comparison get_length_and_gc_content.r @ 12:02e88556ce1d draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/goseq_1_22_0 commit fdd0811efc61c31f88ff17096fbe8ee8cfacd766-dirty
author mvdbeek
date Thu, 25 Feb 2016 06:44:44 -0500
parents 7f8d888e3355
children ea84562a5115
comparison
equal deleted inserted replaced
11:1802ccf465b8 12:02e88556ce1d
3 3
4 library(GenomicRanges) 4 library(GenomicRanges)
5 library(rtracklayer) 5 library(rtracklayer)
6 library(Rsamtools) 6 library(Rsamtools)
7 library(optparse) 7 library(optparse)
8 library(data.table)
8 9
9 option_list <- list( 10 option_list <- list(
10 make_option(c("-g","--gtf"), type="character", help="Input GTF file with gene / exon information."), 11 make_option(c("-g","--gtf"), type="character", help="Input GTF file with gene / exon information."),
11 make_option(c("-f","--fasta"), type="character", default=FALSE, help="Fasta file that corresponds to the supplied GTF."), 12 make_option(c("-f","--fasta"), type="character", default=FALSE, help="Fasta file that corresponds to the supplied GTF."),
12 make_option(c("-o","--output"), type="character", default=FALSE, help="Output file with gene name, length and GC content.") 13 make_option(c("-o","--output"), type="character", default=FALSE, help="Output file with gene name, length and GC content.")
38 nGCs = sum(elementMetadata(x)$nGCs) 39 nGCs = sum(elementMetadata(x)$nGCs)
39 width = sum(elementMetadata(x)$widths) 40 width = sum(elementMetadata(x)$widths)
40 c(width, nGCs/width) 41 c(width, nGCs/width)
41 } 42 }
42 output <- t(sapply(split(reducedGTF, elementMetadata(reducedGTF)$gene_id), calc_GC_length)) 43 output <- t(sapply(split(reducedGTF, elementMetadata(reducedGTF)$gene_id), calc_GC_length))
43 colnames(output) <- c("Length", "GC") 44 output <- setDT(output, keep.rownames = TRUE)[]
45 colnames(output) <- c("#gene_id", "length", "GC")
44 46
45 write.table(output, file=output_file, sep="\t") 47 write.table(output, file=output_file, row.names=FALSE, quote=FALSE, sep="\t")