conda install -c bioconda quast

quast.py assembly.fasta -o quast_output

quast.py assembly.fasta -r reference.fasta -o quast_output

quast.py assembly1.fa assembly2.fa assembly3.fa -o comparison

quast.py assembly.fasta -r reference.fasta -g genes.gff -o quast_output

quast.py --large assembly.fasta -o quast_output -t 16

quast_output/
├── report.txt        # Summary statistics
├── report.html       # Interactive report
├── report.tsv        # Tab-separated stats
├── icarus.html       # Contig viewer
└── aligned_stats/    # If reference provided

conda install -c bioconda busco

busco -i assembly.fasta -m genome -l bacteria_odb10 -o busco_output

busco --list-datasets

busco -i assembly.fasta -m genome --auto-lineage -o busco_output

busco_output/
├── short_summary.txt           # Quick summary
├── full_table.tsv              # All BUSCO results
├── missing_busco_list.tsv      # Missing genes
└── busco_sequences/            # BUSCO gene sequences

C:98.5%[S:97.0%,D:1.5%],F:0.5%,M:1.0%,n:4085

C - Complete (total)
S - Single-copy
D - Duplicated
F - Fragmented
M - Missing
n - Total BUSCO groups

#!/bin/bash
set -euo pipefail

ASSEMBLY=$1
REFERENCE=${2:-}
LINEAGE=${3:-bacteria_odb10}
OUTDIR=${4:-assembly_qc}

mkdir -p $OUTDIR

echo "=== Assembly QC ==="

# QUAST
echo "Running QUAST..."
if [ -n "$REFERENCE" ]; then
    quast.py $ASSEMBLY -r $REFERENCE -o ${OUTDIR}/quast -t 8
else
    quast.py $ASSEMBLY -o ${OUTDIR}/quast -t 8
fi

# BUSCO
echo "Running BUSCO..."
busco -i $ASSEMBLY -m genome -l $LINEAGE -o busco_run -c 8
mv busco_run ${OUTDIR}/busco

# Summary
echo ""
echo "=== QUAST Summary ==="
cat ${OUTDIR}/quast/report.txt

echo ""
echo "=== BUSCO Summary ==="
cat ${OUTDIR}/busco/short_summary*.txt

echo ""
echo "Reports saved to $OUTDIR"

quast.py \
    spades_assembly.fa \
    flye_assembly.fa \
    canu_assembly.fa \
    -r reference.fa \
    -l "SPAdes,Flye,Canu" \
    -o assembly_comparison

# Run BUSCO on each assembly
for asm in spades.fa flye.fa canu.fa; do
    name=$(basename $asm .fa)
    busco -i $asm -m genome -l bacteria_odb10 -o busco_${name}
done

# Generate comparison plot
generate_plot.py -wd . busco_spades busco_flye busco_canu

import pandas as pd

def parse_quast(report_tsv):
    '''Parse QUAST report.tsv file.'''
    df = pd.read_csv(report_tsv, sep='\t', index_col=0)
    return df.T

stats = parse_quast('quast_output/report.tsv')
print(f"N50: {stats['N50'].values[0]}")
print(f"Total length: {stats['Total length'].values[0]}")
print(f"# contigs: {stats['# contigs'].values[0]}")

import re

def parse_busco_summary(summary_file):
    '''Parse BUSCO short summary.'''
    with open(summary_file) as f:
        text = f.read()

    pattern = r'C:(\d+\.\d+)%\[S:(\d+\.\d+)%,D:(\d+\.\d+)%\],F:(\d+\.\d+)%,M:(\d+\.\d+)%,n:(\d+)'
    match = re.search(pattern, text)

    if match:
        return {
            'complete': float(match.group(1)),
            'single': float(match.group(2)),
            'duplicated': float(match.group(3)),
            'fragmented': float(match.group(4)),
            'missing': float(match.group(5)),
            'total': int(match.group(6))
        }
    return None

result = parse_busco_summary('busco_output/short_summary.txt')
print(f"Complete: {result['complete']}%")

metaquast.py metagenome_assembly.fa -o metaquast_output -t 16