Temporal refinement of 3D CNN semantic segmentations on 4D time-series of undersampled tomograms using hidden Markov models.
Ontology highlight
ABSTRACT:
SUBMITTER: Bellos D
PROVIDER: S-EPMC8640015 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:This paper develops a quantile hidden semi-Markov regression to jointly estimate multiple quantiles for the analysis of multivariate time series. The approach is based upon the Multivariate Asymmetric Laplace (MAL) distribution, which allows to model the quantiles of all univariate conditional distributions of a multivariate response simultaneously, incorporating the correlation structure among the outcomes. Unobserved serial heterogeneity across observations is modeled by introducing regime-dependent parameters that evolve according to a latent finite-state semi-Markov chain. Exploiting the hierarchical representation of the MAL, inference is carried out using an efficient Expectation-Maximization algorithm based on closed form updates for all model parameters, without parametric assumptions about the states' sojourn distributions. The validity of the proposed methodology is analyzed both by a simulation study and through the empirical analysis of air pollutant concentrations in a small Italian city.Supplementary informationThe online version contains supplementary material available at 10.1007/s11222-022-10130-1.
| S-EPMC9360757 | biostudies-literature
Project description:BACKGROUND: The Medium-chain Dehydrogenases/Reductases (MDR) form a protein superfamily whose size and complexity defeats traditional means of subclassification; it currently has over 15000 members in the databases, the pairwise sequence identity is typically around 25%, there are members from all kingdoms of life, the chain-lengths vary as does the oligomericity, and the members are partaking in a multitude of biological processes. There are profile hidden Markov models (HMMs) available for detecting MDR superfamily members, but none for determining which MDR family each protein belongs to. The current torrential influx of new sequence data enables elucidation of more and more protein families, and at an increasingly fine granularity. However, gathering good quality training data usually requires manual attention by experts and has therefore been the rate limiting step for expanding the number of available models. RESULTS: We have developed an automated algorithm for HMM refinement that produces stable and reliable models for protein families. This algorithm uses relationships found in data to generate confident seed sets. Using this algorithm we have produced HMMs for 86 distinct MDR families and 34 of their subfamilies which can be used in automated annotation of new sequences. We find that MDR forms with 2 Zn2+ ions in general are dehydrogenases, while MDR forms with no Zn2+ in general are reductases. Furthermore, in Bacteria MDRs without Zn2+ are more frequent than those with Zn2+, while the opposite is true for eukaryotic MDRs, indicating that Zn2+ has been recruited into the MDR superfamily after the initial life kingdom separations. We have also developed a web site http://mdr-enzymes.org that provides textual and numeric search against various characterised MDR family properties, as well as sequence scan functions for reliable classification of novel MDR sequences. CONCLUSIONS: Our method of refinement can be readily applied to create stable and reliable HMMs for both MDR and other protein families, and to confidently subdivide large and complex protein superfamilies. HMMs created using this algorithm correspond to evolutionary entities, making resolution of overlapping models straightforward. The implementation and support scripts for running the algorithm on computer clusters are available as open source software, and the database files underlying the web site are freely downloadable. The web site also makes our findings directly useful also for non-bioinformaticians.
| S-EPMC2976758 | biostudies-literature
Project description:Studies conducted in time series could be far more informative than those that only capture a specific moment in time. However, when it comes to transcriptomic data, time points are sparse creating the need for a constant search for methods capable of extracting information out of experiments of this kind. We propose a feature selection algorithm embedded in a hidden Markov model applied to gene expression time course data on either single or even multiple biological conditions. For the latter, in a simple case-control study features or genes are selected under the assumption of no change over time for the control samples, while the case group must have at least one change. The proposed model reduces the feature space according to a two-state hidden Markov model. The two states define change/no-change in gene expression. Features are ranked in consonance with three scores: number of changes across time, magnitude of such changes and quality of replicates as a measure of how much they deviate from the mean. An important highlight is that this strategy overcomes the few samples limitation, common in transcriptome experiments through a process of data transformation and rearrangement. To prove this method, our strategy was applied to three publicly available data sets. Results show that feature domain is reduced by up to 90% leaving only few but relevant features yet with findings consistent to those previously reported. Moreover, our strategy proved to be robust, stable and working on studies where sample size is an issue otherwise. Hence, even with two biological replicates and/or three time points our method proves to work well.
