Operations on Genomic Intervals and Genome Arithmetic

Introduction

VCF files can contain vast quantities of data, from many chromosomes. However, in cases where only the data from specific genes or genomic regions are required for analysis, these regions can be extracted in R using the Bioconductor GenomicRanges package in R.

IRanges is a library for representing integer ranges, which is useful in genomics because we need to manipulate base pair ranges.

IRanges have a start, an end and an witdh.

Methods

Set working directory:

setwd = ("C:/Users/manso/OneDrive - University of West London/MSc Bioinformatics - UWL/3.DSB - Data Science for Bioinformatics/Practice/W13 - Genomic Intervals and Genome Arithmetic")

Install packages:

install.packages("BiocManager")
BiocManager::install(c("GenomicRanges", "plyranges", "HelloRangesData"))

1. Create IR object

#IR with 6 base-apirs long: start and end are indicated
IR <- IRanges(5,10)
IR
IRanges object with 1 range and 0 metadata columns:
          start       end     width
      <integer> <integer> <integer>
  [1]         5        10         6
start(IR) #return the start value
[1] 5
end(IR) #return 
[1] 10
width(IR) #return the width
[1] 6

2. Introducing Granges

library(plyranges, quietly = TRUE)

genes <- data.frame(seqnames = "VI", 

          start = c(3322, 3030, 1437, 5066, 6426, 836),

          end = c(3846, 3338, 2615, 5521, 7565, 1363),

          strand = c("-", "-", "-", "+", "+", "+"),

          gene_id=c("YFL064C", "YFL065C", "YFL066C", 

               "YFL063W", "YFL062W", "YFL067W"),

          gc = runif(6),

          score = rbinom(6, size = 3, p = 0.1),

          stringsAsFactors = FALSE)

genes <- as_granges(genes)


genes
GRanges object with 6 ranges and 3 metadata columns:
      seqnames    ranges strand |     gene_id         gc     score
         <Rle> <IRanges>  <Rle> | <character>  <numeric> <integer>
  [1]       VI 3322-3846      - |     YFL064C 0.77730361         0
  [2]       VI 3030-3338      - |     YFL065C 0.00456595         0
  [3]       VI 1437-2615      - |     YFL066C 0.57144666         1
  [4]       VI 5066-5521      + |     YFL063W 0.30042006         0
  [5]       VI 6426-7565      + |     YFL062W 0.65073446         1
  [6]       VI  836-1363      + |     YFL067W 0.53914336         0
  -------
  seqinfo: 1 sequence from an unspecified genome; no seqlengths

3. Arithmetics on Ranges

rng <- as_iranges(data.frame(start=c(1,2,3), end=c(5,2,8)))
grng <- as_granges(data.frame(start=c(1,2,3), end=c(5,2,8),
                               seqnames = "seq1",
                               strand=c("+", "*", "-")))
grng
GRanges object with 3 ranges and 0 metadata columns:
      seqnames    ranges strand
         <Rle> <IRanges>  <Rle>
  [1]     seq1       1-5      +
  [2]     seq1         2      *
  [3]     seq1       3-8      -
  -------
  seqinfo: 1 sequence from an unspecified genome; no seqlengths
mutate(rng, width =10)
IRanges object with 3 ranges and 0 metadata columns:
          start       end     width
      <integer> <integer> <integer>
  [1]         1        10        10
  [2]         2        11        10
  [3]         3        12        10

Anchoring fixes either the start, end, center coordinates of the range object, as shown in the figure and code below. Anchors are used in combination with either mutate od stretch.

mutate(anchor_start(rng), width=10)
IRanges object with 3 ranges and 0 metadata columns:
          start       end     width
      <integer> <integer> <integer>
  [1]         1        10        10
  [2]         2        11        10
  [3]         3        12        10
mutate(anchor_end(rng), width=10)
IRanges object with 3 ranges and 0 metadata columns:
          start       end     width
      <integer> <integer> <integer>
  [1]        -4         5        10
  [2]        -7         2        10
  [3]        -1         8        10
mutate(anchor_center(rng), width=10)
IRanges object with 3 ranges and 0 metadata columns:
          start       end     width
      <integer> <integer> <integer>
  [1]        -2         7        10
  [2]        -3         6        10
  [3]         1        10        10
rng
IRanges object with 3 ranges and 0 metadata columns:
          start       end     width
      <integer> <integer> <integer>
  [1]         1         5         5
  [2]         2         2         1
  [3]         3         8         6

4. Import Rsamtools to store VCF file and index as a Tabix object

if (!requireNamespace("BiocManager", quietly =TRUE))
  install.packages("BiocManager")
BiocManager::install("Rsamtools")
BiocManager::install("biomaRt")
BiocManager::install("VariantAnnotation")
library(Rsamtools)
library(GenomicRanges)
library(biomaRt)
library(VariantAnnotation)

Get Data

VCFChr7 <- 
TabixFile("ALL.chr7.phase3_shapeit2_mvncall_integrated_v5b.20130502.genotypes.vcf.gz")
AOC1range <- GRanges(seqnames="7", ranges=IRanges(start=(150824875), end=(150861504), names="AOC1"))
ensembl <- useMart("ensembl")
datasets <- listDatasets(ensembl)
ensembl = useDataset("hsapiens_gene_ensembl", mart=ensembl)
hg38 <- ensembl

Write the VCF data containing only variants for the AOC1 genomic region and it’s index to file.

VCFAOC1 <- readVcf(VCFChr7, "hg38", param =AOC1range)
writeVcf(VCFAOC1, "dsbAOC1ext.vcf", index =TRUE)

The components of the genomic coordinates within a GenomicRanges object can be extracted using the seqnames, ranges, and strand accessor functions.

seqnames(VCFAOC1)
factor-Rle of length 1063 with 1 run
  Lengths: 1063
  Values :    7
Levels(86): 1 2 3 4 5 6 7 ... GL000249.1 MT NC_007605 X Y hs37d5
ranges(VCFAOC1)
IRanges object with 1063 ranges and 0 metadata columns:
                       start       end     width
                   <integer> <integer> <integer>
   7:150824913_G/A 150824913 150824913         1
   7:150825001_C/G 150825001 150825001         1
   7:150825031_C/T 150825031 150825031         1
   7:150825032_G/A 150825032 150825032         1
   7:150825037_T/C 150825037 150825037         1
               ...       ...       ...       ...
   7:150861125_C/A 150861125 150861125         1
  7:150861130_T/TA 150861130 150861130         1
   7:150861227_G/A 150861227 150861227         1
   7:150861287_A/G 150861287 150861287         1
   7:150861381_G/A 150861381 150861381         1
strand(VCFAOC1)
factor-Rle of length 1063 with 1 run
  Lengths: 1063
  Values :    *
Levels(3): + - *

