Fitting mixtures of Kent distributions to aid in joint set identification

When examining a rock mass, joint sets and their orientations can play a significant role with regard to how the rock mass will behave. To identify joint sets present in the rock mass, the orientation of individual fracture planer can be measured on exposed rock faces and the resulting data can be examined for heterogeneity. In this article, the expectation-maximization algorithm is used to lit mixtures of Kent component distributions to the fracture data to aid in the identification of joint sets. An additional uniform component is also included in the model to accommodate the noise present in the data.

Estimating and evaluating the statistics of gapped local-alignment scores

We present a novel maximum-likelihood-based algorithm for estimating the distribution of alignment scores from the scores of unrelated sequences in a database search. Using a new method for measuring the accuracy of p-values, we show that our maximum-likelihood-based algorithm is more accurate than existing regression-based and lookup table methods. We explore a more sophisticated way of modeling and estimating the score distributions (using a two-component mixture model and expectation maximization), but conclude that this does not improve significantly over simply ignoring scores with small E-values during estimation. Finally, we measure the classification accuracy of p-values estimated in different ways and observe that inaccurate p-values can, somewhat paradoxically, lead to higher classification accuracy. We explain this paradox and argue that statistical accuracy, not classification accuracy, should be the primary criterion in comparisons of similarity search methods that return p-values that adjust for target sequence length.

Speeding up the EM algorithm for mixture model-based segmentation of magnetic resonance images

Mixture models implemented via the expectation-maximization (EM) algorithm are being increasingly used in a wide range of problems in pattern recognition such as image segmentation. However, the EM algorithm requires considerable computational time in its application to huge data sets such as a three-dimensional magnetic resonance (MR) image of over 10 million voxels. Recently, it was shown that a sparse, incremental version of the EM algorithm could improve its rate of convergence. In this paper, we show how this modified EM algorithm can be speeded up further by adopting a multiresolution kd-tree structure in performing the E-step. The proposed algorithm outperforms some other variants of the EM algorithm for segmenting MR images of the human brain. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Using the EM Algorithm to Train Neural Networks: Misconceptions and a New Algorithm for Multiclass Classification

The expectation-maximization (EM) algorithm has been of considerable interest in recent years as the basis for various algorithms in application areas of neural networks such as pattern recognition. However, there exists some misconceptions concerning its application to neural networks. In this paper, we clarify these misconceptions and consider how the EM algorithm can be adopted to train multilayer perceptron (MLP) and mixture of experts (ME) networks in applications to multiclass classification. We identify some situations where the application of the EM algorithm to train MLP networks may be of limited value and discuss some ways of handling the difficulties. For ME networks, it is reported in the literature that networks trained by the EM algorithm using iteratively reweighted least squares (IRLS) algorithm in the inner loop of the M-step, often performed poorly in multiclass classification. However, we found that the convergence of the IRLS algorithm is stable and that the log likelihood is monotonic increasing when a learning rate smaller than one is adopted. Also, we propose the use of an expectation-conditional maximization (ECM) algorithm to train ME networks. Its performance is demonstrated to be superior to the IRLS algorithm on some simulated and real data sets.

Use of the EM algorithm to detect QTL affecting multiple-traits in an across half-sib family analysis

QTL detection experiments in livestock species commonly use the half-sib design. Each male is mated to a number of females, each female producing a limited number of progeny. Analysis consists of attempting to detect associations between phenotype and genotype measured on the progeny. When family sizes are limiting experimenters may wish to incorporate as much information as possible into a single analysis. However, combining information across sires is problematic because of incomplete linkage disequilibrium between the markers and the QTL in the population. This study describes formulae for obtaining MLEs via the expectation maximization (EM) algorithm for use in a multiple-trait, multiple-family analysis. A model specifying a QTL with only two alleles, and a common within sire error variance is assumed. Compared to single-family analyses, power can be improved up to fourfold with multi-family analyses. The accuracy and precision of QTL location estimates are also substantially improved. With small family sizes, the multi-family, multi-trait analyses reduce substantially, but not totally remove, biases in QTL effect estimates. In situations where multiple QTL alleles are segregating the multi-family analysis will average out the effects of the different QTL alleles.

