阿尔茨海默病诊断的自适应BP神经网络模型

阿尔茨海默病(AD)和轻度认知功能损伤(MCI)具有患者多、诊断难的特点,改进BP神经网络,提出自适应BP神经网络(ABP)进行100次AD和MCI诊断模拟,ABP神经网络的诊断正确率显著高于BP和RBF神经网络.采用留一法将101例正常人、200例MCI和90例AD患者的样本分为训练集和检测集,用ABP神经网络对其进行诊断模拟,总正确率达到73.91%.     

An improved ensemble learning machine for biological activity prediction of tyrosine kinase inhibitors

Boosting is one of the most important strategies in ensemble learning because of its ability to improve the stability and performance of weak learners. It is nonparametric, multivariate, fast and interpretable but is not robust against outliers. To enhance its prediction accuracy as well as immunize it against outliers, a modified version of a boosting algorithm (AdaBoost R2) was developed and called AdaBoost R3. In the sampling step, extremum samples were added to the boosting set. In the robustness step, a modified Huber loss function was applied to overcome the outlier problem. In the output step, a deterministic threshold was used to guarantee that bad predictions do not participate in the final output. The performance of the modified algorithm was investigated with two anticancer data sets of tyrosine kinase inhibitors, and the mechanism of inhibition was studied using the relative weighted variable importance procedure. Investigating the effect of base learner's strength reveals that boosting is only successful using the classification and regression tree method (a weak to moderate learner) and does not have a significant effect using the radial basis functions partial least square method (a strong base learners). Copyright © 2015 John Wiley & Sons, Ltd.     

Study of the Molecular Mobility in Polymers with the Thermally Stimulated Recovery Technique—A Review

Thermally stimulated recovery (TSR) is a non‐conventional mechanical spectroscopy technique that allows to analyse in detail the relaxation processes of polymeric systems in the low frequency region. This work reviews the main aspects and potentialities of this technique. The different kinds of TSR experiments that can be performed, global and thermal sampling (TS) experiments, are described and illustrated with several examples. Also, the different methods for the determination of the thermokinetic parameters (activation energy and pre‐exponential factor) of the thermal sampling (TS) procedure are explained and compared. In this context, the compensation phenomenon, which always appears in TSR results when the studies are performed in the glass transition region of a given system, is discussed. Examples of the application of this technique to different polymeric systems during the last 20 years are provided. An emphasis will be made on the analysis of the effect of crystallinity degree and crosslink density on the TSR response. A comparison between the results (characteristic times and activation energies) obtained by different techniques, namely TSR, dynamic mechanical analysis (DMA), and differential scanning calorimetry (DSC), is made.     

Banana-shaped mesogens: effect of lateral substituents on seven-ring esters containing a biphenyl moiety

The synthesis and characterization of five homologous series of symmetrical compounds composed of banana-shaped molecules containing a biphenyl moiety are reported. All these compounds are non-Schiff's bases and are esters. The effects of lateral substituents such as fluoro, methyl and ethyl in the side arms of these molecules are examined. These substituents have a strong influence in reducing the clearing temperatures. Banana phases such as B1, B2 and B6 were observed in the above series of compounds. The mesophases were characterized by a combination of polarizing optical microscopy, differential scanning calorimetry, X-ray diffraction and electro-optic studies.     

Enthalpy–Entropy Compensation Combined with Cohesive Free‐Energy Densities for Tuning the Melting Temperatures of Cyanobiphenyl Derivatives

This work illustrates how minor structural perturbations produced by methylation of 4′‐(dodecyloxy)‐4‐cyanobiphenyl leads to enthalpy–entropy compensation for their melting processes, a trend which can be analyzed within the frame of a simple intermolecular cohesive model. The transformation of the melting thermodynamic parameters collected at variable temperatures into cohesive free‐energy densities expressed at a common reference temperature results in a novel linear correlation, from which melting temperatures can be simply predicted from molecular volumes.     

Switching adaptive controllers to control fractional‐order complex systems with unknown structure and input nonlinearities

This article investigates the chaos control problem for the fractional‐order chaotic systems containing unknown structure and input nonlinearities. Two types of nonlinearity in the control input are considered. In the first case, a general continuous nonlinearity input is supposed in the controller, and in the second case, the unknown dead‐zone input is included. In each case, a proper switching adaptive controller is introduced to stabilize the fractional‐order chaotic system in the presence of unknown parameters and uncertainties. The control methods are designed based on the boundedness property of the chaotic system's states, where, in the proposed methods the nonlinear/linear dynamic terms of the fractional‐order chaotic systems are assumed to be fully unknown. The analytical results of the mentioned techniques are proved by the stability analysis theorem of fractional‐order systems and the adaptive control method. In addition, as an application of the proposed methods, single input adaptive controllers are adopted for control of a class of three‐dimensional nonlinear fractional‐order chaotic systems. And finally, some numerical examples illustrate the correctness of the analytical results. © 2014 Wiley Periodicals, Inc. Complexity 21: 211–223, 2015     

Wild-type and molten globular chorismate mutase achieve comparable catalytic rates using very different enthalpy/entropy compensations

The origin of the catalytic power of enzymes with a meta-stable native state,e.g.molten globular state,is an unsolved challenging issue in biochemistry.To help understand the possible differences between this special class of enzymes and the typical ones,we report here computer simulations of the catalysis of both the well-folded wild-type and the molten globular mutant of chorismate mutase.Using the ab initio quantum mechanical/molecular mechanical minimum free-energy path method,we determined the height of reaction barriers that are in good agreement with experimental measurements.Enzyme-substrate interactions were analyzed in detail to identify factors contributing to catalysis.Computed angular order parameters of backbone N–H bonds and side-chain methyl groups suggested site-specific,non-uniform rigidity changes of the enzymes during catalysis.The change of conformational entropy from the ground state to the transition state revealed distinctly contrasting entropy/enthalpy compensations in the dimeric wild-type enzyme and its molten globular monomeric variant.A unique catalytic strategy was suggested for enzymes that are natively molten globules:some may possess large conformational flexibility to provide strong electrostatic interactions to stabilize the transition state of the substrate and compensate for the entropy loss in the transition state.The equilibrium conformational dynamics in the reactant state were analyzed to quantify their contributions to the structural transitions enzymes needed to reach the transition states.The results suggest that large-scale conformational dynamics make important catalytic contributions to sampling conformational regions in favor of binding the transition state of substrate.     

Calcium Carbonate Dissolution from the Laboratory to the Ocean: Kinetics and Mechanism

The ultimate fate, over the course of millennia, of nearly all of the carbon dioxide formed by humankind is for it to react with calcium carbonate in the world's oceans. Although, this reaction is of global relevance, aspects of the calcite dissolution reaction remain poorly described with apparent contradictions present throughout the expansive literature. In this perspective we aim to evidence how a lack of appreciation of the role of mass-transport may have hampered developments in this area. These insights have important implications for both idealised experiments performed under laboratory conditions and for the measurement and modelling of oceanic calcite sediment dissolution.