The genomic ranges can be extracted without corresponding metadata with GRange

granges(VCFAOC1)
GRanges object with 1063 ranges and 5 metadata columns:
                   seqnames    ranges strand | paramRangeID
                      <Rle> <IRanges>  <Rle> |     <factor>
   7:150824913_G/A        7 150824913      * |         AOC1
   7:150825001_C/G        7 150825001      * |         AOC1
   7:150825031_C/T        7 150825031      * |         AOC1
   7:150825032_G/A        7 150825032      * |         AOC1
   7:150825037_T/C        7 150825037      * |         AOC1
               ...      ...       ...    ... .          ...
   7:150861125_C/A        7 150861125      * |         AOC1
  7:150861130_T/TA        7 150861130      * |         AOC1
   7:150861227_G/A        7 150861227      * |         AOC1
   7:150861287_A/G        7 150861287      * |         AOC1
   7:150861381_G/A        7 150861381      * |         AOC1
                              REF                ALT      QUAL
                   <DNAStringSet> <DNAStringSetList> <numeric>
   7:150824913_G/A              G                  A       100
   7:150825001_C/G              C                  G       100
   7:150825031_C/T              C                  T       100
   7:150825032_G/A              G                  A       100
   7:150825037_T/C              T                  C       100
               ...            ...                ...       ...
   7:150861125_C/A              C                  A       100
  7:150861130_T/TA              T                 TA       100
   7:150861227_G/A              G                  A       100
   7:150861287_A/G              A                  G       100
   7:150861381_G/A              G                  A       100
                        FILTER
                   <character>
   7:150824913_G/A        PASS
   7:150825001_C/G        PASS
   7:150825031_C/T        PASS
   7:150825032_G/A        PASS
   7:150825037_T/C        PASS
               ...         ...
   7:150861125_C/A        PASS
  7:150861130_T/TA        PASS
   7:150861227_G/A        PASS
   7:150861287_A/G        PASS
   7:150861381_G/A        PASS
  -------
  seqinfo: 86 sequences from hg38 genome

Annotations for these coordinates can be extracted as a DataFrame object using the mcols accessor.

mcols(VCFAOC1) 
DataFrame with 1063 rows and 5 columns
                 paramRangeID            REF                ALT
                     <factor> <DNAStringSet> <DNAStringSetList>
7:150824913_G/A          AOC1              G                  A
7:150825001_C/G          AOC1              C                  G
7:150825031_C/T          AOC1              C                  T
7:150825032_G/A          AOC1              G                  A
7:150825037_T/C          AOC1              T                  C
...                       ...            ...                ...
7:150861125_C/A          AOC1              C                  A
7:150861130_T/TA         AOC1              T                 TA
7:150861227_G/A          AOC1              G                  A
7:150861287_A/G          AOC1              A                  G
7:150861381_G/A          AOC1              G                  A
                      QUAL      FILTER
                 <numeric> <character>
7:150824913_G/A        100        PASS
7:150825001_C/G        100        PASS
7:150825031_C/T        100        PASS
7:150825032_G/A        100        PASS
7:150825037_T/C        100        PASS
...                    ...         ...
7:150861125_C/A        100        PASS
7:150861130_T/TA       100        PASS
7:150861227_G/A        100        PASS
7:150861287_A/G        100        PASS
7:150861381_G/A        100        PASS

Information about the lengths and names of the sequences in the VCF can also be accessed

