Smooth-Threshold Multivariate Genetic Prediction with Unbiased Model Selection

Smooth-threshold multivariate genetic prediction incorporating gene–environment interactions

We propose a genetic prediction modeling approach for genome-wide association study (GWAS) data that can include not only marginal gene effects but also gene–environment (GxE) interaction effects—i.e., multiplicative effects of environmental factors with genes rather than merely additive effects of each. The proposed approach is a straightforward extension of our previous multiple regression-based method, STMGP (smooth-threshold multivariate genetic prediction), with the new feature being that genome-wide test statistics from a GxE interaction analysis are used to weight the corresponding variants. We develop a simple univariate regression approximation to the GxE interaction effect that allows a direct fit of the STMGP framework without modification. The sparse nature of our model automatically removes irrelevant predictors (including variants and GxE combinations), and the model is able to simultaneously incorporate multiple environmental variables. Simulation studies to evaluate the proposed method in comparison with other modeling approaches demonstrate its superior performance under the presence of GxE interaction effects. We illustrate the usefulness of our prediction model through application to real GWAS data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI).

An Improved Stacked Autoencoder for Metabolomic Data Classification

Naru3 (NR) is a traditional Mongolian medicine with high clinical efficacy and low incidence of side effects. Metabolomics is an approach that can facilitate the development of traditional drugs. However, metabolomic data have a high throughput, sparse, high-dimensional, and small sample nature, and their classification is challenging. Although deep learning methods have a wide range of applications, deep learning-based metabolomic studies have not been widely performed. We aimed to develop an improved stacked autoencoder (SAE) for metabolomic data classification. We established an NR-treated rheumatoid arthritis (RA) mouse model and classified the obtained metabolomic data using the Hessian-free SAE (HF-SAE) algorithm. During training, the unlabeled data were used for pretraining, and the labeled data were used for fine-tuning based on the HF algorithm for gradient descent optimization. The hybrid algorithm successfully classified the data. The results were compared with those of the support vector machine (SVM), k-nearest neighbor (KNN), and gradient descent SAE (GD-SAE) algorithms. A five-fold cross-validation was used to complete the classification experiment. In each fine-tuning process, the mean square error (MSE) and misclassification rates of the training and test data were recorded. We successfully established an NR animal model and an improved SAE for metabolomic data classification.

Machine learning for effectively avoiding overfitting is a crucial strategy for the genetic prediction of polygenic psychiatric phenotypes

The accuracy of previous genetic studies in predicting polygenic psychiatric phenotypes has been limited mainly due to the limited power in distinguishing truly susceptible variants from null variants and the resulting overfitting. A novel prediction algorithm, Smooth-Threshold Multivariate Genetic Prediction (STMGP), was applied to improve the genome-based prediction of psychiatric phenotypes by decreasing overfitting through selecting variants and building a penalized regression model. Prediction models were trained using a cohort of 3685 subjects in Miyagi prefecture and validated with an independently recruited cohort of 3048 subjects in Iwate prefecture in Japan. Genotyping was performed using HumanOmniExpressExome BeadChip Arrays. We used the target phenotype of depressive symptoms and simulated phenotypes with varying complexity and various effect-size distributions of risk alleles. The prediction accuracy and the degree of overfitting of STMGP were compared with those of state-of-the-art models (polygenic risk scores, genomic best linear-unbiased prediction, summary-data-based best linear-unbiased prediction, BayesR, and ridge regression). In the prediction of depressive symptoms, compared with the other models, STMGP showed the highest prediction accuracy with the lowest degree of overfitting, although there was no significant difference in prediction accuracy. Simulation studies suggested that STMGP has a better prediction accuracy for moderately polygenic phenotypes. Our investigations suggest the potential usefulness of STMGP for predicting polygenic psychiatric conditions while avoiding overfitting.

Artificial intelligence powered statistical genetics in biobanks

Large-scale, sometimes nationwide, prospective genomic cohorts biobanking rich biological specimens such as blood, urine and tissues, have been established and released their vast amount of data in several countries. These genetic and epidemiological resources are expected to allow investigators to disentangle genetic and environmental components conferring common complex diseases. There are, however, two major challenges to statistical genetics for this goal: small sample size-high dimensionality and multilayered-heterogenous endophenotypes. Rather counterintuitively, biobank data generally have small sample size relative to their data dimensionality consisting of genomic variation, lifestyle questionnaire, and sometimes their interaction. This is a widely acknowledged difficulty in data analysis, so-called "p»n problem" in statistics or "curse of dimensionality" in machine-learning field. On the other hand, we have too many measurements of individual health status, which are endophenotypes, such as health check-up data, images, psychological test scores in addition to metabolomics and proteomics data. These endophenotypes are rich but not so tractable because of their worsen dimensionality, and substantial correlation, sometimes confusing causation among them. We have tried to overcome the problems inherent to biobank data, using statistical machine-learning and deep-learning technologies.

