Communications inspired linear discriminant analysis

We study the problem of supervised linear dimensionality reduction, taking an information-theoretic viewpoint. The linear projection matrix is designed by maximizing the mutual information between the projected signal and the class label. By harnessing a recent theoretical result on the gradient of mutual information, the above optimization problem can be solved directly using gradient descent, without requiring simplification of the objective function. Theoretical analysis and empirical comparison are made between the proposed method and two closely related methods, and comparisons are also made with a method in which Rényi entropy is used to define the mutual information (in this case the gradient may be computed simply, under a special parameter setting). Relative to these alternative approaches, the proposed method achieves promising results on real datasets. Copyright 2012 by the author(s)/owner(s).

Statistical analysis of crystallization database links protein physico-chemical features with crystallization mechanisms.

X-ray crystallography is the predominant method for obtaining atomic-scale information about biological macromolecules. Despite the success of the technique, obtaining well diffracting crystals still critically limits going from protein to structure. In practice, the crystallization process proceeds through knowledge-informed empiricism. Better physico-chemical understanding remains elusive because of the large number of variables involved, hence little guidance is available to systematically identify solution conditions that promote crystallization. To help determine relationships between macromolecular properties and their crystallization propensity, we have trained statistical models on samples for 182 proteins supplied by the Northeast Structural Genomics consortium. Gaussian processes, which capture trends beyond the reach of linear statistical models, distinguish between two main physico-chemical mechanisms driving crystallization. One is characterized by low levels of side chain entropy and has been extensively reported in the literature. The other identifies specific electrostatic interactions not previously described in the crystallization context. Because evidence for two distinct mechanisms can be gleaned both from crystal contacts and from solution conditions leading to successful crystallization, the model offers future avenues for optimizing crystallization screens based on partial structural information. The availability of crystallization data coupled with structural outcomes analyzed through state-of-the-art statistical models may thus guide macromolecular crystallization toward a more rational basis.

Component-wise gradient boosting and false discovery control in survival analysis with high-dimensional covariates.

MOTIVATION: Technological advances that allow routine identification of high-dimensional risk factors have led to high demand for statistical techniques that enable full utilization of these rich sources of information for genetics studies. Variable selection for censored outcome data as well as control of false discoveries (i.e. inclusion of irrelevant variables) in the presence of high-dimensional predictors present serious challenges. This article develops a computationally feasible method based on boosting and stability selection. Specifically, we modified the component-wise gradient boosting to improve the computational feasibility and introduced random permutation in stability selection for controlling false discoveries. RESULTS: We have proposed a high-dimensional variable selection method by incorporating stability selection to control false discovery. Comparisons between the proposed method and the commonly used univariate and Lasso approaches for variable selection reveal that the proposed method yields fewer false discoveries. The proposed method is applied to study the associations of 2339 common single-nucleotide polymorphisms (SNPs) with overall survival among cutaneous melanoma (CM) patients. The results have confirmed that BRCA2 pathway SNPs are likely to be associated with overall survival, as reported by previous literature. Moreover, we have identified several new Fanconi anemia (FA) pathway SNPs that are likely to modulate survival of CM patients. AVAILABILITY AND IMPLEMENTATION: The related source code and documents are freely available at https://sites.google.com/site/bestumich/issues. CONTACT: yili@umich.edu.

Modeling non-harmonic behavior of materials from experimental inelastic neutron scattering and thermal expansion measurements

Based on thermodynamic principles, we derive expressions quantifying the non-harmonic vibrational behavior of materials, which are rigorous yet easily evaluated from experimentally available data for the thermal expansion coefficient and the phonon density of states. These experimentally- derived quantities are valuable to benchmark first-principles theoretical predictions of harmonic and non-harmonic thermal behaviors using perturbation theory, ab initio molecular-dynamics, or Monte-Carlo simulations. We illustrate this analysis by computing the harmonic, dilational, and anharmonic contributions to the entropy, internal energy, and free energy of elemental aluminum and the ordered compound FeSi over a wide range of temperature. Results agree well with previous data in the literature and provide an efficient approach to estimate anharmonic effects in materials.