seqlengths(VCFAOC1)
         1          2          3          4          5          6 
 249250621  243199373  198022430  191154276  180915260  171115067 
         7          8          9         10         11         12 
 159138663  146364022  141213431  135534747  135006516  133851895 
        13         14         15         16         17         18 
 115169878  107349540  102531392   90354753   81195210   78077248 
        19         20         21         22 GL000191.1 GL000192.1 
  59128983   63025520   48129895   51304566     106433     547496 
GL000193.1 GL000194.1 GL000195.1 GL000196.1 GL000197.1 GL000198.1 
    189789     191469     182896      38914      37175      90085 
GL000199.1 GL000200.1 GL000201.1 GL000202.1 GL000203.1 GL000204.1 
    169874     187035      36148      40103      37498      81310 
GL000205.1 GL000206.1 GL000207.1 GL000208.1 GL000209.1 GL000210.1 
    174588      41001       4262      92689     159169      27682 
GL000211.1 GL000212.1 GL000213.1 GL000214.1 GL000215.1 GL000216.1 
    166566     186858     164239     137718     172545     172294 
GL000217.1 GL000218.1 GL000219.1 GL000220.1 GL000221.1 GL000222.1 
    172149     161147     179198     161802     155397     186861 
GL000223.1 GL000224.1 GL000225.1 GL000226.1 GL000227.1 GL000228.1 
    180455     179693     211173      15008     128374     129120 
GL000229.1 GL000230.1 GL000231.1 GL000232.1 GL000233.1 GL000234.1 
     19913      43691      27386      40652      45941      40531 
GL000235.1 GL000236.1 GL000237.1 GL000238.1 GL000239.1 GL000240.1 
     34474      41934      45867      39939      33824      41933 
GL000241.1 GL000242.1 GL000243.1 GL000244.1 GL000245.1 GL000246.1 
     42152      43523      43341      39929      36651      38154 
GL000247.1 GL000248.1 GL000249.1         MT  NC_007605          X 
     36422      39786      38502      16569     171823  155270560 
         Y     hs37d5 
  59373566   35477943 
names(VCFAOC1)
   [1] "7:150824913_G/A"             "7:150825001_C/G"            
   [3] "7:150825031_C/T"             "7:150825032_G/A"            
   [5] "7:150825037_T/C"             "7:150825060_C/T"            
   [7] "7:150825087_G/A"             "7:150825096_G/C"            
   [9] "7:150825177_T/G"             "7:150825201_G/T"            
  [11] "7:150825223_G/A"             "7:150825315_G/A"            
  [13] "7:150825350_T/C"             "7:150825389_C/T"            
  [15] "7:150825394_T/A"             "7:150825420_C/T"            
  [17] "7:150825432_G/A"             "7:150825492_A/G"            
  [19] "7:150825512_C/T"             "7:150825567_C/T"            
  [21] "7:150825568_G/C"             "7:150825574_G/C"            
  [23] "7:150825589_C/T"             "7:150825593_C/T"            
  [25] "7:150825594_G/A"             "7:150825629_G/A"            
  [27] "7:150825664_C/T"             "7:150825675_G/A"            
  [29] "7:150825676_C/T"             "7:150825688_G/A"            
  [31] "7:150825729_G/T"             "7:150825806_T/A"            
  [33] "7:150825813_G/C"             "7:150825839_G/A"            
  [35] "7:150825865_C/T"             "7:150825866_G/A"            
  [37] "7:150825933_G/T"             "7:150825939_C/G"            
  [39] "7:150825969_T/G"             "7:150825981_A/G"            
  [41] "7:150825992_C/T"             "7:150826035_A/C"            
  [43] "7:150826044_G/A"             "7:150826207_G/A"            
  [45] "7:150826219_C/G"             "7:150826313_C/T"            
  [47] "7:150826318_C/T"             "7:150826345_C/T"            
  [49] "7:150826385_A/G"             "7:150826406_C/G"            
  [51] "7:150826415_G/A"             "7:150826423_C/T"            
  [53] "7:150826434_GC/G"            "7:150826443_C/T"            
  [55] "7:150826454_G/A"             "7:150826470_C/T"            
  [57] "7:150826471_G/A"             "7:150826500_G/C"            
  [59] "7:150826545_C/G"             "7:150826555_A/G"            
  [61] "7:150826561_C/T"             "7:150826575_C/T"            
  [63] "7:150826623_C/G"             "7:150826670_G/A"            
  [65] "7:150826673_C/T"             "7:150826684_A/G"            
  [67] "7:150826687_C/T"             "7:150826766_A/G"            
  [69] "7:150826818_CTCGCGAG/C"      "7:150826912_G/A"            
  [71] "7:150826939_G/A"             "7:150826950_C/A"            
  [73] "7:150826997_C/T"             "7:150827104_G/A"            
  [75] "7:150827114_G/A"             "7:150827117_C/T"            
  [77] "7:150827137_G/A"             "7:150827175_G/A"            
  [79] "7:150827207_A/G"             "7:150827235_C/T"            
  [81] "7:150827243_C/A"             "7:150827245_C/T"            
  [83] "7:150827333_G/A"             "7:150827336_G/A"            
  [85] "7:150827391_G/T"             "7:150827478_C/T"            
  [87] "7:150827674_C/T"             "7:150827682_G/A"            
  [89] "7:150827694_C/T"             "7:150827695_G/A"            
  [91] "7:150827781_G/A"             "7:150827794_C/CTA"          
  [93] "7:150827802_G/A"             "7:150827860_C/T"            
  [95] "7:150827913_G/A"             "7:150827933_G/A"            
  [97] "7:150827951_C/T"             "7:150827975_T/C"            
  [99] "7:150828058_T/A"             "7:150828059_T/C"            
 [101] "7:150828060_C/T"             "7:150828122_G/C"            
 [103] "7:150828169_G/A"             "7:150828219_C/T"            
 [105] "7:150828234_C/T"             "7:150828249_C/T"            
 [107] "7:150828271_C/T"             "7:150828275_C/G"            
 [109] "7:150828316_A/G"             "7:150828344_A/C"            
 [111] "7:150828467_T/C"             "7:150828468_A/G"            
 [113] "7:150828472_C/T"             "7:150828530_G/C"            
 [115] "7:150828556_G/C"             "7:150828564_T/C"            
 [117] "7:150828581_A/G"             "7:150828609_C/T"            
 [119] "7:150828646_C/T"             "7:150828673_C/T"            
 [121] "7:150828676_T/C"             "7:150828692_G/C"            
 [123] "7:150828707_G/A"             "7:150828713_G/A"            
 [125] "7:150828742_C/T"             "7:150828789_G/A"            
 [127] "7:150828815_G/A"             "7:150828858_G/A"            
