library(AnnotationHub)
Loading required package: BiocGenerics
Loading required package: parallel
Attaching package: ‘BiocGenerics’
The following objects are masked from ‘package:parallel’:
clusterApply, clusterApplyLB, clusterCall, clusterEvalQ, clusterExport, clusterMap, parApply,
parCapply, parLapply, parLapplyLB, parRapply, parSapply, parSapplyLB
The following objects are masked from ‘package:stats’:
IQR, mad, sd, var, xtabs
The following objects are masked from ‘package:base’:
anyDuplicated, append, as.data.frame, cbind, colMeans, colnames, colSums, do.call, duplicated, eval,
evalq, Filter, Find, get, grep, grepl, intersect, is.unsorted, lapply, lengths, Map, mapply, match,
mget, order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank, rbind, Reduce, rowMeans, rownames,
rowSums, sapply, setdiff, sort, table, tapply, union, unique, unsplit, which, which.max, which.min
ah <- AnnotationHub()
updating metadata: retrieving 1 resource
|=============================================================================================================| 100%
snapshotDate(): 2017-04-25
gr <- query(ah, "GRanges")
grch38 <- subset(gr, genome == "GRCh38")
grch38
AnnotationHub with 37 records
# snapshotDate(): 2017-04-25
# $dataprovider: Ensembl, Gencode
# $species: Homo sapiens
# $rdataclass: GRanges
# additional mcols(): taxonomyid, genome, description, coordinate_1_based, maintainer, rdatadateadded,
# preparerclass, tags, rdatapath, sourceurl, sourcetype
# retrieve records with, e.g., 'object[["AH28606"]]'
title
AH28606 | Homo_sapiens.GRCh38.78.gtf
AH28674 | Homo_sapiens.GRCh38.76.gtf
AH28743 | Homo_sapiens.GRCh38.79.gtf
AH28812 | Homo_sapiens.GRCh38.77.gtf
AH47066 | Homo_sapiens.GRCh38.80.gtf
... ...
AH53321 | Homo_sapiens.GRCh38.87.gtf
AH53536 | Homo_sapiens.GRCh38.88.abinitio.gtf
AH53537 | Homo_sapiens.GRCh38.88.chr.gtf
AH53538 | Homo_sapiens.GRCh38.88.chr_patch_hapl_scaff.gtf
AH53539 | Homo_sapiens.GRCh38.88.gtf
names(grch38)
[1] "AH28606" "AH28674" "AH28743" "AH28812" "AH47066" "AH47963" "AH49554" "AH49555" "AH49556" "AH49557" "AH49558"
[12] "AH49559" "AH49560" "AH49561" "AH49562" "AH50308" "AH50377" "AH50841" "AH50842" "AH50843" "AH50844" "AH51011"
[23] "AH51012" "AH51013" "AH51014" "AH51952" "AH51953" "AH51954" "AH51955" "AH53318" "AH53319" "AH53320" "AH53321"
[34] "AH53536" "AH53537" "AH53538" "AH53539"
grch38[27:28]
AnnotationHub with 2 records
# snapshotDate(): 2017-04-25
# $dataprovider: Ensembl
# $species: Homo sapiens
# $rdataclass: GRanges
# additional mcols(): taxonomyid, genome, description, coordinate_1_based, maintainer, rdatadateadded,
# preparerclass, tags, rdatapath, sourceurl, sourcetype
# retrieve records with, e.g., 'object[["AH51953"]]'
title
AH51953 | Homo_sapiens.GRCh38.86.chr.gtf
AH51954 | Homo_sapiens.GRCh38.86.chr_patch_hapl_scaff.gtf
ens86 <- grch38[["AH51953"]]
Importing File into R ..
require(“rtracklayer”)
downloading from ‘https://annotationhub.bioconductor.org/fetch/58691’
retrieving 1 resource |=============================================================================================================| 100%
Attaching package: ‘Biostrings’
The following object is masked from ‘package:base’:
strsplit
using guess work to populate seqinfo
Warning message:
Failed to parse headers:
220-220- Welcome to the Ensembl anonymous FTP site
220-220- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
220-220-
220-220- Users of the material provided here in advance of submission to
220-220- public databases should read the Data Release Policy
220-220- and Guidelines and Conditions on use of Data in the respective data
220-220- directory.
