@article {Pajuste060822, author = {Fanny-Dhelia Pajuste and Lauris Kaplinski and M{\"a}rt M{\"o}ls and Tarmo Puurand and Maarja Lepamets and Maido Remm}, title = {FastGT: from raw sequence reads to 30 million genotypes in less than an hour}, elocation-id = {060822}, year = {2016}, doi = {10.1101/060822}, publisher = {Cold Spring Harbor Laboratory}, abstract = {We have developed a computational method that counts the frequencies of unique k-mers in FASTQ-formatted genome data and uses this information to infer the genotypes of known variants. FastGT can detect the variants in a 30x genome in less than 1 hour using ordinary low-cost server hardware. The overall concordance with the genotypes of two Illumina {\textquotedblleft}Platinum{\textquotedblright} genomes is 99.96\%, and the concordance with the genotypes of the Illumina HumanOmniExpress is 99.82\%. Our method provides k-mer database that can be used for the simultaneous genotyping of approximately 30 million single nucleotide variants (SNVs), including \> 23,000 SNVs from Y chromosome.}, URL = {https://www.biorxiv.org/content/early/2016/06/27/060822}, eprint = {https://www.biorxiv.org/content/early/2016/06/27/060822.full.pdf}, journal = {bioRxiv} }