 [129] "7:150828876_A/G"             "7:150828988_C/A"            
 [131] "7:150829071_T/C"             "7:150829082_G/A"            
 [133] "7:150829091_C/T"             "7:150829101_G/T"            
 [135] "7:150829104_C/T"             "7:150829197_C/T"            
 [137] "7:150829221_G/C"             "7:150829222_G/A"            
 [139] "7:150829248_C/T"             "7:150829263_A/G"            
 [141] "7:150829348_G/A"             "7:150829351_C/T"            
 [143] "7:150829352_G/A"             "7:150829378_G/A"            
 [145] "7:150829458_A/G"             "7:150829475_C/G"            
 [147] "7:150829494_G/A"             "7:150829511_T/C"            
 [149] "7:150829533_G/A"             "7:150829613_C/T"            
 [151] "7:150829636_G/A"             "7:150829657_A/G"            
 [153] "7:150829682_G/A"             "7:150829684_A/G"            
 [155] "7:150829689_C/T"             "7:150829709_G/A"            
 [157] "7:150829727_G/A"             "7:150829728_C/T"            
 [159] "7:150829729_G/A"             "7:150829736_T/C"            
 [161] "7:150829738_C/A"             "7:150829743_C/A"            
 [163] "7:150829810_C/T"             "7:150829828_G/A"            
 [165] "7:150829841_G/A"             "7:150829936_C/T"            
 [167] "7:150829963_C/T"             "7:150829978_C/T"            
 [169] "7:150830010_G/C"             "7:150830015_A/G"            
 [171] "7:150830021_C/T"             "7:150830033_C/T"            
 [173] "7:150830034_G/A"             "7:150830037_G/A"            
 [175] "7:150830102_G/A"             "7:150830109_T/A"            
 [177] "7:150830124_C/T"             "7:150830126_C/A"            
 [179] "7:150830127_G/A"             "7:150830148_G/A"            
 [181] "7:150830151_C/T"             "7:150830221_A/G"            
 [183] "7:150830291_A/C"             "7:150830341_G/A"            
 [185] "7:150830363_G/T"             "7:150830385_C/T"            
 [187] "7:150830475_G/A"             "7:150830505_G/A"            
 [189] "7:150830538_C/T"             "7:150830548_C/T"            
 [191] "7:150830563_G/A"             "7:150830593_C/T"            
 [193] "7:150830594_G/A"             "7:150830624_C/T"            
 [195] "7:150830760_C/G"             "7:150830806_C/T"            
 [197] "7:150830807_G/T"             "7:150830866_C/T"            
 [199] "7:150830888_C/T"             "7:150830889_G/A"            
 [201] "7:150830904_C/T"             "7:150830956_C/T"            
 [203] "7:150830999_G/A"             "7:150831032_G/A"            
 [205] "7:150831053_G/T"             "7:150831098_G/C"            
 [207] "7:150831100_C/A"             "7:150831101_A/G"            
 [209] "7:150831113_G/A"             "7:150831205_C/T"            
 [211] "7:150831222_T/C"             "7:150831229_C/T"            
 [213] "7:150831233_G/A"             "7:150831254_C/T"            
 [215] "7:150831289_C/T"             "7:150831309_C/T"            
 [217] "7:150831310_G/A"             "7:150831315_G/A"            
 [219] "7:150831318_C/T"             "7:150831319_G/A"            
 [221] "7:150831343_A/G"             "7:150831363_G/A"            
 [223] "7:150831395_C/T"             "7:150831430_A/G"            
 [225] "7:150831431_C/T"             "7:150831477_C/T"            
 [227] "7:150831530_G/A"             "7:150831602_G/A"            
 [229] "7:150831609_C/T"             "7:150831626_G/A"            
 [231] "7:150831640_C/T"             "7:150831662_C/T"            
 [233] "7:150831764_G/A"             "7:150831772_C/T"            
 [235] "7:150831796_C/T"             "7:150831808_C/T"            
 [237] "7:150831880_G/T"             "7:150831915_G/A"            
 [239] "7:150831923_G/A"             "7:150831953_C/T"            
 [241] "7:150831987_C/T"             "7:150831988_G/A"            
 [243] "7:150832016_G/A"             "7:150832022_G/A"            
 [245] "7:150832037_C/T"             "7:150832051_G/A"            
 [247] "7:150832052_T/C"             "7:150832073_G/A"            
 [249] "7:150832088_C/T"             "7:150832110_T/G"            
 [251] "7:150832160_G/A"             "7:150832217_A/T"            
 [253] "7:150832230_C/T"             "7:150832265_A/G"            
 [255] "7:150832285_C/G"             "7:150832327_G/A"            
 [257] "7:150832374_A/G"             "7:150832381_C/T"            
 [259] "7:150832497_G/A"             "7:150832512_A/G"            
 [261] "7:150832559_C/T"             "7:150832616_A/G"            
 [263] "7:150832783_CA/C"            "7:150832786_G/A"            
 [265] "7:150832913_A/G"             "7:150832923_A/G"            
 [267] "7:150832959_A/G"             "7:150832968_CCTAA/C"        
 [269] "7:150832993_A/C"             "7:150832999_C/T"            
 [271] "7:150833040_A/G"             "7:150833046_A/T"            
 [273] "7:150833130_C/T"             "7:150833151_T/C"            
 [275] "7:150833170_T/G"             "7:150833204_C/T"            
 [277] "7:150833208_G/A"             "7:150833212_C/G"            
 [279] "7:150833223_G/A"             "7:150833270_C/G"            
 [281] "7:150833326_G/A"             "7:150833333_G/A"            
 [283] "7:150833336_C/T"             "7:150833343_C/A"            
 [285] "7:150833359_C/T"             "7:150833380_C/T"            
 [287] "7:150833381_G/A"             "7:150833438_C/T"            
 [289] "7:150833443_C/T"             "7:150833467_C/A"            
 [291] "7:150833471_C/T"             "7:150833504_G/A"            
 [293] "7:150833505_C/T"             "7:150833517_G/A"            
 [295] "7:150833527_G/A"             "7:150833563_C/T"            
 [297] "7:150833577_G/A"             "7:150833579_T/C"            
 [299] "7:150833599_T/G"             "7:150833620_C/T"            
 [301] "7:150833621_G/A"             "7:150833625_C/T"            
 [303] "7:150833699_G/A"             "7:150833755_CAAAG/C"        
 [305] "7:150833798_C/T"             "7:150833799_G/A"            
 [307] "7:150833895_G/C"             "7:150833940_A/G"            
 [309] "7:150834049_C/T"             "7:150834088_C/G"            
 [311] "7:150834096_G/A"             "7:150834114_G/T"            
 [313] "7:150834138_A/T"             "7:150834166_G/A"            
 [315] "7:150834265_C/T"             "7:150834306_C/T"            
