bcftools merge sample1.vcf.gz sample2.vcf.gz -Oz -o merged.vcf.gz

bcftools merge *.vcf.gz -Oz -o all_samples.vcf.gz

# files.txt: one VCF path per line
bcftools merge -l files.txt -Oz -o merged.vcf.gz

# Output missing genotypes as ./. (default)
bcftools merge sample1.vcf.gz sample2.vcf.gz -Oz -o merged.vcf.gz

# Output missing as reference (0/0)
bcftools merge --missing-to-ref sample1.vcf.gz sample2.vcf.gz -Oz -o merged.vcf.gz

bcftools merge --force-samples sample1.vcf.gz sample2.vcf.gz -Oz -o merged.vcf.gz

bcftools merge -r chr1:1000000-2000000 sample1.vcf.gz sample2.vcf.gz -Oz -o merged.vcf.gz

bcftools concat chr1.vcf.gz chr2.vcf.gz chr3.vcf.gz -Oz -o genome.vcf.gz

bcftools concat chr*.vcf.gz -Oz -o genome.vcf.gz

# files.txt: one VCF path per line (in order)
bcftools concat -f files.txt -Oz -o concatenated.vcf.gz

bcftools concat -a chr1_part1.vcf.gz chr1_part2.vcf.gz -Oz -o chr1.vcf.gz

bcftools concat -a -d all file1.vcf.gz file2.vcf.gz -Oz -o merged.vcf.gz

bcftools sort input.vcf -Oz -o sorted.vcf.gz

bcftools sort -T /tmp input.vcf.gz -Oz -o sorted.vcf.gz

bcftools sort -m 4G input.vcf.gz -Oz -o sorted.vcf.gz

bcftools isec -p output_dir sample1.vcf.gz sample2.vcf.gz

bcftools isec -p output_dir -Oz sample1.vcf.gz sample2.vcf.gz

bcftools isec -p output_dir -n=2 sample1.vcf.gz sample2.vcf.gz
# Only outputs variants present in exactly 2 files

# Variants in both files
bcftools isec -n=2 -w1 sample1.vcf.gz sample2.vcf.gz -Oz -o shared.vcf.gz

# Variants only in sample1
bcftools isec -n~10 -w1 sample1.vcf.gz sample2.vcf.gz -Oz -o only_sample1.vcf.gz

# Variants in file1 not in file2
bcftools isec -C sample1.vcf.gz sample2.vcf.gz -Oz -o unique.vcf.gz

bcftools view -s sample1,sample2 input.vcf.gz -Oz -o subset.vcf.gz

bcftools view -s ^sample3 input.vcf.gz -Oz -o without_sample3.vcf.gz

# samples.txt: one sample name per line
bcftools view -S samples.txt input.vcf.gz -Oz -o subset.vcf.gz

bcftools view -r chr1:1000000-2000000 input.vcf.gz -Oz -o region.vcf.gz

bcftools view -R regions.bed input.vcf.gz -Oz -o targets.vcf.gz

echo "old_name new_name" > rename.txt
bcftools reheader -s rename.txt input.vcf.gz -o renamed.vcf.gz

# rename.txt format: old_name new_name
cat > rename.txt << EOF
sample1 patient_001
sample2 patient_002
sample3 patient_003
EOF

bcftools reheader -s rename.txt input.vcf.gz -o renamed.vcf.gz

for sample in $(bcftools query -l input.vcf.gz); do
    bcftools view -s "$sample" input.vcf.gz -Oz -o "${sample}.vcf.gz"
done

for chr in $(bcftools view -h input.vcf.gz | grep "^##contig" | sed 's/.*ID=\([^,]*\).*/\1/'); do
    bcftools view -r "$chr" input.vcf.gz -Oz -o "${chr}.vcf.gz"
done

bcftools norm -m-any input.vcf.gz -Oz -o split.vcf.gz

# Create file list
ls *.vcf.gz > files.txt

# Merge all samples
bcftools merge -l files.txt -Oz -o cohort.vcf.gz
bcftools index cohort.vcf.gz

# After parallel variant calling by chromosome
bcftools concat chr{1..22}.vcf.gz chrX.vcf.gz chrY.vcf.gz -Oz -o genome.vcf.gz
bcftools index genome.vcf.gz

# Find variants called by both GATK and bcftools
bcftools isec -p comparison gatk.vcf.gz bcftools.vcf.gz

# Count results
wc -l comparison/*.vcf

bcftools view -f PASS input.vcf.gz -Oz -o pass_only.vcf.gz
bcftools index pass_only.vcf.gz

from cyvcf2 import VCF, Writer

# WARNING: This concatenates records, not a true merge
# For actual merging of samples, use bcftools merge
vcf1 = VCF('file1.vcf.gz')
writer = Writer('combined.vcf', vcf1)

for variant in vcf1:
    writer.write_record(variant)

writer.close()
vcf1.close()

from cyvcf2 import VCF

# Load positions from first VCF
vcf1_positions = set()
for variant in VCF('sample1.vcf.gz'):
    vcf1_positions.add((variant.CHROM, variant.POS))

# Check second VCF
shared = 0
unique = 0
for variant in VCF('sample2.vcf.gz'):
    if (variant.CHROM, variant.POS) in vcf1_positions:
        shared += 1
    else:
        unique += 1

print(f'Shared: {shared}')
print(f'Unique to sample2: {unique}')