Penalized discriminant methods for the classification of tumors from gene expression data

Due to the advent of high-throughput microarray technology, it has become possible to develop molecular classification systems for various types of cancer. In this article, we propose a methodology using regularized regression models for the classification of tumors in microarray experiments. The performances of principal components, partial least squares, and ridge regression models are studied; these regression procedures are adapted to the classification setting using the optimal scoring algorithm. We also develop a procedure for ranking genes based on the fitted regression models. The proposed methodologies are applied to two microarray studies in cancer.     

Proper multivariate conditional autoregressive models for spatial data analysis

In the past decade conditional autoregressive modelling specifications have found considerable application for the analysis of spatial data. Nearly all of this work is done in the univariate case and employs an improper specification. Our contribution here is to move to multivariate conditional autoregressive models and to provide rich, flexible classes which yield proper distributions. Our approach is to introduce spatial autoregression parameters. We first clarify what classes can be developed from the family of Mardia (1988) and contrast with recent work of Kim et al. (2000). We then present a novel parametric linear transformation which provides an extension with attractive interpretation. We propose to employ these models as specifications for second-stage spatial effects in hierarchical models. Two applications are discussed; one for the two-dimensional case modelling spatial patterns of child growth, the other for a four-dimensional situation modelling spatial variation in HLA-B allele frequencies. In each case, full Bayesian inference is carried out using Markov chain Monte Carlo simulation.     

Experimental studies on reproductive toxicologic effects of lamotrigine in mice

BACKGROUND: Virtually all antiepileptic drugs (AED) tested so far have been found to be teratogenic. The second generation AED possess a number of therapeutic advantages over the older ones. There are, however, very little data on their effects on embryonic development. A recent report suggests that lamotrigine (LTG) can be teratogenic to human fetuses. With only a few cases of prenatal exposure to LTG in the record, however, it has not been possible to establish a recognizable pattern of malformations in the infants of LTG‐treated mothers. OBJECTIVES: The objectives of the present study were to evaluate the reproductive toxic effects of LTG RESULTS: Single (50–200 mg/kg) or multiple doses (25, 50, 75 mg/kg) of LTG were administered by intraperitoneal (i.p.) injection (note that the therapeutic administration is oral) to groups of TO mice on gestation day (GD) 7 or 8. Fetuses were collected on GD 18. Maternal toxic effects including a dose‐related mortality, a high incidence of abortion, embryo lethality, congenital malformations and intrauterine growth retardation (IUGR) were observed in the LTG‐treated group. Administration of LTG in multiple low doses resulted in a better maternal survival and increased incidence of embryonic resorption and malformations with increasing dose; IUGR was significant but not dose‐dependent. The malformations characteristic of the LTG multiple low dose group fetuses included maxillary‐mandibular hypoplasia, exencephaly, cleft palate, median facial cleft, urogenital anomalies and varying degrees of caudal regression. Skeletal malformations and developmental delay of the skeleton were observed both in single and multiple dose groups. CONCLUSIONS: The results of this study indicate that LTG administered i.p. at high doses can induce intrauterine growth retardation and at low multiple doses causes a dose‐dependent increase in embryonic resorption, craniofacial and caudal malformations as well as maternal toxicity in the mouse. Previous studies in other laboratories have used oral route of exposure and concluded that there are no teratogenic effects of LTG at dose levels that are not maternally toxic. Birth Defects Res B 68:428–438, 2003. © 2003 Wiley‐Liss, Inc.     

Non-parametric regression with BayesX: a flexible estimation of trends in human physical stature in 19th century America

The recently developed computer program BayesX provides a Bayesian approach to the estimation of non-parametric additive models. Such models can be useful in applications when the effect of metrical covariates (such as time) are to be estimated while controlling for other factors. In an application of this methodology, trends in the height of West Point cadets in the 19th century are estimated. The results indicate that the biological standard of living of the "middle class" increased relative to the rest of the American society during the Antebellum years.     

Methods for comparison of parameters from longitudinal rhythmometric models with multiple components

Multiple components linear least-squares methods have been proposed for the detection of periodic components in nonsinusoidal longitudinal time series. However, a proper test for comparison of parameters obtained from this method for two or more time series is not yet available. Accordingly, we propose two methods, one parametric and one nonparametric, to compare parameters from rhythmometric models with multiple components. The parametric method is based on techniques commonly and generally employed in linear regression analysis. The comparison of parameters among two or more time series is accomplished by the use of so-called dummy variables. The nonparametric method is based on bootstrap techniques. This approach basically tests if the difference in any given parameter obtained by fitting a model with the same periods to two different longitudinal time series differs from zero. This method calculates a confidence interval for the difference in the tested parameter. If this interval does not contain zero, it can be concluded that the parameters obtained from the two time series are different with high probability. An estimation of the p-value for the corresponding test can also be calculated. By the use of similar bootstrap techniques, confidence intervals can also be obtained for any parameter derived from the multiple component fit of several periods to nonsinusoidal longitudinal time series, including the orthophase (peak time), bathyphase (trough time), and global amplitude (difference between the maximum and the minimum) of the fitted model waveform. These methods represent a valuable tool for the comparison of rhythm parameters obtained by multiple component analysis, and they render this approach as a generally applicable one for waveform representation and detection of periodicities in nonsinusoidal, sparse, and noisy longitudinal time series sampled with either equidistant or unequidistant observations.     

Identifying multiple coral reef regimes and their drivers across the Hawaiian archipelago

Loss of coral reef resilience can lead to dramatic changes in benthic structure, often called regime shifts, which significantly alter ecosystem processes and functioning. In the face of global change and increasing direct human impacts, there is an urgent need to anticipate and prevent undesirable regime shifts and, conversely, to reverse shifts in already degraded reef systems. Such challenges require a better understanding of the human and natural drivers that support or undermine different reef regimes. The Hawaiian archipelago extends across a wide gradient of natural and anthropogenic conditions and provides us a unique opportunity to investigate the relationships between multiple reef regimes, their dynamics and potential drivers. We applied a combination of exploratory ordination methods and inferential statistics to one of the most comprehensive coral reef datasets available in order to detect, visualize and define potential multiple ecosystem regimes. This study demonstrates the existence of three distinct reef regimes dominated by hard corals, turf algae or macroalgae. Results from boosted regression trees show nonlinear patterns among predictors that help to explain the occurrence of these regimes, and highlight herbivore biomass as the key driver in addition to effluent, latitude and depth.