@article{fdi:010077059,
  title = {{B}enchmarking database systems for genomic selection implementation},
  author = {{N}ti-{A}ddae, {Y}. and {M}atthews, {D}. and {U}lat, {V}. {J}. and {S}yed, {R}. and {S}empere, {G}. and {P}etel, {A}. and {R}enner, {J}. and {L}armande, {P}ierre and {G}uignon, {V}. and {J}ones, {E}. and {R}obbins, {K}.},
  editor = {},
  language = {{ENG}},
  abstract = {{M}otivation: {W}ith high-throughput genotyping systems now available, it has become feasible to fully integrate genotyping information into breeding programs. {T}o make use of this information effectively requires {DNA} extraction facilities and marker production facilities that can efficiently deploy the desired set of markers across samples with a rapid turnaround time that allows for selection before crosses needed to be made. {I}n reality, breeders often have a short window of time to make decisions by the time they are able to collect all their phenotyping data and receive corresponding genotyping data. {T}his presents a challenge to organize information and utilize it in downstream analyses to support decisions made by breeders. {I}n order to implement genomic selection routinely as part of breeding programs, one would need an efficient genotyping data storage system. {W}e selected and benchmarked six popular open-source data storage systems, including relational database management and columnar storage systems. {R}esults: {W}e found that data extract times are greatly influenced by the orientation in which genotype data is stored in a system. {HDF}5 consistently performed best, in part because it can more efficiently work with both orientations of the allele matrix.},
  keywords = {},
  booktitle = {},
  journal = {{D}atabase},
  numero = {},
  pages = {baz096 [10p.]},
  ISSN = {1758-0463},
  year = {2019},
  DOI = {10.1093/database/baz096},
  URL = {https://www.documentation.ird.fr/hor/fdi:010077059},
}