 [317] "7:150834326_T/C"             "7:150834348_C/T"            
 [319] "7:150834408_G/T"             "7:150834428_GC/G"           
 [321] "7:150834434_G/A"             "7:150834447_G/A"            
 [323] "7:150834488_G/C"             "7:150834516_G/A"            
 [325] "7:150834539_C/T"             "7:150834582_A/C"            
 [327] "7:150834597_A/G"             "7:150834600_G/T"            
 [329] "7:150834623_G/A"             "7:150834650_C/T"            
 [331] "7:150834687_T/C"             "7:150834727_C/T"            
 [333] "7:150834768_T/C"             "7:150834779_C/T"            
 [335] "7:150834811_C/T"             "7:150834837_G/A"            
 [337] "7:150834900_CAAG/AAAG"       "7:150834913_G/A"            
 [339] "7:150834928_C/T"             "7:150834940_C/T"            
 [341] "7:150835070_G/A"             "7:150835210_C/T"            
 [343] "7:150835217_T/C"             "7:150835222_G/A"            
 [345] "7:150835236_C/T"             "7:150835238_C/A"            
 [347] "7:150835242_C/T"             "7:150835300_C/G"            
 [349] "7:150835306_C/T"             "7:150835336_C/G"            
 [351] "7:150835349_G/A"             "7:150835356_G/A"            
 [353] "7:150835427_C/A"             "7:150835460_G/A"            
 [355] "7:150835680_C/T"             "7:150835683_C/T"            
 [357] "7:150835698_C/T"             "7:150835724_C/T"            
 [359] "7:150835730_C/T"             "7:150835731_G/A"            
 [361] "7:150835762_G/GC"            "7:150835803_C/T"            
 [363] "7:150835811_C/T"             "7:150835812_G/A"            
 [365] "7:150835830_G/T"             "7:150835832_C/T"            
 [367] "7:150835838_C/T"             "7:150835840_G/A"            
 [369] "7:150835844_G/A"             "7:150835848_T/C"            
 [371] "7:150835870_G/A"             "7:150835924_G/C"            
 [373] "7:150835941_T/C"             "7:150835947_T/C"            
 [375] "7:150835962_A/C"             "7:150835966_A/G"            
 [377] "7:150835985_G/A"             "7:150836013_G/T"            
 [379] "7:150836046_C/T"             "7:150836084_T/C"            
 [381] "7:150836093_C/A"             "7:150836149_G/T"            
 [383] "7:150836240_A/G"             "7:150836357_C/T"            
 [385] "7:150836379_G/A"             "7:150836404_C/T"            
 [387] "7:150836497_G/A"             "7:150836562_G/A"            
 [389] "7:150836607_G/A"             "7:150836609_C/A"            
 [391] "7:150836627_C/T"             "7:150836650_A/G"            
 [393] "7:150836727_A/C"             "7:150836791_C/T"            
 [395] "7:150836920_G/A"             "7:150836927_G/C"            
 [397] "7:150836937_C/G"             "7:150836942_G/A"            
 [399] "7:150836944_C/T"             "7:150837007_C/T"            
 [401] "7:150837008_G/A"             "7:150837050_A/C"            
 [403] "7:150837226_C/T"             "7:150837289_A/T"            
 [405] "7:150837349_G/A"             "7:150837353_C/G"            
 [407] "7:150837456_A/G"             "7:150837493_G/A"            
 [409] "7:150837515_C/T"             "7:150837529_C/T"            
 [411] "7:150837899_G/A"             "7:150837925_T/C"            
 [413] "7:150838001_G/A"             "7:150838038_C/T"            
 [415] "7:150838042_G/A"             "7:150838078_A/T"            
 [417] "7:150838091_T/G"             "7:150838166_C/T"            
 [419] "7:150838198_C/T"             "7:150838202_C/T"            
 [421] "7:150838223_C/T"             "7:150838282_C/T"            
 [423] "7:150838327_A/C"             "7:150838342_T/G"            
 [425] "7:150838354_C/A"             "7:150838515_A/ACGC"         
 [427] "7:150838516_C/T"             "7:150838517_G/T"            
 [429] "7:150838571_A/AT"            "7:150838610_T/C"            
 [431] "7:150838633_C/G"             "7:150838694_A/T"            
 [433] "7:150838709_A/T"             "7:150838719_G/T"            
 [435] "7:150838728_T/G"             "7:150838784_T/G"            
 [437] "7:150838808_G/T"             "7:150838850_G/A"            
 [439] "7:150838913_G/A"             "7:150838924_A/G"            
 [441] "7:150838944_G/A"             "7:150838953_G/C"            
 [443] "7:150838976_C/T"             "7:150838998_G/A"            
 [445] "7:150839043_C/T"             "7:150839058_G/A"            
 [447] "7:150839244_C/T"             "7:150839254_G/A"            
 [449] "7:150839256_C/T"             "7:150839271_G/A"            
 [451] "7:150839288_G/GGCCGTCCGC"    "7:150839292_G/A"            
 [453] "7:150839296_G/A"             "7:150839300_C/T"            
 [455] "7:150839304_C/T"             "7:150839324_C/G"            
 [457] "7:150839330_C/T"             "7:150839356_G/T"            
 [459] "7:150839373_G/A"             "7:150839378_G/A"            
 [461] "7:150839487_C/G"             "7:150839524_G/C"            
 [463] "7:150839616_C/T"             "7:150839687_G/A"            
 [465] "7:150839759_G/A"             "7:150839764_C/T"            
 [467] "7:150839924_C/T"             "7:150839947_G/C"            
 [469] "7:150839948_C/A"             "7:150839955_C/T"            
 [471] "7:150839962_G/A"             "7:150840001_C/T"            
 [473] "7:150840002_G/A"             "7:150840009_T/C"            
 [475] "7:150840165_C/T"             "7:150840175_C/G"            
 [477] "7:150840180_C/T"             "7:150840226_C/G"            
 [479] "7:150840228_C/T"             "7:150840229_C/G"            
 [481] "7:150840250_C/G"             "7:150840252_C/G"            
 [483] "7:150840263_G/C"             "7:150840282_C/A"            
 [485] "7:150840283_C/T"             "7:150840287_C/T"            
 [487] "7:150840334_C/G"             "7:150840342_C/T"            
 [489] "7:150840377_G/A"             "7:150840383_C/T"            
 [491] "7:150840384_G/A"             "7:150840401_C/T"            
 [493] "7:150840407_C/G"             "7:150840408_T/G"            
 [495] "7:150840410_A/C"             "7:150840440_A/T"            
 [497] "7:150840549_C/T"             "7:150840566_C/T"            
 [499] "7:150840714_C/T"             "7:150840717_G/A"            
 [501] "7:150840724_T/C"             "7:150840758_C/T"            
