Logistic regression with Markov chains as covariates

The tobacco-specific nitrosamine 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanone (NNK) is an obvious carcinogen for lung cancer. Since CBMN (Cytokinesis-blocked micronucleus) has been found to be extremely sensitive to NNK-induced genetic damage, it is a potential important factor to predict the lung cancer risk. However, the association between lung cancer and NNK-induced genetic damage measured by CBMN assay has not been rigorously examined. ^ This research develops a methodology to model the chromosomal changes under NNK-induced genetic damage in a logistic regression framework in order to predict the occurrence of lung cancer. Since these chromosomal changes were usually not observed very long due to laboratory cost and time, a resampling technique was applied to generate the Markov chain of the normal and the damaged cell for each individual. A joint likelihood between the resampled Markov chains and the logistic regression model including transition probabilities of this chain as covariates was established. The Maximum likelihood estimation was applied to carry on the statistical test for comparison. The ability of this approach to increase discriminating power to predict lung cancer was compared to a baseline "non-genetic" model. ^ Our method offered an option to understand the association between the dynamic cell information and lung cancer. Our study indicated the extent of DNA damage/non-damage using the CBMN assay provides critical information that impacts public health studies of lung cancer risk. This novel statistical method could simultaneously estimate the process of DNA damage/non-damage and its relationship with lung cancer for each individual.^

Astronomically modulated Neogene sediment records of ODP Site 184-1148

General global cooling over the Neogene has been modulated by changes in Earth's orbital parameters. Investigations of deep-sea sediment sequences show that various orbital cycles can dominate climate records for different latitudes or for different time intervals. However, a comprehensive understanding of astronomical imprints over the entire Neogene has been elusive because of the general absence of long, continuous records extending beyond the Pliocene. We present benthic foraminiferal d18O and d13C records over the past 23 Ma at Ocean Drilling Program Site 1148 in the northern South China Sea and construct an astronomically tuned timescale (TJ08) for these records based on natural gamma radiation and color reflectance data at this site. Our results show that a 41 ka cycle has dominated sediment records at this location over the Neogene, displaying a linear response to orbital forcing. A 100 ka cycle has also been significant. However, it is correlated nonlinearly with Earth's orbital variations at the 100 ka band. The sediment records also display a prominent 405 ka cycle. Although this cycle was coherent with orbital forcing during the Oligocene and the early Miocene, it was not coherent with Earth's orbital variations at the 405 ka band over the whole Neogene. Amplification of Northern Hemisphere and Southern Hemisphere glaciation since the middle Miocene may be responsible for this change in sedimentary response. Our benthic foraminifera d18O and d13C records further exhibit amplitude variations with longer periods of 600, 1000, 1200, and 2400 ka. Apparently, these cycles are nonlinear responses to insolation forcing.

Regularized model learning in EDAs for continuous and multi-objective optimization

Probabilistic modeling is the de�ning characteristic of estimation of distribution algorithms (EDAs) which determines their behavior and performance in optimization. Regularization is a well-known statistical technique used for obtaining an improved model by reducing the generalization error of estimation, especially in high-dimensional problems. `1-regularization is a type of this technique with the appealing variable selection property which results in sparse model estimations. In this thesis, we study the use of regularization techniques for model learning in EDAs. Several methods for regularized model estimation in continuous domains based on a Gaussian distribution assumption are presented, and analyzed from di�erent aspects when used for optimization in a high-dimensional setting, where the population size of EDA has a logarithmic scale with respect to the number of variables. The optimization results obtained for a number of continuous problems with an increasing number of variables show that the proposed EDA based on regularized model estimation performs a more robust optimization, and is able to achieve signi�cantly better results for larger dimensions than other Gaussian-based EDAs. We also propose a method for learning a marginally factorized Gaussian Markov random �eld model using regularization techniques and a clustering algorithm. The experimental results show notable optimization performance on continuous additively decomposable problems when using this model estimation method. Our study also covers multi-objective optimization and we propose joint probabilistic modeling of variables and objectives in EDAs based on Bayesian networks, speci�cally models inspired from multi-dimensional Bayesian network classi�ers. It is shown that with this approach to modeling, two new types of relationships are encoded in the estimated models in addition to the variable relationships captured in other EDAs: objectivevariable and objective-objective relationships. An extensive experimental study shows the e�ectiveness of this approach for multi- and many-objective optimization. With the proposed joint variable-objective modeling, in addition to the Pareto set approximation, the algorithm is also able to obtain an estimation of the multi-objective problem structure. Finally, the study of multi-objective optimization based on joint probabilistic modeling is extended to noisy domains, where the noise in objective values is represented by intervals. A new version of the Pareto dominance relation for ordering the solutions in these problems, namely �-degree Pareto dominance, is introduced and its properties are analyzed. We show that the ranking methods based on this dominance relation can result in competitive performance of EDAs with respect to the quality of the approximated Pareto sets. This dominance relation is then used together with a method for joint probabilistic modeling based on `1-regularization for multi-objective feature subset selection in classi�cation, where six di�erent measures of accuracy are considered as objectives with interval values. The individual assessment of the proposed joint probabilistic modeling and solution ranking methods on datasets with small-medium dimensionality, when using two di�erent Bayesian classi�ers, shows that comparable or better Pareto sets of feature subsets are approximated in comparison to standard methods.

