22_GM12878_chr1_200bp resolution
My Nguyen
2024-05-10
GM12878 on bp - After removing telemore and centremore, Study about string of 0
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 17.0 50.0 168.8 116.0 134569.0
Arm 1 - 200bp resolution
Load data
Study string of 0
## [1] 18145summary(zero_regions$bp200_bin_size)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 1.000 3.799 3.000 671.000## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.840e-06 6.893e-03 2.059e-02 3.012e-02 4.340e-02 2.560e-01## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000009 0.1796927 0.4042432 0.4131520 0.6565578 0.9033211## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.840e-06 6.893e-03 2.059e-02 3.012e-02 4.340e-02 2.560e-01## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000009 0.1796927 0.4042432 0.4131520 0.6565578 0.9033211
w = 2000, h= 2000, e = 0.1
smooth_line1 <- read.csv("GM12878/chr1/smooth0to2000_chr1.1_200bp.csv")
smooth_line1 <- smooth_line1[,-1]
probability_table1 <- data.frame(Position = c(1:nrow(data1_200bp_mean)), Probability = data1_200bp_mean$baseProbs)
plot(smooth_line1$y, type = 'l')
Subset plots
Strong boundary
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 2.000 3.000 2.977 4.000 8.000
Set different number of cutt-off for strong boundary
Full length
cut.off.list = c(5:8)
## Full length arm1
strong_boundaries_plot(smooth_line = smooth_line1,boundary_table =all.tads.arm1,
probability_table = probability_table1,
cut.off.list = c(5:8))
Subset length
## Subset arm1
strong_boundaries_plot(smooth_line = smooth_line1[1:100000, ], boundary_table =all.tads.arm1,
probability_table = probability_table1[1:100000,],
cut.off.list = c(5:8))
Windown size
Actual size (not 200bp bin) of all found TAD
### Actual size (not 200bp bin) of all found TAD
summary(report1a$actual_size)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 46200 74900 89400 131462 187800 383800Actual size of all TAD generated by strong boundaries
size.strong.t5 = size_strong_region(strong_boundaries = strong.boundaries[[1]])
size.strong.t6 = size_strong_region(strong_boundaries = strong.boundaries[[2]])
size.strong.t7 = size_strong_region(strong_boundaries = strong.boundaries[[3]])
datatable(size.strong.t5); datatable(size.strong.t6); datatable(size.strong.t7) summary(size.strong.t5$region_size); summary(size.strong.t6$region_size); summary(size.strong.t7$region_size) ## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 61600 883900 2139100 3142200 3278100 16985400## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 652800 2789400 5743800 5784350 7297800 13562800## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5412000 9487400 13562800 13529133 17587700 21612600w = 5000, h= 2000, e = 0.1
Subset plots
Strong boundary
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 1.000 3.000 3.163 4.000 12.000
Set different number of cutt-off for strong boundary
Full length
Subset length
## Subset arm1
strong_boundaries_plot(smooth_line = smooth_line1[1:100000, ], boundary_table =all.tads.arm2,
probability_table = probability_table1[1:100000,],
cut.off.list = c(5:8))
Windown size
Actual size (not 200bp bin) of all found TAD
### Actual size (not 200bp bin) of all found TAD
summary(report2$actual_size)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 46200 80000 184800 273935 437300 989600Actual size of all TAD generated by strong boundaries
size.strong.t6 = size_strong_region(strong_boundaries = strong.boundaries[[1]])
size.strong.t7 = size_strong_region(strong_boundaries = strong.boundaries[[2]])
size.strong.t8 = size_strong_region(strong_boundaries = strong.boundaries[[3]])
size.strong.t9 = size_strong_region(strong_boundaries = strong.boundaries[[4]])
size.strong.t10 = size_strong_region(strong_boundaries = strong.boundaries[[5]])
