Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Bayesian inference”

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 469 records · Page 26Linked to original sources
PubMedDate not supplied

Evaluation of the monophyly of Fomitopsis using parsimony and MCMC methods.

To evaluate the monophyly of Fomitopsis and elucidate phylogenetic relationships of its members, partial nuclear large subunit (partial 28S) ribosomal RNA genes were sequenced from 10 species of Fomitopsis and 15 related species. Phylogenetic analyses indicated that Fomitopsis was phylogenetically heterogeneous and its members were divided into three subgroups. The constrained tree excluding F. palustris (the type species of Pilatoporus) from Fomitopsis core group was rejected, thus rejecting the taxonomic concept to segregate Pilatoporus from Fomitopsis. The monophyly of taxa belonging to F. rosea complex was rejected, thus rejecting the complex definition based on morphological similarities. The exclusion of Piptoporus betulinus (the type species of Piptoporus) from Fomitopsis core group was rejected and Piptoporus proved to be heterogeneous in both best MP and MAP trees. The monophyly of F. officinalis with Fomitopsis core group also was rejected. Fomitopsis officinalis was closely related to Antrodia xantha and formed an independent lineage from Fomitopsis core group at the basal position of brown rotting fungi comprising Antrodia, Daedalea, Fomitopsis, Piptoporus and Postia. The MAP tree topologyobtained from MCMC computation of Bayesian inference was similar to the one of the best MP tree based on the parsimony analysis but showed a higher likelihood score in the Kishino-Hasegawa test and reflected better evolutionary patterns for the phylogeny of Fomitopsis.

Bayes Theorem↗
PubMed1999

[Incidence of acute leukemias, lymphomas and thyroid cancers in children under 15 years, living around the Marcoule nuclear site from 1985 to 1995].

BACKGROUND: The aim of this investigation was to report incidence of childhood leukemia, lymphoma and thyroid neoplasms in children under 15 years of age living in the vicinity of the French Marcoule nuclear reprocessing plant. METHODS: This exhaustive and retrospective survey was carried out between 1985 and 1995 in children aged under 14 at the time of diagnosis and living inside a 35 kilometer zone around the nuclear site. 656 practitioners, 109 medical analysis laboratories and 5 hospitals or cancer institutes were investigated. A panel of experts checked each case. RESULTS: 48 cases of acute leukemia (39 acute lymphoid leukemia and 9 acute myeloid leukemia), 15 cases of lymphoma (8 Hodgkin lymphomas--53%--and 7 non hodgkinian lymphomas including 5 Burkitt lymphomas), 1 case of chronic myeloid leukemia and 1 case of papillary thyroid cancer, appeared among the 1,116,442 children-years followed. The total incidences of leukemias and lymphomas were respectively 4.12 and 1.29.10(-5). Standardised Incidence Ratios, calculated according to Poisson methods and bayesian inference, with various reference rates did not show any excess of risk: 100.67 (95% confidence interval 72-131) for leukemia. Children under 5 years old and living in non exposed areas to dominant winds or downstream rhodanian water drawing presented a 3 or 4 fold decreased risk of leukemia than others (the latter still having an identical risk to that of the general population). This was not true for lymphomas, nor for the other age groups. CONCLUSION: Over the entire zone, children do not have an increased risk of malignant hematology disease but health monitoring by a systematic collection of cases remains useful around Marcoule. The assumption of aquiferous or air contamination thus still remains questionable: further studies investigating models of contamination are needed to take into account all other nonionizing leucemogenic factors (benzene and viral injection in particular) or correlation studies between health indicators and dosimetry.

Acute Disease↗
PubMed2000

[How can one improve the understanding and communication of the importance of medical test results?].

Interpreting medical test results demands statistical reasoning on the part of doctors: How great is the probability of falsely diagnosing an illness based on a positive test result? This probability can be determined with the assistance of Bayes's Rule. Several studies show, however, that doctors often experience problems with these kinds of Bayesian inferences. We demonstrate that doctors' judgments can be considerably improved when numerical information is presented in a form easily accessible to the ways humans process information. This is not the case with the utilization of applied probabilities that has become customary, but is the case when the problem is presented in terms of "natural frequencies" that result from the counting of observed isolated cases in a natural environment. In a series of studies, we varied the representation format of the relevant statistical information. If the information was not presented in the form of probabilities or percentages but simply in natural frequencies, medical experts, as well as laymen, were able to improve their judgments significantly. And dealing with probabilities and percentages can also be easily learned: Two training programs, which showed how probabilities can be translated into natural frequencies, placed the participants in the position of being able to obtain very good results when solving these tasks. Finally, we discuss the impact of a comprehensible risk and utility communication on the doctor-patient relationship.

