% pubman genre = article
@article{item_3519809,
title = {{Expanding the stdpopsim species catalog, and lessons learned for realistic genome simulations}},
author = {Lauterbur, M Elise and Cavassim, Maria Izabel A and Gladstein, Ariella L and Gower, Graham and Pope, Nathaniel S and Tsambos, Georgia and Adrion, Jeffrey and Belsare, Saurabh and Biddanda, Arjun and Caudill, Victoria and Cury, Jean and Echevarria, Ignacio and Haller, Benjamin C and Hasan, Ahmed R and Huang, Xin and Iasi, Leonardo N.M. and Noskova, Ekaterina and Obsteter, Jana and Pavinato, Vitor Antonio Correa and Pearson, Alice and Peede, David and Perez, Manolo F and Rodrigues, Murillo F and Smith, Chris CR and Spence, Jeffrey P and Teterina, Anastasia and Tittes, Silas and Unneberg, Per and Vazquez, Juan Manuel and Waples, Ryan K and Wohns, Anthony Wilder and Wong, Yan and Baumdicker, Franz and Cartwright, Reed A and Gorjanc, Gregor and Gutenkunst, Ryan N and Kelleher, Jerome and Kern, Andrew D and Ragsdale, Aaron P and Ralph, Peter L and Schrider, Daniel R and Gronau, Ilan},
language = {eng},
issn = {2050-084X},
doi = {10.7554/eLife.84874},
publisher = {eLife Sciences Publications, Ltd},
year = {2023},
abstract = {{Simulation is a key tool in population genetics for both methods development and empirical research, but producing simulations that recapitulate the main features of genomic datasets remains a major obstacle. Today, more realistic simulations are possible thanks to large increases in the quantity and quality of available genetic data, and the sophistication of inference and simulation software. However, implementing these simulations still requires substantial time and specialized knowledge. These challenges are especially pronounced for simulating genomes for species that are not well-studied, since it is not always clear what information is required to produce simulations with a level of realism sufficient to confidently answer a given question. The community-developed framework stdpopsim seeks to lower this barrier by facilitating the simulation of complex population genetic models using up-to-date information. The initial version of stdpopsim focused on establishing this framework using six well-characterized model species (Adrion et al., 2020). Here, we report on major improvements made in the new release of stdpopsim (version 0.2), which includes a significant expansion of the species catalog and substantial additions to simulation capabilities. Features added to improve the realism of the simulated genomes include non-crossover recombination and provision of species-specific genomic annotations. Through community-driven efforts, we expanded the number of species in the catalog more than threefold and broadened coverage across the tree of life. During the process of expanding the catalog, we have identified common sticking points and developed the best practices for setting up genome-scale simulations. We describe the input data required for generating a realistic simulation, suggest good practices for obtaining the relevant information from the literature, and discuss common pitfalls and major considerations. These improvements to stdpopsim aim to further promote the use of realistic whole-genome population genetic simulations, especially in non-model organisms, making them available, transparent, and accessible to everyone.}},
journal = {{eLife}},
editor = {Gao, Ziyue and Przeworski, Molly},
volume = {12},
eid = {RP84874},
}