@misc{BarlowHartmannGonzalezetal.2020,
  author    = {Barlow, Axel and Hartmann, Stefanie and Gonzalez, Javier and Hofreiter, Michael and Paijmans, Johanna L. A.},
  title     = {Consensify},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1033},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-47252},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-472521},
  pages     = {24},
  year      = {2020},
  abstract  = {A standard practise in palaeogenome analysis is the conversion of mapped short read data into pseudohaploid sequences, frequently by selecting a single high-quality nucleotide at random from the stack of mapped reads. This controls for biases due to differential sequencing coverage, but it does not control for differential rates and types of sequencing error, which are frequently large and variable in datasets obtained from ancient samples. These errors have the potential to distort phylogenetic and population clustering analyses, and to mislead tests of admixture using D statistics. We introduce Consensify, a method for generating pseudohaploid sequences, which controls for biases resulting from differential sequencing coverage while greatly reducing error rates. The error correction is derived directly from the data itself, without the requirement for additional genomic resources or simplifying assumptions such as contemporaneous sampling. For phylogenetic and population clustering analysis, we find that Consensify is less affected by artefacts than methods based on single read sampling. For D statistics, Consensify is more resistant to false positives and appears to be less affected by biases resulting from different laboratory protocols than other frequently used methods. Although Consensify is developed with palaeogenomic data in mind, it is applicable for any low to medium coverage short read datasets. We predict that Consensify will be a useful tool for future studies of palaeogenomes.},
  language  = {en}
}
@article{BarlowHartmannGonzalezetal.2020,
  author    = {Barlow, Axel and Hartmann, Stefanie and Gonzalez, Javier and Hofreiter, Michael and Paijmans, Johanna L. A.},
  title     = {Consensify},
  series = {Genes / Molecular Diversity Preservation International},
  volume    = {11},
  journal   = {Genes / Molecular Diversity Preservation International},
  number    = {1},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {2073-4425},
  doi       = {10.3390/genes11010050},
  pages     = {22},
  year      = {2020},
  abstract  = {A standard practise in palaeogenome analysis is the conversion of mapped short read data into pseudohaploid sequences, frequently by selecting a single high-quality nucleotide at random from the stack of mapped reads. This controls for biases due to differential sequencing coverage, but it does not control for differential rates and types of sequencing error, which are frequently large and variable in datasets obtained from ancient samples. These errors have the potential to distort phylogenetic and population clustering analyses, and to mislead tests of admixture using D statistics. We introduce Consensify, a method for generating pseudohaploid sequences, which controls for biases resulting from differential sequencing coverage while greatly reducing error rates. The error correction is derived directly from the data itself, without the requirement for additional genomic resources or simplifying assumptions such as contemporaneous sampling. For phylogenetic and population clustering analysis, we find that Consensify is less affected by artefacts than methods based on single read sampling. For D statistics, Consensify is more resistant to false positives and appears to be less affected by biases resulting from different laboratory protocols than other frequently used methods. Although Consensify is developed with palaeogenomic data in mind, it is applicable for any low to medium coverage short read datasets. We predict that Consensify will be a useful tool for future studies of palaeogenomes.},
  language  = {en}
}
@article{AlbertiGonzalezPaijmansetal.2018,
  author    = {Alberti, Federica and Gonzalez, Javier and Paijmans, Johanna L. A. and Basler, Nikolas and Preick, Michaela and Henneberger, Kirstin and Trinks, Alexandra and Rabeder, Gernot and Conard, Nicholas J. and Muenzel, Susanne C. and Joger, Ulrich and Fritsch, Guido and Hildebrandt, Thomas and Hofreiter, Michael and Barlow, Axel},
  title     = {Optimized DNA sampling of ancient bones using Computed Tomography scans},
  series = {Molecular ecology resources},
  volume    = {18},
  journal   = {Molecular ecology resources},
  number    = {6},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {1755-098X},
  doi       = {10.1111/1755-0998.12911},
  pages     = {1196 -- 1208},
  year      = {2018},
  abstract  = {The prevalence of contaminant microbial DNA in ancient bone samples represents the principal limiting factor for palaeogenomic studies, as it may comprise more than 99\% of DNA molecules obtained. Efforts to exclude or reduce this contaminant fraction have been numerous but also variable in their success. Here, we present a simple but highly effective method to increase the relative proportion of endogenous molecules obtained from ancient bones. Using computed tomography (CT) scanning, we identify the densest region of a bone as optimal for sampling. This approach accurately identifies the densest internal regions of petrous bones, which are known to be a source of high-purity ancient DNA. For ancient long bones, CT scans reveal a high-density outermost layer, which has been routinely removed and discarded prior to DNA extraction. For almost all long bones investigated, we find that targeted sampling of this outermost layer provides an increase in endogenous DNA content over that obtained from softer, trabecular bone. This targeted sampling can produce as much as 50-fold increase in the proportion of endogenous DNA, providing a directly proportional reduction in sequencing costs for shotgun sequencing experiments. The observed increases in endogenous DNA proportion are not associated with any reduction in absolute endogenous molecule recovery. Although sampling the outermost layer can result in higher levels of human contamination, some bones were found to have more contamination associated with the internal bone structures. Our method is highly consistent, reproducible and applicable across a wide range of bone types, ages and species. We predict that this discovery will greatly extend the potential to study ancient populations and species in the genomics era.},
  language  = {en}
}