@article{fdi:010094398,
  title = {{E}ffective population size estimation in large marine populations : considering current challenges and opportunities when simulating large data sets with high-density genomic information},
  author = {{D}elord, {C}. and {A}rnaud-{H}aond, {S}. and {L}eone, {A}. and {N}oskova, {E}. and {T}ournebize, {R}{\'e}mi and {J}acques, {P}. and {M}arsac, {F}rancis and {N}ikolic, {N}.},
  editor = {},
  language = {{ENG}},
  abstract = {{N}ext-generation-sequencing has broadened perspectives regarding the estimation of the effective population size ({N}e) by providing high-density genomic information. {T}hese technologies have expanded data collection and analytical tools in population genetics, increasing understanding of populations with high abundance, such as marine species with high commercial or conservation priority. {S}everal common methods for estimating {N}e are based on allele frequency spectra or linkage disequilibrium between loci. {H}owever, their specific constraints make it difficult to apply them to large populations, especially with confounding factors such as migration rates, complex sampling schemes or non-independence between loci. {C}omputer simulations have long represented invaluable tools to explore the influence of biological or logistical factors on {N}e estimation and to assess the robustness of dedicated methods. {H}ere, we outline several {N}e estimation methods and their foundational principles, requirements and likely caveats regarding application to populations of high abundance. {T}hereafter, we present a simulation framework built upon recent computational genomic tools that combine the possibility to generate biologically realistic data sets with realistic patterns of long-term neutral genetic diversity. {T}his framework aims at reproducing and tracking the main critical features of data derived from a large natural population when running a simulation-based population genetics study, for example, evaluating the strengths and limitations of various {N}e estimation methods. {W}e illustrate this framework by generating genotype data sets with varying sample sizes and locus numbers and analysing them with three software tools ({N}e{E}stimator2, {GONE} and {GADMA}). {D}etailed and annotated simulation scripts are provided to ensure reproducibility and to support future research on {N}e estimation. {T}hese resources can support method comparisons and validations, particularly for non-specialists, such as conservation practitioners and students.},
  keywords = {allele frequency spectra ; computational genetics ; conservation genomics ; effective population size ; fisheries management ; linkage disequilibrium},
  booktitle = {},
  journal = {{E}volutionary {A}pplications},
  volume = {18},
  numero = {8},
  pages = {e70121 [22 p.]},
  ISSN = {1752-4571},
  year = {2025},
  DOI = {10.1111/eva.70121},
  URL = {https://www.documentation.ird.fr/hor/fdi:010094398},
}