biomart is pretty reliable for getting mouse annotation data.
annotation_file <- "reference/ixodes_exons.gff"
annot_df <- load_gff_annotations(annotation_file)## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=TRUE)## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=FALSE)## Had a successful gff import with rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=FALSE)## Returning a df with 13 columns and 89845 rows.annot_df$ID <- gsub("\\-", "\\.", annot_df$ID, perl=TRUE)
annot_df$Parent <- gsub("\\-RA","", annot_df$Parent)
rownames(annot_df) <- annot_df$ID
description_file <- "reference/ixodes_mRNA.gff"
description_df <- load_gff_annotations(description_file)## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=TRUE)## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=FALSE)## Had a successful gff import with rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=FALSE)## Returning a df with 13 columns and 20486 rows.descriptions <- merge(annot_df, description_df, by="Parent")
descriptions <- descriptions[,c("ID.x","width.x","description.y")]
rownames(descriptions) <- descriptions$ID.x
colnames(descriptions) <- c("ID","width","description")isc_biomart <- load_biomart_annotations(species="iscapularis",
host="metazoa.ensembl.org",
include_lengths=TRUE)## The biomart annotations file already exists, loading from it.isc_biomart <- isc_biomart$annotation
ixo_expt <- create_expt(metadata="sample_sheets/gut_samples.xlsx", gene_info=isc_biomart)## Reading the sample metadata.## The sample definitions comprises: 10, 22 rows, columns.## Reading count tables.## Reading count tables with read.table().## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0612/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0613/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0614/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0615/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0616/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0617/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0689/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0690/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0691/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## /cbcb/nelsayed-scratch/atb/rnaseq/iscapularis_2017/preprocessing/hpgl0692/outputs/tophat_iscapularis/accepted_hits.count.xz contains 20491 rows and merges to 20491 rows.## Finished reading count tables.## Matched 20486 annotations and counts.## Bringing together the count matrix and gene information.pander::pander(sessionInfo())R version 3.4.4 (2018-03-15)
**Platform:** x86_64-pc-linux-gnu (64-bit)
locale: LC_CTYPE=en_US.utf8, LC_NUMERIC=C, LC_TIME=en_US.utf8, LC_COLLATE=en_US.utf8, LC_MONETARY=en_US.utf8, LC_MESSAGES=en_US.utf8, LC_PAPER=en_US.utf8, LC_NAME=C, LC_ADDRESS=C, LC_TELEPHONE=C, LC_MEASUREMENT=en_US.utf8 and LC_IDENTIFICATION=C
attached base packages: stats, graphics, grDevices, utils, datasets, methods and base
other attached packages: hpgltools(v.2018.03)
loaded via a namespace (and not attached): Rcpp(v.0.12.16), RColorBrewer(v.1.1-2), GenomeInfoDb(v.1.14.0), XVector(v.0.18.0), compiler(v.3.4.4), pillar(v.1.2.1), plyr(v.1.8.4), base64enc(v.0.1-3), bitops(v.1.0-6), iterators(v.1.0.9), tools(v.3.4.4), zlibbioc(v.1.24.0), digest(v.0.6.15), lattice(v.0.20-35), evaluate(v.0.10.1), memoise(v.1.1.0), tibble(v.1.4.2), gtable(v.0.2.0), rlang(v.0.2.0.9001), openxlsx(v.4.0.17), Matrix(v.1.2-14), foreach(v.1.4.4), DelayedArray(v.0.4.1), commonmark(v.1.4), yaml(v.2.1.18), parallel(v.3.4.4), GenomeInfoDbData(v.1.0.0), rtracklayer(v.1.38.3), withr(v.2.1.2), stringr(v.1.3.0), roxygen2(v.6.0.1), xml2(v.1.2.0), knitr(v.1.20), Biostrings(v.2.46.0), IRanges(v.2.12.0), S4Vectors(v.0.16.0), devtools(v.1.13.5), stats4(v.3.4.4), rprojroot(v.1.3-2), grid(v.3.4.4), data.table(v.1.10.4-3), Biobase(v.2.38.0), R6(v.2.2.2), BiocParallel(v.1.12.0), XML(v.3.98-1.11), rmarkdown(v.1.9), pander(v.0.6.1), ggplot2(v.2.2.1), magrittr(v.1.5), matrixStats(v.0.53.1), GenomicAlignments(v.1.14.2), Rsamtools(v.1.30.0), GenomicRanges(v.1.30.3), backports(v.1.1.2), scales(v.0.5.0.9000), codetools(v.0.2-15), htmltools(v.0.3.6), BiocGenerics(v.0.24.0), SummarizedExperiment(v.1.8.1), colorspace(v.1.3-2), stringi(v.1.1.7), RCurl(v.1.95-4.10), lazyeval(v.0.2.1) and munsell(v.0.4.3)
message(paste0("This is hpgltools commit: ", get_git_commit()))## If you wish to reproduce this exact build of hpgltools, invoke the following:## > git clone http://github.com/abelew/hpgltools.git## > git reset 1b009834267dea125ee94934203413fbd606e783## R> packrat::restore()## This is hpgltools commit: Mon Apr 23 14:59:56 2018 -0400: 1b009834267dea125ee94934203413fbd606e783this_save <- paste0(gsub(pattern="\\.Rmd", replace="", x=rmd_file), "-v", ver, ".rda.xz")
message(paste0("Saving to ", this_save))## Saving to 01_annotation_iscapularis-v20180119.rda.xztmp <- sm(saveme(filename=this_save))