Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “model selection”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 559 records · Page 31Linked to original sources
PubMed1990

The generalized multiplicative model for viability selection at multiple loci.

Selection due to differential viability is studied in an n-locus two-allele model using a set indexation that allows the simplicity of the one-locus two-allele model to be carried to multi-locus models. The existence condition is analyzed for polymorphic equilibria with linkage equilibrium: Robbins' equilibria. The local stability condition is given for the Robbins' equilibria on the boundaries in the generalized non-epistatic selection regimes of Karlin and Liberman (1979). These generalized non-epistatic regimes include the additive selection model, the multiplicative selection model and the multiplicative interaction model, and their symmetric versions cover all the symmetric viability models.

Alleles↗
PubMed1988

The coalescent process in models with selection and recombination.

The statistical properties of the process describing the genealogical history of a random sample of genes at a selectively neutral locus which is linked to a locus at which natural selection operates are investigated. It is found that the equations describing this process are simple modifications of the equations describing the process assuming that the two loci are completely linked. Thus, the statistical properties of the genealogical process for a random sample at a neutral locus linked to a locus with selection follow from the results obtained for the selected locus. Sequence data from the alcohol dehydrogenase (Adh) region of Drosophila melanogaster are examined and compared to predictions based on the theory. It is found that the spatial distribution of nucleotide differences between Fast and Slow alleles of Adh is very similar to the spatial distribution predicted if balancing selection operates to maintain the allozyme variation at the Adh locus. The spatial distribution of nucleotide differences between different Slow alleles of Adh do not match the predictions of this simple model very well.

Alcohol Dehydrogenase↗
PubMedDate not supplied

[ A selective filter model of the potassium channel].

A model based on analogy between filter and crown-ether molecule in a two-phase system organic solvent-water is proposed for potassium channel selective filter. The selectivity of K+-channel can be quantitatively described by this model.

Cell Membrane Permeability↗
PubMed2006

Gene selection in cancer classification using sparse logistic regression with Bayesian regularization.

MOTIVATION: Gene selection algorithms for cancer classification, based on the expression of a small number of biomarker genes, have been the subject of considerable research in recent years. Shevade and Keerthi propose a gene selection algorithm based on sparse logistic regression (SLogReg) incorporating a Laplace prior to promote sparsity in the model parameters, and provide a simple but efficient training procedure. The degree of sparsity obtained is determined by the value of a regularization parameter, which must be carefully tuned in order to optimize performance. This normally involves a model selection stage, based on a computationally intensive search for the minimizer of the cross-validation error. In this paper, we demonstrate that a simple Bayesian approach can be taken to eliminate this regularization parameter entirely, by integrating it out analytically using an uninformative Jeffrey's prior. The improved algorithm (BLogReg) is then typically two or three orders of magnitude faster than the original algorithm, as there is no longer a need for a model selection step. The BLogReg algorithm is also free from selection bias in performance estimation, a common pitfall in the application of machine learning algorithms in cancer classification. RESULTS: The SLogReg, BLogReg and Relevance Vector Machine (RVM) gene selection algorithms are evaluated over the well-studied colon cancer and leukaemia benchmark datasets. The leave-one-out estimates of the probability of test error and cross-entropy of the BLogReg and SLogReg algorithms are very similar, however the BlogReg algorithm is found to be considerably faster than the original SLogReg algorithm. Using nested cross-validation to avoid selection bias, performance estimation for SLogReg on the leukaemia dataset takes almost 48 h, whereas the corresponding result for BLogReg is obtained in only 1 min 24 s, making BLogReg by far the more practical algorithm. BLogReg also demonstrates better estimates of conditional probability than the RVM, which are of great importance in medical applications, with similar computational expense. AVAILABILITY: A MATLAB implementation of the sparse logistic regression algorithm with Bayesian regularization (BLogReg) is available from http://theoval.cmp.uea.ac.uk/~gcc/cbl/blogreg/

Algorithms↗
PubMed2006

Demographic models inform selection of biocontrol agents for garlic mustard (Alliaria petiolata).

