Permutation Approach Research Articles

Block Compressed Sensing Using Random Permutation and Reweighted Sampling for Image Compression Applications

Block compressed sensing (BCS) has great potential in image compression applications for its low storage requirement and low computational complexity. However, the sampling efficiency of traditional BCS is very poor since some blocks actually are not sparse enough to apply compressed sensing (CS). In order to improve the sampling efficiency, a novel BCS with random permutation and reweighted sampling (BCS-RP-RS) for image compression applications is proposed. In the proposed method, two effective strategies, including random permutation and reweighted sampling, are used simultaneously to guarantee all blocks of image signals sparse enough to apply CS. As a result, better sampling efficiency can be achieved. Simulation results show that the proposed approach improves the peak signal-to-noise ratio (PSNR) of the reconstructed-images significantly compared with the conventional BCS with random permutation (BCS-RP) approach.

MHC-Dependent Mate Selection within 872 Spousal Pairs of European Ancestry from the Health and Retirement Study.

Disassortative mating refers to the phenomenon in which individuals with dissimilar genotypes and/or phenotypes mate with one another more frequently than would be expected by chance. Although the existence of disassortative mating is well established in plant and animal species, the only documented example of negative assortment in humans involves dissimilarity at the major histocompatibility complex (MHC) locus. Previous studies investigating mating patterns at the MHC have been hampered by limited sample size and contradictory findings. Inspired by the sparse and conflicting evidence, we investigated the role that the MHC region played in human mate selection using genome-wide association data from 872 European American spouses from the Health and Retirement Study (HRS). First, we treated the MHC region as a whole, and investigated genomic similarity between spouses using three levels of genomic variation: single-nucleotide polymorphisms (SNPs), classical human leukocyte antigen (HLA) alleles (both four-digit and two-digit classifications), and amino acid polymorphisms. The extent of MHC dissimilarity between spouses was assessed using a permutation approach. Second, we investigated fine scale mating patterns by testing for deviations from random mating at individual SNPs, HLA genes, and amino acids in HLA molecules. Third, we assessed how extreme the spousal relatedness at the MHC region was compared to the rest of the genome, to distinguish the MHC-specific effects from genome-wide effects. We show that neither the MHC region, nor any single SNPs, classic HLA alleles, or amino acid polymorphisms within the MHC region, were significantly dissimilar between spouses relative to non-spouse pairs. However, dissimilarity in the MHC region was extreme relative to the rest of genome for both spousal and non-spouse pairs. Despite the long-standing controversy, our analyses did not support a significant role of MHC dissimilarity in human mate choice.

Networks and Social Influence in European Legislative Politics

The Treaty of Lisbon strengthened the role of national parliaments in the European Union. It introduced an ‘early warning system’, granting parliamentary chambers the right to reject legislative proposals by the European Commission. Previous studies assumed independence between the decisions of parliaments to reject a legislative proposal. We apply recent advances in inferential network analysis and argue that parliamentary vetoes are better explained by conceptualizing parliaments’ veto actions as a temporal network. Network effects can be observed along the dimension of party families. Based on a new permutation approach, we find that parliaments with similar party majorities influence each other over the course of the decision period (‘social influence’), rather than basing their decisions independently on joint prior partisanship (‘selection’).

A permutation approach to the assignment of the configuration to diastereomeric tetrads by comparison of experimental and ab initio calculated differences in NMR data.

Scoring permutations of experimental chemical shift deviations and DFT/GIAO calculated deviations of isotropic shieldings for sets of four diastereomers can help to assign their relative configurations. This method was exercised on a set of diastereomeric Cinchona alkaloid derivatives, where 13C NMR data always identified the proper configuration. The presented approach is also an attempt to quantify the assignment by exclusion.

Logical and Methodological Issues Affecting Genetic Studies of Humans Reported in Top Neuroscience Journals.

