bio-genome-assembly-scaffolding
Installation
SKILL.md
Genome Scaffolding
Hi-C Data Preprocessing
# Align Hi-C reads to draft assembly
bwa index draft_assembly.fa
bwa mem -5SP -t 16 draft_assembly.fa hic_R1.fq.gz hic_R2.fq.gz | \
samtools view -@ 8 -bhS - > aligned.bam
# Filter for Hi-C contacts (pairtools)
pairtools parse --min-mapq 40 --walks-policy 5unique --max-inter-align-gap 30 \
--nproc-in 8 --nproc-out 8 --chroms-path draft_assembly.fa.fai aligned.bam | \
pairtools sort --nproc 8 | \
pairtools dedup --nproc 8 --mark-dups | \
pairtools split --output-pairs contacts.pairs.gz