Large-scale genetic studies of common human diseases have focused almost exclusively on the independent main effects of single-nucleotide polymorphisms (SNPs) on disease susceptibility. These studies have had some success, but much of the genetic architecture of common disease remains unexplained. Attention is now turning to detecting SNPs that impact disease susceptibility in the context of other genetic factors and environmental exposures. These context-dependent genetic effects can manifest themselves as non-additive interactions, which are more challenging to model using parametric statistical approaches. The dimensionality that results from a multitude of genotype combinations, which results from considering many SNPs simultaneously, renders these approaches underpowered. We previously developed the multifactor dimensionality reduction (MDR) approach as a nonparametric and genetic model-free machine learning alternative. Approaches such as MDR can improve the power to detect gene-gene interactions but are limited in their ability to exhaustively consider SNP combinations in genome-wide association studies (GWAS), due to the combinatorial explosion of the search space. We introduce here a stochastic search algorithm called Crush for the application of MDR to modeling high-order gene-gene interactions in genome-wide data. The Crush-MDR approach uses expert knowledge to guide probabilistic searches within a framework that capitalizes on the use of biological knowledge to filter gene sets prior to analysis. Here we evaluated the ability of Crush-MDR to detect hierarchical sets of interacting SNPs using a biology-based simulation strategy that assumes non-additive interactions within genes and additivity in genetic effects between sets of genes within a biochemical pathway. We show that Crush-MDR is able to identify genetic effects at the gene or pathway level significantly better than a baseline random search with the same number of model evaluations. We then applied the same methodology to a GWAS for Alzheimer’s disease and showed base level validation that Crush-MDR was able to identify a set of interacting genes with biological ties to Alzheimer’s disease. We discuss the role of stochastic search and cloud computing for detecting complex genetic effects in genome-wide data.

Background: Polygenic risk scores (PRS) are linear combinations of genetic markers weighted by effect size that are commonly used to predict disease risk. For complex heritable diseases such as late-onset Alzheimer’s disease (LOAD), PRS models fail to capture much of the heritability. Additionally, PRS models are highly dependent on the population structure of the data on which effect sizes are assessed and have poor generalizability to new data. Objective: The goal of this study is to construct a paragenic risk score that, in addition to single genetic marker data used in PRS, incorporates epistatic interaction features and machine learning methods to predict risk for LOAD. Methods: We construct a new state-of-the-art genetic model for risk of Alzheimer’s disease. Our approach innovates over PRS models in two ways: First, by directly incorporating epistatic interactions between SNP loci using an evolutionary algorithm guided by shared pathway information; and second, by estimating risk via an ensemble of non-linear machine learning models rather than a single linear model. We compare the paragenic model to several PRS models from the literature trained on the same dataset. Results: The paragenic model is significantly more accurate than the PRS models under 10-fold cross-validation, obtaining an AUC of 83% and near-clinically significant matched sensitivity/specificity of 75%. It remains significantly more accurate when evaluated on an independent holdout dataset and maintains accuracy within APOE genotype strata. Conclusions: Paragenic models show potential for improving disease risk prediction for complex heritable diseases such as LOAD over PRS models.

Background/Objectives: To identify US military unknowns, the Armed Forces Medical Examiner System’s Armed Forces DNA Identification Laboratory has historically relied upon mitochondrial DNA and Y-chromosomal short tandem repeat testing. Where no appropriate family reference sample (FRS) is available or skeletal samples are degraded, autosomal single nucleotide polymorphism (SNP) testing with next-generation sequencing could assist. Methods: A method utilizing hybridization capture enrichment of a 95,000 (95K) SNP panel, amenable to FRS and extremely challenging samples, was validated. The Parabon Fx Forensic Analysis Platform was used for analysis and extended kinship inference. Skeletal samples (n = 65) and associated FRS (n = 64) were selected for a performance evaluation and case-type sample study. Results: Considering FRS with ≥7 ng DNA input into library preparation, 94% yielded ≥66,320 SNPs at ≥5X coverage. SNP recovery for skeletal samples at ≥1X coverage ranged from 5 to 94,197 SNPs, averaging 40,770 SNPs. When skeletal samples resulted in ≥13,000 SNPs, the most likely relationship category was consistent with the expected relationship. A log10 likelihood ratio of ≥4 and a posterior probability of ≥99.99% were established as thresholds for strong statistical support, and 87% of inferences met these thresholds while 13% were considered inconclusive. Pairwise kinship inference between unrelated individuals yielded an unrelated result in 85% of comparisons, 66% with strong statistical support. There were 170 instances of false positive 4th degree relationship inferences with strong statistical support. All false positives involved skeletal samples from individuals of admixed ancestry. Conclusions: With this approach, autosomal SNP testing can result in reliable kinship inferences between related individuals out to 3rd, and in some cases 4th, degree relationships, increasing the scope of eligible FRS to aid in identifications.