Genetics and neuroscience are two areas of science that pose particular methodological problems because they involve detecting weak signals (i.e., small effects) in noisy data. In recent years, increasing numbers of studies have attempted to bridge these disciplines by looking for genetic factors associated with individual differences in behavior, cognition, and brain structure or function. However, different methodological approaches to guarding against false positives have evolved in the two disciplines. To explore methodological issues affecting neurogenetic studies, we conducted an in-depth analysis of 30 consecutive articles in 12 top neuroscience journals that reported on genetic associations in nonclinical human samples. It was often difficult to estimate effect sizes in neuroimaging paradigms. Where effect sizes could be calculated, the studies reporting the largest effect sizes tended to have two features: (i) they had the smallest samples and were generally underpowered to detect genetic effects, and (ii) they did not fully correct for multiple comparisons. Furthermore, only a minority of studies used statistical methods for multiple comparisons that took into account correlations between phenotypes or genotypes, and only nine studies included a replication sample or explicitly set out to replicate a prior finding. Finally, presentation of methodological information was not standardized and was often distributed across Methods sections and Supplementary Material, making it challenging to assemble basic information from many studies. Space limits imposed by journals could mean that highly complex statistical methods were described in only a superficial fashion. In summary, methods that have become standard in the genetics literature-stringent statistical standards, use of large samples, and replication of findings-are not always adopted when behavioral, cognitive, or neuroimaging phenotypes are used, leading to an increased risk of false-positive findings. Studies need to correct not just for the number of phenotypes collected but also for the number of genotypes examined, genetic models tested, and subsamples investigated. The field would benefit from more widespread use of methods that take into account correlations between the factors corrected for, such as spectral decomposition, or permutation approaches. Replication should become standard practice; this, together with the need for larger sample sizes, will entail greater emphasis on collaboration between research groups. We conclude with some specific suggestions for standardized reporting in this area.

Eigenvalue significance testing for genetic association.

Genotype eigenvectors are widely used as covariates for control of spurious stratification in genetic association. Significance testing for the accompanying eigenvalues has typically been based on a standard Tracy-Widom limiting distribution for the largest eigenvalue, derived under white-noise assumptions. It is known that even modest local correlation among markers inflates the largest eigenvalues, even in the absence of true stratification. In addition, a few sample eigenvalues may be extreme, creating further complications in accurate testing. We explore several methods to identify appropriate null eigenvalue thresholds, while remaining sensitive to eigenvalues corresponding to population stratification. We introduce a novel block permutation approach, designed to produce an appropriate null eigenvalue distribution by eliminating long-range genomic correlation while preserving local correlation. We also propose a fast approach based on eigenvalue distribution modeling, using a simple fit criterion and the general Marčenko-Pastur equation under a simple discrete eigenvalue model. Block permutation and the model-based approach work well for pure simulations and for data resampled from the 1000 Genomes project. In contrast, we find that the standard approach of computing an "effective" number of markers does not perform well. The performance of the methods is also demonstrated for a motivating example from the International Cystic Fibrosis Consortium.

Physical fitness and shapes of subcortical brain structures in children.

A few studies have recently reported that higher cardiorespiratory fitness is associated with higher volumes of subcortical brain structures in children. It is, however, unknown how different fitness measures relate to shapes of subcortical brain nuclei. We aimed to examine the association of the main health-related physical fitness components with shapes of subcortical brain structures in a sample of forty-four Spanish children aged 9·7 (sd 0·2) years from the NUtraceuticals for a HEALthier life project. Cardiorespiratory fitness, muscular strength and speed agility were assessed using valid and reliable tests (ALPHA-fitness test battery). Shape of the subcortical brain structures was assessed by MRI, and its relationship with fitness was examined after controlling for a set of potential confounders using a partial correlation permutation approach. Our results showed that all physical fitness components studied were significantly related to the shapes of subcortical brain nuclei. These associations were both positive and negative, indicating that a higher level of fitness in childhood is related to both expansions and contractions in certain regions of the accumbens, amygdala, caudate, hippocampus, pallidum, putamen and thalamus. Cardiorespiratory fitness was mainly associated with expansions, whereas handgrip was mostly associated with contractions in the structures studied. Future randomised-controlled trials will confirm or contrast our findings, demonstrating whether changes in fitness modify the shapes of brain structures and the extent to which those changes influence cognitive function.

Bayesian penalized log-likelihood ratio approach for dose response clinical trial studies

ABSTRACTIn literature, there are a few unified approaches to test proof of concept and estimate a target dose, including the multiple comparison procedure using modeling approach, and the permutation approach proposed by Klingenberg. We discuss and compare the operating characteristics of these unified approaches and further develop an alternative approach in a Bayesian framework based on the posterior distribution of a penalized log-likelihood ratio test statistic. Our Bayesian approach is much more flexible to handle linear or nonlinear dose–response relationships and is more efficient than the permutation approach. The operating characteristics of our Bayesian approach are comparable to and sometimes better than both approaches in a wide range of dose–response relationships. It yields credible intervals as well as predictive distribution for the response rate at a specific dose level for the target dose estimation. Our Bayesian approach can be easily extended to continuous, categorical, and time-to-event responses. We illustrate the performance of our proposed method with extensive simulations and Phase II clinical trial data examples.

