There are a few methods of importing annotation data into R. I will attempt some of them in preparation for loading them into the M.musculus RNASeq data.
AnnotationHub is a newer service and has promise to be an excellent top-level resource for gathering annotation data.
tmp <- sm(library(AnnotationHub))
ah = sm(AnnotationHub())
orgdbs <- sm(query(ah, "OrgDb"))
mm_orgdb <- sm(query(ah, c("OrgDB", "musculus")))
mm_orgdb <- mm_orgdb[[1]]
## loading from cache '/home/trey//.AnnotationHub/64720'
mm_orgdb
## OrgDb object:
## | DBSCHEMAVERSION: 2.1
## | Db type: OrgDb
## | Supporting package: AnnotationDbi
## | DBSCHEMA: MOUSE_DB
## | ORGANISM: Mus musculus
## | SPECIES: Mouse
## | EGSOURCEDATE: 2017-Nov6
## | EGSOURCENAME: Entrez Gene
## | EGSOURCEURL: ftp://ftp.ncbi.nlm.nih.gov/gene/DATA
## | CENTRALID: EG
## | TAXID: 10090
## | GOSOURCENAME: Gene Ontology
## | GOSOURCEURL: ftp://ftp.geneontology.org/pub/go/godatabase/archive/latest-lite/
## | GOSOURCEDATE: 2017-Nov01
## | GOEGSOURCEDATE: 2017-Nov6
## | GOEGSOURCENAME: Entrez Gene
## | GOEGSOURCEURL: ftp://ftp.ncbi.nlm.nih.gov/gene/DATA
## | KEGGSOURCENAME: KEGG GENOME
## | KEGGSOURCEURL: ftp://ftp.genome.jp/pub/kegg/genomes
## | KEGGSOURCEDATE: 2011-Mar15
## | GPSOURCENAME: UCSC Genome Bioinformatics (Mus musculus)
## | GPSOURCEURL:
## | GPSOURCEDATE: 2017-Aug8
## | ENSOURCEDATE: 2017-Aug23
## | ENSOURCENAME: Ensembl
## | ENSOURCEURL: ftp://ftp.ensembl.org/pub/current_fasta
## | UPSOURCENAME: Uniprot
## | UPSOURCEURL: http://www.UniProt.org/
## | UPSOURCEDATE: Tue Nov 7 21:07:58 2017
##
## Please see: help('select') for usage information
## Holy crap it worked!
mm_annotv1 <- load_orgdb_annotations(
mm_orgdb,
keytype="entrezid",
fields=c("ensembl", "entrezid", "ensembltrans", "refseq", "genename", "symbol"))
## Unable to find TYPE in the db, removing it.
## Unable to find CHR in the db, removing it.
## Unable to find TXSTRAND in the db, removing it.
## Unable to find TXSTART in the db, removing it.
## Unable to find TXEND in the db, removing it.
## Extracted all gene ids.
## 'select()' returned 1:many mapping between keys and columns
mm_annotv1 <- mm_annotv1[["genes"]]
head(mm_annotv1)
## entrezid genename ensembl ensembltrans
## X11287 11287 PZP, alpha-2-macroglobulin like ENSMUSG00000030359 <NA>
## X11287.1 11287 PZP, alpha-2-macroglobulin like ENSMUSG00000030359 <NA>
## X11298 11298 arylalkylamine N-acetyltransferase ENSMUSG00000020804 <NA>
## X11298.1 11298 arylalkylamine N-acetyltransferase ENSMUSG00000020804 <NA>
## X11298.2 11298 arylalkylamine N-acetyltransferase ENSMUSG00000020804 <NA>
## X11298.3 11298 arylalkylamine N-acetyltransferase ENSMUSG00000020804 <NA>
## refseq symbol
## X11287 NM_007376 Pzp
## X11287.1 NP_031402 Pzp
## X11298 NM_009591 Aanat
## X11298.1 NP_033721 Aanat
## X11298.2 NR_033223 Aanat
## X11298.3 XM_017314223 Aanat
A completely separate and competing annotation source is biomart.