HF spectrum activity prediction model based on HMM for cognitive radio applications

Although most of the research on Cognitive Radio is focused on communication bands above the HF upper limit (30 MHz), Cognitive Radio principles can also be applied to HF communications to make use of the extremely scarce spectrum more efficiently. In this work we consider legacy users as primary users since these users transmit without resorting to any smart procedure, and our stations using the HFDVL (HF Data+Voice Link) architecture as secondary users. Our goal is to enhance an efficient use of the HF band by detecting the presence of uncoordinated primary users and avoiding collisions with them while transmitting in different HF channels using our broad-band HF transceiver. A model of the primary user activity dynamics in the HF band is developed in this work to make short-term predictions of the sojourn time of a primary user in the band and avoid collisions. It is based on Hidden Markov Models (HMM) which are a powerful tool for modelling stochastic random processes and are trained with real measurements of the 14 MHz band. By using the proposed HMM based model, the prediction model achieves an average 10.3% prediction error rate with one minute-long channel knowledge but it can be reduced when this knowledge is extended: with the previous 8 min knowledge, an average 5.8% prediction error rate is achieved. These results suggest that the resulting activity model for the HF band could actually be used to predict primary users activity and included in a future HF cognitive radio based station.

Cooperative off-policy prediction of markov decision processes in adaptive networks

We apply diffusion strategies to propose a cooperative reinforcement learning algorithm, in which agents in a network communicate with their neighbors to improve predictions about their environment. The algorithm is suitable to learn off-policy even in large state spaces. We provide a mean-square-error performance analysis under constant step-sizes. The gain of cooperation in the form of more stability and less bias and variance in the prediction error, is illustrated in the context of a classical model. We show that the improvement in performance is especially significant when the behavior policy of the agents is different from the target policy under evaluation.

On-road visual vehicle tracking using Markov chain Monte Carlo with metropolis sampling

In this study, a method for vehicle tracking through video analysis based on Markov chain Monte Carlo (MCMC) particle filtering with metropolis sampling is proposed. The method handles multiple targets with low computational requirements and is, therefore, ideally suited for advanced-driver assistance systems that involve real-time operation. The method exploits the removed perspective domain given by inverse perspective mapping (IPM) to define a fast and efficient likelihood model. Additionally, the method encompasses an interaction model using Markov Random Fields (MRF) that allows treatment of dependencies between the motions of targets. The proposed method is tested in highway sequences and compared to state-of-the-art methods for vehicle tracking, i.e., independent target tracking with Kalman filtering (KF) and joint tracking with particle filtering. The results showed fewer tracking failures using the proposed method.

A stochastic approximation algorithm with Markov chain Monte-Carlo method for incomplete data estimation problems

We propose a general procedure for solving incomplete data estimation problems. The procedure can be used to find the maximum likelihood estimate or to solve estimating equations in difficult cases such as estimation with the censored or truncated regression model, the nonlinear structural measurement error model, and the random effects model. The procedure is based on the general principle of stochastic approximation and the Markov chain Monte-Carlo method. Applying the theory on adaptive algorithms, we derive conditions under which the proposed procedure converges. Simulation studies also indicate that the proposed procedure consistently converges to the maximum likelihood estimate for the structural measurement error logistic regression model.

Melanoma angiogenesis and metastasis modulated by ribozyme targeting of the secreted growth factor pleiotrophin

Clinical and experimental evidence suggests that spreading of malignant cells from a localized tumor (metastasis) is directly related to the number of microvessels in the primary tumor. This tumor angiogenesis is thought to be mediated by tumor-cell-derived growth factors. However, most tumor cells express a multitude of candidate angiogenesis factors and it is difficult to decipher which of these are rate-limiting factors in vivo. Herein we use ribozyme targeting of pleiotrophin (PTN) in metastatic human melanoma cells to assess the significance of this secreted growth factor for angiogenesis and metastasis. As a model we used human melanoma cells (1205LU) that express high levels of PTN and metastasize from subcutaneous tumors to the lungs of experimental animals. In these melanoma cells, we reduced PTN mRNA and growth factor activity by transfection with PTN-targeted ribozymes and generated cell lines expressing different levels of PTN. We found that the reduction of PTN does not affect growth of the melanoma cells in vitro. In nude mice, however, tumor growth and angiogenesis were decreased in parallel with the reduced PTN levels and apoptosis in the tumors was increased. Concomitantly, the metastatic spread of the tumors from the subcutaneous site to the lungs was prevented. These studies support a direct link between tumor angiogenesis and metastasis through a secreted growth factor and identify PTN as a candidate factor that may be rate-limiting for human melanoma metastasis.

A model of multiplicative neural responses in parietal cortex.

