Genetic Programming Neural Networks: A Powerful Bioinformatics Tool for Human Genetics

The identification of genes that influence the risk of common, complex disease primarily through interactions with other genes and environmental factors remains a statistical and computational challenge in genetic epidemiology. This challenge is partly due to the limitations of parametric statistical methods for detecting genetic effects that are dependent solely or partially on interactions. We have previously introduced a genetic programming neural network (GPNN) as a method for optimizing the architecture of a neural network to improve the identification of genetic and gene-environment combinations associated with disease risk. Previous empirical studies suggest GPNN has excellent power for identifying gene-gene and gene-environment interactions. The goal of this study was to compare the power of GPNN to stepwise logistic regression (SLR) and classification and regression trees (CART) for identifying gene-gene and gene-environment interactions. SLR and CART are standard methods of analysis for genetic association studies. Using simulated data, we show that GPNN has higher power to identify gene-gene and gene-environment interactions than SLR and CART. These results indicate that GPNN may be a useful pattern recognition approach for detecting gene-gene and gene-environment interactions in studies of human disease.     

A new approach to detect epistasis utilizing parallel implementation of ant colony optimization by MapReduce framework

Genome-wide association studies (GWAS) involve the detection and interpretation of epistasis, which is responsible for the ‘missing heritability’ and influences common complex disease susceptibility. Many epistasis detection algorithms cannot be directly applied into GWAS as many combinations of genetic components are present in only a small amount of samples or even none at all. For a huge number of single nucleotide polymorphisms and inappropriate statistical tests, epistasis detection remains a computational and statistical challenge in genetic epidemiology. Here, we develop a novel method to identify epistatic interactions related to disease susceptibility utilizing an ant colony optimization strategy implemented by Google's MapReduce platform. We incorporate expert knowledge used to guide ants to make the best choice in the search process into the pheromone updating rule. We conduct sufficient experiments using simulated and real genome-wide data sets and experimental results demonstrate excellent performance of our algorithm compared with its competitors.     

EpiMiner: A three-stage co-information based method for detecting and visualizing epistatic interactions

Detecting and visualizing nonlinear interactive effects of Single Nucleotide Polymorphisms (SNPs) or epistatic interactions are important topics of signal processing having great mathematical and computational challenges. To address these problems, a three-stage method, epiMiner (epistasis Miner), is proposed based on co-information theory. In screening stage, Co-Information Index (CII) is employed to visualize and rank contributions of individual SNPs to the phenotype, with the number of top ranking SNPs retained to next stage specified by users directly or a support vector machine classifier automatically. In testing stage, co-information and co-information based permutation test are conducted sequentially to search epistatic interactions within the retained SNPs, with the results then ranked by their p-values. For further characterizing broader epistasis landscape, a visualizing stage is designed to dynamically construct epistasis networks by linking pairs of the retained SNPs if their co-information values with respect to the phenotype are stronger than thresholds. The performance of epiMiner is compared with existing methods on a diverse range of simulated data sets containing several epistasis models. Results demonstrate that epiMiner is effective in detecting and visualizing epistatic interactions. In addition, the application of epiMiner on a real Age-related Macular Degeneration (AMD) data set provides several new clues for the exploration of causative factors of AMD. The Matlab version of epiMiner software is available free online at https://sourceforge.net/projects/epiminer/files/.     

Finding susceptible and protective interaction patterns in large-scale genetic association study

Interaction detection in large-scale genetic association studies has attracted intensive research interest, since many diseases have complex traits. Various approaches have been developed for finding significant genetic interactions. In this article, we propose a novel framework SRMiner to detect interacting susceptible and protective genotype patterns. SRMiner can discover not only probable combination of single nucleotide polymorphisms (SNPs) causing diseases but also the corresponding SNPs suppressing their pathogenic functions, which provides a better prospective to uncover the underlying relevance between genetic variants and complex diseases. We have performed extensive experiments on several real Wellcome Trust Case Control Consortium (WTCCC) datasets. We use the pathway-based and the protein-protein interaction (PPI) network-based evaluation methods to verify the discovered patterns. The results show that SRMiner successfully identifies many disease-related genes verified by the existing work. Furthermore, SRMiner can also infer some uncomfirmed but highly possible disease-related genes.     