mm_annotv2 <- sm(load_biomart_annotations(species="mmusculus"))$annotation
head(mm_annotv2)
## transcriptID geneID
## ENSMUST00000000001 ENSMUST00000000001 ENSMUSG00000000001
## ENSMUST00000000003 ENSMUST00000000003 ENSMUSG00000000003
## ENSMUST00000000010 ENSMUST00000000010 ENSMUSG00000020875
## ENSMUST00000000028 ENSMUST00000000028 ENSMUSG00000000028
## ENSMUST00000000033 ENSMUST00000000033 ENSMUSG00000048583
## ENSMUST00000000049 ENSMUST00000000049 ENSMUSG00000000049
## Description
## ENSMUST00000000001 guanine nucleotide binding protein (G protein), alpha inhibiting 3 [Source:MGI Symbol;Acc:MGI:95773]
## ENSMUST00000000003 probasin [Source:MGI Symbol;Acc:MGI:1860484]
## ENSMUST00000000010 homeobox B9 [Source:MGI Symbol;Acc:MGI:96190]
## ENSMUST00000000028 cell division cycle 45 [Source:MGI Symbol;Acc:MGI:1338073]
## ENSMUST00000000033 insulin-like growth factor 2 [Source:MGI Symbol;Acc:MGI:96434]
## ENSMUST00000000049 apolipoprotein H [Source:MGI Symbol;Acc:MGI:88058]
## Type length chromosome strand start end
## ENSMUST00000000001 protein_coding 1065 3 -1 108107280 108146146
## ENSMUST00000000003 protein_coding 525 X -1 77837901 77853623
## ENSMUST00000000010 protein_coding 753 11 1 96271457 96276595
## ENSMUST00000000028 protein_coding 1701 16 -1 18780447 18811987
## ENSMUST00000000033 protein_coding 543 7 -1 142650766 142666816
## ENSMUST00000000049 protein_coding 1038 11 1 108343354 108414396
mm_ontology <- load_biomart_go("mmusculus")$go
## The biomart annotations file already exists, loading from it.
In contrast, it is possible to load most annotations of interest directly from the gff files used in the alignments.
## The old way of getting genome/annotation data
mm_gff <- "reference/mmusculus.gtf.gz"
mm_gff_annotations <- load_gff_annotations(mm_gff, id_col="transcript_id")
## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=TRUE)
## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=FALSE)
## Trying attempt: rtracklayer::import.gff2(gff, sequenceRegionsAsSeqinfo=TRUE)
## Had a successful gff import with rtracklayer::import.gff2(gff, sequenceRegionsAsSeqinfo=TRUE)
## Returning a df with 21 columns and 1405203 rows.
rownames(mm_gff_annotations) <- make.names(mm_gff_annotations$transcript_id, unique=TRUE)
head(mm_gff_annotations)
## seqnames start end width strand source
## NA. chr1 3054233 3054733 501 + pseudogene
## ENSMUST00000160944 chr1 3054233 3054733 501 + unprocessed_pseudogene
## ENSMUST00000160944.1 chr1 3054233 3054733 501 + unprocessed_pseudogene
## NA..1 chr1 3102016 3102125 110 + snRNA
## ENSMUST00000082908 chr1 3102016 3102125 110 + snRNA
## ENSMUST00000082908.1 chr1 3102016 3102125 110 + snRNA
## type score phase gene_id gene_name gene_source
## NA. gene NA NA ENSMUSG00000090025 Gm16088 havana
## ENSMUST00000160944 transcript NA NA ENSMUSG00000090025 Gm16088 havana
## ENSMUST00000160944.1 exon NA NA ENSMUSG00000090025 Gm16088 havana
## NA..1 gene NA NA ENSMUSG00000064842 Gm26206 ensembl
## ENSMUST00000082908 transcript NA NA ENSMUSG00000064842 Gm26206 ensembl
## ENSMUST00000082908.1 exon NA NA ENSMUSG00000064842 Gm26206 ensembl
## gene_biotype transcript_id transcript_name transcript_source
## NA. pseudogene <NA> <NA> <NA>
## ENSMUST00000160944 pseudogene ENSMUST00000160944 Gm16088-001 havana
## ENSMUST00000160944.1 pseudogene ENSMUST00000160944 Gm16088-001 havana
## NA..1 snRNA <NA> <NA> <NA>
## ENSMUST00000082908 snRNA ENSMUST00000082908 Gm26206-201 ensembl
## ENSMUST00000082908.1 snRNA ENSMUST00000082908 Gm26206-201 ensembl
## tag exon_number exon_id ccds_id protein_id
## NA. <NA> <NA> <NA> <NA> <NA>
## ENSMUST00000160944 mRNA_start_NF <NA> <NA> <NA> <NA>
## ENSMUST00000160944.1 mRNA_start_NF 1 ENSMUSE00000848981 <NA> <NA>
## NA..1 <NA> <NA> <NA> <NA> <NA>
## ENSMUST00000082908 <NA> <NA> <NA> <NA> <NA>
## ENSMUST00000082908.1 <NA> 1 ENSMUSE00000522066 <NA> <NA>
In the following block we create an expressionset using the sample sheet and the annotations.