| S-EPMC6786538 | biostudies-literature
Project description:Is it possible to learn and create a first Hidden Markov Model (HMM) without programming skills or understanding the algorithms in detail? In this concise tutorial, we present the HMM through the 2 general questions it was initially developed to answer and describe its elements. The HMM elements include variables, hidden and observed parameters, the vector of initial probabilities, and the transition and emission probability matrices. Then, we suggest a set of ordered steps, for modeling the variables and illustrate them with a simple exercise of modeling and predicting transmembrane segments in a protein sequence. Finally, we show how to interpret the results of the algorithms for this particular problem. To guide the process of information input and explicit solution of the basic HMM algorithms that answer the HMM questions posed, we developed an educational webserver called HMMTeacher. Additional solved HMM modeling exercises can be found in the user's manual and answers to frequently asked questions. HMMTeacher is available at https://hmmteacher.mobilomics.org, mirrored at https://hmmteacher1.mobilomics.org. A repository with the code of the tool and the webpage is available at https://gitlab.com/kmilo.f/hmmteacher.
| S-EPMC8830650 | biostudies-literature
Project description:In previous work, we developed a novel algorithm, VIPR, for analyzing diagnostic microarray data using a training set of empirical hybridizations of infected and uninfected samples. We have expanded up our previous implementation by incorporating a hidden Markov model (HMM) to detect recombination. We trained our HMM on a set of nonrecombinant parental viruses and applied our method to 11 recombinant alphaviruses and 4 recombinant flaviviruses hybridized to a diagnostic microarray in order to evaluate performance of the HMM. VIPR HMM identified 95% of the 62 inter-species recombinant breakpoints in the validation set and only two false positive breakpoints were predicted. This study represents the first description and validation of an algorithm capable of identifying recombination in viruses based on diagnostic microarray hybridization patterns.
2012-10-18 | GSE34490 | GEO
Project description:Empirical codon models (ECMs) estimated from a large number of globular protein families outperformed mechanistic codon models in their description of the general process of protein evolution. Among other factors, ECMs implicitly model the influence of amino acid properties and multiple nucleotide substitutions (MNS). However, the estimation of ECMs requires large quantities of data, and until recently, only few suitable data sets were available. Here, we take advantage of several new Drosophila species genomes to estimate codon models from genome-wide data. The availability of large numbers of genomes over varying phylogenetic depths in the Drosophila genus allows us to explore various divergence levels. In consequence, we can use these data to determine the appropriate level of divergence for the estimation of ECMs, avoiding overestimation of MNS rates caused by saturation. To account for variation in evolutionary rates along the genome, we develop new empirical codon hidden Markov models (ecHMMs). These models significantly outperform previous ones with respect to maximum likelihood values, suggesting that they provide a better fit to the evolutionary process. Using ECMs and ecHMMs derived from genome-wide data sets, we devise new likelihood ratio tests (LRTs) of positive selection. We found classical LRTs very sensitive to the presence of MNSs, showing high false-positive rates, especially with small phylogenies. The new LRTs are more conservative than the classical ones, having acceptable false-positive rates and reduced power.
| S-EPMC3563974 | biostudies-literature
Project description:Hidden Markov random fields (HMRFs) are conventionally assumed to be homogeneous in the sense that the potential functions are invariant across different sites. However in some biological applications, it is desirable to make HMRFs heterogeneous, especially when there exists some background knowledge about how the potential functions vary. We formally define heterogeneous HMRFs and propose an EM algorithm whose M-step combines a contrastive divergence learner with a kernel smoothing step to incorporate the background knowledge. Simulations show that our algorithm is effective for learning heterogeneous HMRFs and outperforms alternative binning methods. We learn a heterogeneous HMRF in a real-world study.