Nonindigenous invasive plants pose a major threat to natural communities worldwide. Biological control of weeds via selected introduction of their natural enemies can affect control over large spatial areas but also risk nontarget effects. To maximize effectiveness while minimizing risk, weed biocontrol programs should introduce the minimum number of host-specific natural enemies necessary to control an invasive nonindigenous plant. We used elasticity analysis of a matrix model to help inform biocontrol agent selection for garlic mustard (Alliaria petiolata (M. Bieb.) Cavara and Grande). The Eurasian biennial A. petiolata is considered one of the most problematic invaders of temperate forests in North America. Four weevil species in the genus Ceutorhynchus (Coleoptera: Curculionidae) are currently considered potential biocontrol agents. These species attack rosettes (C. scrobicollis), stems (C. roberti, C. alliariae), and seeds (C. constrictus) of A. petiolata. Elasticity analyses using A. petiolata demographic parameters from North America indicated that changes in the rosette-to-flowering-plant transition and changes in fecundity consistently had the greatest impact on population growth rate. These results suggest that attack by the rosette-feeder C. scrobicollis, which reduces overwintering survival, and seed or stem feeders that reduce seed output should be particularly effective. Model outcomes differed greatly as A. petiolata demographic parameters were varied within ranges observed in North America, indicating that successful control of A. petiolata populations may occur under some, but not all, conditions. Using these a priori analyses we predict: (1) rosette mortality and reduction of seed output will be the most important factors determining A. petiolata demography; (2) the root-crown feeder C. scrobicollis will have the most significant impact on A. petiolata demography; (3) releases of single control agents are unlikely to control A. petiolata across its full range of demographic variability; (4) combinations of agents that simultaneously reduce rosette survival and seed production will be required to suppress the most vigorous A. petiolata populations. These predictions can be tested using established long-term monitoring sites coupled with a designed release program. If demographic models can successfully predict biocontrol agent impact on invasive plant populations, a continued dialogue and collaboration between empirical and theoretical approaches may be the key to the development of successful biocontrol tactics for plant invaders in the future.

Animals↗
PubMed2006

Variable selection for logistic regression using a prediction-focused information criterion.

In biostatistical practice, it is common to use information criteria as a guide for model selection. We propose new versions of the focused information criterion (FIC) for variable selection in logistic regression. The FIC gives, depending on the quantity to be estimated, possibly different sets of selected variables. The standard version of the FIC measures the mean squared error of the estimator of the quantity of interest in the selected model. In this article, we propose more general versions of the FIC, allowing other risk measures such as the one based on L(p) error. When prediction of an event is important, as is often the case in medical applications, we construct an FIC using the error rate as a natural risk measure. The advantages of using an information criterion which depends on both the quantity of interest and the selected risk measure are illustrated by means of a simulation study and application to a study on diabetic retinopathy.

Biometry↗
PubMed2006

Correlation between brain/plasma ratios and efficacy in neuropathic pain models of selective metabotropic glutamate receptor 1 antagonists.

We have discovered a novel, potent, and selective triazafluorenone series of metabotropic glutamate receptor 1 (mGluR1) antagonists with efficacy in various rat pain models. Pharmacokinetic and pharmacodynamic profiles of these triazafluorenone analogs revealed that brain/plasma ratios of these mGluR1 antagonists were important to achieve efficacy in neuropathic pain models. This correlation could be used to guide our in vivo SAR (structure-activity relationship) modification. For example, compound 4a has a brain/plasma ratio of 0.34, demonstrating only moderate efficacy in neuropathic pain models. On the other hand, antagonist 4b with a brain/plasma ratio of 2.70 was fully efficacious in neuropathic pain models.

Animals↗
PubMed1983

A quantitative genetic model of reciprocal altruism: a condition for kin or group selection to prevail.

