Exact and approximate stepdown methods for multiple hypothesis testing

Consider the problem of testing k hypotheses simultaneously. In this paper,we discuss finite and large sample theory of stepdown methods that providecontrol of the familywise error rate (FWE). In order to improve upon theBonferroni method or Holm's (1979) stepdown method, Westfall and Young(1993) make eective use of resampling to construct stepdown methods thatimplicitly estimate the dependence structure of the test statistics. However,their methods depend on an assumption called subset pivotality. The goalof this paper is to construct general stepdown methods that do not requiresuch an assumption. In order to accomplish this, we take a close look atwhat makes stepdown procedures work, and a key component is a monotonicityrequirement of critical values. By imposing such monotonicity on estimatedcritical values (which is not an assumption on the model but an assumptionon the method), it is demonstrated that the problem of constructing a validmultiple test procedure which controls the FWE can be reduced to the problemof contructing a single test which controls the usual probability of a Type 1error. This reduction allows us to draw upon an enormous resamplingliterature as a general means of test contruction.

Improving generalized regression analysis for the spatial prediction of forest communities

Aim This study used data from temperate forest communities to assess: (1) five different stepwise selection methods with generalized additive models, (2) the effect of weighting absences to ensure a prevalence of 0.5, (3) the effect of limiting absences beyond the environmental envelope defined by presences, (4) four different methods for incorporating spatial autocorrelation, and (5) the effect of integrating an interaction factor defined by a regression tree on the residuals of an initial environmental model. Location State of Vaud, western Switzerland. Methods Generalized additive models (GAMs) were fitted using the grasp package (generalized regression analysis and spatial predictions, http://www.cscf.ch/grasp). Results Model selection based on cross-validation appeared to be the best compromise between model stability and performance (parsimony) among the five methods tested. Weighting absences returned models that perform better than models fitted with the original sample prevalence. This appeared to be mainly due to the impact of very low prevalence values on evaluation statistics. Removing zeroes beyond the range of presences on main environmental gradients changed the set of selected predictors, and potentially their response curve shape. Moreover, removing zeroes slightly improved model performance and stability when compared with the baseline model on the same data set. Incorporating a spatial trend predictor improved model performance and stability significantly. Even better models were obtained when including local spatial autocorrelation. A novel approach to include interactions proved to be an efficient way to account for interactions between all predictors at once. Main conclusions Models and spatial predictions of 18 forest communities were significantly improved by using either: (1) cross-validation as a model selection method, (2) weighted absences, (3) limited absences, (4) predictors accounting for spatial autocorrelation, or (5) a factor variable accounting for interactions between all predictors. The final choice of model strategy should depend on the nature of the available data and the specific study aims. Statistical evaluation is useful in searching for the best modelling practice. However, one should not neglect to consider the shapes and interpretability of response curves, as well as the resulting spatial predictions in the final assessment.

Comparison of different methods for thin section EM analysis of Mycobacterium smegmatis.

Bacteria are generally difficult specimens to prepare for conventional resin section electron microscopy and mycobacteria, with their thick and complex cell envelope layers being especially prone to artefacts. Here we made a systematic comparison of different methods for preparing Mycobacterium smegmatis for thin section electron microscopy analysis. These methods were: (1) conventional preparation by fixatives and epoxy resins at ambient temperature. (2) Tokuyasu cryo-section of chemically fixed bacteria. (3) rapid freezing followed by freeze substitution and embedding in epoxy resin at room temperature or (4) combined with Lowicryl HM20 embedding and ultraviolet (UV) polymerization at low temperature and (5) CEMOVIS, or cryo electron microscopy of vitreous sections. The best preservation of bacteria was obtained with the cryo electron microscopy of vitreous sections method, as expected, especially with respect to the preservation of the cell envelope and lipid bodies. By comparison with cryo electron microscopy of vitreous sections both the conventional and Tokuyasu methods produced different, undesirable artefacts. The two different types of freeze-substitution protocols showed variable preservation of the cell envelope but gave acceptable preservation of the cytoplasm, but not lipid bodies, and bacterial DNA. In conclusion although cryo electron microscopy of vitreous sections must be considered the 'gold standard' among sectioning methods for electron microscopy, because it avoids solvents and stains, the use of optimally prepared freeze substitution also offers some advantages for ultrastructural analysis of bacteria.