Comparison of the thermodynamics and base-pair dynamics of a full LNA:DNA duplex and of the isosequential DNA:DNA duplex

Locked nucleic acids (LNA), conformationally restricted nucleotide analogues, are known to enhance pairing stability and selectivity toward complementary strands. With the aim to contribute to a better understanding of the origin of these effects, the structure, thermal stability, hybridization thermodynamics, and base-pair dynamics of a full-LNA:DNA heteroduplex and of its isosequential DNA:DNA homoduplex were monitored and compared. CD measurements highlight differences in the duplex structures: the homoduplex and heteroduplex present B-type and A-type helical conformations, respectively. The pairing of the hybrid duplex is characterized, at all temperatures monitored (between 15 and 37 degrees C), by a larger stability constant but a less favorable enthalpic term. A major contribution to this thermodynamic profile emanates from the presence of a hairpin structure in the LNA single strand which contributes favorably to the entropy of interaction but leads to an enthalpy penalty upon duplex formation. The base-pair opening dynamics of both systems was monitored by NMR spectroscopy via imino protons exchange measurements. The measurements highlight that hybrid G-C base-pairs present a longer base-pair lifetime and higher stability than natural G-C base-pairs, but that an LNA substitution in an A-T base-pair does not have a favorable effect on the stability. The thermodynamic and dynamic data confirm a more favorable stacking of the bases in the hybrid duplex. This study emphasizes the complementarities between dynamic and thermodynamical studies for the elucidation of the relevant factors in binding events.

Analysis of species hyper-diversity in the tropical rain forests of Indonesia: the problem of non-observance

The main interest in the assessment of forest species diversity for conservation purposes is in the rare species. The main problem in the tropical rain forests is that most of the species are rare. Assessment of species diversity in the tropical rain forests is therefore often concerned with estimating that which is not observed in recorded samples. Statistical methodology is therefore required to try to estimate the truncated tail of the species frequency distribution, or to estimate the asymptote of species/diversity-area curves. A Horvitz-Thompson estimator of the number of unobserved (“virtual”) species in each species intensity class is proposed. The approach allows a definition of an extended definition of diversity, ( or generalised Renyi entropy). The paper presents a case study from data collected in Jambi, Sumatra, and the “extended diversity measure” is used on the species data.

Minimizing total weighted completion time in a proportionate flow shop

We study the special case of the m machine flow shop problem in which the processing time of each operation of job j is equal to pj; this variant of the flow shop problem is known as the proportionate flow shop problem. We show that for any number of machines and for any regular performance criterion we can restrict our search for an optimal schedule to permutation schedules. Moreover, we show that the problem of minimizing total weighted completion time is solvable in O(n2) time. © 1998 John Wiley & Sons, Ltd.

Two-machine shop scheduling: Compromise between flexibility and makespan value

In this paper, we consider the problem of providing flexibility to solutions of two-machine shop scheduling problems. We use the concept of group-scheduling to characterize a whole set of schedules so as to provide more choice to the decision-maker at any decision point. A group-schedule is a sequence of groups of permutable operations defined on each machine where each group is such that any permutation of the operations inside the group leads to a feasible schedule. Flexibility of a solution and its makespan are often conflicting, thus we search for a compromise between a low number of groups and a small value of makespan. We resolve the complexity status of the relevant problems for the two-machine flow shop, job shop and open shop. A number of approximation algorithms are developed and their worst-case performance is analyzed. For the flow shop, an effective heuristic algorithm is proposed and the results of computational experiments are reported.

Two-machine flow shop scheduling problems with no-wait jobs

In this paper we provide a fairly complete complexity classification of various versions of the two-machine permutation flow shop scheduling problem to minimize the makespan in which some of the jobs have to be processed with no-wait in process. For some version, we offer a fully polynomial-time approximation scheme and a 43-approximation algorithm.