Annoyingly, the gff annotations are keyed in a peculiar fashion. Therefore I need to do a little work to merge them.
mm_annotations <- mm_annotv2
mm_expt <- create_expt(metadata="sample_sheets/all_samples.xlsx",
gene_info=mm_annotations,
## file_column="mousefile")
file_column="mouse395")
## Reading the sample metadata.
## The sample definitions comprises: 24, 25 rows, columns.
## Reading count tables.
## Reading count tables with read.table().
## Warning in read_counts_expt(sample_ids, filenames, ...): NAs introduced by coercion
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0840/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0841/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0842/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0843/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0844/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0845/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0846/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0848/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0849/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0850/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0851/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0852/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0853/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0854/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0855/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0856/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0857/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0858/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0859/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0860/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0861/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0862/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## /cbcb/nelsayed-scratch/atb/rnaseq/lmajor_sacks_2017/preprocessing/run0395/hpgl0863/outputs/kallisto_mmusculus/abundance.count.gz contains 88198 rows and merges to 88198 rows.
## Finished reading count tables.
## Matched 87261 annotations and counts.
## Bringing together the count matrix and gene information.
## Some annotations were lost in merging, setting them to 'undefined'.
## inf12 inf14d uninf12hr uninf14d
##mm_expt <- set_expt_colors(expt=mm_expt, colors=c("lightgray", "darkred" , "pink", "darkblue"))
mm_expt <- set_expt_colors(expt=mm_expt, colors=c("darkred", "darkblue" , "pink", "blue"))
## Error in names(colors) <- levels(as.factor(expt[["conditions"]])): 'names' attribute [6] must be the same length as the vector [4]
library(Biobase)
head(exprs(mm_expt$expressionset))