Rank-based permutation approaches for non-parametric factorial designs.

Inference methods for null hypotheses formulated in terms of distribution functions in general non-parametric factorial designs are studied. The methods can be applied to continuous, ordinal or even ordered categorical data in a unified way, and are based only on ranks. In this set-up Wald-type statistics and ANOVA-type statistics are the current state of the art. The first method is asymptotically exact but a rather liberal statistical testing procedure for small to moderate sample size, while the latter is only an approximation which does not possess the correct asymptotic α level under the null. To bridge these gaps, a novel permutation approach is proposed which can be seen as a flexible generalization of the Kruskal-Wallis test to all kinds of factorial designs with independent observations. It is proven that the permutation principle is asymptotically correct while keeping its finite exactness property when data are exchangeable. The results of extensive simulation studies foster these theoretical findings. A real data set exemplifies its applicability.

Some solutions to the multivariate Behrens–Fisher problem for dissimilarity‐based analyses

SummaryThe essence of the generalised multivariate Behrens–Fisher problem (BFP) is how to test the null hypothesis of equality of mean vectors for two or more populations when their dispersion matrices differ. Solutions to the BFP usually assume variables are multivariate normal and do not handle high‐dimensional data. In ecology, species' count data are often high‐dimensional, non‐normal and heterogeneous. Also, interest lies in analysing compositional dissimilarities among whole communities in non‐Euclidean (semi‐metric or non‐metric) multivariate space. Hence, dissimilarity‐based tests by permutation (e.g., PERMANOVA, ANOSIM) are used to detect differences among groups of multivariate samples. Such tests are not robust, however, to heterogeneity of dispersions in the space of the chosen dissimilarity measure, most conspicuously for unbalanced designs. Here, we propose a modification to the PERMANOVA test statistic, coupled with either permutation or bootstrap resampling methods, as a solution to the BFP for dissimilarity‐based tests. Empirical simulations demonstrate that the type I error remains close to nominal significance levels under classical scenarios known to cause problems for the un‐modified test. Furthermore, the permutation approach is found to be more powerful than the (more conservative) bootstrap for detecting changes in community structure for real ecological datasets. The utility of the approach is shown through analysis of 809 species of benthic soft‐sediment invertebrates from 101 sites in five areas spanning 1960 km along the Norwegian continental shelf, based on the Jaccard dissimilarity measure.

The Measurement of Agreement in Medical Research: A Permutation Approach

The Measurement of Agreement in Medical Research: A Permutation Approach

A permutation approach for inferring species networks from gene trees in polyploid complexes by minimising deep coalescences

SummaryContext and purpose. Due to ubiquity of polyploid species formation in angiosperms, reconstructing the evolutionary history of polyploid complexes is at the forefront of methodological field of activity in molecular phylogenetics and systematic botany. The advent of multilocus species tree reconstruction approaches motivated by next‐generation sequencing methods pave the way to species network inference methods, with which phylogenetics could accommodate to the necessity for reconstructing reticulate relationships among diploids and (allo‐)polyploids in an objective manner, simultaneously taking into account gene tree incongruences caused by incomplete lineage sorting and hybridisation.Methods used. The present contribution describes a relatively simple and fast workflow pipeline for the reconstruction of species networks in polyploid complexes based on multilocus gene trees. It uses a permutation strategy and a parsimony‐based principle in species tree reconstruction (Minimising Deep Coalescences,MDC) for the assignment of homoeologs to parental genomes in allopolyploids, which is a crucial step in species network inference for polyploid complexes. Simulations with varying effective population sizes, different temporal scenarios for diploid or polyploid formations and different types of allopolyploid speciation (sister‐species diploids, non‐sister diploids or polyploidisation under participation of ancestral diploids) are used to assess the reliability of the reconstruction.Main results. Simulations show that the proposed method leads to trustworthy reconstructions if effective populations sizes are not too large and divergences among ancestral taxa are not too shallow. The applicability of our method to a real data set is demonstrated by inferring the reticulate relationships among diploid, tetraploid and hexaploid representatives of the genusLeucanthemopsis(Compositae, Anthemideae) based on gene tree topologies from four nuclear single‐copy genes and two plastidic intergenic spacer regions.Conclusion. The proposedMDC‐based method for species network reconstruction in polyploids is fast and manages to trustworthily reconstruct parentage in polyploidisation events. Concerns with and possible improvements of the described method are discussed.

