Bio Genome Assembly Assembly Polishing Agent Skill

conda install -c bioconda pilon

# Map short reads to assembly
bwa index assembly.fasta
bwa mem -t 16 assembly.fasta R1.fq.gz R2.fq.gz | samtools sort -o aligned.bam
samtools index aligned.bam

# Run Pilon
pilon --genome assembly.fasta --frags aligned.bam --output polished

#!/bin/bash
ASSEMBLY=$1
R1=$2
R2=$3
ROUNDS=${4:-3}

current=$ASSEMBLY

for i in $(seq 1 $ROUNDS); do
    echo "=== Pilon round $i ==="
    bwa index $current
    bwa mem -t 16 $current $R1 $R2 | samtools sort -o round${i}.bam
    samtools index round${i}.bam

    pilon --genome $current --frags round${i}.bam --output pilon_round${i} --changes

    current=pilon_round${i}.fasta

    changes=$(wc -l < pilon_round${i}.changes)
    echo "Changes made: $changes"

    if [ $changes -eq 0 ]; then
        echo "No more changes, stopping"
        break
    fi
done

cp $current final_polished.fasta

# Only fix SNPs and small indels
pilon --genome assembly.fa --frags aligned.bam --output polished --fix snps,indels

# Only fill gaps
pilon --genome assembly.fa --frags aligned.bam --output polished --fix gaps

conda install -c bioconda medaka

medaka_consensus -i reads.fastq.gz -d assembly.fasta -o medaka_output -t 8

# List available models
medaka tools list_models

# Use specific model (match your basecaller)
medaka_consensus -i reads.fq.gz -d assembly.fa -o output -m r1041_e82_400bps_sup_v5.1.0

medaka_output/
├── consensus.fasta    # Polished assembly
├── calls_to_draft.bam # Alignments
└── *.hdf              # Intermediate files

conda install -c bioconda racon

# Map reads to assembly
minimap2 -ax map-ont assembly.fasta reads.fastq.gz > aligned.sam

# Polish
racon -t 16 reads.fastq.gz aligned.sam assembly.fasta > polished.fasta

#!/bin/bash
ASSEMBLY=$1
READS=$2
ROUNDS=${3:-3}

current=$ASSEMBLY

for i in $(seq 1 $ROUNDS); do
    echo "=== Racon round $i ==="
    minimap2 -ax map-ont $current $READS > round${i}.sam
    racon -t 16 $READS round${i}.sam $current > racon_round${i}.fasta
    current=racon_round${i}.fasta
done

cp $current racon_polished.fasta

#!/bin/bash
set -euo pipefail

ASSEMBLY=$1      # Flye assembly
ONT_READS=$2     # ONT reads
ILLUMINA_R1=$3   # Illumina R1
ILLUMINA_R2=$4   # Illumina R2
OUTDIR=$5

mkdir -p $OUTDIR

# Step 1: Racon polishing (2 rounds)
echo "=== Racon Polishing ==="
current=$ASSEMBLY
for i in 1 2; do
    minimap2 -ax map-ont $current $ONT_READS > ${OUTDIR}/racon_${i}.sam
    racon -t 16 $ONT_READS ${OUTDIR}/racon_${i}.sam $current > ${OUTDIR}/racon_${i}.fasta
    current=${OUTDIR}/racon_${i}.fasta
done

# Step 2: medaka polishing
echo "=== medaka Polishing ==="
medaka_consensus -i $ONT_READS -d $current -o ${OUTDIR}/medaka -t 8
current=${OUTDIR}/medaka/consensus.fasta

# Step 3: Pilon polishing (2 rounds)
echo "=== Pilon Polishing ==="
for i in 1 2; do
    bwa index $current
    bwa mem -t 16 $current $ILLUMINA_R1 $ILLUMINA_R2 | samtools sort -o ${OUTDIR}/pilon_${i}.bam
    samtools index ${OUTDIR}/pilon_${i}.bam
    pilon --genome $current --frags ${OUTDIR}/pilon_${i}.bam --output ${OUTDIR}/pilon_${i}
    current=${OUTDIR}/pilon_${i}.fasta
done

cp $current ${OUTDIR}/final_polished.fasta
echo "Done: ${OUTDIR}/final_polished.fasta"

conda install -c bioconda nextpolish

# Create config file
cat > run.cfg << EOF
[General]
job_type = local
job_prefix = nextPolish
task = best
rewrite = yes
rerun = 3
parallel_jobs = 2
multithread_jobs = 8
genome = assembly.fasta
genome_size = auto
workdir = ./01_rundir
[lgs_option]
lgs_fofn = lgs.fofn
lgs_options = -min_read_len 1k -max_depth 100
lgs_minimap2_options = -x map-ont
[sgs_option]
sgs_fofn = sgs.fofn
sgs_options = -max_depth 100
EOF

# File of filenames
ls reads.fastq.gz > lgs.fofn
ls R1.fq.gz R2.fq.gz > sgs.fofn

# Run
nextPolish run.cfg

# Compare to reference (if available)
quast.py -r reference.fa original.fa polished.fa -o quast_comparison

# Check error rate
minimap2 -ax map-ont polished.fa reads.fq.gz | samtools stats | grep "error rate"