Novel inclusion complex of ibuprofen tromethamine with cyclodextrins: Physico-chemical characterization

Guest-host interactions of ibuprofen tromethamine salt (Ibu.T) with native and modified cyclodextrins (CyDs) have been investigated using several techniques, namely phase solubility diagrams (PSDs), proton nuclear magnetic resonance (H-1 NMR), differential scanning calorimetry (DSC), Fourier transform infrared spectroscopy (FT-IR), X-ray powder diffractometry (XRPD). scanning-electron microscopy (SEM) and molecular mechanics (MM). From the analysis of PSD data (A(L)-type) it is concluded that the anionic tromethamine salt of ibuprofen (pK(a) = 4.55) forms 1: 1 soluble complexes with all CyDs investigated in buffered water at pH 7.0, while the neutral form of Ibu forms an insoluble complex with beta-CyD (B-S-type) in buffered water at pH 2.0. Ibu.T has a lower tendency to complex with beta-CyD (K-11 = 58 M-1 at pH 7.0) compared with the neutral Ibu (K-11 = 4200 M (1)) in water. Complex formation of Ibu.T with beta-CyD (Delta G degrees = -20.4 kJ/mol) is enthalpy driven (Delta H degrees = -22.9 kJ/mol) and is accompanied by a small unfavorable entropy (Delta S degrees = -8.4 J/mol K) change. H-1 NMR studies and MM computations revealed that, on complexation, the hydrophobic central benzene ring of lbu.T and part of the isobutyl group reside within the beta-CyD cavity leaving the peripheral groups (carboxylate, tromethamine and methyl groups) located near the hydroxyl group networks at either rim of beta-CyD. PSD, H-1 NMR, DSC, FT-IR, XRPD, SEM and MM studies confirmed the formation of Ibu.T/beta-CyD inclusion complex in solution and the solid state. (C) 2009 Elsevier B.V. All rights reserved.

Determination of micelle/water partition coefficients and associated thermodynamic data for dialkyl phthalate esters

Micelle/water partition coefficients for three dialkyl phthalate esters - dimethyl phthalate ester (DMP), diethyl phthalate ester (DEP) and dipropyl phthalate ester (DPP) were obtained by micellar liquid chromatography (MLC). Experiments were conducted over a temperature range which led to calculation of a Gibbs free energy, enthalpy and entropy of transfer for the phthalate esters. In addition, small angle neutron scattering (SANS) experiments were conducted with no substantial change observed in micelle size before and after phthalate ester incorporation. Overall, a novel method for obtaining thermodynamic information, based on partitioning data, has been developed for dialkyl phthalate esters using micellar liquid chromatography.

Do pigs form preferential associations?

This investigation examined whether pigs form long-term preferential associations or ‘friendships’ and factors that may influence the formation of these relationships. Thirty-three pigs from 16 litters were housed together from 4 weeks of age. At 10 weeks they were split into two groups of 16 and 17 pigs and each introduced into 3.05 m × 3.66 m observation pens (1st pen). At 17 weeks the two groups swapped pens (2nd pen). The lying patterns of each group were recorded over 3 weeks in both the 1st and 2nd pens. To identify dyads with preferential associations, association indices were calculated for each pair based on their lying patterns and analysed using SOCPROG1.3 and the permutation method [Whitehead, H., 1999. Programs for analysing social structure. SOCPROG 1.2, http://is.dal.cal/~whitelab/index.htm]. Dyads with high association indices for at least 2 out of 3 weeks in either pen, i.e. =0.10 (twice the mean), were classed as having preferential associations. Mantel tests were used to examine the relationship between the relative sex, weight, familiarity and relatedness of a dyad and their level of association and to examine consistency of associations between pens. The existence of preferential associations was identified in both groups, since the standard deviations for the observed half-weight association index means were significantly higher than for the randomly permuted half-weight association index means (P < 0.001). Of the 33 pigs observed, 32 formed preferential associations with one or more pigs in their group, resulting in 50 dyads. Only six dyads (12 pigs) formed preferential associations in both pens, suggesting that the remaining dyads either formed short-term associations only or were simply displaying a shared preference for the same lying location. Levels of association between pens showed no significant correlation. The relative sex, weight, familiarity and relatedness of dyad members also showed no significant correlation with their level of association. These findings suggest that unrelated pigs are capable of forming preferential associations. However, it is unclear whether such associations are widespread or important to pigs, since most dyads’ preferential associations were not consistent between pens.

