Bayesian adaptive designs in early phase clinical trials

There are two practical challenges in the phase I clinical trial conduct: lack of transparency to physicians, and the late onset toxicity. In my dissertation, Bayesian approaches are used to address these two problems in clinical trial designs. The proposed simple optimal designs cast the dose finding problem as a decision making process for dose escalation and deescalation. The proposed designs minimize the incorrect decision error rate to find the maximum tolerated dose (MTD). For the late onset toxicity problem, a Bayesian adaptive dose-finding design for drug combination is proposed. The dose-toxicity relationship is modeled using the Finney model. The unobserved delayed toxicity outcomes are treated as missing data and Bayesian data augment is employed to handle the resulting missing data. Extensive simulation studies have been conducted to examine the operating characteristics of the proposed designs and demonstrated the designs' good performances in various practical scenarios.^

Speaker diarization : "who spoke when"

Speaker diarization is the process of annotating an input audio with information that attributes temporal regions of the audio signal to their respective sources, which may include both speech and non-speech events. For speech regions, the diarization system also specifies the locations of speaker boundaries and assign relative speaker labels to each homogeneous segment of speech. In short, speaker diarization systems effectively answer the question of ‘who spoke when’. There are several important applications for speaker diarization technology, such as facilitating speaker indexing systems to allow users to directly access the relevant segments of interest within a given audio, and assisting with other downstream processes such as summarizing and parsing. When combined with automatic speech recognition (ASR) systems, the metadata extracted from a speaker diarization system can provide complementary information for ASR transcripts including the location of speaker turns and relative speaker segment labels, making the transcripts more readable. Speaker diarization output can also be used to localize the instances of specific speakers to pool data for model adaptation, which in turn boosts transcription accuracies. Speaker diarization therefore plays an important role as a preliminary step in automatic transcription of audio data. The aim of this work is to improve the usefulness and practicality of speaker diarization technology, through the reduction of diarization error rates. In particular, this research is focused on the segmentation and clustering stages within a diarization system. Although particular emphasis is placed on the broadcast news audio domain and systems developed throughout this work are also trained and tested on broadcast news data, the techniques proposed in this dissertation are also applicable to other domains including telephone conversations and meetings audio. Three main research themes were pursued: heuristic rules for speaker segmentation, modelling uncertainty in speaker model estimates, and modelling uncertainty in eigenvoice speaker modelling. The use of heuristic approaches for the speaker segmentation task was first investigated, with emphasis placed on minimizing missed boundary detections. A set of heuristic rules was proposed, to govern the detection and heuristic selection of candidate speaker segment boundaries. A second pass, using the same heuristic algorithm with a smaller window, was also proposed with the aim of improving detection of boundaries around short speaker segments. Compared to single threshold based methods, the proposed heuristic approach was shown to provide improved segmentation performance, leading to a reduction in the overall diarization error rate. Methods to model the uncertainty in speaker model estimates were developed, to address the difficulties associated with making segmentation and clustering decisions with limited data in the speaker segments. The Bayes factor, derived specifically for multivariate Gaussian speaker modelling, was introduced to account for the uncertainty of the speaker model estimates. The use of the Bayes factor also enabled the incorporation of prior information regarding the audio to aid segmentation and clustering decisions. The idea of modelling uncertainty in speaker model estimates was also extended to the eigenvoice speaker modelling framework for the speaker clustering task. Building on the application of Bayesian approaches to the speaker diarization problem, the proposed approach takes into account the uncertainty associated with the explicit estimation of the speaker factors. The proposed decision criteria, based on Bayesian theory, was shown to generally outperform their non- Bayesian counterparts.