Bayes Theorem↗
PubMed2004

[Introduction to the methods of constructing phylogenetic trees with DNA sequences].

Construction of phylogenetic trees is a key means in molecular evolutionary studies. The methods of constructing phylogenetic trees include the distance-based methods, parsimony, maximum likelihood, and Bayesian inference methods. To resolve a special problem about phylogeny, several notices are necessary: first, to select the reasonable data at less bias as possible; second, to choose the proper method to reconstruct phylogenetic tree; third, to evaluate the conclusions and explain them on the field of evolution. The present paper provides a brief introduction of the principles of data selection and tree-construction methods, and discusses about their advantage and disadvantage points.

Base Sequence↗
PubMed2006

Neutral theory, phylogenies, and the relationship between phenotypic change and evolutionary rates.

The neutral theory of molecular evolution predicts that rates of phenotypic change are largely independent from genotypic change. A recent study by Bromham et al. (2002) confirmed this expectation, finding no evidence for correlated phenotypic and molecular evolutionary rates in animals. We reevaluate this hypothesis, sampling at different taxonomic levels in plants and animals, using Bayesian inference to reconstruct phylogenetic trees and estimate rates of molecular evolution. We use independent contrasts in branch lengths to maximize the information extracted from each of the trees and nodal posterior probabilities to assess the influence of phylogenetic error. Our results indicate that in vascular plants between 2% and 11% of the variation in phenotypic rates of change can be explained by the rate of genotypic change. These results may be explained by the idea that processes that affect general evolutionary rates, such as body size, may also be expected to influence rates of morphological change.

Animals↗
PubMed2006

[An approach to adaptive stereo brain image's segmentation].

This paper presents a new method for automatically segmenting brain parenchyma and cerebrospinal fluid in routine single-echo MR images. This method is based on the coupled Markov models. They can model intensity measurement at each voxel site to implement piecewise smoothness constraint, and at the same time, model discontinuities to control the interaction between each pair of the neighboring voxel. The method is to derive the maximum a posteriori estimate of the regions and the boundaries by using Bayesian inference and neighborhood constraints based on Markov random fields (MRFs) models. This method has the following desirable properties: (1) the brain image can be well classified into white matter, grey matter and cerebrospinal fluid (CSF), and (2) it has a better robustness to noise and intensity inhomogeneity.

Algorithms↗
PubMed1991

Information retrieval using a "digital book shelf".

WALT (Washington University's Approach to Lots of Text), is a prototype interface designed to support information retrieval research. The WALT interface serves as a "front end" to a wide array of retrieval engines including those based on Boolean retrieval, latent semantic indexing, term frequency--inverse document frequency, and Bayesian inference techniques. The WALT interface is composed of seven distinct components: a document examination component known as the Document Browsing Area; four navigation components called the Book Shelf, the Book Spine, the Table of Contents, and the Path Clipboard; a term-based information retrieval component called Control Panel; and a relevance feedback component known as the Reader Feedback Panel. WALT's most unique feature may be it's use of "book shelf" and "book spine" metaphors both to facilitate navigation and to provide a histogram-based display showing documents deemed appropriate for answering user queries.

Books↗
PubMed1995

Effective access to distributed heterogeneous medical text databases.

