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 = 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 = 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 4.3.0 RC (2023-04-13 r84269 ucrt)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows Server 2022 x64 (build 20348)
## 
## Matrix products: default
## 
## 
## 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_1.1.2                 gwascat_2.32.0             
##  [5] GSEABase_1.62.0             graph_1.78.0               
##  [7] annotate_1.78.0             XML_3.99-0.14              
##  [9] png_0.1-8                   ggplot2_3.4.2              
## [11] knitr_1.42                  data.table_1.14.8          
## [13] GO.db_3.17.0                GenomicFiles_1.36.0        
## [15] rtracklayer_1.60.0          Rsamtools_2.16.0           
## [17] Biostrings_2.68.0           XVector_0.40.0             
## [19] BiocParallel_1.34.0         SummarizedExperiment_1.30.0
## [21] GenomicRanges_1.52.0        GenomeInfoDb_1.36.0        
## [23] MatrixGenerics_1.12.0       matrixStats_0.63.0         
## [25] org.Hs.eg.db_3.17.0         AnnotationDbi_1.62.0       
## [27] IRanges_2.34.0              S4Vectors_0.38.0           
## [29] Biobase_2.60.0              BiocGenerics_0.46.0        
## [31] TFutils_1.20.0              BiocStyle_2.28.0           
## 
## loaded via a namespace (and not attached):
##  [1] DBI_1.1.3                bitops_1.0-7             gridExtra_2.3           
##  [4] readxl_1.4.2             biomaRt_2.56.0           rlang_1.1.0             
##  [7] compiler_4.3.0           RSQLite_2.3.1            GenomicFeatures_1.52.0  
## [10] vctrs_0.6.2              stringr_1.5.0            pkgconfig_2.0.3         
## [13] crayon_1.5.2             fastmap_1.1.1            dbplyr_2.3.2            
## [16] ellipsis_0.3.2           labeling_0.4.2           utf8_1.2.3              
## [19] promises_1.2.0.1         rmarkdown_2.21           tzdb_0.3.0              
## [22] bit_4.0.5                xfun_0.39                zlibbioc_1.46.0         
## [25] cachem_1.0.7             jsonlite_1.8.4           progress_1.2.2          
## [28] blob_1.2.4               highr_0.10               later_1.3.0             
## [31] DelayedArray_0.26.0      parallel_4.3.0           prettyunits_1.1.1       
## [34] R6_2.5.1                 VariantAnnotation_1.46.0 bslib_0.4.2             
## [37] stringi_1.7.12           jquerylib_0.1.4          cellranger_1.1.0        
## [40] bookdown_0.33            Rcpp_1.0.10              readr_2.1.4             
## [43] splines_4.3.0            httpuv_1.6.9             Matrix_1.5-4            
## [46] tidyselect_1.2.0         yaml_2.3.7               codetools_0.2-19        
## [49] miniUI_0.1.1.1           curl_5.0.0               plyr_1.8.8              
## [52] lattice_0.21-8           tibble_3.2.1             withr_2.5.0             
## [55] shiny_1.7.4              KEGGREST_1.40.0          evaluate_0.20           
## [58] survival_3.5-5           BiocFileCache_2.8.0      xml2_1.3.3              
## [61] snpStats_1.50.0          pillar_1.9.0             BiocManager_1.30.20     
## [64] filelock_1.0.2           generics_0.1.3           RCurl_1.98-1.12         
## [67] hms_1.1.3                munsell_0.5.0            scales_1.2.1            
## [70] xtable_1.8-4             glue_1.6.2               tools_4.3.0             
## [73] BiocIO_1.10.0            BSgenome_1.68.0          GenomicAlignments_1.36.0
## [76] colorspace_2.1-0         GenomeInfoDbData_1.2.10  restfulr_0.0.15         
## [79] cli_3.6.1                rappdirs_0.3.3           fansi_1.0.4             
## [82] gtable_0.3.3             sass_0.4.5               digest_0.6.31           
## [85] farver_2.1.1             rjson_0.2.21             memoise_2.0.1           
## [88] htmltools_0.5.5          lifecycle_1.0.3          httr_1.4.5              
## [91] mime_0.12                bit64_4.0.5