% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Deutelmoser:164053,
      author       = {H. Deutelmoser$^*$ and D. Scherer and H. Brenner$^*$ and M.
                      Waldenberger and K. Suhre and G. Kastenmüller and J.
                      Lorenzo Bermejo},
      collaboration = {I. study},
      title        = {{R}obust {H}uber-{LASSO} for improved prediction of
                      protein, metabolite and gene expression levels relying on
                      individual genotype data.},
      journal      = {Briefings in bioinformatics},
      volume       = {22},
      number       = {4},
      issn         = {1477-4054},
      address      = {Oxford [u.a.]},
      publisher    = {Oxford University Press},
      reportid     = {DKFZ-2020-02221},
      pages        = {bbaa230},
      year         = {2021},
      note         = {#EA:C120#},
      abstract     = {Least absolute shrinkage and selection operator (LASSO)
                      regression is often applied to select the most promising set
                      of single nucleotide polymorphisms (SNPs) associated with a
                      molecular phenotype of interest. While the penalization
                      parameter λ restricts the number of selected SNPs and the
                      potential model overfitting, the least-squares loss function
                      of standard LASSO regression translates into a strong
                      dependence of statistical results on a small number of
                      individuals with phenotypes or genotypes divergent from the
                      majority of the study population-typically comprised of
                      outliers and high-leverage observations. Robust methods have
                      been developed to constrain the influence of divergent
                      observations and generate statistical results that apply to
                      the bulk of study data, but they have rarely been applied to
                      genetic association studies. In this article, we review, for
                      newcomers to the field of robust statistics, a novel version
                      of standard LASSO that utilizes the Huber loss function. We
                      conduct comprehensive simulations and analyze real protein,
                      metabolite, mRNA expression and genotype data to compare the
                      stability of penalization, the cross-iteration concordance
                      of the model, the false-positive and true-positive rates and
                      the prediction accuracy of standard and robust Huber-LASSO.
                      Although the two methods showed controlled false-positive
                      rates $≤2.1\%$ and similar true-positive rates, robust
                      Huber-LASSO outperformed standard LASSO in the accuracy of
                      predicted protein, metabolite and gene expression levels
                      using individual SNP data. The conducted simulations and
                      real-data analyses show that robust Huber-LASSO represents a
                      valuable alternative to standard LASSO in genetic studies of
                      molecular phenotypes.},
      subtyp        = {Review Article},
      cin          = {C120 / C070},
      ddc          = {004},
      cid          = {I:(DE-He78)C120-20160331 / I:(DE-He78)C070-20160331},
      pnm          = {313 - Krebsrisikofaktoren und Prävention (POF4-313)},
      pid          = {G:(DE-HGF)POF4-313},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:33063116},
      doi          = {10.1093/bib/bbaa230},
      url          = {https://inrepo02.dkfz.de/record/164053},
}