An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization

Objective: Inpatient length of stay (LOS) is an important measure of hospital activity, health care resource consumption, and patient acuity. This research work aims at developing an incremental expectation maximization (EM) based learning approach on mixture of experts (ME) system for on-line prediction of LOS. The use of a batchmode learning process in most existing artificial neural networks to predict LOS is unrealistic, as the data become available over time and their pattern change dynamically. In contrast, an on-line process is capable of providing an output whenever a new datum becomes available. This on-the-spot information is therefore more useful and practical for making decisions, especially when one deals with a tremendous amount of data. Methods and material: The proposed approach is illustrated using a real example of gastroenteritis LOS data. The data set was extracted from a retrospective cohort study on all infants born in 1995-1997 and their subsequent admissions for gastroenteritis. The total number of admissions in this data set was n = 692. Linked hospitalization records of the cohort were retrieved retrospectively to derive the outcome measure, patient demographics, and associated co-morbidities information. A comparative study of the incremental learning and the batch-mode learning algorithms is considered. The performances of the learning algorithms are compared based on the mean absolute difference (MAD) between the predictions and the actual LOS, and the proportion of predictions with MAD < 1 day (Prop(MAD < 1)). The significance of the comparison is assessed through a regression analysis. Results: The incremental learning algorithm provides better on-line prediction of LOS when the system has gained sufficient training from more examples (MAD = 1.77 days and Prop(MAD < 1) = 54.3%), compared to that using the batch-mode learning. The regression analysis indicates a significant decrease of MAD (p-value = 0.063) and a significant (p-value = 0.044) increase of Prop(MAD

Multi-level zero-inflated Poisson regression modelling of correlated count data with excess zeros

Count data with excess zeros relative to a Poisson distribution are common in many biomedical applications. A popular approach to the analysis of such data is to use a zero-inflated Poisson (ZIP) regression model. Often, because of the hierarchical Study design or the data collection procedure, zero-inflation and lack of independence may occur simultaneously, which tender the standard ZIP model inadequate. To account for the preponderance of zero counts and the inherent correlation of observations, a class of multi-level ZIP regression model with random effects is presented. Model fitting is facilitated using an expectation-maximization algorithm, whereas variance components are estimated via residual maximum likelihood estimating equations. A score test for zero-inflation is also presented. The multi-level ZIP model is then generalized to cope with a more complex correlation structure. Application to the analysis of correlated count data from a longitudinal infant feeding study illustrates the usefulness of the approach.

Multilevel modelling for inference of genetic regulatory networks

Time-course experiments with microarrays are often used to study dynamic biological systems and genetic regulatory networks (GRNs) that model how genes influence each other in cell-level development of organisms. The inference for GRNs provides important insights into the fundamental biological processes such as growth and is useful in disease diagnosis and genomic drug design. Due to the experimental design, multilevel data hierarchies are often present in time-course gene expression data. Most existing methods, however, ignore the dependency of the expression measurements over time and the correlation among gene expression profiles. Such independence assumptions violate regulatory interactions and can result in overlooking certain important subject effects and lead to spurious inference for regulatory networks or mechanisms. In this paper, a multilevel mixed-effects model is adopted to incorporate data hierarchies in the analysis of time-course data, where temporal and subject effects are both assumed to be random. The method starts with the clustering of genes by fitting the mixture model within the multilevel random-effects model framework using the expectation-maximization (EM) algorithm. The network of regulatory interactions is then determined by searching for regulatory control elements (activators and inhibitors) shared by the clusters of co-expressed genes, based on a time-lagged correlation coefficients measurement. The method is applied to two real time-course datasets from the budding yeast (Saccharomyces cerevisiae) genome. It is shown that the proposed method provides clusters of cell-cycle regulated genes that are supported by existing gene function annotations, and hence enables inference on regulatory interactions for the genetic network.

Superior electric double layer capacitors using ordered mesoporous carbons

This paper reports for the first time superior electric double layer capacitive properties of ordered mesoporous carbon (OMCs) with varying ordered pore symmetries and mesopore structure. Compared to commercially used activated carbon electrode, Maxsorb, these OMC carbons have superior capacitive behavior, power output and high-frequency performance in EDLCs due to the unique structure of their mesopore network, which is more favorable for fast ionic transport than the pore networks in disordered microporous carbons. As evidenced by N-2 sorption, cyclic voltammetry and frequency response measurements, OMC carbons with large mesopores, and especially with 2-D pore symmetry, show superior capacitive behaviors (exhibiting a high capacitance of over 180 F/g even at very high sweep rate of 50 mV/s, as compared to much reduced capacitance of 73 F/g for Maxsorb at the same sweep rate). OMC carbons can provide much higher power density while still maintaining good energy density. OMC carbons demonstrate excellent high-frequency performances due to its higher surface area in pores larger than 3 nm. Such ordered mesoporous carbons (OMCs) offer a great potential in EDLC capacitors, particularly for applications where high power output and good high-frequency capacitive performances are required. (C) 2005 Elsevier Ltd. All rights reserved.