INQUERY is an advanced text information retrieval system developed by the Information Retrieval Laboratory of the University of Massachusetts in Amherst. It is based on Bayesian inference networks, which are probabilistic models for reasoning with multiple sources of uncertain evidence. The evidence, in this case, is the presence or absence of words and/or phrases in a document. Evidence is combined into belief that a document is relevant. The INQUERY retrieval engine has been developed with the support of ARPA, NSF, and industrial funding. It has a number of unique features and has achieved excellent results in the TIPSTER and TREC evaluations. Informatics research and application development using INQUERY has recently begun in the medical domain, including a new ARPA initiative concerned with clinical text. The features that we will focus on in this demonstration are: Automatic processing of natural language queries, including the extraction of phrases and specific medical concepts such as drug doses; Document selection through automatic relevance feedback and routing techniques, including the construction of complex queries using the INQUERY query language; The integration of conventional database techniques with text analysis and retrieval; Automatic thesaurus generation and query expansion using the PhraseFinder system; Distributed database access, including automatic database selection and merging of local searches; this will be demonstrated using a collection of medical databases; Retrieval based on passages, rather than whole documents.

Bayes Theorem↗
PubMed1997

Analysis of aerial survey data on Florida manatee using Markov chain Monte Carlo.

We assess population trends of the Atlantic coast population of Florida manatee, Trichechus manatus latirostris, by reanalyzing aerial survey data collected between 1982 and 1992. To do so, we develop an explicit biological model that accounts for the method by which the manatees are counted, the mammals' movement between surveys, and the behavior of the population total over time. Bayesian inference, enabled by Markov chain Monte Carlo, is used to combine the survey data with the biological model. We compute marginal posterior distributions for all model parameters and predictive distributions for future counts. Several conclusions, such as a decreasing population growth rate and low sighting probabilities, are consistent across different prior specifications.

Animals↗
PubMed2005

Bayesian and maximum likelihood phylogenetic analyses of protein sequence data under relative branch-length differences and model violation.

BACKGROUND: Bayesian phylogenetic inference holds promise as an alternative to maximum likelihood, particularly for large molecular-sequence data sets. We have investigated the performance of Bayesian inference with empirical and simulated protein-sequence data under conditions of relative branch-length differences and model violation. RESULTS: With empirical protein-sequence data, Bayesian posterior probabilities provide more-generous estimates of subtree reliability than does the nonparametric bootstrap combined with maximum likelihood inference, reaching 100% posterior probability at bootstrap proportions around 80%. With simulated 7-taxon protein-sequence datasets, Bayesian posterior probabilities are somewhat more generous than bootstrap proportions, but do not saturate. Compared with likelihood, Bayesian phylogenetic inference can be as or more robust to relative branch-length differences for datasets of this size, particularly when among-sites rate variation is modeled using a gamma distribution. When the (known) correct model was used to infer trees, Bayesian inference recovered the (known) correct tree in 100% of instances in which one or two branches were up to 20-fold longer than the others. At ratios more extreme than 20-fold, topological accuracy of reconstruction degraded only slowly when only one branch was of relatively greater length, but more rapidly when there were two such branches. Under an incorrect model of sequence change, inaccurate trees were sometimes observed at less extreme branch-length ratios, and (particularly for trees with single long branches) such trees tended to be more inaccurate. The effect of model violation on accuracy of reconstruction for trees with two long branches was more variable, but gamma-corrected Bayesian inference nonetheless yielded more-accurate trees than did either maximum likelihood or uncorrected Bayesian inference across the range of conditions we examined. Assuming an exponential Bayesian prior on branch lengths did not improve, and under certain extreme conditions significantly diminished, performance. The two topology-comparison metrics we employed, edit distance and Robinson-Foulds symmetric distance, yielded different but highly complementary measures of performance. CONCLUSIONS: Our results demonstrate that Bayesian inference can be relatively robust against biologically reasonable levels of relative branch-length differences and model violation, and thus may provide a promising alternative to maximum likelihood for inference of phylogenetic trees from protein-sequence data.

Bayes Theorem↗
PubMed2004

Molecular phylogeny of the genus Physconia (Ascomycota, Lecanorales) inferred from a Bayesian analysis of nuclear ITS rDNA sequences.

A Bayesian analysis of nuclear ribosomal DNA internal transcribed spacer (ITS) sequences was used to infer phylogenetic relationships of 14 Physconia species. The analysis supports the monophyly of the genus. Three well supported clades can be distinguished within Physconia: the series griseae, venustae and pulverulentae. The relationships of these clades, however, is not resolved with confidence. Cortical characters are re-evaluated on the basis of the phylogenetic hypothesis. Anatomical features of the upper cortex are only diagnostic above the species level for two special forms of two-layered cortices, while morphological characters, such as lower surface and rhizine-type are characteristic for distinct clades. P. venusta and P. perisidiosa are not separated in this analysis, but populations of P. muscigena, and European and North American samples of P. americana are clearly distinct and the monophyly of both P. americana and P. muscigena s. lat. is rejected on the basis of a Bayesian hypothesis testing.

