library(valr)
library(dplyr)
snps <- read_bed(valr_example("hg19.snps147.chr22.bed.gz"))
genes <- read_bed(valr_example("genes.hg19.chr22.bed.gz"))
# find snps in intergenic regions
intergenic <- bed_subtract(snps, genes)
#> Warning: The `min_overlap` argument of `bed_subtract()` is deprecated as of valr 0.8.0.
#> ℹ The default will change from 0 (book-ended intervals overlap) to 1 (strict
#>   overlap) in a future version.
#> ℹ Set `min_overlap = 0L` to keep the legacy behavior, or `min_overlap = 1L` for
#>   bedtools-compatible behavior.
#> This warning is displayed once every 8 hours.
#> Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
#> generated.
# find distance from intergenic snps to nearest gene
nearby <- bed_closest(intergenic, genes)
nearby |>
  select(starts_with("name"), .overlap, .dist) |>
  filter(abs(.dist) < 5000)
#> # A tibble: 1,047 × 4
#>    name.x      name.y   .overlap .dist
#>    <chr>       <chr>       <int> <int>
#>  1 rs530458610 P704P           0  2579
#>  2 rs2261631   P704P           0  -268
#>  3 rs570770556 POTEH           0  -913
#>  4 rs538163832 POTEH           0  -953
#>  5 rs190224195 POTEH           0 -1399
#>  6 rs2379966   DQ571479        0  4750
#>  7 rs142687051 DQ571479        0  3558
#>  8 rs528403095 DQ571479        0  3309
#>  9 rs555126291 DQ571479        0  2745
#> 10 rs5747567   DQ571479        0 -1778
#> # ℹ 1,037 more rows