 [503] "7:150840764_T/C"             "7:150840835_C/T"            
 [505] "7:150840850_C/T"             "7:150840869_C/A"            
 [507] "7:150840881_C/T"             "7:150840963_C/T"            
 [509] "7:150840967_C/T"             "7:150841011_G/A"            
 [511] "7:150841027_A/G"             "7:150841052_G/C"            
 [513] "7:150841087_C/T"             "7:150841146_G/A"            
 [515] "7:150841149_G/A"             "7:150841151_C/G"            
 [517] "7:150841182_C/T"             "7:150841246_G/T"            
 [519] "7:150841318_A/G"             "7:150841350_C/T"            
 [521] "7:150841377_C/T"             "7:150841378_G/A"            
 [523] "7:150841439_C/T"             "7:150841479_T/C"            
 [525] "7:150841518_C/T"             "7:150841530_T/A"            
 [527] "7:150841603_G/T"             "7:150841638_G/A"            
 [529] "7:150841642_G/A"             "7:150841665_T/G"            
 [531] "7:150841741_C/T"             "7:150841743_C/T"            
 [533] "7:150841794_C/G"             "7:150841807_CTTTTTTTTTTTT/C"
 [535] "7:150841831_A/G"             "7:150841836_G/C"            
 [537] "7:150841866_T/C"             "7:150841875_G/A"            
 [539] "7:150841883_G/A"             "7:150841970_C/T"            
 [541] "7:150842011_T/C"             "7:150842065_C/T"            
 [543] "7:150842066_G/A"             "7:150842113_C/T"            
 [545] "7:150842114_G/A"             "7:150842139_C/T"            
 [547] "7:150842143_A/T"             "7:150842158_T/G"            
 [549] "7:150842159_C/T"             "7:150842236_C/G"            
 [551] "7:150842261_G/A"             "7:150842298_GAGA/G"         
 [553] "7:150842316_C/T"             "7:150842342_C/CAGAT"        
 [555] "7:150842363_A/G"             "7:150842446_C/A"            
 [557] "7:150842465_TG/T"            "7:150842471_G/T"            
 [559] "7:150842485_T/G"             "7:150842597_G/GCTCT"        
 [561] "7:150842598_C/A"             "7:150842599_T/C"            
 [563] "7:150842625_T/C"             "7:150842661_CTT/C"          
 [565] "7:150842671_A/T"             "7:150842675_TA/T"           
 [567] "7:150842686_A/C"             "7:150842702_A/G"            
 [569] "7:150842708_G/A"             "7:150842745_C/T"            
 [571] "7:150842762_G/A"             "7:150842807_C/T"            
 [573] "7:150842827_A/G"             "7:150842841_G/A"            
 [575] "7:150842853_G/A"             "7:150842888_G/A"            
 [577] "7:150842974_C/T"             "7:150842979_C/CG"           
 [579] "7:150842981_G/C"             "7:150842987_G/GA"           
 [581] "7:150842988_A/G"             "7:150842989_A/AG"           
 [583] "7:150843037_CATA/C"          "7:150843090_C/T"            
 [585] "7:150843123_A/C"             "7:150843179_T/C"            
 [587] "7:150843219_G/A"             "7:150843227_A/G"            
 [589] "7:150843235_A/G"             "7:150843244_C/T"            
 [591] "7:150843246_C/T"             "7:150843250_A/G"            
 [593] "7:150843306_G/A"             "7:150843310_G/C"            
 [595] "7:150843344_T/C"             "7:150843384_C/G"            
 [597] "7:150843463_A/G"             "7:150843464_T/C"            
 [599] "7:150843489_C/A"             "7:150843522_G/A"            
 [601] "7:150843523_C/T"             "7:150843576_C/T"            
 [603] "7:150843587_C/T"             "7:150843602_A/G"            
 [605] "7:150843609_T/C"             "7:150843611_C/T"            
 [607] "7:150843614_G/A"             "7:150843635_C/A"            
 [609] "7:150843651_C/T"             "7:150843653_C/A"            
 [611] "7:150843666_G/A"             "7:150843681_C/T"            
 [613] "7:150843684_C/G"             "7:150843707_G/T"            
 [615] "7:150843758_G/A"             "7:150843796_G/A"            
 [617] "7:150843843_C/T"             "7:150843853_C/T"            
 [619] "7:150843857_G/A"             "7:150843876_A/G"            
 [621] "7:150843903_G/A"             "7:150843979_A/G"            
 [623] "7:150843988_C/T"             "7:150844041_C/T"            
 [625] "7:150844043_C/T"             "7:150844044_G/A"            
 [627] "7:150844046_C/T"             "7:150844091_A/C"            
 [629] "7:150844119_G/A"             "7:150844126_G/A"            
 [631] "7:150844235_T/C"             "7:150844303_A/G"            
 [633] "7:150844319_C/T"             "7:150844337_C/T"            
 [635] "7:150844360_C/T"             "7:150844439_C/G"            
 [637] "7:150844455_G/A"             "7:150844466_C/T"            
 [639] "7:150844484_A/C"             "7:150844491_C/G"            
 [641] "7:150844631_G/C"             "7:150844634_GAGA/G"         
 [643] "7:150844660_G/T"             "7:150844687_C/T"            
 [645] "7:150844747_G/A"             "7:150844788_G/T"            
 [647] "7:150844859_C/T"             "7:150844982_G/A"            
 [649] "7:150844992_A/C"             "7:150845001_C/T"            
 [651] "7:150845002_G/A"             "7:150845032_G/A"            
 [653] "7:150845155_T/C"             "7:150845164_C/T"            
 [655] "7:150845213_G/A"             "7:150845226_G/A"            
 [657] "7:150845618_A/G"             "7:150845650_G/A"            
 [659] "7:150845717_G/A"             "7:150845792_T/C"            
 [661] "7:150845853_G/T"             "7:150845912_G/A"            
 [663] "7:150845977_C/T"             "7:150845996_C/T"            
 [665] "7:150846051_G/C"             "7:150846070_T/G"            
 [667] "7:150846083_G/A"             "7:150846105_A/C"            
 [669] "7:150846129_G/A"             "7:150846138_G/A"            
 [671] "7:150846188_C/T"             "7:150846322_G/A"            
 [673] "7:150846415_T/C"             "7:150846417_G/C"            
 [675] "7:150846427_T/C"             "7:150846429_G/C"            
 [677] "7:150846480_C/T"             "7:150846531_C/G"            
 [679] "7:150846581_C/T"             "7:150846583_T/G"            
 [681] "7:150846630_C/T"             "7:150846676_G/A"            
 [683] "7:150846699_C/T"             "7:150846702_G/T"            
 [685] "7:150846765_C/CA"            "7:150846886_C/T"            
 [687] "7:150846923_G/T"             "7:150846973_C/A"            
 [689] "7:150847002_C/G"             "7:150847022_G/A"            
