Page Comparison

#how many raw genotyped sites to be have?
vcftools --vcf raw_calls.vcf


      #After filtering, kept 4 out of 4 Individuals
      #After filtering, kept 14559 out of a possible 14559 Sites


#now perform basic quality filtering on raw calls
bcftools filter --exclude 'QUAL < 30' raw_calls.vcf | bcftools view > filt0.vcf
 
#check the new quality checked vcf
vcftools --vcf filt0.vcf


#Additionally, you can filter on representation among samples, allele frequency, and other options with VCFtools


#Filter for biallelic sites variants 
#genotyped in 75% of samples,
#with at least two reads covering the site


vcftools --vcf filt0.vcf --max-alleles 2 --max-missing 0.75 --minDP 2 --recode --out filt2