Contents

1 Introduction

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.

suppressPackageStartupMessages({
library(TFutils)
library(GenomicRanges)
})
fimo16
## GenomicFiles object with 0 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!

2 Importing with scanTabix

We 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 = GenomicFiles::reduceByRange(fimo16[, c("POU2F1", "VDR")],
   MAP=function(r,f) scanTabix(f, param=r))
 str(lk2)
}

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 = GenomicFiles::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
}
sessionInfo()
## R version 4.5.0 RC (2025-04-04 r88126 ucrt)
## Platform: x86_64-w64-mingw32/x64
## Running under: Windows Server 2022 x64 (build 20348)
## 
## Matrix products: default
##   LAPACK version 3.12.1
## 
## locale:
## [1] LC_COLLATE=C                          
## [2] LC_CTYPE=English_United States.utf8   
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C                          
## [5] LC_TIME=English_United States.utf8    
## 
## time zone: America/New_York
## tzcode source: internal
## 
## 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_1.1.4                 gwascat_2.40.0             
##  [5] GSEABase_1.70.0             graph_1.86.0               
##  [7] annotate_1.86.0             XML_3.99-0.18              
##  [9] png_0.1-8                   ggplot2_3.5.2              
## [11] knitr_1.50                  data.table_1.17.0          
## [13] GO.db_3.21.0                GenomicFiles_1.44.0        
## [15] rtracklayer_1.68.0          Rsamtools_2.24.0           
## [17] Biostrings_2.76.0           XVector_0.48.0             
## [19] BiocParallel_1.42.0         SummarizedExperiment_1.38.0
## [21] GenomicRanges_1.60.0        GenomeInfoDb_1.44.0        
## [23] MatrixGenerics_1.20.0       matrixStats_1.5.0          
## [25] org.Hs.eg.db_3.21.0         AnnotationDbi_1.70.0       
## [27] IRanges_2.42.0              S4Vectors_0.46.0           
## [29] Biobase_2.68.0              BiocGenerics_0.54.0        
## [31] generics_0.1.3              TFutils_1.28.0             
## [33] BiocStyle_2.36.0           
## 
## loaded via a namespace (and not attached):
##  [1] DBI_1.2.3                bitops_1.0-9             gridExtra_2.3           
##  [4] readxl_1.4.5             rlang_1.1.6              compiler_4.5.0          
##  [7] RSQLite_2.3.9            GenomicFeatures_1.60.0   vctrs_0.6.5             
## [10] pkgconfig_2.0.3          crayon_1.5.3             fastmap_1.2.0           
## [13] dbplyr_2.5.0             labeling_0.4.3           promises_1.3.2          
## [16] rmarkdown_2.29           UCSC.utils_1.4.0         bit_4.6.0               
## [19] xfun_0.52                zlibbioc_1.54.0          cachem_1.1.0            
## [22] jsonlite_2.0.0           blob_1.2.4               later_1.4.2             
## [25] DelayedArray_0.34.0      parallel_4.5.0           R6_2.6.1                
## [28] VariantAnnotation_1.54.0 bslib_0.9.0              jquerylib_0.1.4         
## [31] cellranger_1.1.0         bookdown_0.43            Rcpp_1.0.14             
## [34] splines_4.5.0            httpuv_1.6.15            Matrix_1.7-3            
## [37] tidyselect_1.2.1         abind_1.4-8              yaml_2.3.10             
## [40] codetools_0.2-20         miniUI_0.1.1.1           curl_6.2.2              
## [43] plyr_1.8.9               lattice_0.22-7           tibble_3.2.1            
## [46] withr_3.0.2              shiny_1.10.0             KEGGREST_1.48.0         
## [49] evaluate_1.0.3           survival_3.8-3           BiocFileCache_2.16.0    
## [52] snpStats_1.58.0          pillar_1.10.2            BiocManager_1.30.25     
## [55] filelock_1.0.3           RCurl_1.98-1.17          munsell_0.5.1           
## [58] scales_1.3.0             xtable_1.8-4             glue_1.8.0              
## [61] tools_4.5.0              BiocIO_1.18.0            BSgenome_1.76.0         
## [64] GenomicAlignments_1.44.0 colorspace_2.1-1         GenomeInfoDbData_1.2.14 
## [67] restfulr_0.0.15          cli_3.6.4                S4Arrays_1.8.0          
## [70] gtable_0.3.6             sass_0.4.10              digest_0.6.37           
## [73] SparseArray_1.8.0        farver_2.1.2             rjson_0.2.23            
## [76] memoise_2.0.1            htmltools_0.5.8.1        lifecycle_1.0.4         
## [79] httr_1.4.7               mime_0.13                bit64_4.6.0-1