A condition is derived for reciprocal altruism to evolve by kin or group selection. It is assumed that many additively acting genes of small effect and the environment determine the probability that an individual is a reciprocal altruist, as opposed to being unconditionally selfish. The particular form of reciprocal altruism considered is TIT FOR TAT, a strategy that involves being altruistic on the first encounter with another individual and doing whatever the other did on the previous encounter in subsequent encounters with the same individual. Encounters are restricted to individuals of the same generation belonging to the same kin or breeding group, but first encounters occur at random within that group. The number of individuals with which an individual interacts is assumed to be the same within any kin or breeding group. There are 1 + i expected encounters between two interacting individuals. On any encounter, it is assumed that an individual who behaves altruistically suffers a cost in personal fitness proportional to c while improving his partner's fitness by the same proportion of b. Then, the condition for kin or group selection to prevail is [Formula: see text] if group size is sufficiently large and the group mean and the within-group genotypic variance of the trait value (i.e., the probability of being a TIT-FOR-TAT strategist) are uncorrelated. Here, C, Vb, and Tb are the population mean, between-group variance, and between-group third central moment of the trait value and r is the correlation between the additive genotypic values of interacting kin or of individuals within the same breeding group. The right-hand side of the above inequality is monotone decreasing in C if we hold Tb/Vb constant, and kin and group selection become superfluous beyond a certain threshold value of C. The effect of finite group size is also considered in a kin-selection model.

Altruism↗
PubMed2006

Putting competition strategies into ideal free distribution models: habitat selection as a tug of war.

When resources are patchily distributed in an environment, behavioral ecologists frequently turn to ideal free distribution (IFD) models to predict the spatial distribution of organisms. In these models, predictions about distributions depend upon two key factors: the quality of habitat patches and the nature of competition between consumers. Surprisingly, however, no IFD models have explored the possibility that consumers modulate their competitive efforts in an evolutionarily stable manner. Instead, previous models assume that resource acquisition ability and competition are fixed within species or within phenotypes. We explored the consequences of adaptive modulation of competitive effort by incorporating tug-of-war theory into payoff equations from the two main classes of IFD models (continuous input (CI) and interference). In the models we develop, individuals can increase their share of the resources available in a patch, but do so at the costs of increased resource expenditures and increased negative interactions with conspecifics. We show how such models can provide new hypotheses to explain what are thought to be deviations from IFDs (e.g., the frequent observation of fewer animals than predicted in "good" patches of habitat). We also detail straightforward predictions made uniquely by the models we develop, and we outline experimental tests that will distinguish among alternatives.

Animals↗
PubMed2006

Land-use forecasting and hydrologic model integration for improved land-use decision support.

This paper develops a methodology for integrating a land-use forecasting model with an event scale, rainfall-runoff model in support of improving land-use policy formulation at the watershed scale. The models selected for integration are loosely coupled, structured upon a common GIS platform that facilitates data exchange. The hydrologic model HEC-HMS is calibrated for a specific storm event that occurred within central Washington State. The land-use forecasting model, What If? is implemented to forecast future spatial distributions of low-density residential land-uses under low and high population growth estimates. Forecasted land-use distribution patterns for the years 2015, 2025, and 2050 are then used as land-use data input for the calibrated hydrologic model, keeping all other parameters constant. Impacts to the stream discharge hydrograph are predicted as the study area becomes increasingly developed as forecasted by What If?. The initial results of this integration process demonstrate the synergy that can be generated through the linkage of the selected models. The ability to quantifiably forecast the potential hydrologic implications of proposed land-use policies before their implementation offers land-use decision-makers a valuable tool for discerning which proposed land-use alternatives will be effective at minimizing storm water runoff.

Conservation of Natural Resources↗
PubMed1984

Evolutionary dynamics in frequency-dependent two-phenotype models.

General frequency-dependent selection models based on two phenotypic classes are analyzed with underlying one-locus multiallele phenotypic determination systems in diploid populations. It is proved that the mean phenotypic fitnesses tend to equality over discrete generations and genetic mutations if a phenotypic polymorphism is to be maintained. The exact conditions are examined. The present results are valid for a wide class of models whenever random groupings or assortative patterns based on phenotype and affecting fitness, linearly or not, are independent of sex, mating preferences, or kinship. They can also be applied to two-sex haploid models.

