• Publications
  • Influence
FaST linear mixed models for genome-wide association studies
TLDR
We describe factored spectrally transformed linear mixed models (FaST-LMM), an algorithm for genome-wide association studies that scales linearly with cohort size in both run time and memory use. Expand
  • 790
  • 83
  • PDF
Improved linear mixed models for genome-wide association studies
to determine these similarities1. Here, however, we show theoretically and experimentally that carefully selecting a small number of SNPs systematically increases power (that is, it jointly reducesExpand
  • 325
  • 27
Multiple Alignment of Continuous Time Series
TLDR
We present the Continuous Profile Model (CPM), a generative model in which each observed time series is a non-uniformly subsampled version of a single latent trace, to which local rescaling and additive noise are applied. Expand
  • 153
  • 17
  • PDF
Gaussian Process Prior Variational Autoencoders
TLDR
We introduce a new model, the Gaussian Process (GP) Prior Variational Autoencoder (GPPVAE), to combine the power of VAEs with the ability to model correlations afforded by GP priors. Expand
  • 31
  • 10
  • PDF
Difference detection in LC-MS data for protein biomarker discovery
TLDR
In this paper we present a technique for discovering differences in protein signal between two classes of samples of LC-MS serum proteomic data without use of tandem mass spectrometry, gels or labeling. Expand
  • 90
  • 9
  • PDF
Correction for hidden confounders in the genetic analysis of gene expression
TLDR
We present a statistical framework for joint correction of population structure and EH in eQTL studies showing that such a correction is needed and that other models that might naturally be applied to this problem do not perform well. Expand
  • 142
  • 9
  • PDF
A powerful and efficient set test for genetic markers that handles confounders
TLDR
We introduce a new, powerful and computation- ally efficient likelihood ratio-based set test that accounts for rich confounding structure. Expand
  • 72
  • 9
  • PDF
Leveraging Information Across HLA Alleles/Supertypes Improves Epitope Prediction
TLDR
We present a model for predicting HLA class I restricted CTL epitopes. Expand
  • 61
  • 5
  • PDF
Determining the Number of Non-Spurious Arcs in a Learned DAG Model: Investigation of a Bayesian and a Frequentist Approach
TLDR
We investigate the use of a Bayesian and a frequentist approach to determining the number of non-spurious arcs in a learned DAG model with discrete variables and known variable ordering. Expand
  • 27
  • 5
  • PDF
Greater power and computational efficiency for kernel-based association testing of sets of genetic variants
TLDR
We compared a standard statistical test—a score test—with a recently developed likelihood ratio (LR) test. Expand
  • 25
  • 5
  • PDF