Ten Years of the Relative Risk Model and Regional Scale Ecological Risk Assessment

It has been 10 years since the publication of the relative risk model (RRM) for regional scale ecological risk assessment. The approach has since been used successfully for a variety of freshwater, marine, and terrestrial environments in North America, South America, and Australia. During this period the types of stressors have been expanded to include more than contaminants. Invasive species, habitat loss, stream alteration and blockage, temperature, change in land use, and climate have been incorporated into the assessments. Major developments in the RRM have included the extensive use of geographical information systems, uncertainty analysis using Monte Carlo techniques, and its application to retrospective assessments to determine causation. The future uses of the RRM include assessments for forestry and conservation management, an increasing use in invasive species evaluation, and in sustainability. Developments in risk communication, the use of Bayesian approaches, and in uncertainty analyses are on the horizon.

The complete mitochondrial genomes of the whistling duck (Dendrocygna javanica) and black swan (Cygnus atratus): dating evolutionary divergence in Galloanserae

Galloanserae is an ancient and diverse avian group, for which comprehensive molecular evidence relevant to phylogenetic analysis in the context of molecular chronology is lacking. In this study, we present two additional mitochondrial genome sequences of Galloanserae (the whistling duck, Dendrocygna javanica, and the black swan, Cygnus atratus) to broaden the scope of molecular phylogenetic reconstruction. The lengths of the whistling duck's and black swan's mitochondrial genomes are 16,753 and 16,748 bases, respectively. Phylogenetic analyses suggest that Dendrocygna is more likely to be in a basal position of the branch consisting of Anatinae and Anserinae, an affiliation that does not conform to its traditional classification. Bayesian approaches were employed to provide a rough timescale for Galloanserae evolution. In general, a narrow range of 95% confidence intervals gave younger estimates than those based on limited genes and estimated that at least two lineages originated before the Coniacian epoch around 90 MYA, well before the Cretaceous-Tertiary boundary. In addition, these results, which were compatible with estimates from fossil evidence, also imply that the origin of numerous genera in Anseriformes took place in the late Oligocene to early Miocene. Taken together, the results presented here provide a working framework for future research on Galloanserae evolution, and they underline the utility of whole mitochondrial genome sequences for the resolution of deep divergence.

Towards a Unified Theory of Neocortex: Laminar Cortical Circuits for Vision and Cognition

A key goal of computational neuroscience is to link brain mechanisms to behavioral functions. The present article describes recent progress towards explaining how laminar neocortical circuits give rise to biological intelligence. These circuits embody two new and revolutionary computational paradigms: Complementary Computing and Laminar Computing. Circuit properties include a novel synthesis of feedforward and feedback processing, of digital and analog processing, and of pre-attentive and attentive processing. This synthesis clarifies the appeal of Bayesian approaches but has a far greater predictive range that naturally extends to self-organizing processes. Examples from vision and cognition are summarized. A LAMINART architecture unifies properties of visual development, learning, perceptual grouping, attention, and 3D vision. A key modeling theme is that the mechanisms which enable development and learning to occur in a stable way imply properties of adult behavior. It is noted how higher-order attentional constraints can influence multiple cortical regions, and how spatial and object attention work together to learn view-invariant object categories. In particular, a form-fitting spatial attentional shroud can allow an emerging view-invariant object category to remain active while multiple view categories are associated with it during sequences of saccadic eye movements. Finally, the chapter summarizes recent work on the LIST PARSE model of cognitive information processing by the laminar circuits of prefrontal cortex. LIST PARSE models the short-term storage of event sequences in working memory, their unitization through learning into sequence, or list, chunks, and their read-out in planned sequential performance that is under volitional control. LIST PARSE provides a laminar embodiment of Item and Order working memories, also called Competitive Queuing models, that have been supported by both psychophysical and neurobiological data. These examples show how variations of a common laminar cortical design can embody properties of visual and cognitive intelligence that seem, at least on the surface, to be mechanistically unrelated.

Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem

This paper studies the multiplicity-correction effect of standard Bayesian variable-selection priors in linear regression. Our first goal is to clarify when, and how, multiplicity correction happens automatically in Bayesian analysis, and to distinguish this correction from the Bayesian Ockham's-razor effect. Our second goal is to contrast empirical-Bayes and fully Bayesian approaches to variable selection through examples, theoretical results and simulations. Considerable differences between the two approaches are found. In particular, we prove a theorem that characterizes a surprising aymptotic discrepancy between fully Bayes and empirical Bayes. This discrepancy arises from a different source than the failure to account for hyperparameter uncertainty in the empirical-Bayes estimate. Indeed, even at the extreme, when the empirical-Bayes estimate converges asymptotically to the true variable-inclusion probability, the potential for a serious difference remains. © Institute of Mathematical Statistics, 2010.