Association between the A-2518G polymorphism in the monocyte chemoattractant protein-1 gene and insulin resistance and Type 2 diabetes mellitus.

AIMS/HYPOTHESIS: The molecular mechanisms of obesity-related insulin resistance are incompletely understood. Macrophages accumulate in adipose tissue of obese individuals. In obesity, monocyte chemoattractant protein-1 (MCP-1), a key chemokine in the process of macrophage accumulation, is overexpressed in adipose tissue. MCP-1 is an insulin-responsive gene that continues to respond to exogenous insulin in insulin-resistant adipocytes and mice. MCP-1 decreases insulin-stimulated glucose uptake into adipocytes. The A-2518G polymorphism in the distal regulatory region of MCP-1 may regulate gene expression. The aim of this study was to investigate the impact of this gene polymorphism on insulin resistance. METHODS: We genotyped the Ludwigshafen Risk and Cardiovascular Health (LURIC) cohort ( n=3307). Insulin resistance, estimated by homeostasis model assessment, and Type 2 diabetes were diagnosed in 803 and 635 patients respectively. RESULTS: Univariate analysis revealed that plasma MCP-1 levels were significantly and positively correlated with WHR ( p=0.011), insulin resistance ( p=0.0097) and diabetes ( p<0.0001). Presence of the MCP-1 G-2518 allele was associated with decreased plasma MCP-1 ( p=0.017), a decreased prevalence of insulin resistance (odds ratio [OR]=0.82, 95% CI: 0.70-0.97, p=0.021) and a decreased prevalence of diabetes (OR=0.80, 95% CI: 0.67-0.96, p=0.014). In multivariate analysis, the G allele retained statistical significance as a negative predictor of insulin resistance (OR=0.78, 95% CI: 0.65-0.93, p=0.0060) and diabetes (OR=0.80, 95% CI: 0.66-0.96, p=0.018). CONCLUSIONS/INTERPRETATION: In a large cohort of Caucasians, the MCP-1 G-2518 gene variant was significantly and negatively correlated with plasma MCP-1 levels and the prevalence of insulin resistance and Type 2 diabetes. These results add to recent evidence supporting a role for MCP-1 in pathologies associated with hyperinsulinaemia.

Methods for integration site distribution analyses in animal cell genomes.

The question of where retroviral DNA becomes integrated in chromosomes is important for understanding (i) the mechanisms of viral growth, (ii) devising new anti-retroviral therapy, (iii) understanding how genomes evolve, and (iv) developing safer methods for gene therapy. With the completion of genome sequences for many organisms, it has become possible to study integration targeting by cloning and sequencing large numbers of host-virus DNA junctions, then mapping the host DNA segments back onto the genomic sequence. This allows statistical analysis of the distribution of integration sites relative to the myriad types of genomic features that are also being mapped onto the sequence scaffold. Here we present methods for recovering and analyzing integration site sequences.

Isolating DNA from sexual assault cases: a comparison of standard methods with a nuclease-based approach.

AbstractText BACKGROUND: Profiling sperm DNA present on vaginal swabs taken from rape victims often contributes to identifying and incarcerating rapists. Large amounts of the victim's epithelial cells contaminate the sperm present on swabs, however, and complicate this process. The standard method for obtaining relatively pure sperm DNA from a vaginal swab is to digest the epithelial cells with Proteinase K in order to solubilize the victim's DNA, and to then physically separate the soluble DNA from the intact sperm by pelleting the sperm, removing the victim's fraction, and repeatedly washing the sperm pellet. An alternative approach that does not require washing steps is to digest with Proteinase K, pellet the sperm, remove the victim's fraction, and then digest the residual victim's DNA with a nuclease. METHODS: The nuclease approach has been commercialized in a product, the Erase Sperm Isolation Kit (PTC Labs, Columbia, MO, USA), and five crime laboratories have tested it on semen-spiked female buccal swabs in a direct comparison with their standard methods. Comparisons have also been performed on timed post-coital vaginal swabs and evidence collected from sexual assault cases. RESULTS: For the semen-spiked buccal swabs, Erase outperformed the standard methods in all five laboratories and in most cases was able to provide a clean male profile from buccal swabs spiked with only 1,500 sperm. The vaginal swabs taken after consensual sex and the evidence collected from rape victims showed a similar pattern of Erase providing superior profiles. CONCLUSIONS: In all samples tested, STR profiles of the male DNA fractions obtained with Erase were as good as or better than those obtained using the standard methods.