| S-EPMC4232933 | biostudies-literature
Project description:Bayesian inference for coupled hidden Markov models frequently relies on data augmentation techniques for imputation of the hidden state processes. Considerable progress has been made on developing such techniques, mainly using Markov chain Monte Carlo (MCMC) methods. However, as the dimensionality and complexity of the hidden processes increase some of these methods become inefficient, either because they produce MCMC chains with high autocorrelation or because they become computationally intractable. Motivated by this fact we developed a novel MCMC algorithm, which is a modification of the forward filtering backward sampling algorithm, that achieves a good balance between computation and mixing properties, and thus can be used to analyze models with large numbers of hidden chains. Even though our approach is developed under the assumption of a Markovian model, we show how this assumption can be relaxed leading to minor modifications in the algorithm. Our approach is particularly well suited to epidemic models, where the hidden Markov chains represent the infection status of an individual through time. The performance of our method is assessed on simulated data on epidemic models for the spread of Escherichia coli O157:H7 in cattle. Supplementary materials for this article are available online.
| S-EPMC7455056 | biostudies-literature
Project description:Existing methods for the prediction of immunologically active T-cell epitopes are based on the amino acid sequence or structure of pathogen proteins. Additional information regarding the locations of epitopes may be acquired by considering the evolution of viruses in hosts with different immune backgrounds. In particular, immune-dependent evolutionary patterns at sites within or near T-cell epitopes can be used to enhance epitope identification. We have developed a mutation-selection model of T-cell epitope evolution that allows the human leukocyte antigen (HLA) genotype of the host to influence the evolutionary process. This is one of the first examples of the incorporation of environmental parameters into a phylogenetic model and has many other potential applications where the selection pressures exerted on an organism can be related directly to environmental factors. We combine this novel evolutionary model with a hidden Markov model to identify contiguous amino acid positions that appear to evolve under immune pressure in the presence of specific host immune alleles and that therefore represent potential epitopes. This phylogenetic hidden Markov model provides a rigorous probabilistic framework that can be combined with sequence or structural information to improve epitope prediction. As a demonstration, we apply the model to a data set of HIV-1 protein-coding sequences and host HLA genotypes.
| S-EPMC2857806 | biostudies-other
Project description:BackgroundRoutine surveillance of disease notification data can enable the early detection of localised disease outbreaks. Although hidden Markov models (HMMs) have been recognised as an appropriate method to model disease surveillance data, they have been rarely applied in public health practice. We aimed to develop and evaluate a simple flexible HMM for disease surveillance which is suitable for use with sparse small area count data and requires little baseline data.MethodsA Bayesian HMM was designed to monitor routinely collected notifiable disease data that are aggregated by residential postcode. Semi-synthetic data were used to evaluate the algorithm and compare outbreak detection performance with the established Early Aberration Reporting System (EARS) algorithms and a negative binomial cusum.ResultsAlgorithm performance varied according to the desired false alarm rate for surveillance. At false alarm rates around 0.05, the cusum-based algorithms provided the best overall outbreak detection performance, having similar sensitivity to the HMMs and a shorter average time to detection. At false alarm rates around 0.01, the HMM algorithms provided the best overall outbreak detection performance, having higher sensitivity than the cusum-based Methods and a generally shorter time to detection for larger outbreaks. Overall, the 14-day HMM had a significantly greater area under the receiver operator characteristic curve than the EARS C3 and 7-day negative binomial cusum algorithms.ConclusionOur findings suggest that the HMM provides an effective method for the surveillance of sparse small area notifiable disease data at low false alarm rates. Further investigations are required to evaluation algorithm performance across other diseases and surveillance contexts.
| S-EPMC2735038 | biostudies-literature