Evolving cellular automata to generate nonlinear sequences with desirable properties

This paper presents a new chromosomal representation and associated genetic operators for the evolution of highly nonlinear cellular automata that generate pseudorandom number sequences with desirable properties ensured. This chromosomal representation reduces the computational complexity of genetic operators to evolve valid solutions while facilitating fitness evaluation based on the DIEHARD statistical tests.     

Fiuncho: a program for any-order epistasis detection in CPU clusters

Epistasis can be defined as the statistical interaction of genes during the expression of a phenotype. It is believed that it plays a fundamental role in gene expression, as individual genetic variants have reported a very small increase in disease risk in previous Genome-Wide Association Studies. The most successful approach to epistasis detection is the exhaustive method, although its exponential time complexity requires a highly parallel implementation in order to be used. This work presents Fiuncho, a program that exploits all levels of parallelism present in x86_64 CPU clusters in order to mitigate the complexity of this approach. It supports epistasis interactions of any order, and when compared with other exhaustive methods, it is on average 358, 7 and 3 times faster than MDR, MPI3SNP and BitEpi, respectively.

     

Genetic Algorithms for Solving a Class of Constrained Nonlinear Integer Programs

We consider a class of constrained nonlinear integer programs, which arise in manufacturing batch-sizing problems with multiple raw materials. In this paper, we investigate the use of genetic algorithms (GAs) for solving these models. Both binary and real coded genetic algorithms with six different penalty functions are developed. The real coded genetic algorithm works well for all six penalty functions compared to binary coding. A new method to calculate the penalty coefficient is also discussed. Numerical examples are provided and computational experiences are discussed.     

基于U统计量和集成学习的基因互作检测方法

在全基因组关联研究GWAS中,多数方法对疾病与单核苷酸多态性位点之间的互作关系形式给出了强假设,这降低了相关方法的挖掘能力.近几年,以基因作为研究单位的基因-基因相互作用检测方法,因其在统计效力与生物可解释性方面的优势受到重视.针对已有方法检测相互作用类型时存在的局限性,提出一种基于U统计值与集成学习器的假设检验方法GBUtrees,通过构造统计量用于表征疾病性状与2个基因之间关系偏离加性模型的程度,检测以基因为单位的基因-基因相互作用.该统计量在不同子样例集下结果的平均值满足U统计量理论,从而可以利用U统计量的渐进正态分布性质获得所构造统计量的分布信息.GBUtrees对相互作用的形式不作假设,增强该方法对不同形式相互作用的挖掘能力.仿真与真实实验结果表明：该方法能够有效地进行不同类型相互作用的挖掘,可以应用于全基因组关联研究.     

Computational expressiveness of Genetic Systems

We introduce Genetic Systems, a formalism inspired by genetic regulatory networks and suitable for modeling the interactions between the genes and the proteins, acting as regulatory products.The generation of new objects, representing proteins, is driven by genetic gates: a new object is produced when all the activator objects are available in the system, and no inhibitor object is available. Activators are not consumed by the application of such an evolution rule. Objects disappear because of degradation: each object is equipped with a lifetime, and the object decays when such a lifetime expires.We investigate the computational expressiveness of Genetic Systems: we show that they are Turing equivalent by providing encodings of Random Access Machines in Genetic Systems.     

Evolving Receptive-Field Controllers for Mobile Robots

The use of evolutionary methods to generate controllers for real-world autonomous agents has attracted recent attention. Most of the pertinent research has employed genetic algorithms or variations thereof. Recent research has applied an alternative evolutionary method, evolution strategies, to the generation of simple Braitenberg vehicles. This application accelerates the development of such controllers by more than an order of magnitude (a few hours compared to more than two days). Motivated by this useful speedup, this paper investigates the evolution of more complex architectures, receptive-field controllers, that can employ nonlinear interactions and, therefore, can yield more complex behavior. It is interesting to note that the evolution strategy yields the same efficacy in terms of function evaluations, even though the second class of controllers requires up to 10 times more parameters than the simple Braitenberg architecture. In addition to the speedup, there is an important theoretical reason for preferring an evolution strategy over a genetic algorithm for this problem, namely the presence of epistasis.     

