Thanks Valerie. On 02.05.2012 17:46, Valerie Obenchain wrote: > I'm sorry Alex, I missed your point the first time. Yes, there was a > bug in renameSeqlevels() wrt changing the chromosome names when the > renaming vector was out of order with 'x'. > > Now fixed in 1.8.5 release /1.9.13 devel. Thanks for reporting this. > > Valerie > > > > On 05/02/2012 09:25 AM, Valerie Obenchain wrote: >> Hi Alex, >> >> The ordering of the chromosome names displayed by seqlevels() comes >> from the seqlinfo object in the txdb. The ordering in the txdb or the >> txbygene before renaming is the same as after the renaming. >> >> txdb = TxDb.Hsapiens.UCSC.hg19.knownGene >> seqinfo(txdb) >> seqlevels(txdb) >> >> txbygene = transcriptsBy(txdb,"gene") >> seqinfo(txbygene) >> seqlevels(txbygene) >> >> This is not necessarily the same order as the seqnames (i.e., order >> of the ranges) in the txbygene object. >> seqnames(txbygene) >> >> Renaming the seqlevels has not changed the order of your txbygene >> ranges if that was the concern. No, the renaming vector does not need >> to match the ordering of the original names. >> >> Here is another way to prepare your new seqlevel names, >> >> nms <- seqlevels(txbygene)[1:24] >> vlu <- sub("chr", "", seqlevels(txbygene)[1:24], fixed=TRUE) >> names(vlu) <- nms >> renameSeqlevels(txbygene, vlu) >> >> Valerie >> >> >> On 05/02/2012 04:43 AM, Alex Gutteridge wrote: >>> Is this a bug in renameSeqlevels or expected behaviour? Note the >>> weird ordering of chromosome names in txbygene (chrX between chr7 and >>> chr8) which then results in misnaming when I try to use >>> renameSeqlevels (everything after chr7 is off by one). The docs for >>> renameSeqlevels aren't explicit in whether the renaming vector has to >>> match the ordering of the original names, but I thought the point of >>> making it named vector is that it doesn't? >>> >>>> library(TxDb.Hsapiens.UCSC.hg19.knownGene) >>> Loading required package: GenomicFeatures >>> Loading required package: BiocGenerics >>> >>> Attaching package: ?BiocGenerics? >>> >>> The following object(s) are masked from ?package:stats?: >>> >>> xtabs >>> >>> The following object(s) are masked from ?package:base?: >>> >>> anyDuplicated, cbind, colnames, duplicated, eval, Filter, Find, >>> get, intersect, lapply, Map, mapply, mget, order, paste, pmax, >>> pmax.int, pmin, pmin.int, Position, rbind, Reduce, rep.int, >>> rownames, sapply, setdiff, table, tapply, union, unique >>> >>> Loading required package: IRanges >>> Loading required package: GenomicRanges >>> Loading required package: AnnotationDbi >>> Loading required package: Biobase >>> Welcome to Bioconductor >>> >>> Vignettes contain introductory material; view with >>> 'browseVignettes()'. To cite Bioconductor, see >>> 