You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

139 lines
8.0KB

  1. cat tier1.sv tier2.sv | grep DEL | cut -f1,2,5 | sed s'/END=//g' > SV.DEL
  2. cat tier1.sv tier2.sv | grep DUP | cut -f1,2,5 | sed s'/END=//g' > SV.DUP
  3. cat tier1.sv tier2.sv | grep INS | cut -f1,2 > SV.INS
  4. cat SV.INS | awk '{print $1 "\t" ($2 - 500) "\t" ($2+500)}' | sort -k1,1 -k2,2n > sv.ins.break.point.500.bed
  5. cat SV.DEL | awk '{print $1 "\t" ($2 - 500) "\t" $2}' > sv.del.break.point.left
  6. cat SV.DEL | awk '{print $1 "\t" $3 "\t" ($3 + 500)}' > sv.del.break.point.right
  7. cat sv.del.break.point.left sv.del.break.point.right | sort -k1,1 -k2,2n > sv.del.break.point.500.bed
  8. cat tier1.sv tier2.sv | grep TRA | grep -v 'chrM' | cut -f1,2,4,5 > SV.TRA
  9. cat SV.TRA | awk '{print $1 "\t" ($2 - 500) "\t" ($2 + 500)}' > sv.tra.chr1
  10. cat SV.TRA | cut -f3,4 | sed s'/CHR2=//g' | sed s'/END=//g' |awk '{print $1 "\t" ($2 - 500) "\t" ($2 + 500)}' > sv.tra.chr2
  11. cat sv.tra.chr1 sv.tra.chr2 | sort -k1,1 -k2,2n > sv.tra.break.point.500.bed
  12. cat tier1.sv tier2.sv | grep INV | cut -f1,2,5 | sed s'/END=//g' > SV.INV
  13. cat SV.INV | awk '{print $1 "\t" ($2 - 500) "\t" $2}' > sv.inv.break.point.left
  14. cat SV.INV | awk '{print $1 "\t" $3 "\t" ($3 + 500)}' > sv.inv.break.point.right
  15. cat sv.inv.break.point.left sv.inv.break.point.right | sort -k1,1 -k2,2n > sv.inv.break.point.500.bed
  16. cat SV.DUP | awk '{print $1 "\t" ($2 - 500) "\t" $2}' > sv.dup.break.point.left
  17. cat SV.DUP | awk '{print $1 "\t" $3 "\t" ($3 + 500)}' > sv.dup.break.point.right
  18. cat sv.dup.break.point.left sv.dup.break.point.right | grep -v 'chrM' | sort -k1,1 -k2,2n > sv.dup.break.point.500.bed
  19. cat SV.INS | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.50
  20. cat sv.ins.left.50 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.100
  21. cat sv.ins.left.100 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.150
  22. cat sv.ins.left.150 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.200
  23. cat sv.ins.left.200 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.250
  24. cat sv.ins.left.250 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.300
  25. cat sv.ins.left.300 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.350
  26. cat sv.ins.left.350 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.400
  27. cat sv.ins.left.400 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.450
  28. cat sv.ins.left.450 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.500
  29. cat sv.ins.left.500 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.550
  30. cat sv.ins.left.550 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.600
  31. cat sv.ins.left.600 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.650
  32. cat sv.ins.left.650 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.700
  33. cat sv.ins.left.700 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.750
  34. cat sv.ins.left.750 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.800
  35. cat sv.ins.left.800 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.850
  36. cat sv.ins.left.850 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.900
  37. cat sv.ins.left.900 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.950
  38. cat sv.ins.left.950 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1000
  39. cat sv.ins.left.1000 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1050
  40. cat sv.ins.left.1050 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1100
  41. cat sv.ins.left.1100 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1150
  42. cat sv.ins.left.1150 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1200
  43. cat sv.ins.left.1200 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1250
  44. cat sv.ins.left.1250 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1300
  45. cat sv.ins.left.1300 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1350
  46. cat sv.ins.left.1350 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1400
  47. cat sv.ins.left.1400 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1450
  48. cat sv.ins.left.1450 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.ins.left.1500
  49. cat SV.INS | awk '{print $1"\t"$2 "\t" ($2 + 50)}' > sv.ins.right.50
  50. cat sv.ins.right.50 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.100
  51. cat sv.ins.right.100 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.150
  52. cat sv.ins.right.150 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.200
  53. cat sv.ins.right.200 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.250
  54. cat sv.ins.right.250 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.300
  55. cat sv.ins.right.300 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.350
  56. cat sv.ins.right.350 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.400
  57. cat sv.ins.right.400 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.450
  58. cat sv.ins.right.450 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.500
  59. cat sv.ins.right.500 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.550
  60. cat sv.ins.right.550 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.600
  61. cat sv.ins.right.600 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.650
  62. cat sv.ins.right.650 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.700
  63. cat sv.ins.right.700 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.750
  64. cat sv.ins.right.750 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.800
  65. cat sv.ins.right.800 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.850
  66. cat sv.ins.right.850 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.900
  67. cat sv.ins.right.900 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.950
  68. cat sv.ins.right.950 | awk '{print $1"\t"$3 "\t" ($3 + 50)}' > sv.ins.right.1000
  69. cat SV.DEL | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.50
  70. cat sv.del.left.50 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.100
  71. cat sv.del.left.100 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.150
  72. cat sv.del.left.150 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.200
  73. cat sv.del.left.200 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.250
  74. cat sv.del.left.250 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.300
  75. cat sv.del.left.300 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.350
  76. cat sv.del.left.350 | awk '{print $1 "\t" ($2 - 50) "\t" $2}' > sv.del.left.400
  77. cat SV.DEL | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.50
  78. cat sv.del.right.50 | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.100
  79. cat sv.del.right.100 | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.150
  80. cat sv.del.right.150 | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.200
  81. cat sv.del.right.200 | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.250
  82. cat sv.del.right.250 | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.300
  83. cat sv.del.right.300 | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.350
  84. cat sv.del.right.350 | awk '{print $1 "\t" $3 "\t" ($3 + 50)}' > sv.del.right.400
  85. bedtools subtract -a GRCh38.bed -b diff.merged.bed > easy_region.bed
  86. python /mnt/pgx_src_data_pool_4/home/renluyao/manuscript/SV/count_bed.py LCL5.high.confidence.bed
  87. bedtools intersect -a LCL5.high.confidence.bed -b /mnt/pgx_src_data_pool_4/home/renluyao/Quartet/GIAB/NA12878_HG001/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed > LCL5.nist.common.bed
  88. bedtools intersect -a LCL6.high.confidence.bed -b /mnt/pgx_src_data_pool_4/home/renluyao/Quartet/GIAB/NA12878_HG001/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed > LCL6.nist.common.bed
  89. bedtools intersect -a LCL7.high.confidence.bed -b /mnt/pgx_src_data_pool_4/home/renluyao/Quartet/GIAB/NA12878_HG001/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed > LCL7.nist.common.bed
  90. bedtools intersect -a LCL8.high.confidence.bed -b /mnt/pgx_src_data_pool_4/home/renluyao/Quartet/GIAB/NA12878_HG001/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed > LCL8.nist.common.bed
  91. bedtools intersect -a LCL5.high.confidence.bed -b ensembl.bed > LCL5.ensembl.bed
  92. rtg vcffilter -i clinivar.chr.vcf.gz -o clinivar.chr.LCL5.vcf.gz --include-bed=LCL5.high.confidence.bed