Sequence-based TF affinity scoring can be conducted with the FIMO suite, see @Sonawane2017. We have serialized an object with references to FIMO outputs for 16 TFs.
## GenomicFiles object with 1 ranges and 16 files:
## files: M0635_1.02sort.bed.gz, M3433_1.02sort.bed.gz, ..., M6159_1.02sort.bed.gz, M6497_1.02sort.bed.gz
## detail: use files(), rowRanges(), colData(), ...While the token bed is used in the filenames, the files are
not actually bed format!
scanTabixWe can use reduceByRange to import selected scans.
if (.Platform$OS.type != "windows") {
si = TFutils::seqinfo_hg19_chr17
myg = GRanges("chr17", IRanges(38.07e6,38.09e6), seqinfo=si)
colnames(fimo16) = fimo16$HGNC
lk2 = reduceByRange(fimo16[, c("POU2F1", "VDR")],
MAP=function(r,f) scanTabix(f, param=r))
str(lk2)
}## List of 1
## $ :List of 2
## ..$ POU2F1:List of 1
## .. ..$ chr17:38077000-38084000: chr [1:12] "chr17\t38077313\t38077331\tchr17:38077313-38077331\t2.15306\t+\t0.000352" "chr17\t38078549\t38078567\tchr17:38078549-38078567\t0.102041\t-\t0.000634" "chr17\t38078556\t38078574\tchr17:38078556-38078574\t-0.0408163\t-\t0.00066" "chr17\t38080045\t38080063\tchr17:38080045-38080063\t1.66327\t-\t0.000407" ...
## ..$ VDR :List of 1
## .. ..$ chr17:38077000-38084000: chr [1:18] "chr17\t38077445\t38077460\tchr17:38077445-38077460\t-1.9899\t-\t0.000666" "chr17\t38078536\t38078551\tchr17:38078536-38078551\t-2.66667\t-\t0.0008" "chr17\t38078574\t38078589\tchr17:38078574-38078589\t1.65657\t+\t0.000235" "chr17\t38078796\t38078811\tchr17:38078796-38078811\t2.07071\t-\t0.000207" ...This result can be massaged into a GRanges or other desirable structure.
fimo_granges takes care of this.
#fimo_ranges = function(gf, query) { # prototypical code
# rowRanges(gf) = query
# ans = reduceByRange(gf, MAP=function(r,f) scanTabix(f, param=r))
# ans = unlist(ans, recursive=FALSE) # drop top list structure
# tabs = lapply(ans, lapply, function(x) {
# con = textConnection(x)
# on.exit(close(con))
# dtf = read.delim(con, h=FALSE, stringsAsFactors=FALSE, sep="\t")
# colnames(dtf) = c("chr", "start", "end", "rname", "score", "dir", "pval")
# ans = with(dtf, GRanges(seqnames=chr, IRanges(start, end),
# rname=rname, score=score, dir=dir, pval=pval))
# ans
# })
# GRangesList(unlist(tabs, recursive=FALSE))
#}
if (.Platform$OS.type != "windows") {
rr = fimo_granges(fimo16[, c("POU2F1", "VDR")], myg)
