Menu

Javascript is not activated in your browser. This website needs javascript activated to work properly.
You are here

An Object-Oriented Regression for Building Disease Predictive Models with Multiallelic HLA Genes

Author:
  • Lue Ping Zhao
  • Hamid Bolouri
  • Michael Zhao
  • Daniel E. Geraghty
  • Åke Lernmark
Publishing year: 2016-05-01
Language: English
Pages: 315-332
Publication/Series: Genetic Epidemiology
Volume: 40
Issue: 4
Document type: Journal article
Publisher: John Wiley & Sons

Abstract english

Recent genome-wide association studies confirm that human leukocyte antigen (HLA) genes have the strongest associations with several autoimmune diseases, including type 1 diabetes (T1D), providing an impetus to reduce this genetic association to practice through an HLA-based disease predictive model. However, conventional model-building methods tend to be suboptimal when predictors are highly polymorphic with many rare alleles combined with complex patterns of sequence homology within and between genes. To circumvent this challenge, we describe an alternative methodology; treating complex genotypes of HLA genes as "objects" or "exemplars," one focuses on systemic associations of disease phenotype with "objects" via similarity measurements. Conceptually, this approach assigns disease risks base on complex genotype profiles instead of specific disease-associated genotypes or alleles. Effectively, it transforms large, discrete, and sparse HLA genotypes into a matrix of similarity-based covariates. By the Kernel representative theorem and machine learning techniques, it uses a penalized likelihood method to select disease-associated exemplars in building predictive models. To illustrate this methodology, we apply it to a T1D study with eight HLA genes (HLA-DRB1, HLA-DRB3, HLA-DRB4, HLA-DRB5, HLA-DQA1, HLA-DQB1, HLA-DPA1, and HLA-DPB1) to build a predictive model. The resulted predictive model has an area under curve of 0.92 in the training set, and 0.89 in the validating set, indicating that this methodology is useful to build predictive models with complex HLA genotypes.

Keywords

  • Endocrinology and Diabetes
  • Medical Genetics
  • Generalized linear model
  • Kernel machine
  • Multiallelic genotypes
  • Penalized regression
  • Prediction
  • Similarity regression
  • Statistical learning

Other

Published
  • Diabetes and Celiac Unit
  • ISSN: 0741-0395
E-mail: ake [dot] lernmark [at] med [dot] lu [dot] se

Principal investigator

Diabetes and Celiac Unit

+46 40 39 19 01

+46 70 616 47 79

60:11:015

Jan Waldenströms gata 35, Malmö

33

Lund University Diabetes Centre, CRC, SUS Malmö, Jan Waldenströms gata 35, House 91:12. SE-214 28 Malmö. Telephone: +46 40 39 10 00