datatable(size.strong.t6); datatable(size.strong.t7); datatable(size.strong.t8); datatable(size.strong.t9); datatable(size.strong.t10); summary(size.strong.t6$region_size); summary(size.strong.t7$region_size); summary(size.strong.t8$region_size); summary(size.strong.t9$region_size); summary(size.strong.t10$region_size); ## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 80000 583100 1320600 1813458 2801350 6759600## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 331800 1208500 2465000 3061631 3693800 11426600## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 943000 1879200 2823800 5191461 6356400 22626200## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1998400 4777600 7072700 9950300 14791550 22626200## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 7430000 9792800 17716100 16129567 21075800 24567800w = 10000, h= 2000, e = 0.1
Subset size
Strong boundary
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 1.000 2.000 2.243 2.000 15.000
Set different number of cutt-off for strong boundary
Full length
Subset length
## Subset arm1
strong_boundaries_plot(smooth_line = smooth_line1[1:100000, ], boundary_table =all.tads.arm3,
probability_table = probability_table1[1:100000,],
cut.off.list = cut.off.list )
Windown size
Actual size (not 200bp bin) of all found TAD
### Actual size (not 200bp bin) of all found TAD
summary(report3$actual_size)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 46200 202800 586600 669810 1038600 1952000Actual size of all TAD generated by strong boundaries
reports <- lapply(strong.boundaries, size_strong_region)
reports## [[1]]
## left_boundary_region right_boundary_region region_size
## 1 267000 267000 0
## 2 267000 1050200 783200
## 3 1050200 2576800 1526600
## 4 2576800 3643400 1066600
## 5 3643400 4655200 1011800
## 6 4655200 7658000 3002800
## 7 7658000 8562600 904600
## 8 8562600 10510400 1947800
## 9 10510400 11646800 1136400
## 10 11646800 12210800 564000
## 11 12210800 14104200 1893400
## 12 14104200 15814600 1710400
## 13 15814600 17490200 1675600
## 14 17490200 18895000 1404800
## 15 18895000 19250200 355200
## 16 19250200 20503000 1252800
## 17 20503000 22650000 2147000
## 18 22650000 23200000 550000
## 19 23200000 24834800 1634800
## 20 24834800 26606200 1771400
## 21 26606200 27404200 798000
## 22 27404200 29195400 1791200
## 23 29195400 30784200 1588800
## 24 30784200 31948000 1163800
## 25 31948000 33629400 1681400
## 26 33629400 34861400 1232000
## 27 34861400 37686400 2825000
## 28 37686400 38823400 1137000
## 29 38823400 39806400 983000
## 30 39806400 41507200 1700800
## 31 41507200 42922200 1415000
## 32 42922200 44801400 1879200
## 33 44801400 45501600 700200
## 34 45501600 47181800 1680200
## 35 47181800 48560600 1378800
## 36 48560600 49293200 732600
## 37 49293200 50350800 1057600
## 38 50350800 52828800 2478000
## 39 52828800 54804600 1975800
## 40 54804600 55010200 205600
## 41 55010200 57278200 2268000
## 42 57278200 58043600 765400
## 43 58043600 59960800 1917200
## 44 59960800 60148800 188000
## 45 60148800 62751600 2602800
## 46 62751600 63688000 936400
## 47 63688000 64255400 567400
## 48 64255400 66362000 2106600
## 49 66362000 67766600 1404600
## 50 67766600 68339200 572600
## 51 68339200 70500600 2161400
## 52 70500600 71064000 563400
## 53 71064000 72624600 1560600
## 54 72624600 73997800 1373200
## 55 73997800 74762600 764800
## 56 74762600 75908200 1145600
## 57 75908200 78127000 2218800
## 58 78127000 79497400 1370400
## 59 79497400 81548800 2051400
## 60 81548800 82223000 674200
## 61 82223000 82635600 412600
## 62 82635600 84949400 2313800
## 63 84949400 86499800 1550400
## 64 86499800 87143600 643800
## 65 87143600 89614400 2470800
## 66 89614400 91523400 1909000
## 67 91523400 92614800 1091400
## 68 92614800 94052600 1437800
## 69 94052600 95046000 993400
## 70 95046000 95311600 265600
## 71 95311600 96842400 1530800
## 72 96842400 97044400 202000
## 73 97044400 98050600 1006200
## 74 98050600 100463600 2413000
## 75 100463600 101439400 975800
## 76 101439400 102185400 746000
## 77 102185400 104643600 2458200
## 78 104643600 105028000 384400
## 79 105028000 105793600 765600
## 80 105793600 107135600 