Visual responses of neurons in parietal area 7a are modulated by a combined eye and head position signal in a multiplicative manner. Neurons with multiplicative responses can act as powerful computational elements in neural networks. In the case of parietal cortex, multiplicative gain modulation appears to play a crucial role in the transformation of object locations from retinal to body-centered coordinates. It has proven difficult to uncover single-neuron mechanisms that account for neuronal multiplication. Here we show that multiplicative responses can arise in a network model through population effects. Specifically, neurons in a recurrently connected network with excitatory connections between similarly tuned neurons and inhibitory connections between differently tuned neurons can perform a product operation on additive synaptic inputs. The results suggest that parietal responses may be based on this architecture.

Size-Dependent and Step-Modulated Supramolecular Electrochemical Properties of Catechol-Derived Adlayers at Pt(hkl) Surfaces

The electrochemical reactivity of catechol-derived adlayers is reported at platinum (Pt) single-crystal electrodes. Pt(111) and stepped vicinal surfaces are used as model surfaces possessing well-ordered nanometer-sized Pt(111) terraces ranging from 0.4 to 12 nm. The electrochemical experiments were designed to probe how the control of monatomic step-density and of atomic-level step structure can be used to modulate molecule–molecule interactions during self-assembly of aromatic-derived organic monolayers at metallic single-crystal electrode surfaces. A hard sphere model of surfaces and a simplified band formation model are used as a theoretical framework for interpretation of experimental results. The experimental results reveal (i) that supramolecular electrochemical effects may be confined, propagated, or modulated by the choice of atomic level crystallographic features (i.e.monatomic steps), deliberately introduced at metallic substrate surfaces, suggesting (ii) that substrate-defect engineering may be used to tune the macroscopic electronic properties of aromatic molecular adlayers and of smaller molecular aggregates.

Treatment-seeking behavior and delay in children with severe malaria in Uganda: results of a Markov analysis

Thesis (Master's)--University of Washington, 2016-06

Aspects of Markov Chains and Particle Systems

Thesis (Ph.D.)--University of Washington, 2016-06

Modulation of the antibody response by Porphyromonas gingivalis and Fusobacterium nucleatum in a mouse model

Successive immunization of mice with Fusobacterium nucleatum and Porphyromonas gingivalis has been shown to modulate the specific serum IgG responses to these organisms. The aim of this study was to investigate these antibody responses further by examining the IgG subclasses induced as well as the opsonizing properties of the specific antibodies. Serum samples from BALB/c mice immunized with F. nucleatum (gp1-F), P. gingivalis (gp2-P), P. gingivalis followed by F. nucleatum (gp3-PF) F. nucleatum followed by P. gingivalis (gp4-FP) or saline alone (gp5-S) were examined for specific IgG1 (Th2) and IgG2a (Th1) antibody levels using an ELISA and the opsonizing properties measured using a neutrophil chemiluminescence assay. While IgG1 and IgG2a subclasses were induced in all immunized groups, there was a tendency towards an IgG1 response in mice immunized with P. gingivalis alone, while immunization with F. nucleatum followed by P. gingivalis induced significantly higher anti-P. gingivalis IgG2a levels than IgG1. The maximum light output due to neutrophil phagocytosis of P. gingivalis occurred at 10 min using nonopsonized bacteria. Chemiluminescence was reduced using serum-opsonized P. gingivalis and, in particular, sera from P. gingivalis-immunized mice (gp2-P), with maximum responses occurring at 40 min. In contrast, phagocytosis of immune serum-opsonized F. nucleatum demonstrated peak light output at 10 min, while that of F. nucleatum opsonized with sera from saline injected mice (gp5-S) and control nonopsonized bacteria showed peak responses at 40 min. The lowest phagocytic response occurred using gp4-FP serum-opsonized F. nucleatum. In conclusion, the results of the present study have demonstrated a systemic Th1/Th2 response in mice immunized with P. gingivalis and/or F. nucleatum with a trend towards a Th2 response in P. gingivalis-immunized mice and a significantly increased anti-P. gingivalis IgG2a (Th1) response in mice immunized with F. nucleatum prior to P. gingivalis. Further, the inhibition of neutrophil phagocytosis of immune serum-opsonized P. gingivalis was modulated by the presence of anti-F. nucleatum antibodies, while anti-P. gingivalis antibodies induced an inhibitory effect on the phagocytic response to F. nucleatum.

A generalized Markov sampler

A recent development of the Markov chain Monte Carlo (MCMC) technique is the emergence of MCMC samplers that allow transitions between different models. Such samplers make possible a range of computational tasks involving models, including model selection, model evaluation, model averaging and hypothesis testing. An example of this type of sampler is the reversible jump MCMC sampler, which is a generalization of the Metropolis-Hastings algorithm. Here, we present a new MCMC sampler of this type. The new sampler is a generalization of the Gibbs sampler, but somewhat surprisingly, it also turns out to encompass as particular cases all of the well-known MCMC samplers, including those of Metropolis, Barker, and Hastings. Moreover, the new sampler generalizes the reversible jump MCMC. It therefore appears to be a very general framework for MCMC sampling. This paper describes the new sampler and illustrates its use in three applications in Computational Biology, specifically determination of consensus sequences, phylogenetic inference and delineation of isochores via multiple change-point analysis.