Dynamic graphics of parametrically linked multivariate methods used in compositional data analysis

Many multivariate methods that are apparently distinct can be linked by introducing oneor more parameters in their definition. Methods that can be linked in this way arecorrespondence analysis, unweighted or weighted logratio analysis (the latter alsoknown as "spectral mapping"), nonsymmetric correspondence analysis, principalcomponent analysis (with and without logarithmic transformation of the data) andmultidimensional scaling. In this presentation I will show how several of thesemethods, which are frequently used in compositional data analysis, may be linkedthrough parametrizations such as power transformations, linear transformations andconvex linear combinations. Since the methods of interest here all lead to visual mapsof data, a "movie" can be made where where the linking parameter is allowed to vary insmall steps: the results are recalculated "frame by frame" and one can see the smoothchange from one method to another. Several of these "movies" will be shown, giving adeeper insight into the similarities and differences between these methods.

Forecasting with missing data: Application to a real case

This paper presents a comparative analysis of linear and mixed modelsfor short term forecasting of a real data series with a high percentage of missing data. Data are the series of significant wave heights registered at regular periods of three hours by a buoy placed in the Bay of Biscay.The series is interpolated with a linear predictor which minimizes theforecast mean square error. The linear models are seasonal ARIMA models and themixed models have a linear component and a non linear seasonal component.The non linear component is estimated by a non parametric regression of dataversus time. Short term forecasts, no more than two days ahead, are of interestbecause they can be used by the port authorities to notice the fleet.Several models are fitted and compared by their forecasting behavior.

Genome-Wide Prediction Methods in Highly Diverse and Heterozygous Species: Proof-of-Concept through Simulation in Grapevine.

Nowadays, genome-wide association studies (GWAS) and genomic selection (GS) methods which use genome-wide marker data for phenotype prediction are of much potential interest in plant breeding. However, to our knowledge, no studies have been performed yet on the predictive ability of these methods for structured traits when using training populations with high levels of genetic diversity. Such an example of a highly heterozygous, perennial species is grapevine. The present study compares the accuracy of models based on GWAS or GS alone, or in combination, for predicting simple or complex traits, linked or not with population structure. In order to explore the relevance of these methods in this context, we performed simulations using approx 90,000 SNPs on a population of 3,000 individuals structured into three groups and corresponding to published diversity grapevine data. To estimate the parameters of the prediction models, we defined four training populations of 1,000 individuals, corresponding to these three groups and a core collection. Finally, to estimate the accuracy of the models, we also simulated four breeding populations of 200 individuals. Although prediction accuracy was low when breeding populations were too distant from the training populations, high accuracy levels were obtained using the sole core-collection as training population. The highest prediction accuracy was obtained (up to 0.9) using the combined GWAS-GS model. We thus recommend using the combined prediction model and a core-collection as training population for grapevine breeding or for other important economic crops with the same characteristics.

A simple randomized algorithm for consistent sequential prediction of ergodic time series

We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if thesequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.

The application of NMR and MS methods for detection of adulteration of wine, fruit juices, and olive oil. A review

This review covers two important techniques, high resolution nuclear magnetic resonance (NMR) spectroscopy and mass spectrometry (MS), used to characterize food products and detect possible adulteration of wine, fruit juices, and olive oil, all important products of the Mediterranean Basin. Emphasis is placed on the complementary use of SNIF-NMR (site-specific natural isotopic fractionation nuclear magnetic resonance) and IRMS (isotope-ratio mass spectrometry) in association with chemometric methods for detecting the adulteration.