Ascomycota↗
PubMed2005

Comparison of Bayesian and maximum-likelihood inference of population genetic parameters.

UNLABELLED: Comparison of the performance and accuracy of different inference methods, such as maximum likelihood (ML) and Bayesian inference, is difficult because the inference methods are implemented in different programs, often written by different authors. Both methods were implemented in the program MIGRATE, that estimates population genetic parameters, such as population sizes and migration rates, using coalescence theory. Both inference methods use the same Markov chain Monte Carlo algorithm and differ from each other in only two aspects: parameter proposal distribution and maximization of the likelihood function. Using simulated datasets, the Bayesian method generally fares better than the ML approach in accuracy and coverage, although for some values the two approaches are equal in performance. MOTIVATION: The Markov chain Monte Carlo-based ML framework can fail on sparse data and can deliver non-conservative support intervals. A Bayesian framework with appropriate prior distribution is able to remedy some of these problems. RESULTS: The program MIGRATE was extended to allow not only for ML(-) maximum likelihood estimation of population genetics parameters but also for using a Bayesian framework. Comparisons between the Bayesian approach and the ML approach are facilitated because both modes estimate the same parameters under the same population model and assumptions.

Bayes Theorem↗
PubMedDate not supplied

A Bayesian approach to infer geographical origins of migrants through surnames.

BACKGROUND: Surnames are an easy tool to analyse human genetic structure, mobility and evolution. Few studies use surnames to estimate human migration at different geographical level. PRIMARY OBJECTIVE: Here we propose the application of a Bayesian method to estimate the probability of geographical origin (pgo) of migrants in a given area using surnames. METHOD: This method can be applied with data recordings when they are available for at least two successive periods and in the areas which are the potential sources of emigration. The principle is that the new surnames which are arriving during the second period in the area under investigation can provide information on their geographical origins. The probability of the origin of migrants can easily be estimated iteratively from the frequency of surnames by using the Bayes' theorem. RESULTS: This method is exemplified using civil birth registers at different geographical scales. The pgo of migrants, estimated between two periods (1891-1915 and 1916-1940), (i) from French departments to Paris (ii), from these departments to Tarbes, and (iii) from counties surrounding Tarbes to Tarbes, are mapped and discussed.

Bayes Theorem↗
PubMed2004

Estimation of the hemodynamic response in event-related functional MRI: Bayesian networks as a framework for efficient Bayesian modeling and inference.

A convenient way to analyze blood-oxygen-level-dependent functional magnetic resonance imaging data consists of modeling the whole brain as a stationary, linear system characterized by its transfer function: the hemodynamic response function (HRF). HRF estimation, though of the greatest interest, is still under investigation, for the problem is ill-conditioned. In this paper, we recall the most general Bayesian model for HRF estimation and show how it can beneficially be translated in terms of Bayesian graphical models, leading to 1) a clear and efficient representation of all structural and functional relationships entailed by the model, and 2) a straightforward numerical scheme to approximate the joint posterior distribution, allowing for estimation of the HRF, as well as all other model parameters. We finally apply this novel technique on both simulations and real data.

Adolescent↗
PubMed2002

A Bayesian approach to inferring population structure from dominant markers.

Molecular markers derived from polymerase chain reaction (PCR) amplification of genomic DNA are an important part of the toolkit of evolutionary geneticists. Random amplified polymorphic DNA markers (RAPDs), amplified fragment length polymorphisms (AFLPs) and intersimple sequence repeat (ISSR) polymorphisms allow analysis of species for which previous DNA sequence information is lacking, but dominance makes it impossible to apply standard techniques to calculate F-statistics. We describe a Bayesian method that allows direct estimates of FST from dominant markers. In contrast to existing alternatives, we do not assume previous knowledge of the degree of within-population inbreeding. In particular, we do not assume that genotypes within populations are in Hardy-Weinberg proportions. Our estimate of FST incorporates uncertainty about the magnitude of within-population inbreeding. Simulations show that samples from even a relatively small number of loci and populations produce reliable estimates of FST. Moreover, some information about the degree of within-population inbreeding (FIS) is available from data sets with a large number of loci and populations. We illustrate the method with a reanalysis of RAPD data from 14 populations of a North American orchid, Platanthera leucophaea.