'citation("Biobase")', and for packages 'citation("pkgname")'. >>> >>>> txdb = TxDb.Hsapiens.UCSC.hg19.knownGene >>>> txbygene = transcriptsBy(txdb,"gene") >>>> tx = >>>> renameSeqlevels(txbygene,c("chr1"="1","chr2"="2","chr3"="3","chr4 "="4", >>> + >>> "chr5"="5","chr6"="6","chr7"="7","chr8"="8", >>> + >>> "chr9"="9","chr10"="10","chr11"="11","chr12"="12", >>> + >>> "chr13"="13","chr14"="14","chr15"="15","chr16"="16", >>> + >>> "chr17"="17","chr18"="18","chr19"="19","chr20"="20", >>> + >>> "chr21"="21","chr22"="22","chrX"="X")) >>>> seqlevels(txbygene) >>> [1] "chr1" "chr2" "chr3" >>> [4] "chr4" "chr5" "chr6" >>> [7] "chr7" "chrX" "chr8" >>> [10] "chr9" "chr10" "chr11" >>> [13] "chr12" "chr13" "chr14" >>> [16] "chr15" "chr16" "chr17" >>> [19] "chr18" "chr20" "chrY" >>> [22] "chr19" "chr22" "chr21" >>> [25] "chr6_ssto_hap7" "chr6_mcf_hap5" >>> "chr6_cox_hap2" >>> [28] "chr6_mann_hap4" "chr6_apd_hap1" >>> "chr6_qbl_hap6" >>> [31] "chr6_dbb_hap3" "chr17_ctg5_hap1" >>> "chr4_ctg9_hap1" >>> [34] "chr1_gl000192_random" "chrUn_gl000225" >>> "chr4_gl000194_random" >>> [37] "chr4_gl000193_random" "chr9_gl000200_random" >>> "chrUn_gl000222" >>> [40] "chrUn_gl000212" "chr7_gl000195_random" >>> "chrUn_gl000223" >>> [43] "chrUn_gl000224" "chrUn_gl000219" >>> "chr17_gl000205_random" >>> [46] "chrUn_gl000215" "chrUn_gl000216" >>> "chrUn_gl000217" >>> [49] "chr9_gl000199_random" "chrUn_gl000211" >>> "chrUn_gl000213" >>> [52] "chrUn_gl000220" "chrUn_gl000218" >>> "chr19_gl000209_random" >>> [55] "chrUn_gl000221" "chrUn_gl000214" >>> "chrUn_gl000228" >>> [58] "chrUn_gl000227" "chr1_gl000191_random" >>> "chr19_gl000208_random" >>> [61] "chr9_gl000198_random" "chr17_gl000204_random" >>> "chrUn_gl000233" >>> [64] "chrUn_gl000237" "chrUn_gl000230" >>> "chrUn_gl000242" >>> [67] "chrUn_gl000243" "chrUn_gl000241" >>> "chrUn_gl000236" >>> [70] "chrUn_gl000240" "chr17_gl000206_random" >>> "chrUn_gl000232" >>> [73] "chrUn_gl000234" "chr11_gl000202_random" >>> "chrUn_gl000238" >>> [76] "chrUn_gl000244" "chrUn_gl000248" >>> "chr8_gl000196_random" >>> [79] "chrUn_gl000249" "chrUn_gl000246" >>> "chr17_gl000203_random" >>> [82] "chr8_gl000197_random" "chrUn_gl000245" >>> "chrUn_gl000247" >>> [85] "chr9_gl000201_random" "chrUn_gl000235" >>> "chrUn_gl000239" >>> [88] "chr21_gl000210_random" "chrUn_gl000231" >>> "chrUn_gl000229" >>> [91] "chrM" "chrUn_gl000226" >>> "chr18_gl000207_random" >>>> seqlevels(tx) >>> [1] "1" "2" "3" >>> [4] "4" "5" "6" >>> [7] "7" "8" "9" >>> [10] "10" "11" "12" >>> [13] "13" "14" "15" >>> [16] "16" "17" "18" >>> [19] "19" "20" "chrY" >>> [22] "21" "22" "X" >>> [25] "chr6_ssto_hap7" "chr6_mcf_hap5" >>> "chr6_cox_hap2" >>> [28] "chr6_mann_hap4" "chr6_apd_hap1" >>> "chr6_qbl_hap6" >>> [31] "chr6_dbb_hap3" "chr17_ctg5_hap1" >>> "chr4_ctg9_hap1" >>> [34] "chr1_gl000192_random" "chrUn_gl000225" >>> "chr4_gl000194_random" >>> [37] "chr4_gl000193_random" "chr9_gl000200_random" >>> "chrUn_gl000222" >>> [40] "chrUn_gl000212" "chr7_gl000195_random" >>> "chrUn_gl000223" >>> [43] "chrUn_gl000224" "chrUn_gl000219" >>> "chr17_gl000205_random" >>> [46] "chrUn_gl000215" "chrUn_gl000216" >>> "chrUn_gl000217" >>> [49] "chr9_gl000199_random" "chrUn_gl000211" >>> "chrUn_gl000213" >>> [52] "chrUn_gl000220" "chrUn_gl000218" >>> "chr19_gl000209_random" >>> [55] "chrUn_gl000221" "chrUn_gl000214" >>> "chrUn_gl000228" >>> [58] "chrUn_gl000227" "chr1_gl000191_random" >>> "chr19_gl000208_random" >>> [61] "chr9_gl000198_random" "chr17_gl000204_random" >>> "chrUn_gl000233" >>> [64] "chrUn_gl000237" "chrUn_gl000230" >>> "chrUn_gl000242" >>> [67] "chrUn_gl000243" "chrUn_gl000241" >>> "chrUn_gl000236" >>> [70] "chrUn_gl000240" "chr17_gl000206_random" >>> "chrUn_gl000232" >>> [73] "chrUn_gl000234" "chr11_gl000202_random" >>> "chrUn_gl000238" >>> [76] "chrUn_gl000244" "chrUn_gl000248" >>> "chr8_gl000196_random" >>> [79] "chrUn_gl000249" "chrUn_gl000246" >>> "chr17_gl000203_random" >>> [82] "chr8_gl000197_random" "chrUn_gl000245" >>> "chrUn_gl000247" >>> [85] "chr9_gl000201_random" "chrUn_gl000235" >>> "chrUn_gl000239" >>> [88] "chr21_gl000210_random" "chrUn_gl000231" >>> "chrUn_gl000229" >>> [91] "chrM" "chrUn_gl000226" >>> "chr18_gl000207_random" >>>> txbygene$'5327' >>> GRanges with 6 ranges and 2 elementMetadata cols: >>> seqnames ranges strand | tx_id tx_name >>> <rle> <iranges> <rle> | <integer> <character> >>> [1] chr8 [42032236, 42050729] - | 31953 uc010lxf.1 >>> [2] chr8 [42032236, 42050729] - | 31954 uc010lxg.1 >>> [3] chr8 [42032236, 42065194] - | 31955 uc003xos.2 >>> [4] chr8 [42032236, 42065194] - | 31956 uc003xot.2 >>> [5] chr8 [42032236, 42065194] - | 31957 uc011lcm.1 >>> [6] chr8 [42032236, 42065194] - | 31958 uc011lcn.1 >>> --- >>> seqlengths: >>> chr1 chr2 ... >>> chr18_gl000207_random >>> 249250621 243199373 ... >>> 4262 >>>> tx$'5327' >>> GRanges with 6 ranges and 2 elementMetadata cols: >>> seqnames ranges strand | tx_id tx_name >>> <rle> <iranges> <rle> | <integer> <character> >>> [1] 9 [42032236, 42050729] - | 31953 uc010lxf.1 >>> [2] 9 [42032236, 42050729] - | 31954 uc010lxg.1 >>> [3] 9 [42032236, 42065194] - | 31955 uc003xos.2 >>> [4] 9 [42032236, 42065194] - | 31956 uc003xot.2 >>> [5] 9 [42032236, 42065194] - | 31957 uc011lcm.1 >>> [6] 9 [42032236, 42065194] - | 31958 uc011lcn.1 >>> --- >>> seqlengths: >>> 1 2 ... >>> chr18_gl000207_random >>> 249250621 243199373 ... >>> 4262 >>>> txbygene$'1956' >>> GRanges with 11 ranges and 2 elementMetadata cols: >>> seqnames ranges strand | tx_id tx_name >>> <rle> <iranges> <rle> | <integer> <character> >>> [1] chr7 [55086725, 55224644] + | 