Lognormal and gamma mixed negative binomial regression

In regression analysis of counts, a lack of simple and efficient algorithms for posterior computation has made Bayesian approaches appear unattractive and thus underdeveloped. We propose a lognormal and gamma mixed negative binomial (NB) regression model for counts, and present efficient closed-form Bayesian inference; unlike conventional Poisson models, the proposed approach has two free parameters to include two different kinds of random effects, and allows the incorporation of prior information, such as sparsity in the regression coefficients. By placing a gamma distribution prior on the NB dispersion parameter r, and connecting a log-normal distribution prior with the logit of the NB probability parameter p, efficient Gibbs sampling and variational Bayes inference are both developed. The closed-form updates are obtained by exploiting conditional conjugacy via both a compound Poisson representation and a Polya-Gamma distribution based data augmentation approach. The proposed Bayesian inference can be implemented routinely, while being easily generalizable to more complex settings involving multivariate dependence structures. The algorithms are illustrated using real examples. Copyright 2012 by the author(s)/owner(s).

Cape Verde coastal ecosystem: a study of community structure, trophic interactions and exploitation pattern

Tese de dout., Ciências e Tecnologia das Pescas, Faculdade de Ciências do Mar e do Ambiente, Universidade do Algarve, 2005

Phylogénie moléculaire du genre Salix L. (Salicaceae) en Amérique du Nord

La culture de saules (Salix sp.) est une pratique courante en Europe et en Amérique du Nord pour produire de la biomasse végétale. Cependant, le développement d’outils moléculaires est très récent. De plus, la phylogénie des saules est incomplète. Il y a un manque d’information pour les programmes de sélection d'espèces indigènes et pour la compréhension de l’évolution du genre. Le genre Salix inclut 500 espèces réparties principalement dans les régions tempérées et boréo-arctique de l’hémisphère nord. Nous avons obtenu l’ensemble des espèces retrouvées naturellement en Amérique (121 indigènes et introduites). Dans un premier temps, nous avons développé de nouveaux outils moléculaires et méthodes : extraction d’ADN, marqueurs microsatellites et gènes nucléaires. Puis, nous avons séquencé deux gènes chloroplastiques (matK et rbcL) et la région ITS. Les analyses phylogénétiques ont été réalisées selon trois approches : parcimonie, maximum de vraisemblance et Bayésienne. L’arbre d’espèces obtenu a un fort support et divise le genre Salix en deux sous-genres, Salix et Vetrix. Seize espèces ont une position ambiguë. La diversité génétique du sous-genre Vetrix est plus faible. Une phylogénie moléculaire complète a été établie pour les espèces américaines. D’autres analyses et marqueurs sont nécessaires pour déterminer les relations phylogénétiques entre certaines espèces. Nous affirmons que le genre Salix est divisé en deux clades.

An illustration of the modelling of cost and efficacy data from a clinical trial

Health care providers, purchasers and policy makers need to make informed decisions regarding the provision of cost-effective care. When a new health care intervention is to be compared with the current standard, an economic evaluation alongside an evaluation of health benefits provides useful information for the decision making process. We consider the information on cost-effectiveness which arises from an individual clinical trial comparing the two interventions. Recent methods for conducting a cost-effectiveness analysis for a clinical trial have focused on the net benefit parameter. The net benefit parameter, a function of costs and health benefits, is positive if the new intervention is cost-effective compared with the standard. In this paper we describe frequentist and Bayesian approaches to cost-effectiveness analysis which have been suggested in the literature and apply them to data from a clinical trial comparing laparoscopic surgery with open mesh surgery for the repair of inguinal hernias. We extend the Bayesian model to allow the total cost to be divided into a number of different components. The advantages and disadvantages of the different approaches are discussed. In January 2001, NICE issued guidance on the type of surgery to be used for inguinal hernia repair. We discuss our example in the light of this information. Copyright © 2003 John Wiley & Sons, Ltd.

