Transition-transversion encoding and genetic relationship metric in ReliefF feature selection improves pathway enrichment in GWAS

Mutations in Growth-Related Genes Induced by EMS Treatment in Scallops

Background: The goal of genetic breeding is to select variants with mutations that are related to expected traits, such as fast growth. Artificial induction has been widely used to obtain strains with more mutations for further selection. Ethylmethylsulfone (EMS) is one of the most commonly used chemical mutagens in plant and microorganism breeding. However, the application of EMS mutagenesis in shellfish has not been reported. The aim of this study is to evaluate the potential use of EMS as a mutagen in scallop breeding, especially in characterization of mutations in growth-related genes. Results: Our results indicated that hatching of about 50% of fertilized eggs was blocked by treatment with 20 mM EMS for 3 h and the resulted larvae developed normally into adult stages. We then evaluated the mutagenic effects of EMS by sequencing the genomes of 4 adult scallops from the control group and 12 from the treatment group at 8 months after fertilization. On average, after removing shared types of mutations, there were 1,151,380 ± 258,188 SNPs (Single Nucleotide Polymorphisms) and 229,256 ± 51,714 InDels (insertion-deletion) in each animal in the EMS treatment group, while there were only134841 ± 10,115 SNPs and 42,605 ± 5,136 InDels in the control group. The average mutation rate in the genome of the EMS treatment group (0.0137 ± 0.0013%) was about 9 times that of the control group (0.0015 ± 0.0002%). GO (Gene Ontology) annotation and KEGG (Kyoto Encyclopedia of Genes and Genomes) enrichment analyses revealed that mutations induced by EMS occurred evenly in most biological processes, cellular components and functions, as well in most pathways. However, significant lower percentage of mutations were found in the exonic region, in non-synonymous or Stopgain/Stoploss SNPs and in coding domains, suggesting apparent DNA repair or selection during grow-out stage. Analyses of the growth-related genes with mutations indicated that mutations in MFS (Major Facilitator Superfamily) and Tubulin were only found in the large-sized group (Five largest scallops: Treated-1, Treated-2, Treated-3, Treated-4, and Treated-5) and Homeobox and Socs (Suppressor of cytokine signaling) only in the small group (Two smallest scallops: Treated-11 and Treated-12). These results suggested that these genes may be involved in the regulation of growth in these animals, although further verification is certainly warranted. Conclusion: Treatment of fertilized eggs with 20 mM EMS for 3 h induced 9 times more mutations in scallop genomes. We found that mutations in MFS and Tubulin may be related to fast growth in the large-sized group and those mutations in Homeobox and SOCs may be involved in the slow growth in the small-sized scallops. EMS can be used to accelerate selection of economically important traits in molluscs.

Brief Survey on Machine Learning in Epistasis

In biology, the term "epistasis" indicates the effect of the interaction of a gene with another gene. A gene can interact with an independently sorted gene, located far away on the chromosome or on an entirely different chromosome, and this interaction can have a strong effect on the function of the two genes. These changes then can alter the consequences of the biological processes, influencing the organism's phenotype. Machine learning is an area of computer science that develops statistical methods able to recognize patterns from data. A typical machine learning algorithm consists of a training phase, where the model learns to recognize specific trends in the data, and a test phase, where the trained model applies its learned intelligence to recognize trends in external data. Scientists have applied machine learning to epistasis problems multiple times, especially to identify gene-gene interactions from genome-wide association study (GWAS) data. In this brief survey, we report and describe the main scientific articles published in data mining and epistasis. Our article confirms the effectiveness of machine learning in this genetics subfield.

Theoretical properties of distance distributions and novel metrics for nearest-neighbor feature selection

The performance of nearest-neighbor feature selection and prediction methods depends on the metric for computing neighborhoods and the distribution properties of the underlying data. Recent work to improve nearest-neighbor feature selection algorithms has focused on new neighborhood estimation methods and distance metrics. However, little attention has been given to the distributional properties of pairwise distances as a function of the metric or data type. Thus, we derive general analytical expressions for the mean and variance of pairwise distances for L_q metrics for normal and uniform random data with p attributes and m instances. The distribution moment formulas and detailed derivations provide a resource for understanding the distance properties for metrics and data types commonly used with nearest-neighbor methods, and the derivations provide the starting point for the following novel results. We use extreme value theory to derive the mean and variance for metrics that are normalized by the range of each attribute (difference of max and min). We derive analytical formulas for a new metric for genetic variants, which are categorical variables that occur in genome-wide association studies (GWAS). The genetic distance distributions account for minor allele frequency and the transition/transversion ratio. We introduce a new metric for resting-state functional MRI data (rs-fMRI) and derive its distance distribution properties. This metric is applicable to correlation-based predictors derived from time-series data. The analytical means and variances are in strong agreement with simulation results. We also use simulations to explore the sensitivity of the expected means and variances in the presence of correlation and interactions in the data. These analytical results and new metrics can be used to inform the optimization of nearest neighbor methods for a broad range of studies, including gene expression, GWAS, and fMRI data.

Nearest-Neighbor Projected Distance Regression for Epistasis Detection in GWAS With Population Structure Correction

Nearest-neighbor Projected-Distance Regression (NPDR) is a feature selection technique that uses nearest-neighbors in high dimensional data to detect complex multivariate effects including epistasis. NPDR uses a regression formalism that allows statistical significance testing and efficient control for multiple testing. In addition, the regression formalism provides a mechanism for NPDR to adjust for population structure, which we apply to a GWAS of systemic lupus erythematosus (SLE). We also test NPDR on benchmark simulated genetic variant data with epistatic effects, main effects, imbalanced data for case-control design and continuous outcomes. NPDR identifies potential interactions in an epistasis network that influences the SLE disorder.

Nearest-neighbor Projected-Distance Regression (NPDR) for detecting network interactions with adjustments for multiple tests and confounding

SUMMARY

Machine learning feature selection methods are needed to detect complex interaction-network effects in complicated modeling scenarios in high-dimensional data, such as GWAS, gene expression, eQTL and structural/functional neuroimage studies for case-control or continuous outcomes. In addition, many machine learning methods have limited ability to address the issues of controlling false discoveries and adjusting for covariates. To address these challenges, we develop a new feature selection technique called Nearest-neighbor Projected-Distance Regression (NPDR) that calculates the importance of each predictor using generalized linear model regression of distances between nearest-neighbor pairs projected onto the predictor dimension. NPDR captures the underlying interaction structure of data using nearest-neighbors in high dimensions, handles both dichotomous and continuous outcomes and predictor data types, statistically corrects for covariates, and permits statistical inference and penalized regression. We use realistic simulations with interactions and other effects to show that NPDR has better precision-recall than standard Relief-based feature selection and random forest importance, with the additional benefit of covariate adjustment and multiple testing correction. Using RNA-Seq data from a study of major depressive disorder (MDD), we show that NPDR with covariate adjustment removes spurious associations due to confounding. We apply NPDR to eQTL data to identify potentially interacting variants that regulate transcripts associated with MDD and demonstrate NPDR's utility for GWAS and continuous outcomes.

AVAILABILITY AND IMPLEMENTATION

Available at: https://insilico.github.io/npdr/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.