1342000
## 81 107135600 109102000 1966400
## 82 109102000 111211000 2109000
## 83 111211000 113969200 2758200
## 84 113969200 114968800 999600
## 85 114968800 116150800 1182000
## 86 116150800 117064800 914000
## 87 117064800 119670600 2605800
##
## [[2]]
## left_boundary_region right_boundary_region region_size
## 1 267000 1050200 783200
## 2 1050200 2576800 1526600
## 3 2576800 3643400 1066600
## 4 3643400 4655200 1011800
## 5 4655200 7658000 3002800
## 6 7658000 10510400 2852400
## 7 10510400 11646800 1136400
## 8 11646800 12210800 564000
## 9 12210800 14104200 1893400
## 10 14104200 15814600 1710400
## 11 15814600 17490200 1675600
## 12 17490200 18895000 1404800
## 13 18895000 19250200 355200
## 14 19250200 20503000 1252800
## 15 20503000 22650000 2147000
## 16 22650000 24834800 2184800
## 17 24834800 26606200 1771400
## 18 26606200 27404200 798000
## 19 27404200 29195400 1791200
## 20 29195400 30784200 1588800
## 21 30784200 31948000 1163800
## 22 31948000 33629400 1681400
## 23 33629400 34861400 1232000
## 24 34861400 37686400 2825000
## 25 37686400 38823400 1137000
## 26 38823400 41507200 2683800
## 27 41507200 42922200 1415000
## 28 42922200 44801400 1879200
## 29 44801400 45501600 700200
## 30 45501600 47181800 1680200
## 31 47181800 48560600 1378800
## 32 48560600 50350800 1790200
## 33 50350800 52828800 2478000
## 34 52828800 54804600 1975800
## 35 54804600 58043600 3239000
## 36 58043600 59960800 1917200
## 37 59960800 60148800 188000
## 38 60148800 62751600 2602800
## 39 62751600 63688000 936400
## 40 63688000 66362000 2674000
## 41 66362000 67766600 1404600
## 42 67766600 68339200 572600
## 43 68339200 70500600 2161400
## 44 70500600 71064000 563400
## 45 71064000 72624600 1560600
## 46 72624600 73997800 1373200
## 47 73997800 75908200 1910400
## 48 75908200 78127000 2218800
## 49 78127000 79497400 1370400
## 50 79497400 81548800 2051400
## 51 81548800 84949400 3400600
## 52 84949400 86499800 1550400
## 53 86499800 87143600 643800
## 54 87143600 89614400 2470800
## 55 89614400 91523400 1909000
## 56 91523400 94052600 2529200
## 57 94052600 95311600 1259000
## 58 95311600 96842400 1530800
## 59 96842400 97044400 202000
## 60 97044400 98050600 1006200
## 61 98050600 100463600 2413000
## 62 100463600 101439400 975800
## 63 101439400 102185400 746000
## 64 102185400 104643600 2458200
## 65 104643600 107135600 2492000
## 66 107135600 109102000 1966400
## 67 109102000 111211000 2109000
## 68 111211000 113969200 2758200
## 69 113969200 114968800 999600
## 70 114968800 116150800 1182000
## 71 116150800 117064800 914000
## 72 117064800 119670600 2605800
##
## [[3]]
## left_boundary_region right_boundary_region region_size
## 1 267000 1050200 783200
## 2 1050200 2576800 1526600
## 3 2576800 4655200 2078400
## 4 4655200 7658000 3002800
## 5 7658000 10510400 2852400
## 6 10510400 12210800 1700400
## 7 12210800 14104200 1893400
## 8 14104200 15814600 1710400
## 9 15814600 17490200 1675600
## 10 17490200 18895000 1404800
## 11 18895000 19250200 355200
## 12 19250200 22650000 3399800
## 13 22650000 24834800 2184800
## 14 24834800 26606200 1771400
## 15 26606200 27404200 798000
## 16 27404200 30784200 3380000
## 17 30784200 33629400 2845200
## 18 33629400 34861400 1232000
## 19 34861400 37686400 2825000
## 20 37686400 41507200 3820800
## 21 41507200 42922200 1415000
## 22 42922200 44801400 1879200
## 23 44801400 45501600 700200
## 24 45501600 47181800 1680200
## 25 47181800 48560600 1378800
## 26 48560600 50350800 1790200
## 27 50350800 52828800 2478000
## 28 52828800 54804600 1975800
## 29 54804600 59960800 5156200
## 30 59960800 60148800 188000
## 31 60148800 62751600 2602800
## 32 62751600 63688000 936400
## 33 63688000 66362000 2674000
## 34 66362000 67766600 1404600
## 35 67766600 68339200 572600
## 36 68339200 70500600 2161400
## 37 70500600 71064000 563400
## 38 71064000 72624600 1560600
## 39 72624600 75908200 3283600
## 40 75908200 78127000 2218800
## 41 78127000 79497400 1370400
## 42 79497400 81548800 