Diploidy↗
PubMed2001

How the brain encodes the order of letters in a printed word: the SERIOL model and selective literature review.

This paper describes a novel theoretical framework of how the position of a letter within a string is encoded, the SERIOL model (sequential encoding regulated by inputs to oscillations within letter units). Letter order is represented by a temporal activation pattern across letter units, as is consistent with current theories of information coding based on the precise timing of neural spikes. The framework specifies how this pattern is invoked via an activation gradient that interacts with subthreshold oscillations and how it is decoded via contextual units that activate word units. Using mathematical modeling, this theoretical framework is shown to account for the experimental data from a wide variety of string-processing studies, including hemispheric asymmetries, the optimal viewing position, and positional priming effects.

Attention↗
PubMed2006

Why do we still use stepwise modelling in ecology and behaviour?

1. The biases and shortcomings of stepwise multiple regression are well established within the statistical literature. However, an examination of papers published in 2004 by three leading ecological and behavioural journals suggested that the use of this technique remains widespread: of 65 papers in which a multiple regression approach was used, 57% of studies used a stepwise procedure. 2. The principal drawbacks of stepwise multiple regression include bias in parameter estimation, inconsistencies among model selection algorithms, an inherent (but often overlooked) problem of multiple hypothesis testing, and an inappropriate focus or reliance on a single best model. We discuss each of these issues with examples. 3. We use a worked example of data on yellowhammer distribution collected over 4 years to highlight the pitfalls of stepwise regression. We show that stepwise regression allows models containing significant predictors to be obtained from each year's data. In spite of the significance of the selected models, they vary substantially between years and suggest patterns that are at odds with those determined by analysing the full, 4-year data set. 4. An information theoretic (IT) analysis of the yellowhammer data set illustrates why the varying outcomes of stepwise analyses arise. In particular, the IT approach identifies large numbers of competing models that could describe the data equally well, showing that no one model should be relied upon for inference.

Algorithms↗
PubMed2002

Combined data, Bayesian phylogenetics, and the origin of the New Zealand cicada genera.

We have applied Bayesian and maximum likelihood methods of phylogenetic estimation to data from four mitochondrial genes (COI, COII, 12S, and 16S) and a single nuclear gene (EF1alpha) from several genera of New Zealand, Australian, and New Caledonian cicada taxa. We specifically focused on the heterogeneity of phylogenetic signal among the different data partitions and the biogeographic origins of the New Zealand cicada fauna. The Bayesian analyses circumvent many of the problems associated with other statistical tests for comparing data partitions. We took an information-theoretic approach to model selection based on the Akaike Information Criterion (AIC). This approach indicated that there was considerable uncertainty in identifying the best-fit model for some of the partitions. Additionally, a large amount of uncertainty was associated with many parameter estimates from the substitution model. However, a sensitivity analysis on the combined dataset indicated that the model selection uncertainty had little effect on estimates of topology because these estimates were largely insensitive to changes in the assumed model. This outcome suggests strong signal in our data. Our analyses support a New Caledonian affiliation of the New Zealand cicada genera Maoricicada, Kikihia, and Rhodopsalta and Australian affinities for the genera Amphipsalta and Notopsalta. This result was surprising, given that previous cicada biologists suspected a close relationship between Amphipsalta, Notopsalta, and Rhodopsalta based on genitalic characters. Relationships among the closely related genera Maoricicada, Kikihia, and Rhodopsalta were poorly resolved, the mitochondrial data and the EF1alpha data favoring different arrangements within this clade.

Animals↗
PubMed1988

Guanethidine adrenergic neuropathy: an animal model of selective autonomic neuropathy.