An Evolutionary Algorithm to Find Associations in Dense Genetic Maps

Discovering the genetic basis of common human diseases will be assisted by large-scale association studies with a large number of individuals and genetic markers, such as single-nucleotide polymorphisms (SNPs). The potential size of the data and the resulting model space require the development of efficient methodology to unravel associations between epidemiological outcomes and SNPs in dense genetic maps. We apply an evolutionary algorithm (EA) to construct models consisting of logic trees. These trees are Boolean expressions involving nodes that contain strings of SNPs in high linkage disequilibrium (LD), that is, SNPs that are highly correlated with each other. At each generation of the algorithm, a population of logic tree models is modified using selection, crossover, and mutation moves. Logic trees are selected for the next generation using a fitness function based on the marginal likelihood in a Bayesian regression framework. Mutation and crossover moves use LD measures to propose changes to the trees, and facilitate the movement through the model space. We demonstrate our method on data from a candidate gene study of quantitative genetic variation.     

基于多步筛选法的心脑血管疾病全基因组关联研究

全基因组关联研究是研究复杂疾病和性状遗传效应的一种有效手段。现有关联分析主要用的是边缘统计检验的方法,但未考虑特征间相关性、阈值选取不稳定等问题。该文以心脑血管疾病为研究对象,提出了一种基于多步筛选法的全基因组关联分析新方法。该方法可以简要概括为以下 两步：首先利用 Gini 指数做特征初始筛选,获得一个候选单核苷酸多态性子集,再用基于随机森林的递归聚类消除法从单核苷酸多态性子集中发现关联单核苷酸多态性。实验结果表明,多步筛选法比单步特征选择的效果更好,基于 Gini 指数的基于随机森林的递归聚类消除法筛选的单核苷酸多态性子集与疾病的关联性更高。     

Simulation of a natural circulation loop using a least squares hp-adaptive solver

In this work the implementation of a high-order method for the simulation of a natural circulation loop is discussed. An adaptive method is developed in order to improve both accuracy and computational time in the resolution of nonlinear problems. Finally, several numerical simulations are discussed in relation to the development of this kind of high-order adaptive methods for unstable thermo-hydraulic systems.     

Intelligent computing for numerical treatment of nonlinear prey–predator models

In this study, a new computing paradigm is presented for evaluation of dynamics of nonlinear prey–predator mathematical model by exploiting the strengths of integrated intelligent mechanism through artificial neural networks, genetic algorithms and interior-point algorithm. In the scheme, artificial neural network based differential equation models of the system are constructed and optimization of the networks is performed with effective global search ability of genetic algorithm and its hybridization with interior-point algorithm for rapid local search. The proposed technique is applied to variants of nonlinear prey–predator models by taking different rating factors and comparison with Adams numerical solver certify the correctness for each scenario. The statistical studies have been conducted to authenticate the accuracy and convergence of the design methodology in terms of mean absolute error, root mean squared error and Nash-Sutcliffe efficiency performance indices.     

AN ENHANCED DETERMINISTIC FUZZY TIME SERIES FORECASTING MODEL

The study of fuzzy time series has attracted great interest and is expected to expand rapidly. Various forecasting models including high-order models have been proposed to improve forecasting accuracy or reducing computational cost. However, there exist two important issues, namely, rule redundancy and high-order redundancy that have not yet been investigated. This article proposes a novel forecasting model to tackle such issues. It overcomes the major hurdle of determining the k-order in high-order models and is enhanced to allow the handling of multi-factor forecasting problems by removing the overhead of deriving all fuzzy logic relationships beforehand. Two novel performance evaluation metrics are also formally derived for comparing performances of related forecasting models. Experimental results demonstrate that the proposed forecasting model outperforms the existing models in efficiency.     

