Harvey2023.downsampling.bib

@ARTICLE{Harvey2023,
  title    = "Whole-genome long-read sequencing downsampling and its effect on
              variant-calling precision and recall",
  author   = "Harvey, William T and Ebert, Peter and Ebler, Jana and Audano,
              Peter A and Munson, Katherine M and Hoekzema, Kendra and
              Porubsky, David and Beck, Christine R and Marschall, Tobias and
              Garimella, Kiran and Eichler, Evan E",
  abstract = "Advances in long-read sequencing (LRS) technologies continue to
              make whole-genome sequencing more complete, affordable, and
              accurate. LRS provides significant advantages over short-read
              sequencing approaches, including phased de novo genome assembly,
              access to previously excluded genomic regions, and discovery of
              more complex structural variants (SVs) associated with disease.
              Limitations remain with respect to cost, scalability, and
              platform-dependent read accuracy and the tradeoffs between
              sequence coverage and sensitivity of variant discovery are
              important experimental considerations for the application of LRS.
              We compare the genetic variant-calling precision and recall of
              Oxford Nanopore Technologies (ONT) and Pacific Biosciences
              (PacBio) HiFi platforms over a range of sequence coverages. For
              read-based applications, LRS sensitivity begins to plateau around
              12-fold coverage with a majority of variants called with
              reasonable accuracy (F1 score above 0.5), and both platforms
              perform well for SV detection. Genome assembly increases
              variant-calling precision and recall of SVs and indels in HiFi
              data sets with HiFi outperforming ONT in quality as measured by
              the F1 score of assembly-based variant call sets. While both
              technologies continue to evolve, our work offers guidance to
              design cost-effective experimental strategies that do not
              compromise on discovering novel biology.",
  journal  = "Genome Res.",
  month    =  dec,
  year     =  2023
}