Chronic administration of guanethidine to adult rats induces a selective autoimmune adrenergic neuropathy. Physiological and biochemical features of this disorder in the peripheral nervous system were explored in young adult Sprague-Dawley rats given daily intraperitoneal guanethidine monosulfate for 5 weeks. Control rats received daily saline injections. The guanethidine-treated animals gained less weight, had ptosis, and had a lower mean arterial blood pressure in the supine and upright tilted positions. Norepinephrine was depleted in the peroneal, sural, tibial, and vagal nerves, the nutrient artery to the tibial nerve and in the superior cervical sympathetic ganglion of the drug-treated animals. On light microscopy, there was an inflammatory cell infiltrate and neuron loss in the superior cervical ganglion. Caudal and sciatic-tibial nerve conduction values were well preserved in the guanethidine-treated animals as was the 'C' potential derived from unmyelinated vagal fibers recorded in an in vitro chamber. The 'C' potential recorded from the cervical sympathetic trunk, however, was reduced in amplitude correlating with the loss of norepinephrine content in the harvested contralateral superior cervical sympathetic ganglion. The findings further support the view that guanethidine produces a selective adrenergic neuropathy in the rat--providing a useful standard with which to gauge autonomic involvement in other models of neuropathy. In addition, loss of the cervical sympathetic 'C' potential suggests that this presumed preganglionic structure also contains postganglionic adrenergic fibers.

Animals↗
PubMed2006

[Effects of different durations of thromboembolism on blood gases, hemodynamics, pulmonary arteriography and thrombo-pathology in a canine model with selective embolization of pulmonary lobar arteries].

OBJECTIVE: To investigate the effects of different durations of thromboembolism on blood gases, hemodynamic parameters, pulmonary arteriography and thrombo-pathology in an animal model mimicking chronic pulmonary thromboembolism (PTE). METHODS: Sixteen dogs were embolized with five thrombi developed by autologous blood into the left lower pulmonary artery (n = 15) and the right lower pulmonary artery (n = 1, used to confirm the available method of selective embolization). The 15 dogs were divided into three groups: sham group (n = 5), one-week group (n = 5) and two-week group (n = 5) according to the different durations of embolization. Swan-Ganz catheter was used to guide a plastic duct, through which the thrombi were injected selectively into the left or right lower pulmonary artery by X-ray fluoroscopy. Local pulmonary arteriography of lower pulmonary arteries was taken. Blood pressure (BP), and blood gases were measured. Central venous pressure (CVP), mean pulmonary arterial pressure (MPAP), pulmonary arteriole wedge pressure (PAWP), and cardiac output (CO) were recorded, and pulmonary vascular resistance (PVR) was calculated. Each dog underwent muscular injection with tranexamic acid for one or two weeks to prevent thrombolysis. The lower lung lobe was dissected to confirm the thromboembolism after one or two weeks. The lung sections were stained with phosphotungstic acid hematoxylin (PTAH) to observe thromboemboli with optical microscopy. RESULTS: In the PTE group, PaO(2)/FiO(2), MPAP and PVR changed significantly as compared to baseline values (P < 0.05) after one hour of embolization, with MPAP increasing from (15 +/- 3) mm Hg to (21 +/- 4) mm Hg, PVR increasing from (178 +/- 114) mm Hg.s/L to (404 +/- 260) mm Hg.s/L, and PaO(2)/FiO(2) decreasing from (508 +/- 58) mm Hg to (395 +/- 100) mm Hg; these parameters returned to the baseline values one or two weeks later. After embolization, pulmonary arteriography demonstrated lower lobar artery cut-off perfusion defects. One week later, pulmonary arteriography demonstrated irregularities and stiffness of the arterial wall, enlarged proximal part of lower pulmonary artery and cut-off perfusion defects. Poor filling at embolus site was evident after embolization for two weeks. In the 1-week PTE group, organized tissue covered with the blue-purple fibrin nest was observed in the thrombus with PTAH stain. In the two-week group, the well organized thrombi were partially recanalized and surrounded and invaded by hyperplastic tissues from pulmonary artery wall. CONCLUSIONS: A canine model mimicking chronic PTE can be established by the use of fibrinolytic inhibitor tranexamic acid. Different manifestations on pulmonary arteriography and varied degree of organization of thrombi are evident at different times after embolization.

Angiography↗