@article{10.1371/journal.pone.0040294, doi = {10.1371/journal.pone.0040294}, author = {Rosenfeld, Jeffrey A. AND Mason, Christopher E. AND Smith, Todd M.}, journal = {PLOS ONE}, publisher = {Public Library of Science}, title = {Limitations of the Human Reference Genome for Personalized Genomics}, year = {2012}, month = {07}, volume = {7}, url = {https://doi.org/10.1371/journal.pone.0040294}, pages = {1-9}, abstract = {Data from the 1000 genomes project (1KGP) and Complete Genomics (CG) have dramatically increased the numbers of known genetic variants and challenge several assumptions about the reference genome and its uses in both clinical and research settings. Specifically, 34% of published array-based GWAS studies for a variety of diseases utilize probes that overlap unanticipated single nucleotide polymorphisms (SNPs), indels, or structural variants. Linkage disequilibrium (LD) block length depends on the numbers of markers used, and the mean LD block size decreases from 16 kb to 7 kb,when HapMap-based calculations are compared to blocks computed from1KGP data. Additionally, when 1KGP and CG variants are compared, 19% of the single nucleotide variants (SNVs) reported from common genomes are unique to one dataset; likely a result of differences in data collection methodology, alignment of reads to the reference genome, and variant-calling algorithms. Together these observations indicate that current research resources and informatics methods do not adequately account for the high level of variation that already exists in the human population and significant efforts are needed to create resources that can accurately assess personal genomics for health, disease, and predict treatment outcomes.}, number = {7}, }