## HPGL0840 HPGL0841 HPGL0842 HPGL0843 HPGL0844 HPGL0845 HPGL0846
## ENSMUST00000000001 0 21.000 0 0 5 9.000 9
## ENSMUST00000000003 0 0.000 0 0 0 0.000 0
## ENSMUST00000000010 0 0.000 0 0 0 0.000 0
## ENSMUST00000000028 0 0.000 0 0 0 0.000 0
## ENSMUST00000000033 0 1.299 0 0 0 1.296 0
## ENSMUST00000000049 0 1.000 0 0 0 0.000 0
## HPGL0848 HPGL0849 HPGL0850 HPGL0851 HPGL0852 HPGL0853 HPGL0854
## ENSMUST00000000001 23 69.0000 0 0 770.00 506.00 2
## ENSMUST00000000003 0 0.0000 0 0 0.00 0.00 0
## ENSMUST00000000010 0 0.0000 0 0 0.00 0.00 0
## ENSMUST00000000028 0 0.0000 0 0 0.00 0.00 0
## ENSMUST00000000033 0 0.3723 0 0 37.03 24.28 0
## ENSMUST00000000049 0 0.0000 0 0 0.00 0.00 0
## HPGL0855 HPGL0856 HPGL0857 HPGL0858 HPGL0859 HPGL0860 HPGL0861
## ENSMUST00000000001 16 77.000 116 30 87.000 451.00 118.000
## ENSMUST00000000003 0 0.000 0 0 0.000 0.00 0.000
## ENSMUST00000000010 0 0.000 0 0 0.000 0.00 0.000
## ENSMUST00000000028 0 0.000 0 0 0.000 0.00 0.000
## ENSMUST00000000033 0 2.586 0 0 0.745 11.63 7.819
## ENSMUST00000000049 0 0.000 0 0 0.000 0.00 0.000
## HPGL0862 HPGL0863
## ENSMUST00000000001 112.000 206
## ENSMUST00000000003 0.000 0
## ENSMUST00000000010 0.000 0
## ENSMUST00000000028 0.000 0
## ENSMUST00000000033 4.247 0
## ENSMUST00000000049 0.000 0
head(fData(mm_expt$expressionset))
## transcriptID geneID
## ENSMUST00000000001 ENSMUST00000000001 ENSMUSG00000000001
## ENSMUST00000000003 ENSMUST00000000003 ENSMUSG00000000003
## ENSMUST00000000010 ENSMUST00000000010 ENSMUSG00000020875
## ENSMUST00000000028 ENSMUST00000000028 ENSMUSG00000000028
## ENSMUST00000000033 ENSMUST00000000033 ENSMUSG00000048583
## ENSMUST00000000049 ENSMUST00000000049 ENSMUSG00000000049
## Description
## ENSMUST00000000001 guanine nucleotide binding protein (G protein), alpha inhibiting 3 [Source:MGI Symbol;Acc:MGI:95773]
## ENSMUST00000000003 probasin [Source:MGI Symbol;Acc:MGI:1860484]
## ENSMUST00000000010 homeobox B9 [Source:MGI Symbol;Acc:MGI:96190]
## ENSMUST00000000028 cell division cycle 45 [Source:MGI Symbol;Acc:MGI:1338073]
## ENSMUST00000000033 insulin-like growth factor 2 [Source:MGI Symbol;Acc:MGI:96434]
## ENSMUST00000000049 apolipoprotein H [Source:MGI Symbol;Acc:MGI:88058]
## Type length chromosome strand start end
## ENSMUST00000000001 protein_coding 1065 3 -1 108107280 108146146
## ENSMUST00000000003 protein_coding 525 X -1 77837901 77853623
## ENSMUST00000000010 protein_coding 753 11 1 96271457 96276595
## ENSMUST00000000028 protein_coding 1701 16 -1 18780447 18811987
## ENSMUST00000000033 protein_coding 543 7 -1 142650766 142666816
## ENSMUST00000000049 protein_coding 1038 11 1 108343354 108414396
head(pData(mm_expt$expressionset))
## dnarnanumber projectid rmlid inst organism investigator
## HPGL0840 RNA10165 HS_157 10845 HS Mouse/Leshmania SangLee/David Sacks/A.Sher
## HPGL0841 RNA10166 HS_157 10851 HS Mouse/Leshmania SangLee/David Sacks/A.Sher
## HPGL0842 RNA10167 HS_157 10857 HS Mouse/Leshmania SangLee/David Sacks/A.Sher
## HPGL0843 RNA10168 HS_157 10863 HS Mouse/Leshmania SangLee/David Sacks/A.Sher
## HPGL0844 RNA10169 HS_157 10846 HS Mouse/Leshmania SangLee/David Sacks/A.Sher
## HPGL0845 