Detecting the influence of environmental covariates on animal movement: a semivariance approach

Summary Movements of organisms are influenced by environmental variation. For example, the movement rates of animals in unsuitable habitats are often different from movement rates of animals foraging in high‐quality habitats. Different statistical methods to detect such effects exist, but they often rely on complete and regularly sampled data or require the formulation of an explicit movement model. We propose an extension to a recently introduced semivariance framework to identify the effects of environmental or other kinds of covariates on animal movement. Our extension also applies to sparse and irregularly sampled data, and it does not require the formulation of an explicit movement model. Within this extension of the semivariance framework, the observed movement rates at different time lags are modelled as a linear regression of the environmental covariates. To account for the inherent autocorrelation in semivariance data, we test for the statistical significance of the influence of covariates using a permutation approach. Our approach correctly identified covariates that influenced or did not influence movement rates in a simulation study. In a case study based on tracking data of a single female red deer (Cervus elaphus) individual from southern Austria, an application of the method showed that movement rates peaked during periods of intermediate temperature, but they do not co‐vary with altitude and precipitation.

Medulla oblongata damage and cardiac autonomic dysfunction in Parkinson disease.

To characterize medulla oblongata damage using diffusion tensor imaging (DTI) in Parkinson disease (PD) and correlate it with dysfunction of the cardiac sympathetic/vagal balance. Fifty-two patients with PD and 24 healthy controls were included in the study. All participants underwent clinical examination and 3T MRI using 3D T1-weighted imaging and DTI. DTI metrics were calculated within manually drawn regions of interest. Heart rate variability was evaluated using spectral analysis of the R-R cardiac interval during REM and slow-wave sleep based on continuous overnight electrocardiographic monitoring. Respiratory frequency was measured in 30-second contiguous epochs of REM and slow-wave sleep. The relationships between imaging and cardiac variables were calculated using partial correlations followed by the multiple comparisons permutation approach. The changes in heart rate and respiratory frequency variability from slow-wave sleep to REM sleep in healthy controls were no longer detectable in patients with PD. There were significant increases in the mean (p = 0.006), axial (p = 0.006), and radial diffusivities (p = 0.005) in the medulla oblongata of patients with PD. In PD, diffusion changes were specifically correlated with a lower heart rate and respiratory frequency variability during REM sleep. This study provides evidence that medulla oblongata damage underlies cardiac sympathetic/vagal balance and respiratory dysfunction in patients with PD.

A unified model based multifactor dimensionality reduction framework for detecting gene-gene interactions.

Gene-gene interaction (GGI) is one of the most popular approaches for finding and explaining the missing heritability of common complex traits in genome-wide association studies. The multifactor dimensionality reduction (MDR) method has been widely studied for detecting GGI effects. However, there are several disadvantages of the existing MDR-based approaches, such as the lack of an efficient way of evaluating the significance of multi-locus models and the high computational burden due to intensive permutation. Furthermore, the MDR method does not distinguish marginal effects from pure interaction effects. We propose a two-step unified model based MDR approach (UM-MDR), in which, the significance of a multi-locus model, even a high-order model, can be easily obtained through a regression framework with a semi-parametric correction procedure for controlling Type I error rates. In comparison to the conventional permutation approach, the proposed semi-parametric correction procedure avoids heavy computation in order to achieve the significance of a multi-locus model. The proposed UM-MDR approach is flexible in the sense that it is able to incorporate different types of traits and evaluate significances of the existing MDR extensions. The simulation studies and the analysis of a real example are provided to demonstrate the utility of the proposed method. UM-MDR can achieve at least the same power as MDR for most scenarios, and it outperforms MDR especially when there are some single nucleotide polymorphisms that only have marginal effects, which masks the detection of causal epistasis for the existing MDR approaches. UM-MDR provides a very good supplement of existing MDR method due to its efficiency in achieving significance for every multi-locus model, its power and its flexibility of handling different types of traits. A R package "umMDR" and other source codes are freely available at http://statgen.snu.ac.kr/software/umMDR/ CONTACT: tspark@stats.snu.ac.kr Supplementary data are available at Bioinformatics online.