 [691] "7:150847023_C/T"             "7:150847162_A/G"            
 [693] "7:150847392_T/C"             "7:150847400_G/A"            
 [695] "7:150847414_A/G"             "7:150847424_AG/A"           
 [697] "7:150847426_A/G"             "7:150847431_G/A"            
 [699] "7:150847446_C/A"             "7:150847543_C/T"            
 [701] "7:150847592_A/G"             "7:150847616_G/A"            
 [703] "7:150847691_C/T"             "7:150847711_C/T"            
 [705] "7:150847723_C/T"             "7:150847726_C/A"            
 [707] "7:150847749_A/G"             "7:150847782_A/G"            
 [709] "7:150847795_C/T"             "7:150847866_G/A"            
 [711] "7:150847872_G/C"             "7:150847980_T/C"            
 [713] "7:150848041_G/A"             "7:150848111_G/A"            
 [715] "7:150848117_C/G"             "7:150848128_C/T"            
 [717] "7:150848129_T/C"             "7:150848134_G/A"            
 [719] "7:150848150_C/G"             "7:150848195_G/A"            
 [721] "7:150848237_C/A"             "7:150848252_T/A"            
 [723] "7:150848267_C/T"             "7:150848288_C/A"            
 [725] "7:150848321_C/T"             "7:150848384_G/C"            
 [727] "7:150848433_G/A"             "7:150848435_C/T"            
 [729] "7:150848439_C/T"             "7:150848480_C/T"            
 [731] "7:150848481_C/A"             "7:150848486_G/A"            
 [733] "7:150848487_C/A"             "7:150848537_A/G"            
 [735] "7:150848604_T/C"             "7:150848715_G/A"            
 [737] "7:150848732_C/T"             "7:150848880_C/T"            
 [739] "7:150848927_A/G"             "7:150848964_C/T"            
 [741] "7:150848975_C/T"             "7:150849001_G/C"            
 [743] "7:150849077_G/A"             "7:150849097_C/T"            
 [745] "7:150849153_A/G"             "7:150849158_C/T"            
 [747] "7:150849164_A/G"             "7:150849172_T/C"            
 [749] "7:150849279_C/T"             "7:150849293_T/G"            
 [751] "7:150849353_G/A"             "7:150849364_C/T"            
 [753] "7:150849425_C/T"             "7:150849430_T/C"            
 [755] "7:150849580_T/C"             "7:150849607_A/T"            
 [757] "7:150849681_T/G"             "7:150849723_A/C"            
 [759] "7:150849732_G/A"             "7:150849784_G/A"            
 [761] "7:150849808_C/G"             "7:150849874_C/T"            
 [763] "7:150849913_C/T"             "7:150849952_C/T"            
 [765] "7:150849953_G/A"             "7:150849994_C/T"            
 [767] "7:150850044_A/C"             "7:150850056_C/T"            
 [769] "7:150850148_G/T"             "7:150850165_T/C"            
 [771] "7:150850194_T/C"             "7:150850209_A/T"            
 [773] "7:150850210_T/C"             "7:150850252_G/A"            
 [775] "7:150850279_G/A"             "7:150850329_C/A"            
 [777] "7:150850397_C/T"             "7:150850425_T/C"            
 [779] "7:150850440_G/A"             "7:150850472_A/G"            
 [781] "7:150850487_G/A"             "7:150850636_CT/C"           
 [783] "7:150850692_T/A"             "7:150850731_C/T"            
 [785] "7:150850814_A/T"             "7:150850835_T/A"            
 [787] "7:150850872_A/G"             "7:150850881_C/T"            
 [789] "7:150850938_C/T"             "7:150851180_C/T"            
 [791] "7:150851235_T/C"             "7:150851246_A/G"            
 [793] "7:150851253_G/A"             "7:150851259_C/T"            
 [795] "7:150851274_G/A"             "7:150851277_G/A"            
 [797] "7:150851279_CAG/C"           "7:150851293_C/T"            
 [799] "7:150851353_C/T"             "7:150851360_T/C"            
 [801] "7:150851372_A/T"             "7:150851396_A/C"            
 [803] "7:150851417_A/G"             "7:150851482_T/TA"           
 [805] "7:150851549_T/C"             "7:150851566_T/C"            
 [807] "7:150851595_C/T"             "7:150851598_C/A"            
 [809] "7:150851606_C/G"             "7:150851608_A/G"            
 [811] "7:150851665_A/G"             "7:150851718_C/T"            
 [813] "7:150851767_T/C"             "7:150851783_G/A"            
 [815] "7:150851823_G/C"             "7:150851825_G/A"            
 [817] "7:150851839_G/T"             "7:150851874_G/A"            
 [819] "7:150851901_T/C"             "7:150851911_C/T"            
 [821] "7:150851919_G/A"             "7:150851946_T/C"            
 [823] "7:150851977_T/G"             "7:150851993_C/T"            
 [825] "7:150852013_C/T"             "7:150852023_A/G"            
 [827] "7:150852026_G/A"             "7:150852028_G/A"            
 [829] "7:150852099_C/T"             "7:150852104_C/T"            
 [831] "7:150852129_C/T"             "7:150852144_T/C"            
 [833] "7:150852148_C/T"             "7:150852151_A/G"            
 [835] "7:150852211_T/C"             "7:150852217_C/T"            
 [837] "7:150852261_A/G"             "7:150852300_A/G"            
 [839] "7:150852322_C/T"             "7:150852335_C/T"            
 [841] "7:150852344_G/C"             "7:150852375_G/C"            
 [843] "7:150852393_T/A"             "7:150852472_T/C"            
 [845] "7:150852493_A/G"             "7:150852575_A/G"            
 [847] "7:150852881_T/C"             "7:150852888_A/G"            
 [849] "7:150852920_G/A"             "7:150852990_G/A"            
 [851] "7:150853064_G/A"             "7:150853159_T/C"            
 [853] "7:150853220_T/C"             "7:150853281_G/A"            
 [855] "7:150853379_T/C"             "7:150853404_C/T"            
 [857] "7:150853449_G/A"             "7:150853556_C/G"            
 [859] "7:150853581_T/G"             "7:150853599_A/G"            
 [861] "7:150853664_A/T"             "7:150853715_C/T"            
 [863] "7:150853745_G/A"             "7:150853794_G/A"            
 [865] "7:150853801_G/C"             "7:150853931_G/C"            
 [867] "7:150853937_C/T"             "7:150853943_G/A"            
 [869] "7:150853956_C/A"             "7:150853986_C/T"            
 [871] "7:150854001_G/A"             "7:150854009_T/C"            
 [873] "7:150854020_A/G"             "7:150854035_G/A"            
 [875] "7:150854038_C/T"             "7:150854123_G/A"            