Deficits on self ordered tasks associated with hyperostosis frontalis interna

A 74 year old patient, EW, with dorsolateral frontal cortical compression due to hyperostosis frontalis interna, in the absence of the Morgagni or Stewart-Morel syndromes, is described. In addition to conventional neuropsychological measures EW was administered one nonspatial and two spatial self ordered working memory tasks, as well as a standard measure of fluid intelligence or g. She showed impaired performance on all three self ordered working memory tasks compared with a normal control group of 10 subjects matched for age, education, sex, and IQ. By contrast, her performance on the fluid intelligence test was comparable with that of the controls. It is concluded that the compression of dorsolateral frontal cortex accompanying hyperostosis frontalis interna may produce selective cognitive impairment.

Phenotypic characterization of five dendritic cell subsets in human tonsils

Heterogeneous expression of several antigens on the three currently defined tonsil dendritic cell (DC) subsets encouraged us to re-examine tonsil DCs using a new method that minimized DC differentiation and activation during their preparation. Three-color flow cytometry and dual-color immunohistology was used in conjunction with an extensive panel of antibodies to relevant DC-related antigens to analyze lin(-) HLA-DR+ tonsil DCs. Here we identify, quantify, and locate five tonsil DC subsets based on their relative expression of the HLA-DR, CD11c, CD13, and CD123 antigens. In situ localization identified four of these DC subsets as distinct interdigitating DC populations. These included three new interdigitating DC subsets defined as HLA-DRhi CD11c(+) DCs, HLA-DRmod CD11c+ CD13(+) DCs, and HLA-DRmod CD11c(-) CD123(-) DCs, as well as the plasmacytoid DCs (HLA-DRmod CD11c- CD123(+)). These subsets differed in their expression of DC-associated differentiation/activation antigens and co-stimulator molecules including CD83, CMRF-44, CMRF-56, 2-7, CD86, and 4-1BB ligand. The fifth HLA-DRmod CD11c(+) DC subset was identified as germinal center DCs, but contrary to previous reports they are redefined as lacking the CD13 antigen. The definition and extensive phenotypic analysis of these five DC subsets In human tonsil extends our understanding of the complexity of DC biology.

Functional heterogeneity within rhodamine123(lo) Hoechst33342(lo/sp) primitive hemopoietic stem cells revealed by pyronin Y

Objective. The aim of this study was to determine the function of primitive hematopoietic stem cells (PHSC) at phases G(0) and G(1) of the cell cycle. Materials and Methods. A combination of supravital dyes rhodamine123 (Rh), Hoechst33342 (Ho), and pyronin (PY) was used to isolate the G(0) and G(1) subsets of PHSC. A competitive repopulation assay was used to evaluate their in vivo function. Results. We confirmed that the Rh(lo)Lin(-)Kit(+)Sca-1(+) PHSC were relatively quiescent when compared with the more mature Rh(hi)Lin(-)Kit(+)Sca-1 HSC and Rh(hi)Lin(-)Kit(+)Sca-1(-) progenitors. In addition, cells with Rh(lo)Lin(-)Kit(+)Sca-1(+), Rh(lo)Ho(lo)Lin(-)Sca-1(+), or Rh(lo)Ho(sp)Lin(-)Sca-1(+) phenotypes identified the same cell population. We further subfractionated the Rh(lo)Ho(lo/sp)Lin(-)Sca-1(+) PHSC using PY into PYlo and PYhi subsets. Limiting dilution analysis revealed that the frequency of long-term in vivo competitive repopulating units (CRU) of the (PYRhHolo/sp)-Rh-lo-Ho-lo PHSC was 1 in 10 cells, whereas there was at least a three-fold lower frequency in those isolated at the G(1) phase (PYhi) We found a dose-dependent PY-mediated cytotoxicity that at moderate concentration affected most of the murine hematopoietic compartment but spared the early HSC compartment. Conclusion. Our data confirm that the HSC compartment is hierarchically ordered on the basis of quiescence and further extend this concept to PY-mediated cytotoxicity. PY supravital dye can be used to reveal functional heterogeneity within the (RhHolosp)-Ho-lo PHSC population but is of limited use in dissecting the relatively more mature hematopoietic stem/progenitor cell population. (C) 2001 International Society for Experimental Hematology. Published by Elsevier Science Inc.