%0 Journal Article %1 danek2018maintain %A Danek, Agnieszka %A Deorowicz, Sebastian %D 2018 %J Bioinformatics %K data_structures genomic_data methods %N 11 %P 1834-1840 %R 10.1093/bioinformatics/bty023 %T GTC: how to maintain huge genotype collections in a compressed form %U https://doi.org/10.1093/bioinformatics/bty023 %V 34 %X Nowadays, genome sequencing is frequently used in many research centers. In projects, such as the Haplotype Reference Consortium or the Exome Aggregation Consortium, huge databases of genotypes in large populations are determined. Together with the increasing size of these collections, the need for fast and memory frugal ways of representation and searching in them becomes crucial.We present GTC (GenoType Compressor), a novel compressed data structure for representation of huge collections of genetic variation data. It significantly outperforms existing solutions in terms of compression ratio and time of answering various types of queries. We show that the largest of publicly available database of about 60 000 haplotypes at about 40 million SNPs can be stored in \<4 GB, while the queries related to variants are answered in a fraction of a second.GTC can be downloaded from https://github.com/refresh-bio/GTC or http://sun.aei.polsl.pl/REFRESH/gtc.Supplementary data are available at Bioinformatics online.

@article{danek2018maintain, abstract = {{Nowadays, genome sequencing is frequently used in many research centers. In projects, such as the Haplotype Reference Consortium or the Exome Aggregation Consortium, huge databases of genotypes in large populations are determined. Together with the increasing size of these collections, the need for fast and memory frugal ways of representation and searching in them becomes crucial.We present GTC (GenoType Compressor), a novel compressed data structure for representation of huge collections of genetic variation data. It significantly outperforms existing solutions in terms of compression ratio and time of answering various types of queries. We show that the largest of publicly available database of about 60 000 haplotypes at about 40 million SNPs can be stored in \\<4 GB, while the queries related to variants are answered in a fraction of a second.GTC can be downloaded from https://github.com/refresh-bio/GTC or http://sun.aei.polsl.pl/REFRESH/gtc.Supplementary data are available at Bioinformatics online.}}, added-at = {2020-06-29T22:05:30.000+0200}, author = {Danek, Agnieszka and Deorowicz, Sebastian}, biburl = {https://www.bibsonomy.org/bibtex/2dd9a006a89027f7823b1fe6c709569fa/peter.ralph}, doi = {10.1093/bioinformatics/bty023}, eprint = {https://academic.oup.com/bioinformatics/article-pdf/34/11/1834/25121502/bty023.pdf}, interhash = {9aead2adb3a41b02541cf13c5218945a}, intrahash = {dd9a006a89027f7823b1fe6c709569fa}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {data_structures genomic_data methods}, month = {01}, number = 11, pages = {1834-1840}, timestamp = {2020-06-29T22:05:30.000+0200}, title = {{GTC}: how to maintain huge genotype collections in a compressed form}, url = {https://doi.org/10.1093/bioinformatics/bty023}, volume = 34, year = 2018 }