 [877] "7:150854128_T/C"             "7:150854144_G/C"            
 [879] "7:150854168_A/G"             "7:150854174_G/C"            
 [881] "7:150854190_C/G"             "7:150854208_C/A"            
 [883] "7:150854275_C/A"             "7:150854304_A/G"            
 [885] "7:150854306_C/A"             "7:150854315_G/A"            
 [887] "7:150854322_G/A"             "7:150854337_C/T"            
 [889] "7:150854339_C/T"             "7:150854348_A/G"            
 [891] "7:150854410_C/T"             "7:150854442_T/C"            
 [893] "7:150854456_C/T"             "7:150854478_AG/A"           
 [895] "7:150854501_C/T"             "7:150854506_T/C"            
 [897] "7:150854510_C/A"             "7:150854539_C/G"            
 [899] "7:150854629_G/T"             "7:150854637_T/C"            
 [901] "7:150854647_C/A"             "7:150854696_G/A"            
 [903] "7:150854713_G/A"             "7:150854733_G/C"            
 [905] "7:150854751_C/T"             "7:150854773_G/A"            
 [907] "7:150854778_CT/C"            "7:150854796_C/T"            
 [909] "7:150854902_C/T"             "7:150854926_G/A"            
 [911] "7:150854970_G/A"             "7:150855025_C/T"            
 [913] "7:150855033_T/C"             "7:150855133_A/G"            
 [915] "7:150855163_T/C"             "7:150855169_TACAAG/T"       
 [917] "7:150855190_G/A"             "7:150855232_A/G"            
 [919] "7:150855244_G/A"             "7:150855311_C/T"            
 [921] "7:150855523_A/G"             "7:150855532_TTTTTTG/T"      
 [923] "7:150855545_T/C"             "7:150855550_G/T"            
 [925] "7:150855556_T/G"             "7:150855583_G/A"            
 [927] "7:150855661_C/T"             "7:150855662_G/A"            
 [929] "7:150855706_T/C"             "7:150855745_G/A"            
 [931] "7:150855793_A/G"             "7:150855801_T/C"            
 [933] "7:150855811_T/C"             "7:150855950_G/A"            
 [935] "7:150855952_A/G"             "7:150856045_T/A"            
 [937] "7:150856068_C/T"             "7:150856115_C/T"            
 [939] "7:150856131_C/T"             "7:150856147_C/G"            
 [941] "7:150856162_AAGT/A"          "7:150856165_T/C"            
 [943] "7:150856172_A/T"             "7:150856208_G/A"            
 [945] "7:150856226_T/C"             "7:150856232_C/G"            
 [947] "7:150856268_C/T"             "7:150856357_G/A"            
 [949] "7:150856390_C/T"             "7:150856392_C/G"            
 [951] "7:150856393_G/A"             "7:150856458_GA/G"           
 [953] "7:150856470_G/A"             "7:150856476_G/A"            
 [955] "7:150856567_A/C"             "7:150856592_C/T"            
 [957] "7:150856620_C/T"             "7:150856654_A/G"            
 [959] "7:150856764_G/A"             "7:150856780_G/A"            
 [961] "7:150856942_C/A"             "7:150856966_A/G"            
 [963] "7:150857001_G/A"             "7:150857128_G/C"            
 [965] "7:150857144_C/G"             "7:150857176_G/T"            
 [967] "7:150857295_T/G"             "7:150857346_C/T"            
 [969] "7:150857371_C/T"             "7:150857465_C/T"            
 [971] "7:150857486_A/G"             "7:150857556_G/A"            
 [973] "7:150857562_T/G"             "7:150857632_C/A"            
 [975] "7:150857730_T/G"             "7:150857746_T/G"            
 [977] "7:150857771_A/G"             "7:150857798_C/T"            
 [979] "7:150857812_C/G"             "7:150857824_C/A"            
 [981] "7:150857876_A/C"             "7:150857906_C/T"            
 [983] "7:150857907_G/A"             "7:150857956_A/C"            
 [985] "7:150857960_C/T"             "7:150857963_T/G"            
 [987] "7:150857975_T/C"             "7:150857978_G/C"            
 [989] "7:150857983_T/C"             "7:150857998_C/T"            
 [991] "7:150858180_T/C"             "7:150858192_C/G"            
 [993] "7:150858194_G/A"             "7:150858209_A/G"            
 [995] "7:150858271_A/G"             "7:150858337_T/C"            
 [997] "7:150858347_T/C"             "7:150858349_C/A"            
 [999] "7:150858354_A/G"             "7:150858459_T/C"            
[1001] "7:150858514_G/T"             "7:150858541_AGGG/A"         
[1003] "7:150858602_A/G"             "7:150858616_T/C"            
[1005] "7:150858657_G/A"             "7:150858660_G/A"            
[1007] "7:150858688_C/G"             "7:150858731_G/A"            
[1009] "7:150858801_G/A"             "7:150859031_G/C"            
[1011] "7:150859179_C/G"             "7:150859180_T/G"            
[1013] "7:150859211_G/A"             "7:150859264_G/A"            
[1015] "7:150859315_C/A"             "7:150859358_C/A"            
[1017] "7:150859361_G/A"             "7:150859381_T/C"            
[1019] "7:150859384_C/T"             "7:150859468_G/C"            
[1021] "7:150859492_G/A"             "7:150859521_A/T"            
[1023] "7:150859533_C/T"             "7:150859597_A/G"            
[1025] "7:150859598_A/G"             "7:150859748_A/G"            
[1027] "7:150859838_T/C"             "7:150859891_CT/C"           
[1029] "7:150860036_G/A"             "7:150860055_G/A"            
[1031] "7:150860067_A/T"             "7:150860098_G/T"            
[1033] "7:150860144_C/T"             "7:150860153_A/G"            
[1035] "7:150860182_C/T"             "7:150860183_G/A"            
[1037] "7:150860201_T/G"             "7:150860246_G/A"            
[1039] "7:150860330_G/A"             "7:150860353_C/T"            
[1041] "7:150860383_C/T"             "7:150860448_C/T"            
[1043] "7:150860528_G/A"             "7:150860541_C/T"            
[1045] "7:150860621_A/G"             "7:150860657_T/C"            
[1047] "7:150860677_A/C"             "7:150860739_T/A"            
[1049] "7:150860772_C/T"             "7:150860846_T/C"            
[1051] "7:150860889_C/T"             "7:150860890_T/C"            
[1053] "7:150860993_C/T"             "7:150861060_C/A"            
[1055] "7:150861061_A/G"             "7:150861070_T/G"            
[1057] "7:150861081_C/T"             "7:150861098_G/C"            
[1059] "7:150861125_C/A"             "7:150861130_T/TA"           
[1061] "7:150861227_G/A"             "7:150861287_A/G"            
[1063] "7:150861381_G/A"            
length(VCFAOC1)
[1] 1063