28336 uc003tqh.3 >>> [2] chr7 [55086725, 55236328] + | 28337 uc003tqi.3 >>> [3] chr7 [55086725, 55238738] + | 28338 uc003tqj.3 >>> [4] chr7 [55086725, 55270769] + | 28339 uc022adm.1 >>> [5] chr7 [55086725, 55270769] + | 28340 uc010kzg.2 >>> [6] chr7 [55086725, 55275031] + | 28341 uc003tqk.3 >>> [7] chr7 [55086725, 55275031] + | 28342 uc022adn.1 >>> [8] chr7 [55177540, 55275031] + | 28343 uc011kco.2 >>> [9] chr7 [55224226, 55238906] + | 28345 uc011kcq.1 >>> [10] chr7 [55224226, 55238906] + | 28346 uc011kcp.1 >>> [11] chr7 [55248979, 55259567] + | 28349 uc022ado.1 >>> --- >>> seqlengths: >>> chr1 chr2 ... >>> chr18_gl000207_random >>> 249250621 243199373 ... >>> 4262 >>>> tx$'1956' >>> GRanges with 11 ranges and 2 elementMetadata cols: >>> seqnames ranges strand | tx_id tx_name >>> <rle> <iranges> <rle> | <integer> <character> >>> [1] 7 [55086725, 55224644] + | 28336 uc003tqh.3 >>> [2] 7 [55086725, 55236328] + | 28337 uc003tqi.3 >>> [3] 7 [55086725, 55238738] + | 28338 uc003tqj.3 >>> [4] 7 [55086725, 55270769] + | 28339 uc022adm.1 >>> [5] 7 [55086725, 55270769] + | 28340 uc010kzg.2 >>> [6] 7 [55086725, 55275031] + | 28341 uc003tqk.3 >>> [7] 7 [55086725, 55275031] + | 28342 uc022adn.1 >>> [8] 7 [55177540, 55275031] + | 28343 uc011kco.2 >>> [9] 7 [55224226, 55238906] + | 28345 uc011kcq.1 >>> [10] 7 [55224226, 55238906] + | 28346 uc011kcp.1 >>> [11] 7 [55248979, 55259567] + | 28349 uc022ado.1 >>> --- >>> seqlengths: >>> 1 2 ... >>> chr18_gl000207_random >>> 249250621 243199373 ... >>> 4262> sessionInfo() >>> R version 2.15.0 (2012-03-30) >>> Platform: x86_64-unknown-linux-gnu (64-bit) >>> >>> locale: >>> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C >>> [3] 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 >>> [7] LC_PAPER=C LC_NAME=C >>> [9] LC_ADDRESS=C LC_TELEPHONE=C >>> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C >>> >>> attached base packages: >>> [1] stats graphics grDevices utils datasets methods >>> base >>> >>> other attached packages: >>> [1] TxDb.Hsapiens.UCSC.hg19.knownGene_2.7.1 >>> [2] GenomicFeatures_1.8.1 >>> [3] AnnotationDbi_1.18.0 >>> [4] Biobase_2.16.0 >>> [5] GenomicRanges_1.8.3 >>> [6] IRanges_1.14.2 >>> [7] BiocGenerics_0.2.0 >>> >>> loaded via a namespace (and not attached): >>> [1] biomaRt_2.12.0 Biostrings_2.24.1 bitops_1.0-4.1 >>> BSgenome_1.24.0 >>> [5] DBI_0.2-5 RCurl_1.91-1 Rsamtools_1.8.3 >>> RSQLite_0.11.1 >>> [9] rtracklayer_1.16.1 stats4_2.15.0 tools_2.15.0 >>> XML_3.9-4 >>> [13] zlibbioc_1.2.0 >>> >> >> _______________________________________________ >> Bioconductor mailing list >> Bioconductor at r-project.org >> https://stat.ethz.ch/mailman/listinfo/bioconductor >> Search the archives: >> http://news.gmane.org/gmane.science.biology.informatics.conductor -- Alex Gutteridge