#!/usr/bin/R
# Importing transcript abundance datasets with tximport
library(tximportData)
dir <- 'dwhelper/1/quants/quants'
dir_quants <- '/home/prabat/dwhelper/1/quants'
setwd(dir)
samples <- read.csv('SraRunTable_1.csv', header = T)
samples$condition <- factor(rep(c('A', 'B'), each = 9))
rownames(samples) <- samples$Run_s
files <- file.path(dir_quants, samples$Run_s, 'quant.sf')
names(files) <- samples$Run_s
names(files)
files
all(file.exists(files))

library(biomaRt)
library(GenomicFeatures)
# mart <- useMart(biomart = 'plants_mart', host = 'plants.ensembl.org')
# datasets <- listDatasets(mart)
# datasets[1:6, 1:2]
#
# idx <- grep('oryza', datasets$description, ignore.case = T)
# datasets[idx, 1:2]

txdb <- makeTxDbFromBiomart(biomart="plants_mart",
                            dataset="osativa_eg_gene",
                            host="plants.ensembl.org")
k <-  keys(txdb, keytype = 'GENEID')
df <- select(txdb, keys = k, keytype = 'GENEID', columns = 'TXNAME')

tx2gene <- df[,2:1]
head(tx2gene)

write.csv(x = tx2gene, file = 'tx2gene.csv')
save(txdb, file = 'txdb')