Enhanced Model-Based Clustering,Density Estimation,and Discriminant Analysis Software: MCLUST

MCLUST is a software package for model-based clustering, density estimation and discriminant analysis interfaced to the S-PLUS commercial software and the R language. It implements parameterized Gaussian hierarchical clustering algorithms and the EM algorithm for parameterized Gaussian mixture models with the possible addition of a Poisson noise term. Also included are functions that combine hierarchical clustering, EM and the Bayesian Information Criterion (BIC) in comprehensive strategies for clustering, density estimation, and discriminant analysis. MCLUST provides functionality for displaying and visualizing clustering and classification results. A web page with related links can be found at .     

Predicting stock index volatility: can market volume help?

This paper explores a number of statistical models for predicting the daily stock return volatility of an aggregate of all stocks traded on the NYSE. An application of linear and non-linear Granger causality tests highlights evidence of bidirectional causality, although the relationship is stronger from volatility to volume than the other way around. The out-of-sample forecasting performance of various linear, GARCH, EGARCH, GJR and neural network models of volatility are evaluated and compared. The models are also augmented by the addition of a measure of lagged volume to form more general ex-ante forecasting models. The results indicate that augmenting models of volatility with measures of lagged volume leads only to very modest improvements, if any, in forecasting performance. © 1998 John Wiley & Sons, Ltd.     

Robust associations of four new chromosome regions from genome-wide analyses of type 1 diabetes

The Wellcome Trust Case Control Consortium (WTCCC) primary genome-wide association (GWA) scan on seven diseases, including the multifactorial autoimmune disease type 1 diabetes (T1D), shows associations at P < 5 x 10(-7) between T1D and six chromosome regions: 12q24, 12q13, 16p13, 18p11, 12p13 and 4q27. Here, we attempted to validate these and six other top findings in 4,000 individuals with T1D, 5,000 controls and 2,997 family trios independent of the WTCCC study. We confirmed unequivocally the associations of 12q24, 12q13, 16p13 and 18p11 (P(follow-up) 相似文献   

Distribution of the milliped genus Narceus Rafinesque, 1820 (Spirobolida: Spirobolidae): occurrences in New England and west of the Mississippi River; a summary of peripheral localities; and first records from Connecticut, Delaware, Maine, and Minnesota

The milliped genus Narceus Rafinesque, 1820 (Spirobolida: Spirobolidae) occupies parts or all of 2 Canadian provinces, Québec and Ontario; every U.S. state east of the Mississippi River; and 9 states to the west including Minnesota, Iowa, Missouri, Arkansas, Louisiana, Nebraska, Kansas, Oklahoma, and Texas. Records are detailed for the "western" states and New England and include the first from Minnesota, Connecticut, Delaware, and Maine; occurrence is projected for southeastern Minnesota and the Delmarva Peninsula. The genus presently comprises 2 valid species that are endemic to Florida— N. gordanus (Chamberlin, 1943) and N. woodruffi Causey, 1959—and 2 of uncertain status that occur throughout the generic range and are referenced as the " N. americanus/annularis complex"; geographic evidence suggests greater diversity, particularly in the south, and a 2nd generic revision is in order to update the existing one by Keeton (1960). Records cluster within a large, semicontinuous area whose northern, southern, and western range extremes, respectively, are Saint-Nicolas, Lévis Census Division, Québec; Key West, Monroe County, Florida, and northeastern Duval County and Rockport, Aransas County, Texas; and Garner State Park, Uvalde County, Texas. The eastern limit is the Atlantic Ocean, and records are available from Cape Cod and Tuckernuck Island, Massachusetts; Long Island, New York; Cape Hatteras, North Carolina; and James Island, South Carolina. The projected western boundary, based on peripheral localities, angles southwestward from Omaha, Nebraska, to Uvalde County; and the northern boundary passes through central Iowa and Wisconsin (encompassing the Door Peninsula) and the southern periphery of the Upper Peninsula of Michigan. The lone Minnesota locality, from Lyon County in the southwest, lies substantially north of the projected border in Iowa and well west of the expected area of occurrence in southeastern Minnesota. The northernmost record west of the Mississippi River, it may represent an allopatric population that extends westward into eastern South Dakota.     

Apolipoprotein-mediated pathways of lipid antigen presentation

Peptide antigens are presented to T cells by major histocompatibility complex (MHC) molecules, with endogenous peptides presented by MHC class I and exogenous peptides presented by MHC class II. In contrast to the MHC system, CD1 molecules bind lipid antigens that are presented at the antigen-presenting cell (APC) surface to lipid antigen-reactive T cells. Because CD1 molecules survey endocytic compartments, it is self-evident that they encounter antigens from extracellular sources. However, the mechanisms of exogenous lipid antigen delivery to CD1-antigen-loading compartments are not known. Serum apolipoproteins are mediators of extracellular lipid transport for metabolic needs. Here we define the pathways mediating markedly efficient exogenous lipid antigen delivery by apolipoproteins to achieve T-cell activation. Apolipoprotein E binds lipid antigens and delivers them by receptor-mediated uptake into endosomal compartments containing CD1 in APCs. Apolipoprotein E mediates the presentation of serum-borne lipid antigens and can be secreted by APCs as a mechanism to survey the local environment to capture antigens or to transfer microbial lipids from infected cells to bystander APCs. Thus, the immune system has co-opted a component of lipid metabolism to develop immunological responses to lipid antigens.