Imputing missing genotypic data of single-nucleotide polymorphisms using neural networks

Abstract

With advances in high-throughput single-nucleotide polymorphism (SNP) genotyping, the amount of genotype data available for genetic studies is steadily increasing, and with it comes new abilities to study multigene interactions as well as to develop higher dimensional genetic models that more closely represent the polygenic nature of common disease risk. The combined impact of even small amounts of missing data on a multi-SNP analysis may be considerable. In this study, we present a neural network method for imputing missing SNP genotype data. We compared its imputation accuracy with fastPHASE and an expectation-maximization algorithm implemented in HelixTree. In a simulation data set of 1000 SNPs and 1000 subjects, 1, 5 and 10% of genotypes were randomly masked. Four levels of linkage disequilibrium (LD), LD R 2 o0.2, R 2 o0.5, R 2 o0.8 and no LD threshold, were examined to evaluate the impact of LD on imputation accuracy. All three methods are capable of imputing most missing genotypes accurately (accuracy 486%). The neural network method accurately predicted 92.0-95.9% of the missing genotypes. In a real data set comparison with 419 subjects and 126 SNPs from chromosome 2, the neural network method achieves the highest imputation accuracies 483.1% with missing rate from 1 to 5%. Using 90 HapMap subjects with 1962 SNPs, fastPHASE had the highest accuracy (B97%) while the other two methods had 495% accuracy. These results indicate that the neural network model is an accurate and convenient tool, requiring minimal parameter tuning for SNP data recovery, and provides a valuable alternative to usual complete-case analysis.

Application of machine learning algorithms to predict coronary artery calcification with a sibship‐based design

“…Missing genotypes were computed through the 20-SNP haplotypes with EM convergence tolerance of 0.001 and maximum EM iteration number of 50. In a simulation study, this method achieved imputation accuracy above 95% with missing rates ranging from 1 to 10% [Sun and Kardia, 2008]. The same complete data set was analyzed with Random Forests and RuleFit methods.…”

Utilizing Genotype Imputation for the Augmentation of Sequence Data

“…As a result of LD, a disease-susceptibility SNP need not be genotyped, as long as it is “tagged” by a SNP or set of SNPs that are genotyped (i.e., SNPs in LD with the disease-susceptibility SNP are genotyped). Recently this concept has been further exploited by the introduction of methods to impute genotypes at untyped markers, based on genotypes at typed markers and information about LD within the region [3], [4], [5], [6], [7], [8], [9], [10], [11], [12]. These methods are particularly useful in the context of failed genotyping and combining data across multiple platforms and recently have been extended to untyped markers using a reference data set [8], [10], [11].…”

Radial Basis Function Networks

“…In Sun and Kardia (2008), the authors employ an Artificial Neural Networks based method for imputing the MVs artificially generated over genotype data. Pisoni, Pastor, and Volta (2008) also use Artificial Neural Networks for interpolating missing satellite data.…”