• MeSH
• Algorithms MeSH
• Artifacts MeSH
• Diagnostic Imaging trends   MeSH
• Entropy * MeSH
• Fourier Analysis MeSH
• Humans MeSH
• Nuclear Magnetic Resonance, Biomolecular * methods   MeSH
• Image Processing, Computer-Assisted * methods   utilization   MeSH
• Signal-To-Noise Ratio MeSH
• Spectrum Analysis trends   utilization   MeSH
• Check Tag
• Humans MeSH

Maximum entropy estimation is of broad interest for inferring properties of systems across many disciplines. Using a recently introduced technique for estimating the maximum entropy of a set of random discrete variables when conditioning on bivariate mutual informations and univariate entropies, we show how this can be used to estimate the direct network connectivity between interacting units from observed activity. As a generic example, we consider phase oscillators and show that our approach is typically superior to simply using the mutual information. In addition, we propose a nonparametric formulation of connected informations, used to test the explanatory power of a network description in general. We give an illustrative example showing how this agrees with the existing parametric formulation, and demonstrate its applicability and advantages for resting-state human brain networks, for which we also discuss its direct effective connectivity. Finally, we generalize to continuous random variables and vastly expand the types of information-theoretic quantities one can condition on. This allows us to establish significant advantages of this approach over existing ones. Not only does our method perform favorably in the undersampled regime, where existing methods fail, but it also can be dramatically less computationally expensive as the cardinality of the variables increases.

• MeSH
• Entropy MeSH
• Information Systems * MeSH
• Humans MeSH
• Nerve Net MeSH
• Models, Theoretical MeSH
• Check Tag
• Humans MeSH
• Publication type
• Research Support, Non-U.S. Gov't MeSH

• MeSH
• Algorithms MeSH
• Financing, Organized MeSH
• Humans MeSH
• Blood Pressure Determination methods   instrumentation   utilization   MeSH
• Monte Carlo Method MeSH
• Blood Pressure Monitors utilization   MeSH
• Plethysmography utilization   MeSH
• Signal Processing, Computer-Assisted MeSH
• Blood Flow Velocity physiology   MeSH
• Blood Volume Determination methods   utilization   MeSH
• Statistics as Topic methods   MeSH
• Catheters, Indwelling utilization   MeSH
• Check Tag
• Humans MeSH

Reconstructing the structural connectivity between interacting units from observed activity is a challenge across many different disciplines. The fundamental first step is to establish whether or to what extent the interactions between the units can be considered pairwise and, thus, can be modeled as an interaction network with simple links corresponding to pairwise interactions. In principle, this can be determined by comparing the maximum entropy given the bivariate probability distributions to the true joint entropy. In many practical cases, this is not an option since the bivariate distributions needed may not be reliably estimated or the optimization is too computationally expensive. Here we present an approach that allows one to use mutual informations as a proxy for the bivariate probability distributions. This has the advantage of being less computationally expensive and easier to estimate. We achieve this by introducing a novel entropy maximization scheme that is based on conditioning on entropies and mutual informations. This renders our approach typically superior to other methods based on linear approximations. The advantages of the proposed method are documented using oscillator networks and a resting-state human brain network as generic relevant examples.

• MeSH
• Entropy MeSH
• Information Systems * MeSH
• Correlation of Data MeSH
• Neural Networks, Computer MeSH
• Models, Theoretical MeSH
• Publication type
• Research Support, Non-U.S. Gov't MeSH

Feature selection is a significant part of many machine learning applications dealing with small-sample and high-dimensional data. Choosing the most important features is an essential step for knowledge discovery in many areas of biomedical informatics. The increased popularity of feature selection methods and their frequent utilisation raise challenging new questions about the interpretability and stability of feature selection techniques. In this study, we compared the behaviour of ten state-of-the-art filter methods for feature selection in terms of their stability, similarity, and influence on prediction performance. All of the experiments were conducted on eight two-class datasets from biomedical areas. While entropy-based feature selection appears to be the most stable, the feature selection techniques yielding the highest prediction performance are minimum redundance maximum relevance method and feature selection based on Bhattacharyya distance. In general, univariate feature selection techniques perform similarly to or even better than more complex multivariate feature selection techniques with high-dimensional datasets. However, with more complex and smaller datasets multivariate methods slightly outperform univariate techniques.