Establishment of Integrated Biobank for Precision Medicine and Personalized Healthcare: The Tohoku Medical Megabank Project

The Tohoku Medical Megabank (TMM) project was established to provide creative reconstruction of the Tohoku area that suffered from a huge earthquake and ensuing tsunami (the Great East Japan Earthquake, GEJE). TMM aims to establish two large-scale genome cohorts and an integrated biobank managing biospecimen and related information. It supports community medicine by establishing next-generation medical systems through a combination of the prospective genome cohort studies with a total of 150,000 participants and genomic medicine. The strategies for genome analyses in TMM are to develop an elaborate genome reference panel by means of high-fidelity Japanese whole-genome sequence, to design custom single nucleotide polymorphism (SNP) arrays based on the reference panel, and to obtain genotype data for all the TMM cohort participants subsequently. Disease-associated genomic information and omics data, including metabolomics and microbiome analysis, provide an essential platform for precision medicine and personalized healthcare (PHC). Ethical, legal, and social issues (ELSI) and education are important for implementing genomic medicine. The major considerations of ELSI regarding each participant of the cohort studies are the respect for the autonomy and the protection of privacies. Moreover, developing and provide human resources not only for the TMM project but also for the social implementation of precision medicine and PHC is required. We started a pilot study of the return of genomic results for familial hypercholesterolemia (FH) as a target disease. TMM aims to establish solid platforms that support precision medicine and PHC based on the genomic and omics information and environmental and lifestyle factors of the individuals, which is one of the most advanced medical care beyond the evidenced-based medicine in the near future.

Genome analyses for the Tohoku Medical Megabank Project towards establishment of personalized healthcare

Personalized healthcare (PHC) based on an individual's genetic make-up is one of the most advanced, yet feasible, forms of medical care. The Tohoku Medical Megabank (TMM) Project aims to combine population genomics, medical genetics and prospective cohort studies to develop a critical infrastructure for the establishment of PHC. To date, a TMM CommCohort (adult general population) and a TMM BirThree Cohort (birth+three-generation families) have conducted recruitments and baseline surveys. Genome analyses as part of the TMM Project will aid in the development of a high-fidelity whole-genome Japanese reference panel, in designing custom single-nucleotide polymorphism (SNP) arrays specific to Japanese, and in estimation of the biological significance of genetic variations through linked investigations of the cohorts. Whole-genome sequencing from >3,500 unrelated Japanese and establishment of a Japanese reference genome sequence from long-read data have been done. We next aim to obtain genotype data for all TMM cohort participants (>150,000) using our custom SNP arrays. These data will help identify disease-associated genomic signatures in the Japanese population, while genomic data from TMM BirThree Cohort participants will be used to improve the reference genome panel. Follow-up of the cohort participants will allow us to test the genetic markers and, consequently, contribute to the realization of PHC.

Prediction of treatment response in rheumatoid arthritis patients using genome-wide SNP data

Although a number of treatments are available for rheumatoid arthritis (RA), each of them shows a significant nonresponse rate in patients. Therefore, predicting a priori the likelihood of treatment response would be of great patient benefit. Here, we conducted a comparison of a variety of statistical methods for predicting three measures of treatment response, between baseline and 3 or 6 months, using genome-wide SNP data from RA patients available from the MAximising Therapeutic Utility in Rheumatoid Arthritis (MATURA) consortium. Two different treatments and 11 different statistical methods were evaluated. We used 10-fold cross validation to assess predictive performance, with nested 10-fold cross validation used to tune the model hyperparameters when required. Overall, we found that SNPs added very little prediction information to that obtained using clinical characteristics only, such as baseline trait value. This observation can be explained by the lack of strong genetic effects and the relatively small sample sizes available; in analysis of simulated and real data, with larger effects and/or larger sample sizes, prediction performance was much improved. Overall, methods that were consistent with the genetic architecture of the trait were able to achieve better predictive ability than methods that were not. For treatment response in RA, methods that assumed a complex underlying genetic architecture achieved slightly better prediction performance than methods that assumed a simplified genetic architecture.

An adaptive threshold determination method of feature screening for genomic selection

Background

Although the dimension of the entire genome can be extremely large, only a parsimonious set of influential SNPs are correlated with a particular complex trait and are important to the prediction of the trait. Efficiently and accurately selecting these influential SNPs from millions of candidates is in high demand, but poses challenges. We propose a backward elimination iterative distance correlation (BE-IDC) procedure to select the smallest subset of SNPs that guarantees sufficient prediction accuracy, while also solving the unclear threshold issue for traditional feature screening approaches.

Results

Verified through six simulations, the adaptive threshold estimated by the BE-IDC performed uniformly better than fixed threshold methods that have been used in the current literature. We also applied BE-IDC to an Arabidopsis thaliana genome-wide data. Out of 216,130 SNPs, BE-IDC selected four influential SNPs, and confirmed the same FRIGIDA gene that was reported by two other traditional methods.

Conclusions

BE-IDC accommodates both the prediction accuracy and the computational speed that are highly demanded in the genomic selection.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-017-1617-9) contains supplementary material, which is available to authorized users.