Predicting epistasis from mathematical models

Classically, epistasis is either computed exactly by Walsh coefficients or estimated by sampling. Exact computation is usually of theoretical interest since the computation typically grows exponentially with the number of bits in the domain. Given an evaluation function, epistasis also can be estimated by sampling. However this approach gives us little insight into the origin of the epistasis and is prone to sampling error. This paper presents theorems establishing the bounds of epistasis for problems that can be stated as mathematical expressions. This leads to substantial computational savings for bounding the difficulty of a problem. Furthermore, working with these theorems in a mathematical context, one can gain insight into the mathematical origins of epistasis and how a problem's epistasis might be reduced. We present several new measures for epistasis and give empirical evidence and examples to demonstrate the application of the theorems. In particular, we show that some functions display "parity" such that by picking a well-defined representation, all Walsh coefficients of either odd or even index become zero, thereby reducing the nonlinearity of the function.     

应用遗传算法原理确定函数的最优解

本文主要介绍了一种新型的、随机性的全局优化方法即遗传算法.一般应用于在一个问题的解集中查找最优解情况,如是一个问题有多个答案,但是想查找一个最优答案的话,那么使用遗传算法可以达到更快更好的效果.即在浮点编码遗传算法中加入一个函数,构成适于不可微函数全局优化的遗传算法.该算法改善了遗传算法的局部搜索能力,显著提高了遗传算法求得全局解的概率.     

Fast implementation of a scan statistic for identifying chromosomal patterns of genome wide association studies

In order to take into account the complex genomic distribution of SNP variations when identifying chromosomal regions with significant SNP effects, a single nucleotide polymorphism (SNP) association scan statistic was developed. To address the computational needs of genome wide association (GWA) studies, a fast Java application, which combines single-locus SNP tests and a scan statistic for identifying chromosomal regions with significant clusters of significant SNP effects, was developed and implemented. To illustrate this application, SNP associations were analyzed in a pharmacogenomic study of the blood pressure lowering effect of thiazide-diuretics (N=195) using the Affymetrix Human Mapping 100 K Set. 55,335 tagSNPs (pair-wise linkage disequilibrium R²<0.5) were selected to reduce the frequency correlation between SNPs. A typical workstation can complete the whole genome scan including 10,000 permutation tests within 3 h. The most significant regions locate on chromosome 3, 6, 13 and 16, two of which contain candidate genes that may be involved in the underlying drug response mechanism. The computational performance of ChromoScan-GWA and its scalability were tested with up to 1,000,000 SNPs and up to 4000 subjects. Using 10,000 permutations, the computation time grew linearly in these datasets. This scan statistic application provides a robust statistical and computational foundation for identifying genomic regions associated with disease and provides a method to compare GWA results even across different platforms.     

Genetic regulatory network-based symbiotic evolution

The main theme of this paper is to present a novel evolution, the genetic regulatory network-based symbiotic evolution (GRNSE), to improve the convergent speed and solution accuracy of genetic algorithms. The proposed GRNSE utilizes genetic regulatory network (GRN) reinforcement learning to improve the diversity and symbiotic evolution (SE) initialization to achieve the parallelism. In particular, GRN-based learning increases the global rate by regulating members of genes in symbiotic evolution. To compare the efficiency of the proposed method, we adopt 41 benchmarks that contain many nonlinear and complex optimal problems. The influences of dimension, individual population size, and gene population size are examined. A new control parameter, the population rate is introduced to initiate the ratio between the gene and chromosome. Finally, all the studies of there 41 benchmarks demonstrate that from the statistic point of view, GRNSE give a better convergence speed and a more accurate optimal solution than GA and SE.     

Efficient mining of multilevel gene association rules from microarray and gene ontology

Some recent studies have shown that association rules can reveal the interactions between genes that might not have been revealed using traditional analysis methods like clustering. However, the existing studies consider only the association rules among individual genes. In this paper, we propose a new data mining method named MAGO for discovering the multilevel gene association rules from the gene microarray data and the concept hierarchy of Gene Ontology (GO). The proposed method can efficiently find out the relations between GO terms by analyzing the gene expressions with the hierarchy of GO. For example, with the biological process in GO, some rules like Process A (up) → Process B (up) cab be discovered, which indicates that the genes involved in Process B of GO are likely to be up-regulated whenever those involved in Process A are up-regulated. Moreover, we also propose a constrained mining method named CMAGO for discovering the multilevel gene expression rules with user-specified constraints. Through empirical evaluation, the proposed methods are shown to have excellent performance in discovering the hidden multilevel gene association rules.