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 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!

2 Importing with scanTabix

We can use reduceByRange to import selected scans.

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))
#}
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