2051400
## 43 81548800 84949400 3400600
## 44 84949400 86499800 1550400
## 45 86499800 87143600 643800
## 46 87143600 89614400 2470800
## 47 89614400 91523400 1909000
## 48 91523400 94052600 2529200
## 49 94052600 95311600 1259000
## 50 95311600 96842400 1530800
## 51 96842400 97044400 202000
## 52 97044400 100463600 3419200
## 53 100463600 101439400 975800
## 54 101439400 102185400 746000
## 55 102185400 104643600 2458200
## 56 104643600 107135600 2492000
## 57 107135600 109102000 1966400
## 58 109102000 111211000 2109000
## 59 111211000 113969200 2758200
## 60 113969200 114968800 999600
## 61 114968800 116150800 1182000
## 62 116150800 117064800 914000
## 63 117064800 119670600 2605800
##
## [[4]]
## left_boundary_region right_boundary_region region_size
## 1 267000 1050200 783200
## 2 1050200 2576800 1526600
## 3 2576800 4655200 2078400
## 4 4655200 7658000 3002800
## 5 7658000 10510400 2852400
## 6 10510400 12210800 1700400
## 7 12210800 14104200 1893400
## 8 14104200 15814600 1710400
## 9 15814600 18895000 3080400
## 10 18895000 19250200 355200
## 11 19250200 24834800 5584600
## 12 24834800 26606200 1771400
## 13 26606200 27404200 798000
## 14 27404200 30784200 3380000
## 15 30784200 33629400 2845200
## 16 33629400 34861400 1232000
## 17 34861400 37686400 2825000
## 18 37686400 41507200 3820800
## 19 41507200 42922200 1415000
## 20 42922200 45501600 2579400
## 21 45501600 47181800 1680200
## 22 47181800 48560600 1378800
## 23 48560600 50350800 1790200
## 24 50350800 59960800 9610000
## 25 59960800 62751600 2790800
## 26 62751600 66362000 3610400
## 27 66362000 67766600 1404600
## 28 67766600 68339200 572600
## 29 68339200 70500600 2161400
## 30 70500600 71064000 563400
## 31 71064000 72624600 1560600
## 32 72624600 75908200 3283600
## 33 75908200 78127000 2218800
## 34 78127000 79497400 1370400
## 35 79497400 86499800 7002400
## 36 86499800 87143600 643800
## 37 87143600 89614400 2470800
## 38 89614400 91523400 1909000
## 39 91523400 94052600 2529200
## 40 94052600 95311600 1259000
## 41 95311600 96842400 1530800
## 42 96842400 97044400 202000
## 43 97044400 100463600 3419200
## 44 100463600 104643600 4180000
## 45 104643600 109102000 4458400
## 46 109102000 111211000 2109000
## 47 111211000 116150800 4939800
## 48 116150800 119670600 3519800
##
## [[5]]
## left_boundary_region right_boundary_region region_size
## 1 267000 2576800 2309800
## 2 2576800 4655200 2078400
## 3 4655200 7658000 3002800
## 4 7658000 10510400 2852400
## 5 10510400 12210800 1700400
## 6 12210800 14104200 1893400
## 7 14104200 18895000 4790800
## 8 18895000 19250200 355200
## 9 19250200 24834800 5584600
## 10 24834800 26606200 1771400
## 11 26606200 27404200 798000
## 12 27404200 30784200 3380000
## 13 30784200 33629400 2845200
## 14 33629400 34861400 1232000
## 15 34861400 37686400 2825000
## 16 37686400 42922200 5235800
## 17 42922200 45501600 2579400
## 18 45501600 47181800 1680200
## 19 47181800 48560600 1378800
## 20 48560600 59960800 11400200
## 21 59960800 62751600 2790800
## 22 62751600 66362000 3610400
## 23 66362000 67766600 1404600
## 24 67766600 68339200 572600
## 25 68339200 70500600 2161400
## 26 70500600 71064000 563400
## 27 71064000 72624600 1560600
## 28 72624600 75908200 3283600
## 29 75908200 78127000 2218800
## 30 78127000 79497400 1370400
## 31 79497400 86499800 7002400
## 32 86499800 87143600 643800
## 33 87143600 89614400 2470800
## 34 89614400 91523400 1909000
## 35 91523400 94052600 2529200
## 36 94052600 95311600 1259000
## 37 95311600 97044400 1732800
## 38 97044400 100463600 3419200
## 39 100463600 104643600 4180000
## 40 104643600 109102000 4458400
## 41 109102000 111211000 2109000
## 42 111211000 116150800 4939800
##
## [[6]]
## left_boundary_region right_boundary_region region_size
## 1 267000 2576800 2309800
## 2 2576800 4655200 2078400
## 3 4655200 7658000 3002800
## 4 7658000 12210800 4552800
## 5 12210800 14104200 1893400
## 6 14104200 19250200 5146000
## 7 19250200 24834800 5584600
## 8 24834800 