Advertisement
asherrar

Pipeline

Feb 24th, 2023 (edited)
81
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Bash 2.10 KB | None | 0 0
  1. ## Each part of this pipeline was run separately
  2. ## This will probably not run as-is, I pulled each part of the pipeline into a single script for convenience
  3. #!/bin/bash
  4.  
  5. base_dir=/scratch/asherrar/vg_test
  6. ref=/home/asherrar/t2t_sequence/v2.0/chm13v2.0.fa
  7. vardir=/scratch/asherrar/sgdp
  8. tmpdir=/scratch/asherrar/vg_tmp
  9.  
  10. cd $base_dir
  11.  
  12. variants=""
  13. for i in {1..22} X Y; do variants+="-v $vardir/SGDP.CHM13v2.0.chr$i.recalibrated.snp_indel.pass.vcf.gz "; done
  14.  
  15. ## < Step 1 - Graph Construction > ##
  16.  
  17. # construct base graph and index
  18. echo "constructing base graph"
  19. vg autoindex -r $ref -p $base_dir/t2t $variants -T $tmpdir -M 256G -V 2
  20. vg convert -p $base_dir/t2t.vg > $base_dir/t2t.xg
  21. vg convert -p $base_dir/t2t.xg > $base_dir/t2t.pg
  22.  
  23. ## < Step 2 - Read Mapping > ##
  24.  
  25. echo "mapping reads"
  26. vg map -m "long" -d $base_dir/t2t -f /scratch/asherrar/aicardi_longread/PAE47322.fasta > $base_dir/PAE47322.gam
  27.  
  28. ## < Step 3 - Graph Chunking > ##
  29.  
  30. mkdir -p $base_dir/chunks
  31. vg chunk -x $base_dir/t2t.xg -M -O pg -b $base_dir/chunks/t2t
  32.  
  33. ## < Step 4 - Calling against Chunks > ##
  34.  
  35. # run for each chunk:
  36.  
  37. base_dir=/scratch/asherrar/vg_test
  38. mkdir -p $base_dir/chunk_steps
  39. mkdir -p $base_dir/chunk_vcf
  40. chunkdir=$base_dir/chunk_steps
  41.  
  42. chunkname=chr${current_chunk}
  43. chunk=$base_dir/chunks/t2t_$chunkname.pg
  44.  
  45. echo "calling variants on $chunkname"
  46.  
  47. echo " - augmenting graph"
  48. vg augment -v -p -s -t 24 -m 4 -q 5 -Q 5 -A $chunkdir/${chunkname}_PAE47322_augmented.gam $chunk $base_dir/PAE47322.gam > $chunkdir/${chunkname}_PAE47322_augmented.pg
  49. echo " - calculating snarls"
  50. vg snarls $chunkdir/${chunkname}_PAE47322_augmented.pg > $chunkdir/${chunkname}_PAE47322_augmented.snarls
  51. echo " - packing graph"
  52. vg pack -x $chunkdir/${chunkname}_PAE47322_augmented.pg -g $chunkdir/${chunkname}_PAE47322_augmented.gam -o $chunkdir/${chunkname}_PAE47322_augmented.pack
  53. echo " - calling variants"
  54. vg call $chunkdir/${chunkname}_PAE47322_augmented.pg -r $chunkdir/${chunkname}_PAE47322_augmented.snarls -k $chunkdir/${chunkname}_PAE47322_augmented.pack -s PAE47322_reads > $base_dir/chunk_vcf/${chunkname}_PAE47322_readcalls.vcf
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement