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 Under development (unstable) (2024-10-26 r87273 ucrt)
## Platform: x86_64-w64-mingw32/x64
## 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_1.1.4                 gwascat_2.39.0             
##  [5] GSEABase_1.69.0             graph_1.85.0               
##  [7] annotate_1.85.0             XML_3.99-0.17              
##  [9] png_0.1-8                   ggplot2_3.5.1              
## [11] knitr_1.49                  data.table_1.16.2          
## [13] GO.db_3.20.0                GenomicFiles_1.43.0        
## [15] rtracklayer_1.67.0          Rsamtools_2.23.0           
## [17] Biostrings_2.75.1           XVector_0.47.0             
## [19] BiocParallel_1.41.0         SummarizedExperiment_1.37.0
## [21] GenomicRanges_1.59.0        GenomeInfoDb_1.43.0        
## [23] MatrixGenerics_1.19.0       matrixStats_1.4.1          
## [25] org.Hs.eg.db_3.20.0         AnnotationDbi_1.69.0       
## [27] IRanges_2.41.0              S4Vectors_0.45.1           
## [29] Biobase_2.67.0              BiocGenerics_0.53.2        
## [31] generics_0.1.3              TFutils_1.27.1             
## [33] BiocStyle_2.35.0           
## 
## loaded via a namespace (and not attached):
##  [1] DBI_1.2.3                bitops_1.0-9             gridExtra_2.3           
##  [4] readxl_1.4.3             rlang_1.1.4              compiler_4.5.0          
##  [7] RSQLite_2.3.7            GenomicFeatures_1.59.1   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           utf8_1.2.4              
## [16] promises_1.3.0           rmarkdown_2.29           tzdb_0.4.0              
## [19] UCSC.utils_1.3.0         bit_4.5.0                xfun_0.49               
## [22] zlibbioc_1.53.0          cachem_1.1.0             jsonlite_1.8.9          
## [25] blob_1.2.4               later_1.3.2              DelayedArray_0.33.1     
## [28] parallel_4.5.0           R6_2.5.1                 VariantAnnotation_1.53.0
## [31] bslib_0.8.0              jquerylib_0.1.4          cellranger_1.1.0        
## [34] bookdown_0.41            Rcpp_1.0.13-1            readr_2.1.5             
## [37] splines_4.5.0            httpuv_1.6.15            Matrix_1.7-1            
## [40] tidyselect_1.2.1         abind_1.4-8              yaml_2.3.10             
## [43] codetools_0.2-20         miniUI_0.1.1.1           curl_6.0.0              
## [46] plyr_1.8.9               lattice_0.22-6           tibble_3.2.1            
## [49] withr_3.0.2              shiny_1.9.1              KEGGREST_1.47.0         
## [52] evaluate_1.0.1           survival_3.7-0           BiocFileCache_2.15.0    
## [55] snpStats_1.57.0          pillar_1.9.0             BiocManager_1.30.25     
## [58] filelock_1.0.3           RCurl_1.98-1.16          hms_1.1.3               
## [61] munsell_0.5.1            scales_1.3.0             xtable_1.8-4            
## [64] glue_1.8.0               tools_4.5.0              BiocIO_1.17.0           
## [67] BSgenome_1.75.0          GenomicAlignments_1.43.0 colorspace_2.1-1        
## [70] GenomeInfoDbData_1.2.13  restfulr_0.0.15          cli_3.6.3               
## [73] fansi_1.0.6              S4Arrays_1.7.1           gtable_0.3.6            
## [76] sass_0.4.9               digest_0.6.37            SparseArray_1.7.1       
## [79] farver_2.1.2             rjson_0.2.23             memoise_2.0.1           
## [82] htmltools_0.5.8.1        lifecycle_1.0.4          httr_1.4.7              
## [85] mime_0.12                bit64_4.5.2