26606200 1771400
## 9 26606200 33629400 7023200
## 10 33629400 42922200 9292800
## 11 42922200 45501600 2579400
## 12 45501600 47181800 1680200
## 13 47181800 48560600 1378800
## 14 48560600 59960800 11400200
## 15 59960800 62751600 2790800
## 16 62751600 66362000 3610400
## 17 66362000 67766600 1404600
## 18 67766600 68339200 572600
## 19 68339200 71064000 2724800
## 20 71064000 72624600 1560600
## 21 72624600 78127000 5502400
## 22 78127000 79497400 1370400
## 23 79497400 86499800 7002400
## 24 86499800 89614400 3114600
## 25 89614400 91523400 1909000
## 26 91523400 94052600 2529200
## 27 94052600 97044400 2991800
## 28 97044400 104643600 7599200
## 29 104643600 109102000 4458400
## 30 109102000 111211000 2109000
## 31 111211000 116150800 4939800
##
## [[7]]
## left_boundary_region right_boundary_region region_size
## 1 267000 2576800 2309800
## 2 2576800 4655200 2078400
## 3 4655200 12210800 7555600
## 4 12210800 14104200 1893400
## 5 14104200 19250200 5146000
## 6 19250200 24834800 5584600
## 7 24834800 26606200 1771400
## 8 26606200 33629400 7023200
## 9 33629400 42922200 9292800
## 10 42922200 45501600 2579400
## 11 45501600 47181800 1680200
## 12 47181800 62751600 15569800
## 13 62751600 66362000 3610400
## 14 66362000 67766600 1404600
## 15 67766600 68339200 572600
## 16 68339200 78127000 9787800
## 17 78127000 79497400 1370400
## 18 79497400 86499800 7002400
## 19 86499800 89614400 3114600
## 20 89614400 91523400 1909000
## 21 91523400 97044400 5521000
## 22 97044400 104643600 7599200
## 23 104643600 109102000 4458400
## 24 109102000 111211000 2109000
##
## [[8]]
## left_boundary_region right_boundary_region region_size
## 1 267000 2576800 2309800
## 2 2576800 4655200 2078400
## 3 4655200 12210800 7555600
## 4 12210800 24834800 12624000
## 5 24834800 45501600 20666800
## 6 45501600 47181800 1680200
## 7 47181800 62751600 15569800
## 8 62751600 66362000 3610400
## 9 66362000 68339200 1977200
## 10 68339200 78127000 9787800
## 11 78127000 89614400 11487400
## 12 89614400 91523400 1909000
## 13 91523400 97044400 5521000
## 14 97044400 104643600 7599200
##
## [[9]]
## left_boundary_region right_boundary_region region_size
## 1 267000 45501600 45234600
## 2 45501600 47181800 1680200
## 3 47181800 66362000 19180200
## 4 66362000 68339200 1977200
## 5 68339200 78127000 9787800
## 6 78127000 89614400 11487400
##
## [[10]]
## left_boundary_region right_boundary_region region_size
## 1 267000 45501600 45234600
## 2 45501600 47181800 1680200
## 3 47181800 89614400 42432600
##
## [[11]]
## left_boundary_region right_boundary_region region_size
## 1 267000 47181800 46914800
## 2 47181800 89614400 42432600region_size_summaries <- lapply(reports, function(df) summary(df$region_size))
region_size_summaries## [[1]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0 790600 1370400 1372455 1901200 3002800
##
## [[2]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 188000 1118950 1632200 1658383 2167250 3400600
##
## [[3]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 188000 1245500 1790200 1895295 2510600 5156200
##
## [[4]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 202000 1412400 2093700 2487575 3131200 9610000
##
## [[5]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 355200 1590500 2264300 2759138 3355900 11400200
##
## [[6]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 572600 1901200 2790800 3738187 5042900 11400200
##
## [[7]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 572600 1905100 3362500 4622667 7007600 15569800
##
## [[8]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1680200 2136250 6538300 7455471 11062500 20666800
##
## [[9]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1680200 3929850 10637600 14891233 17257000 45234600
##
## [[10]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1680200 22056400 42432600 29782467 43833600 45234600
##
## [[11]]
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 42432600 43553150 44673700 44673700 45794250 46914800