220-220-
220-220- Please report any unusual problems you may have with this server
220-220- via e-mail to webmaster@ensembl.org
220-220-
220-220- All connections and transfers are logged
220-220-
220-220 (ensembl ftp server)
220
331 Please specify the password.
230 Login successful.
257 "/"
250 Directory successfully changed.
250 Directory successfully changed.
250 Directory successfully changed.
250 Directory successfully changed.
213 20160913145847
229 Entering Extended Passive Mode (|||31017|)
200 Switching to Binary mode.
213 45751175
150 Opening BINARY mode data connection for Homo_sapiens.GRCh3 [... truncated]
ens86_chr_patch_hapl_scaff <- grch38[["AH51954"]]
Importing File into R ..
downloading from ‘https://annotationhub.bioconductor.org/fetch/58692’
retrieving 1 resource
|=============================================================================================================| 100%
Error: failed to load resource
name: AH51954
title: Homo_sapiens.GRCh38.86.chr_patch_hapl_scaff.gtf
reason: invalid class “GRanges” object: 'seqnames(x)' contains missing values
In addition: Warning message:
Failed to parse headers:
213 20160913150653
229 Entering Extended Passive Mode (|||39568|)
213 49520204
150 Opening BINARY mode data connection for Homo_sapiens.GRCh38.86.chr_patch_hapl_scaff.gtf.gz (49520204 bytes).
226 Transfer complete.
sessionInfo()
R version 3.4.2 (2017-09-28)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 16.04.3 LTS
Matrix products: default
BLAS: /usr/lib/atlas-base/atlas/libblas.so.3.0
LAPACK: /usr/lib/atlas-base/atlas/liblapack.so.3.0
locale:
[1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
[5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8 LC_PAPER=en_US.UTF-8 LC_NAME=C
[9] LC_ADDRESS=C LC_TELEPHONE=C LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
attached base packages:
[1] stats4 parallel stats graphics grDevices utils datasets methods base
other attached packages:
[1] BSgenome.Hsapiens.NCBI.GRCh38_1.3.1000 BSgenome_1.44.2
[3] Biostrings_2.44.2 XVector_0.16.0
[5] rtracklayer_1.36.6 GenomicRanges_1.28.6
[7] GenomeInfoDb_1.12.3 IRanges_2.10.5
[9] S4Vectors_0.14.7 AnnotationHub_2.8.2
[11] BiocGenerics_0.22.1 nvimcom_0.9-36
[13] colorout_1.1-2
loaded via a namespace (and not attached):
[1] Rcpp_0.12.13 BiocInstaller_1.26.1 compiler_3.4.2
[4] bitops_1.0-6 tools_3.4.2 zlibbioc_1.22.0
[7] digest_0.6.12 bit_1.1-12 lattice_0.20-35
[10] RSQLite_2.0 memoise_1.1.0 tibble_1.3.4
[13] pkgconfig_2.0.1 rlang_0.1.2 Matrix_1.2-11
[16] DelayedArray_0.2.7 shiny_1.0.5 DBI_0.7
[19] curl_3.0 yaml_2.1.14 GenomeInfoDbData_0.99.0
[22] httr_1.3.1 grid_3.4.2 bit64_0.9-7
[25] Biobase_2.36.2 R6_2.2.2 AnnotationDbi_1.38.2
[28] BiocParallel_1.10.1 XML_3.98-1.9 blob_1.1.0
[31] matrixStats_0.52.2 GenomicAlignments_1.12.2 Rsamtools_1.28.0
[34] htmltools_0.3.6 SummarizedExperiment_1.6.5 mime_0.5
[37] interactiveDisplayBase_1.14.0 xtable_1.8-2 httpuv_1.3.5
[40] RCurl_1.95-4.8