• MeSH
• Algorithms MeSH
• Databases, Factual MeSH
• Humans MeSH
• Multivariate Analysis MeSH
• Parkinson Disease diagnosis   MeSH
• Oligonucleotide Array Sequence Analysis methods   MeSH
• Software MeSH
• Models, Statistical MeSH
• Computational Biology methods   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Comparative Study MeSH

• MeSH
• Mathematical Computing MeSH
• Mathematics MeSH
• Numerical Analysis, Computer-Assisted * MeSH
• Publication type
• Monograph MeSH

• Conspectus
• Počítačová věda. Výpočetní technika. Informační technologie
• NML Fields
• přírodní vědy
• přírodní vědy

PURPOSE: Imaging biomarker research focuses on discovering relationships between radiological features and histological findings. In glioblastoma patients, methylation of the O(6)-methylguanine methyltransferase (MGMT) gene promoter is positively correlated with an increased effectiveness of current standard of care. In this paper, the authors investigate texture features as potential imaging biomarkers for capturing the MGMT methylation status of glioblastoma multiforme (GBM) tumors when combined with supervised classification schemes. METHODS: A retrospective study of 155 GBM patients with known MGMT methylation status was conducted. Co-occurrence and run length texture features were calculated, and both support vector machines (SVMs) and random forest classifiers were used to predict MGMT methylation status. RESULTS: The best classification system (an SVM-based classifier) had a maximum area under the receiver-operating characteristic (ROC) curve of 0.85 (95% CI: 0.78-0.91) using four texture features (correlation, energy, entropy, and local intensity) originating from the T2-weighted images, yielding at the optimal threshold of the ROC curve, a sensitivity of 0.803 and a specificity of 0.813. CONCLUSIONS: Results show that supervised machine learning of MRI texture features can predict MGMT methylation status in preoperative GBM tumors, thus providing a new noninvasive imaging biomarker.

• MeSH
• DNA Modification Methylases genetics   MeSH
• DNA Repair Enzymes genetics   MeSH
• Glioblastoma diagnostic imaging   genetics   surgery   MeSH
• Humans MeSH
• Magnetic Resonance Imaging methods   MeSH
• DNA Methylation * MeSH
• Brain diagnostic imaging   surgery   MeSH
• Biomarkers, Tumor genetics   MeSH
• Tumor Suppressor Proteins genetics   MeSH
• Brain Neoplasms diagnostic imaging   genetics   surgery   MeSH
• Promoter Regions, Genetic MeSH
• Retrospective Studies MeSH
• ROC Curve MeSH
• Support Vector Machine MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

The cat flea (Ctenocephalides felis) is the most common parasite of domestic cats and dogs worldwide. Due to the morphological ambiguity of C. felis and a lack of - particularly largescale - phylogenetic data, we do not know whether global C. felis populations are morphologically and genetically conserved, or whether human-mediated migration of domestic cats and dogs has resulted in homogenous global populations. To determine the ancestral origin of the species and to understand the level of global pervasion of the cat flea and related taxa, our study aimed to document the distribution and phylogenetic relationships of Ctenocephalides fleas found on cats and dogs worldwide. We investigated the potential drivers behind the establishment of regional cat flea populations using a global collection of fleas from cats and dogs across six continents. We morphologically and molecularly evaluated six out of the 14 known taxa comprising genus Ctenocephalides, including the four original C. felis subspecies (Ctenocephalides felis felis, Ctenocephalides felis strongylus, Ctenocephalides felis orientis and Ctenocephalides felis damarensis), the cosmopolitan species Ctenocephalides canis and the African species Ctenocephalides connatus. We confirm the ubiquity of the cat flea, representing 85% of all fleas collected (4357/5123). Using a multigene approach combining two mitochondrial (cox1 and cox2) and two nuclear (Histone H3 and EF-1α) gene markers, as well as a cox1 survey of 516 fleas across 56 countries, we demonstrate out-of-Africa origins for the genus Ctenocephalides and high levels of genetic diversity within C. felis. We define four bioclimatically limited C. felis clusters (Temperate, Tropical I, Tropical II and African) using maximum entropy modelling. This study defines the global distribution, African origin and phylogenetic relationships of global Ctenocephalides fleas, whilst resolving the taxonomy of the C. felis subspecies and related taxa. We show that humans have inadvertently precipitated the expansion of C. felis throughout the world, promoting diverse population structure and bioclimatic plasticity. By demonstrating the link between the global cat flea communities and their affinity for specific bioclimatic niches, we reveal the drivers behind the establishment and success of the cat flea as a global parasite.

• MeSH
• Ctenocephalides classification   genetics   growth & development   MeSH
• Phylogeny MeSH
• Genetic Markers MeSH
• Flea Infestations parasitology   veterinary   MeSH
• Cats MeSH
• Humans MeSH
• Cat Diseases parasitology   MeSH
• Dog Diseases parasitology   MeSH
• Dogs MeSH
• Animals MeSH
• Check Tag
• Cats MeSH
• Humans MeSH
• Male MeSH
• Dogs MeSH
• Female MeSH
• Animals MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Geographicals
• Africa MeSH