RNA10170 HS_157 10852 HS Mouse/Leshmania SangLee/David Sacks/A.Sher
## batch condition sampleid investigatorsample librarystartdate preppedby
## HPGL0840 a promastigote HPGL0840 Promastigote1 42830 KB
## HPGL0841 b promastigote HPGL0841 Promastigote2 42830 KB
## HPGL0842 c promastigote HPGL0842 Promastigote3 42830 KB
## HPGL0843 d promastigote HPGL0843 Promastigote4 42830 KB
## HPGL0844 a amastigote HPGL0844 Amastigote1 42830 KB
## HPGL0845 b amastigote HPGL0845 Amastigote2 42830 KB
## librarytype averagesize
## HPGL0840 SMARTer Stranded Total RNA - Pico Mammalian_300pg-starting 340
## HPGL0841 SMARTer Stranded Total RNA - Pico Mammalian_300pg-starting 310
## HPGL0842 SMARTer Stranded Total RNA - Pico Mammalian_300pg-starting 340
## HPGL0843 SMARTer Stranded Total RNA - Pico Mammalian_300pg-starting 320
## HPGL0844 SMARTer Stranded Total RNA - Pico Mammalian_300pg-starting 310
## HPGL0845 SMARTer Stranded Total RNA - Pico Mammalian_300pg-starting 355
## titrationamt sequencelength lane indexmid startrundate
## HPGL0840 10 100/8/8/100 1,2 D501-D701 4/7/2017; 4/11/2017
## HPGL0841 10 100/8/8/100 1,2 D501-D707 4/7/2017; 4/11/2017
## HPGL0842 10 100/8/8/100 1,2 D502-D701 4/7/2017; 4/11/2017
## HPGL0843 10 100/8/8/100 1,2 D502-D707 4/7/2017; 4/11/2017
## HPGL0844 10 100/8/8/100 1,2 D501-D702 4/7/2017; 4/11/2017
## HPGL0845 10 100/8/8/100 1,2 D501-D708 4/7/2017; 4/11/2017
## runname samplenumber
## HPGL0840 170407_SN406_0395_Ahjncnbcxy ;170411_SN406_0396_BHJNCCBCXY 840
## HPGL0841 170407_SN406_0395_Ahjncnbcxy ;170411_SN406_0396_BHJNCCBCXY 841
## HPGL0842 170407_SN406_0395_Ahjncnbcxy ;170411_SN406_0396_BHJNCCBCXY 842
## HPGL0843 170407_SN406_0395_Ahjncnbcxy ;170411_SN406_0396_BHJNCCBCXY 843
## HPGL0844 170407_SN406_0395_Ahjncnbcxy ;170411_SN406_0396_BHJNCCBCXY 844
## HPGL0845 170407_SN406_0395_Ahjncnbcxy ;170411_SN406_0396_BHJNCCBCXY 845
## mousefile lmajorfile
## HPGL0840 <NA> preprocessing/hpgl0840/outputs/tophat_lmajor/accepted_paired.count.xz
## HPGL0841 <NA> preprocessing/hpgl0841/outputs/tophat_lmajor/accepted_paired.count.xz
## HPGL0842 <NA> preprocessing/hpgl0842/outputs/tophat_lmajor/accepted_paired.count.xz
## HPGL0843 <NA> preprocessing/hpgl0843/outputs/tophat_lmajor/accepted_paired.count.xz
## HPGL0844 <NA> preprocessing/hpgl0844/outputs/tophat_lmajor/accepted_paired.count.xz
## HPGL0845 <NA> preprocessing/hpgl0845/outputs/tophat_lmajor/accepted_paired.count.xz
## lmajor395
## HPGL0840 preprocessing/run0395/hpgl0840/outputs/bowtie2_lmajor/hpgl0840-trimmed.count.xz
## HPGL0841 <NA>
## HPGL0842 preprocessing/run0395/hpgl0842/outputs/bowtie2_lmajor/hpgl0842-trimmed.count.xz
## HPGL0843 preprocessing/run0395/hpgl0843/outputs/bowtie2_lmajor/hpgl0843-trimmed.count.xz
## HPGL0844 preprocessing/run0395/hpgl0844/outputs/bowtie2_lmajor/hpgl0844-trimmed.count.xz
## HPGL0845 preprocessing/run0395/hpgl0845/outputs/bowtie2_lmajor/hpgl0845-trimmed.count.xz