rr
}## $POU2F1
## $POU2F1$`chr17:38070000-38090000`
## GRanges object with 76 ranges and 4 metadata columns:
## seqnames ranges strand | rname score
## <Rle> <IRanges> <Rle> | <character> <numeric>
## [1] chr17 38070239-38070257 * | chr17:38070239-38070.. -1.5408200
## [2] chr17 38070579-38070597 * | chr17:38070579-38070.. -0.9693880
## [3] chr17 38070851-38070869 * | chr17:38070851-38070.. 0.1224490
## [4] chr17 38071025-38071043 * | chr17:38071025-38071.. 0.0918367
## [5] chr17 38071253-38071271 * | chr17:38071253-38071.. 3.6734700
## ... ... ... ... . ... ...
## [72] chr17 38088602-38088620 * | chr17:38088602-38088.. 4.06122
## [73] chr17 38088637-38088655 * | chr17:38088637-38088.. 11.69390
## [74] chr17 38089141-38089159 * | chr17:38089141-38089.. 13.18370
## [75] chr17 38089439-38089457 * | chr17:38089439-38089.. -1.35714
## [76] chr17 38089822-38089840 * | chr17:38089822-38089.. 3.67347
## dir pval
## <character> <numeric>
## [1] + 0.000989
## [2] - 0.000849
## [3] - 0.000631
## [4] - 0.000636
## [5] + 0.000222
## ... ... ...
## [72] + 1.98e-04
## [73] - 1.32e-05
## [74] - 7.09e-06
## [75] - 9.42e-04
## [76] - 2.22e-04
## -------
## seqinfo: 1 sequence from hg19 genome
##
##
## $VDR
## $VDR$`chr17:38070000-38090000`
## GRanges object with 40 ranges and 4 metadata columns:
## seqnames ranges strand | rname score
## <Rle> <IRanges> <Rle> | <character> <numeric>
## [1] chr17 38070016-38070031 * | chr17:38070016-38070.. 0.0505051
## [2] chr17 38070387-38070402 * | chr17:38070387-38070.. -3.3838400
## [3] chr17 38070925-38070940 * | chr17:38070925-38070.. 5.7171700
## [4] chr17 38071183-38071198 * | chr17:38071183-38071.. -0.6767680
## [5] chr17 38072289-38072304 * | chr17:38072289-38072.. -0.3333330
## ... ... ... ... . ... ...
## [36] chr17 38086915-38086930 * | chr17:38086915-38086.. -0.353535
## [37] chr17 38087304-38087319 * | chr17:38087304-38087.. 0.101010
## [38] chr17 38087866-38087881 * | chr17:38087866-38087.. 5.343430
## [39] chr17 38088893-38088908 * | chr17:38088893-38088.. -0.111111
## [40] chr17 38089214-38089229 * | chr17:38089214-38089.. 1.101010
## dir pval
## <character> <numeric>
## [1] + 3.77e-04
## [2] + 9.66e-04
## [3] - 6.44e-05
## [4] + 4.63e-04
## [5] - 4.21e-04
## ... ... ...
## [36] - 0.000423
## [37] - 0.000371
## [38] + 0.000073
## [39] - 0.000395
## [40] - 0.000277
## -------
## seqinfo: 1 sequence from hg19 genome## R version 4.3.1 (2023-06-16)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 22.04.3 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.18-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_GB LC_COLLATE=C
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## time zone: America/New_York
## tzcode source: system (glibc)
##
## attached base packages:
## [1] grid stats4 stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] UpSetR_1.4.0 magrittr_2.0.3
## [3] dplyr_1.1.3 gwascat_2.34.0
## [5] GSEABase_1.64.0 graph_1.80.0
## [7] annotate_1.80.0 XML_3.99-0.14
## [9] png_0.1-8 ggplot2_3.4.4
## [11] knitr_1.44 data.table_1.14.8
## [13] GO.db_3.18.0 GenomicFiles_1.38.0
## [15] rtracklayer_1.62.0 Rsamtools_2.18.0
## [17] Biostrings_2.70.0 XVector_0.42.0
## [19] BiocParallel_1.36.0 SummarizedExperiment_1.32.0
## [21] GenomicRanges_1.54.0 GenomeInfoDb_1.38.0
## [23] MatrixGenerics_1.14.0 matrixStats_1.0.0
## [25] org.Hs.eg.db_3.18.0 AnnotationDbi_1.64.0
## [27] IRanges_2.36.0 S4Vectors_0.40.0
## [29] Biobase_2.62.0 BiocGenerics_0.48.0
## [31] TFutils_1.22.0 BiocStyle_2.30.0
##
## loaded via a namespace (and not attached):
## [1] jsonlite_1.8.7 GenomicFeatures_1.54.0 farver_2.1.1
## [4] rmarkdown_2.25 BiocIO_1.12.0 zlibbioc_1.48.0
## [7] vctrs_0.6.4 memoise_2.0.1 RCurl_1.98-1.12
## [10] htmltools_0.5.6.1 S4Arrays_1.2.0 progress_1.2.2
## [13] curl_5.1.0 cellranger_1.1.0 SparseArray_1.2.0
## [16] sass_0.4.7 bslib_0.5.1 plyr_1.8.9
## [19] cachem_1.0.8 GenomicAlignments_1.38.0 mime_0.12
## [22] lifecycle_1.0.3 pkgconfig_2.0.3 Matrix_1.6-1.1
## [25] R6_2.5.1 fastmap_1.1.1 GenomeInfoDbData_1.2.11
## [28] shiny_1.7.5.1 digest_0.6.33 colorspace_2.1-0
## [31] RSQLite_2.3.1 filelock_1.0.2 labeling_0.4.3
## [34] fansi_1.0.5 httr_1.4.7 abind_1.4-5
## [37] compiler_4.3.1 bit64_4.0.5 withr_2.5.1
## [40] DBI_1.1.3 biomaRt_2.58.0 rappdirs_0.3.3
## [43] DelayedArray_0.28.0 rjson_0.2.21 tools_4.3.1
## [46] httpuv_1.6.12 glue_1.6.2 restfulr_0.0.15
## [49] promises_1.2.1 generics_0.1.3 gtable_0.3.4
## [52] BSgenome_1.70.0 tzdb_0.4.0 hms_1.1.3
## [55] xml2_1.3.5 utf8_1.2.4 pillar_1.9.0
## [58] stringr_1.5.0 later_1.3.1 splines_4.3.1
## [61] BiocFileCache_2.10.0 lattice_0.22-5 survival_3.5-7
## [64] bit_4.0.5 tidyselect_1.2.0 miniUI_0.1.1.1
## [67] gridExtra_2.3 bookdown_0.36 snpStats_1.52.0
## [70] xfun_0.40 stringi_1.7.12 yaml_2.3.7
## [73] evaluate_0.22 codetools_0.2-19 tibble_3.2.1
## [76] BiocManager_1.30.22 cli_3.6.1 xtable_1.8-4
## [79] munsell_0.5.0 jquerylib_0.1.4 Rcpp_1.0.11
## [82] readxl_1.4.3 dbplyr_2.3.4 parallel_4.3.1
## [85] ellipsis_0.3.2 readr_2.1.4 blob_1.2.4
## [88] prettyunits_1.2.0 bitops_1.0-7 VariantAnnotation_1.48.0
## [91] scales_1.2.1 crayon_1.5.2 rlang_1.1.1
## [94] KEGGREST_1.42.0