Worst-case bounds for the logarithmic loss of predictors

We investigate on-line prediction of individual sequences. Given a class of predictors, the goal is to predict as well as the best predictor in the class, where the loss is measured by the self information (logarithmic) loss function. The excess loss (regret) is closely related to the redundancy of the associated lossless universal code. Using Shtarkov's theorem and tools from empirical process theory, we prove a general upper bound on the best possible (minimax) regret. The bound depends on certain metric properties of the class of predictors. We apply the bound to both parametric and nonparametric classes ofpredictors. Finally, we point out a suboptimal behavior of the popular Bayesian weighted average algorithm.

Variance reduction methods for simulation of densities on Wiener space

We develop a general error analysis framework for the Monte Carlo simulationof densities for functionals in Wiener space. We also study variancereduction methods with the help of Malliavin derivatives. For this, wegive some general heuristic principles which are applied to diffusionprocesses. A comparison with kernel density estimates is made.

Prospective study evaluating the predictability of need for retreatment with intravitreal ranibizumab for age-related macular degeneration.

PURPOSE: To investigate the rhythm and predictability of the need for retreatment with intravitreal injections of ranibizumab for neovascular age-related macular degeneration (nAMD). METHODS: This prospective study enrolled 39 patients with treatment-naïve nAMD. After three loading doses of intravitreal ranibizumab, patients underwent an intensified follow-up for 12 months (initially weekly, then with stepwise increases to every 2 weeks and to monthly after each injection). Patients were retreated on an as-needed basis if any fluid or increased central retinal thickness (CRT) (>50μm) was found on spectral domain optical coherence tomography (OCT). Statistical analysis included patients who received at least two retreatments (five injections). RESULTS: A mean of 7.5 injections (range 0-12) were given between months 3 and 15. The mean visual acuity increased by 13.1 and 12.6 ETDRS letters at months 12 and 15 respectively. Two or more injection-retreatment intervals were found in 31 patients. The variability of their intra-individual intervals up to 14 weeks was small (SD 0-2.13 weeks), revealing a high regularity of the retreatment rhythm. The SD was correlated with the mean interval duration (r = 0.89, p < 0.001). The first interval was a good predictor of the following intervals (regression coefficient =0.81). One retreatment criterion was stable in 97 % of patients (cysts or subretinal fluid). CONCLUSION: The results of this study demonstrate a high intra-individual predictability of retreatment need with ranibizumab injections for nAMD. These findings may be helpful for developing individualized treatment plans for maintained suppression of disease activity with a minimum of injections and visits.

iLOGP: A Simple, Robust, and Efficient Description of n-Octanol/Water Partition Coefficient for Drug Design Using the GB/SA Approach.

The n-octanol/water partition coefficient (log Po/w) is a key physicochemical parameter for drug discovery, design, and development. Here, we present a physics-based approach that shows a strong linear correlation between the computed solvation free energy in implicit solvents and the experimental log Po/w on a cleansed data set of more than 17,500 molecules. After internal validation by five-fold cross-validation and data randomization, the predictive power of the most interesting multiple linear model, based on two GB/SA parameters solely, was tested on two different external sets of molecules. On the Martel druglike test set, the predictive power of the best model (N = 706, r = 0.64, MAE = 1.18, and RMSE = 1.40) is similar to six well-established empirical methods. On the 17-drug test set, our model outperformed all compared empirical methodologies (N = 17, r = 0.94, MAE = 0.38, and RMSE = 0.52). The physical basis of our original GB/SA approach together with its predictive capacity, computational efficiency (1 to 2 s per molecule), and tridimensional molecular graphics capability lay the foundations for a promising predictor, the implicit log P method (iLOGP), to complement the portfolio of drug design tools developed and provided by the SIB Swiss Institute of Bioinformatics.