## mouse395
## HPGL0840 preprocessing/run0395/hpgl0840/outputs/kallisto_mmusculus/abundance.count.gz
## HPGL0841 preprocessing/run0395/hpgl0841/outputs/kallisto_mmusculus/abundance.count.gz
## HPGL0842 preprocessing/run0395/hpgl0842/outputs/kallisto_mmusculus/abundance.count.gz
## HPGL0843 preprocessing/run0395/hpgl0843/outputs/kallisto_mmusculus/abundance.count.gz
## HPGL0844 preprocessing/run0395/hpgl0844/outputs/kallisto_mmusculus/abundance.count.gz
## HPGL0845 preprocessing/run0395/hpgl0845/outputs/kallisto_mmusculus/abundance.count.gz
## file
## HPGL0840 null
## HPGL0841 null
## HPGL0842 null
## HPGL0843 null
## HPGL0844 null
## HPGL0845 null
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: stats4, parallel, stats, graphics, grDevices, utils, datasets, methods and base
other attached packages: hpgltools(v.2018.03), org.Lmajor.Friedlin.v36.eg.db(v.2018.03), bindrcpp(v.0.2), AnnotationDbi(v.1.40.0), IRanges(v.2.12.0), S4Vectors(v.0.16.0), Biobase(v.2.38.0), AnnotationHub(v.2.10.1) and BiocGenerics(v.0.24.0)
loaded via a namespace (and not attached): httr(v.1.3.1), RMySQL(v.0.10.14), bit64(v.0.9-7), jsonlite(v.1.5), foreach(v.1.4.4), shiny(v.1.0.5), assertthat(v.0.2.0), interactiveDisplayBase(v.1.16.0), highr(v.0.6), pander(v.0.6.1), blob(v.1.1.0), GenomeInfoDbData(v.1.0.0), Rsamtools(v.1.30.0), yaml(v.2.1.18), progress(v.1.1.2), pillar(v.1.2.1), RSQLite(v.2.0), backports(v.1.1.2), lattice(v.0.20-35), glue(v.1.2.0), digest(v.0.6.15), RColorBrewer(v.1.1-2), GenomicRanges(v.1.30.3), XVector(v.0.18.0), colorspace(v.1.3-2), htmltools(v.0.3.6), httpuv(v.1.3.6.2), Matrix(v.1.2-12), plyr(v.1.8.4), XML(v.3.98-1.10), pkgconfig(v.2.0.1), devtools(v.1.13.5), biomaRt(v.2.34.2), zlibbioc(v.1.24.0), xtable(v.1.8-2), scales(v.0.5.0), openxlsx(v.4.0.17), BiocParallel(v.1.12.0), tibble(v.1.4.2), ggplot2(v.2.2.1), withr(v.2.1.2), SummarizedExperiment(v.1.8.1), GenomicFeatures(v.1.30.3), lazyeval(v.0.2.1), magrittr(v.1.5), mime(v.0.5), memoise(v.1.1.0), evaluate(v.0.10.1), xml2(v.1.2.0), BiocInstaller(v.1.28.0), tools(v.3.4.4), data.table(v.1.10.4-3), prettyunits(v.1.0.2), matrixStats(v.0.53.1), stringr(v.1.3.0), munsell(v.0.4.3), DelayedArray(v.0.4.1), Biostrings(v.2.46.0), compiler(v.3.4.4), GenomeInfoDb(v.1.14.0), rlang(v.0.2.0), grid(v.3.4.4), RCurl(v.1.95-4.10), tximport(v.1.6.0), iterators(v.1.0.9), bitops(v.1.0-6), base64enc(v.0.1-3), rmarkdown(v.1.9), gtable(v.0.2.0), codetools(v.0.2-15), DBI(v.0.8), roxygen2(v.6.0.1), curl(v.3.1), R6(v.2.2.2), GenomicAlignments(v.1.14.1), knitr(v.1.20), dplyr(v.0.7.4), rtracklayer(v.1.38.3), bit(v.1.1-12), bindr(v.0.1.1), commonmark(v.1.4), rprojroot(v.1.3-2), stringi(v.1.1.7) and Rcpp(v.0.12.16)
this_save <- paste0(gsub(pattern="\\.Rmd", replace="", x=rmd_file), "-v", ver, ".rda.xz")
message(paste0("Saving to ", this_save))
## Saving to 01_annotation_mmusculus-v20180402.rda.xz
tt <- sm(saveme(filename=this_save))