Elusive relationships within order fabales: phylogenetic analyses using matK and rbcL sequence data

The order Fabales, including Leguminosae, Polygalaceae, Quillajaceae and Surianaceae, represents a novel hypothesis emerging from angiosperm molecular phylogenies. Despite good support for the order, molecular studies to date have suggested contradictory, poorly supported interfamilial relationships. Our reappraisal of relationships within Fabales addresses past taxon sampling deficiencies, and employs parsimony and Bayesian approaches using sequences from the plastid regions rbcL (166 spp.) and matK (78 spp.). Five alternative hypotheses for interfamilial relationships within Fabales were recovered. The Shimodaira-Hasegawa test found the likelihood of a resolved topology significantly higher than the one calculated for a polytomy, but did not favour any of the alternative hypotheses of relationship within Fabales. In the light of the morphological evidence available and the comparative behavior of rbcL and matK, the topology recovering Polygalaceae as sister to the rest of the order Fabales with Leguminosae more closely related to Quillajaceae + Surianaceae, is considered the most likely hypothesis of interfamilial relationships of the order. Dating of selected crown clades in the Fabales phylogeny using penalized likelihood suggests rapid radiation of the Leguminosae, Polygalaceae, and (Quillajaceae + Surianaceae) crown clades.

Adaptive designs for Phase I dose-finding studies

Improving methodology for Phase I dose-finding studies is currently of great interest in pharmaceutical and medical research. This article discusses the current atmosphere and attitude towards adaptive designs and focuses on the influence of Bayesian approaches.

Combined phylogenetic analyses reveal interfamilial relationships and patterns of floral evolution in the eudicot order Fabales

Relationships between the four families placed in the angiosperm order Fabales (Leguminosae, Polygalaceae, Quillajaceae, Surianaceae) were hitherto poorly resolved. We combine published molecular data for the chloroplast regions matK and rbcL with 66 morphological characters surveyed for 73 ingroup and two outgroup species, and use Parsimony and Bayesian approaches to explore matrices with different missing data. All combined analyses using Parsimony recovered the topology Polygalaceae (Leguminosae (Quillajaceae + Surianaceae)). Bayesian analyses with matched morphological and molecular sampling recover the same topology, but analyses based on other data recover a different Bayesian topology: ((Polygalaceae + Leguminosae) (Quillajaceae + Surianaceae)). We explore the evolution of floral characters in the context of the more consistent topology: Polygalaceae (Leguminosae (Quillajaceae + Surianaceae)). This reveals synapomorphies for (Leguminosae (Quillajaceae + Surianaceae)) as the presence of free filaments and marginal/ventral placentation, for (Quillajaceae + Surianaceae) as pentamery and apocarpy, and for Leguminosae the presence of an abaxial median sepal and unicarpellate gynoecium. An octamerous androecium is synapomorphic for Polygalaceae. The development of papilionate flowers, and the evolutionary context in which these phenotypes appeared in Leguminosae and Polygalaceae, shows that the morphologies are convergent rather than synapomorphic within Fabales.

Solving the Levins' paradox in the logistic model to the population growth

We introduce a new method to improve Markov maps by means of a Bayesian approach. The method starts from an initial map model, wherefrom a likelihood function is defined which is regulated by a temperature-like parameter. Then, the new constraints are added by the use of Bayes rule in the prior distribution. We applied the method to the logistic map of population growth of a single species. We show that the population size is limited for all ranges of parameters, allowing thus to overcome difficulties in interpretation of the concept of carrying capacity known as the Levins paradox. © Published under licence by IOP Publishing Ltd.

Análise Bayesiana para a distribuição Exponencial-Logarítmica

Pós-graduação em Matematica Aplicada e Computacional - FCT