Bayes Theorem↗
PubMed2004

Biogeography of the Pistia clade (Araceae): based on chloroplast and mitochondrial DNA sequences and Bayesian divergence time inference.

Pistia stratiotes (water lettuce) and Lemna (duckweeds) are the only free-floating aquatic Araceae. The geographic origin and phylogenetic placement of these unrelated aroids present long-standing problems because of their highly modified reproductive structures and wide geographical distributions. We sampled chloroplast (trnL-trnF and rpl20-rps12 spacers, trnL intron) and mitochondrial sequences (nad1 b/c intron) for all genera implicated as close relatives of Pistia by morphological, restriction site, and sequencing data, and present a hypothesis about its geographic origin based on the consensus of trees obtained from the combined data, using Bayesian, maximum likelihood, parsimony, and distance analyses. Of the 14 genera closest to Pistia, only Alocasia, Arisaema, and Typhonium are species-rich, and the latter two were studied previously, facilitating the choice of representatives that span the roots of these genera. Results indicate that Pistia and the Seychelles endemic Protarum sechellarum are the basalmost branches in a grade comprising the tribes Colocasieae (Ariopsis, Steudnera, Remusatia, Alocasia, Colocasia), Arisaemateae (Arisaema, Pinellia), and Areae (Arum, Biarum, Dracunculus, Eminium, Helicodiceros, Theriophonum, Typhonium). Unexpectedly, all Areae genera are embedded in Typhonium, which throws new light on the geographic history of Areae. A Bayesian analysis of divergence times that explores the effects of multiple fossil and geological calibration points indicates that the Pistia lineage is 90 to 76 million years (my) old. The oldest fossils of the Pistia clade, though not Pistia itself, are 45-my-old leaves from Germany; the closest outgroup, Peltandreae (comprising a few species in Florida, the Mediterranean, and Madagascar), is known from 60-my-old leaves from Europe, Kazakhstan, North Dakota, and Tennessee. Based on the geographic ranges of close relatives, Pistia likely originated in the Tethys region, with Protarum then surviving on the Seychelles, which became isolated from Madagascar and India in the Late Cretaceous (85 my ago). Pistia and Protarum provide striking examples of ancient lineages that appear to have survived in unique or isolated habitats.

Araceae↗
PubMed2004

Phylogenetic relationships and biogeography of the desert plant genus Fagonia (Zygophyllaceae), inferred by parsimony and Bayesian model averaging.

Phylogenetic relationships within Fagonia were inferred from analyses of plastid trnL intron and nuclear ribosomal ITS DNA sequences. Sampling of the genus was nearly complete, including 32 of 34 species. Phylogenetic analysis was carried out using parsimony, and Bayesian model averaging. The latter method allows model-based inference while accounting for model-selection uncertainty, and is here used for the first time in phylogenetic analyses. All species of Fagonia in the Old World, except F. cretica, form a weakly supported clade, and all Fagonia species of the New World, except F. scoparia, are well supported as sister to the Old World clade. Fagonia scoparia, from Mexico, and F. cretica, from Northern Africa, are well supported as sisters to all other Fagonia species. Vicariance-dispersal analysis, using DIVA, indicated that the occurrences of Fagonia in South America and southern Africa are due to dispersals, and also, that the ancestor of Fagonia had a distribution compatible with the boreotropics hypothesis.

Base Sequence↗
PubMed2006

Inference in multiply sectioned Bayesian networks: methods and performance comparison.

This paper extends lazy propagation for inference in single-agent Bayesian networks (BNs) to multiagent lazy inference in multiply sectioned BNs (MSBNs). Two methods are proposed using distinct runtime structures. It was proved that the new methods are exact and efficient when the domain structure is sparse. Both improve space and time complexity more than the existing method, which allows multiagent probabilistic reasoning to be performed in much larger domains given the computational resource. The relative performances of the three methods are compared analytically and experimentally.

Algorithms↗