Epistatic Features and Machine Learning Improve Alzheimer's Disease Risk Prediction Over Polygenic Risk Scores.

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.

Epistatic Features and Machine Learning Improve Alzheimer's Risk Prediction Over Polygenic Risk Scores.

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 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 lifetime risk for LOAD. Methods: We construct a new state-of-the-art genetic model for lifetime 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 machine learning models (gradient boosting machines and deep learning) instead of simple logistic regression. We compare the paragenic model to a PRS model from the literature trained on the same dataset. Results: The paragenic model is significantly more accurate than the PRS model under 10-fold cross-validation, obtaining an AUC of 83% and near-clinically significant matched sensitivity/specificity of 75%, and remains significantly more accurate when evaluated on an independent holdout dataset. Additionally, the paragenic model maintains accuracy within APOE genotypes. Conclusion: Paragenic models show potential for improving lifetime disease risk prediction for complex heritable diseases such as LOAD over PRS models.

Northeastern Asian and Jomon-related genetic structure in the Three Kingdoms period of Gimhae, Korea.

The genetic history of prehistoric and protohistoric Korean populations is not well understood because only a small number of ancient genomes are available. Here, we report the first paleogenomic data from the Korean Three Kingdoms period, a crucial point in the cultural and historic formation of Korea. These data comprise eight shotgun-sequenced genomes from ancient Korea (0.7×-6.1× coverage). They were derived from two archeological sites in Gimhae: the Yuha-ri shell mound and the Daesung-dong tumuli, the latter being the most important funerary complex of the Gaya confederacy. All individuals are from between the 4th and 5th century CE and are best modeled as an admixture between a northern China Bronze Age genetic source and a source of Jomon-related ancestry that shares similarities with the present-day genomes from Japan. The observed substructure and proportion of Jomon-related ancestry suggest the presence of two genetic groups within the population and diversity among the Gaya population. We could not correlate the genomic differences between these two groups with either social status or sex. All the ancient individuals' genomic profiles, including phenotypically relevant SNPs associated with hair and eye color, facial morphology, and myopia, imply strong genetic and phenotypic continuity with modern Koreans for the last 1,700 years.