A machine vision approach to the grading of crushed aggregate

The grading of crushed aggregate is carried out usually by sieving. We describe a new image-based approach to the automatic grading of such materials. The operational problem addressed is where the camera is located directly over a conveyor belt. Our approach characterizes the information content of each image, taking into account relative variation in the pixel data, and resolution scale. In feature space, we find very good class separation using a multidimensional linear classifier. The innovation in this work includes (i) introducing an effective image-based approach into this application area, and (ii) our supervised classification using wavelet entropy-based features.

A reactive force field simulation of liquid-liquid phase transitions in phosphorus

A force field model of phosphorus has been developed based on density functional (DF) computations and experimental results, covering low energy forms of local tetrahedral symmetry and more compact (simple cubic) structures that arise with increasing pressure. Rules tailored to DF data for the addition, deletion, and exchange of covalent bonds allow the system to adapt the bonding configuration to the thermodynamic state. Monte Carlo simulations in the N-P-T ensemble show that the molecular (P-4) liquid phase, stable at low pressure P and relatively low temperature T, transforms to a polymeric (gel) state on increasing either P or T. These phase changes are observed in recent experiments at similar thermodynamic conditions, as shown by the close agreement of computed and measured structure factors in the molecular and polymer phases. The polymeric phase obtained by increasing pressure has a dominant simple cubic character, while the polymer obtained by raising T at moderate pressure is tetrahedral. Comparison with DF results suggests that the latter is a semiconductor, while the cubic form is metallic. The simulations show that the T-induced polymerization is due to the entropy of the configuration of covalent bonds, as in the polymerization transition in sulfur. The transition observed with increasing P is the continuation at high T of the black P to arsenic (A17) structure observed in the solid state, and also corresponds to a semiconductor to metal transition. (C) 2004 American Institute of Physics.

Density functional and Monte Carlo studies of sulfur. II. Equilibrium polymerization of the liquid phase

The equilibrium polymerization of sulfur is investigated by Monte Carlo simulations. The potential energy model is based on density functional results for the cohesive energy, structural, and vibrational properties as well as reactivity of sulfur rings and chains [Part I, J. Chem. Phys. 118, 9257 (2003)]. Liquid samples of 2048 atoms are simulated at temperatures 450less than or equal toTless than or equal to850 K and P=0 starting from monodisperse S-8 molecular compositions. Thermally activated bond breaking processes lead to an equilibrium population of unsaturated atoms that can change the local pattern of covalent bonds and allow the system to approach equilibrium. The concentration of unsaturated atoms and the kinetics of bond interchanges is determined by the energy DeltaE(b) required to break a covalent bond. Equilibrium with respect to the bond distribution is achieved for 15less than or equal toDeltaE(b)less than or equal to21 kcal/mol over a wide temperature range (Tgreater than or equal to450 K), within which polymerization occurs readily, with entropy from the bond distribution overcompensating the increase in enthalpy. There is a maximum in the polymerized fraction at temperature T-max that depends on DeltaE(b). This fraction decreases at higher temperature because broken bonds and short chains proliferate and, for Tless than or equal toT(max), because entropy is less important than enthalpy. The molecular size distribution is described well by a Zimm-Schulz function, plus an isolated peak for S-8. Large molecules are almost exclusively open chains. Rings tend to have fewer than 24 atoms, and only S-8 is present in significant concentrations at all T. The T dependence of the density and the dependence of polymerization fraction and degree on DeltaE(b) give estimates of the polymerization temperature T-f=450+/-20 K. (C) 2003 American Institute of Physics.