An information-theoretic approach to statistical dependence: Copula information

We discuss the connection between information and copula theories by showing that a copula can be employed to decompose the information content of a multivariate distribution into marginal and dependence components, with the latter quantified by the mutual information. We define the information excess as a measure of deviation from a maximum-entropy distribution. The idea of marginal invariant dependence measures is also discussed and used to show that empirical linear correlation underestimates the amplitude of the actual correlation in the case of non-Gaussian marginals. The mutual information is shown to provide an upper bound for the asymptotic empirical log-likelihood of a copula. An analytical expression for the information excess of T-copulas is provided, allowing for simple model identification within this family. We illustrate the framework in a financial data set. Copyright (C) EPLA, 2009

PCA Tomography: how to extract information from data cubes

Astronomy has evolved almost exclusively by the use of spectroscopic and imaging techniques, operated separately. With the development of modern technologies, it is possible to obtain data cubes in which one combines both techniques simultaneously, producing images with spectral resolution. To extract information from them can be quite complex, and hence the development of new methods of data analysis is desirable. We present a method of analysis of data cube (data from single field observations, containing two spatial and one spectral dimension) that uses Principal Component Analysis (PCA) to express the data in the form of reduced dimensionality, facilitating efficient information extraction from very large data sets. PCA transforms the system of correlated coordinates into a system of uncorrelated coordinates ordered by principal components of decreasing variance. The new coordinates are referred to as eigenvectors, and the projections of the data on to these coordinates produce images we will call tomograms. The association of the tomograms (images) to eigenvectors (spectra) is important for the interpretation of both. The eigenvectors are mutually orthogonal, and this information is fundamental for their handling and interpretation. When the data cube shows objects that present uncorrelated physical phenomena, the eigenvector`s orthogonality may be instrumental in separating and identifying them. By handling eigenvectors and tomograms, one can enhance features, extract noise, compress data, extract spectra, etc. We applied the method, for illustration purpose only, to the central region of the low ionization nuclear emission region (LINER) galaxy NGC 4736, and demonstrate that it has a type 1 active nucleus, not known before. Furthermore, we show that it is displaced from the centre of its stellar bulge.

Shared information in stationary states at criticality

We consider bipartitions of one-dimensional extended systems whose probability distribution functions describe stationary states of stochastic models. We define estimators of the information shared between the two subsystems. If the correlation length is finite, the estimators stay finite for large system sizes. If the correlation length diverges, so do the estimators. The definition of the estimators is inspired by information theory. We look at several models and compare the behaviors of the estimators in the finite-size scaling limit. Analytical and numerical methods as well as Monte Carlo simulations are used. We show how the finite-size scaling functions change for various phase transitions, including the case where one has conformal invariance.

Crystal structure and statistical coupling analysis of highly glycosylated peroxidase from royal palm tree (Roystonea regia)

Royal palm tree peroxidase (RPTP) is a very stable enzyme in regards to acidity, temperature, H(2)O(2), and organic solvents. Thus, RPTP is a promising candidate for developing H(2)O(2)-sensitive biosensors for diverse applications in industry and analytical chemistry. RPTP belongs to the family of class III secretory plant peroxidases, which include horseradish peroxidase isozyme C, soybean and peanut peroxidases. Here we report the X-ray structure of native RPTP isolated from royal palm tree (Roystonea regia) refined to a resolution of 1.85 angstrom. RPTP has the same overall folding pattern of the plant peroxidase superfamily, and it contains one heme group and two calcium-binding sites in similar locations. The three-dimensional structure of RPTP was solved for a hydroperoxide complex state, and it revealed a bound 2-(N-morpholino) ethanesulfonic acid molecule (MES) positioned at a putative substrate-binding secondary site. Nine N-glycosylation sites are clearly defined in the RPTP electron-density maps, revealing for the first time conformations of the glycan chains of this highly glycosylated enzyme. Furthermore, statistical coupling analysis (SCA) of the plant peroxidase superfamily was performed. This sequence-based method identified a set of evolutionarily conserved sites that mapped to regions surrounding the heme prosthetic group. The SCA matrix also predicted a set of energetically coupled residues that are involved in the maintenance of the structural folding of plant peroxidases. The combination of crystallographic data and SCA analysis provides information about the key structural elements that could contribute to explaining the unique stability of RPTP. (C) 2009 Elsevier Inc. All rights reserved.

An Information Theory framework for two-stage binary image operator design

The design of translation invariant and locally defined binary image operators over large windows is made difficult by decreased statistical precision and increased training time. We present a complete framework for the application of stacked design, a recently proposed technique to create two-stage operators that circumvents that difficulty. We propose a novel algorithm, based on Information Theory, to find groups of pixels that should be used together to predict the Output Value. We employ this algorithm to automate the process of creating a set of first-level operators that are later combined in a global operator. We also propose a principled way to guide this combination, by using feature selection and model comparison. Experimental results Show that the proposed framework leads to better results than single stage design. (C) 2009 Elsevier B.V. All rights reserved.