Testing neutrality at copy-number-variable loci under the finite-allele and finite-site models

Copy-number variation (CNV) is an important form of DNA structural variation because a certain proportion of genomes in many eukaryotic species can contribute to such variations. Owing to the differences between CNVs and single nucleotide polymorphisms (SNPs) in size, mutation rate and maintaining mechanism, it is more realistic to characterize CNV evolution under the finite-allele and finite-site models. Here, we propose a method to test multiple CNVs neutrality under the finite-allele and finite-site models and the assumption of mutation–drift process. The statistical property of the method is evaluated through Monte Carlo simulations under the effects of the sample size, the scaled mutation rates, the number of CNVs, the population demographic change, and selection. Different from Tajima’s D test, a bootstrap or a permutation approach is suggested to conduct a neutrality test. Application of this method is illustrated using the diploid CNV genotypes measured in discrete copy numbers in 11 HapMap phase III populations. The results show that the mutation–drift process can explain the variation of genome-wide CNVs among 1184 individuals (856 CNVs, ∼0.02Mb on average in size), irrespective of the historical demographic changes. Patterns from allele-frequency-spectrum analysis also support the hypothesis of neutral CNVs. Our results suggest that most human chromosomal changes in healthy individuals via unbalanced rearrangements of the segments with certain sizes are neutral.

A Scalable Permutation Approach Reveals Replication and Preservation Patterns of Network Modules in Large Datasets

Network modules-topologically distinct groups of edges and nodes-that are preserved across datasets can reveal common features of organisms, tissues, cell types, and molecules. Many statistics to identify such modules have been developed, but testing their significance requires heuristics. Here, we demonstrate that current methods for assessing module preservation are systematically biased and produce skewed p values. We introduce NetRep, arapid and computationally efficient method that uses a permutation approach to score module preservation without assuming data are normally distributed. NetRep produces unbiased p values and can distinguish between true and false positives during multiple hypothesis testing. We use NetRep to quantify preservation of gene coexpression modules across murine brain, liver, adipose, and muscle tissues. Complex patterns of multi-tissue preservation were revealed, including a liver-derived housekeeping module that displayed adipose- and muscle-specific association with body weight. Finally, we demonstrate the broader applicability of NetRep by quantifying preservation of bacterial networks in gut microbiota between men and women.

On the Evaluation of Module Preservation

The ability to compare the modular structure of gene expression networks requires fast and accurate statistical tools. NetRep software provides a permutation approach which validates seven measures used to contrast the preservation of co-expression across diverse datasets.

Investigating covariate-by-centre interaction in survival data.

In survival analysis, assessing the existence of potential centre effects on the baseline hazard or on the effect of fixed covariates on the baseline hazard, such as treatment-by-centre interaction, is a frequent clinical concern in multicentre studies. Survival models with random effects on the baseline hazard and/or on the effect of the covariates of interest have been largely applied, for instance, to investigate potential centre effects. We aimed to develop a procedure to routinely test for multiple random effects in survival analyses. We propose a statistic and a permutation approach to test whether all or a subset of components of the variance-covariance matrix of random effects are non-zero in a mixed-effects Cox model framework. Performances of the proposed permutation tests are examined under different null hypotheses corresponding to the different components of the variance-covariance matrix, i.e ., to the different random effects considered on the baseline hazard and/or on the covariates effects. Several alternative hypotheses are evaluated using simulations. The results indicate that the permutation tests have valid type I error rates under the null and achieve satisfactory power under all alternatives. The procedure is applied to two European cohorts of haematological stem cell transplants in acute leukaemia to investigate the heterogeneity across centres in leukaemia-free survival and the potential heterogeneity in prognostic factors effects across centres.

Permutation approach for ordinal preference data

ABSTRACTBest et al. (Best, D. J., Rayner, J. C. W., O'Sullivan, M. G. (2000). Product maps for consumer categorical data. Food Quality and Preference, 11:91–97) suggested tests based on partitioning the X2 statistic into relevant components of location, dispersion, and skewness effects for testing equality of each effect for ordinal preference data. It is known that the chi-square approximation requires large counts for categories. For this purpose, in this study, we investigate a permutation approach for these statistics and compare the performance of these tests with simulation study. In addition, the permutation approach can be used to produce a product map that classifies the products. We illustrate the approach with a real data example.