant.sf")
names(files) <- paste0("sample",c(1:16))
all(file.exists(files))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

# 从公共数据获取
library(AnnotationHub)
ah <- AnnotationHub()
ath <- query(ah,'thaliana')
ath_tx <- ath[['AH52247']]columns(ath_tx)
k <- keys(ath_tx,keytype = "GENEID")
df <- select(ath_tx, keys=k, keytype = "GENEID",columns = "TXNAME")
tx2gene <- df[,2:1] # TXID在前， GENEID在后

# 或自行制备
GENEID <- paste0("ObjectGene",sprintf("%04d", c(1:8946)))
TXNAME <- paste0("ObjectGene",sprintf("%04d", c(1:8946)))
tx2gene <- data.frame(GENEID, TXNAME)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

# install.packages("readr")
# install.packages("rsjon")
library("tximport")
library("readr")
txi <- tximport(files, type = "salmon", tx2gene = tx2gene)

names(txi)

head(txi$length)
head(txi$counts)

write.csv(txi$abundance, "salmon_valid_TPM.csv", quote = FALSE)

1
2
3
4

library("DESeq2")
sampleTable <- data.frame(condition = factor(rep(c("Day0","Day1","Day2","Day3"),each=4)))
rownames(sampleTable) <- colnames(txi$counts)
dds <- DESeqDataSetFromTximport(txi, sampleTable, ~condition)