Belief Combination of Classifiers for Incomplete Data

Data with missing values,or incomplete information,brings some challenges to the development of classification,as the incompleteness may significantly affect the performance of classifiers.In this paper,we handle missing values in both training and test sets with uncertainty and imprecision reasoning by proposing a new belief combination of classifier(BCC)method based on the evidence theory.The proposed BCC method aims to improve the classification performance of incomplete data by characterizing the uncertainty and imprecision brought by incompleteness.In BCC,different attributes are regarded as independent sources,and the collection of each attribute is considered as a subset.Then,multiple classifiers are trained with each subset independently and allow each observed attribute to provide a sub-classification result for the query pattern.Finally,these sub-classification results with different weights(discounting factors)are used to provide supplementary information to jointly determine the final classes of query patterns.The weights consist of two aspects:global and local.The global weight calculated by an optimization function is employed to represent the reliability of each classifier,and the local weight obtained by mining attribute distribution characteristics is used to quantify the importance of observed attributes to the pattern classification.Abundant comparative experiments including seven methods on twelve datasets are executed,demonstrating the out-performance of BCC over all baseline methods in terms of accuracy,precision,recall,F1 measure,with pertinent computational costs.

Structural characteristics and the label-free detection of poly(3,4-ethylenedioxythiophene/cucurbit[7]uril)pseudorotaxane at single molecule level

A multi-technique approach to prove the preparation of poly(3,4-ethylenedioxythiophene/cucurbit[7]uril)pseudorotaxanes(PEDOT∙CB7-PPs)is reported.Molecular docking simulation and matrix-assisted laser desorption/ionization mass spectrometry(MALDI MS)validate the complexation ability of the CB7 molecule towards 3,4-ethylenedioxythiophene(EDOT),which leads to the EDOT∙CB7 inclusion complex.Oxidative polymerization of EDOT∙CB7 enabled the synthesis of PEDOT∙CB7-PPs.The water-soluble part of PEDOT∙CB7-PPs was selected,freeze-dried,and chemically characterized.Furthermore,dynamic light scattering(DLS)has been used to study the particle size and z-potential(ZP-ζ)of PEDOT∙CB7-PPs.The ZP-ζvalue(35 mV)evidenced that the PEDOT∙CB7-PPs formed stable water dispersion.By combining the emerging nanopore resistive pulse sensing technique(Np-RPS)and computational modeling,we identified strong interactions of PEDOT∙CB7-PPs with the aerolysin(Ael)nanopore.PEDOT∙CB7-PPs behave as positive charged species,and thus trans negative bias promotes its interactions with the Ael nanopore.The computational modeling results are fully consistent with the Np-RPS detection,which also reveals strong interactions between PEDOT∙CB7-PPs and the Ael nanopore.With this study,we hope to provide new insights and a better understanding of the interactions between supramolecular complexes based on CB7 and biological entities,which is instrumental for future applications in the field of nanobiotechnology.

Focus on using nanopore technology for societal health,environmental,and energy challenges

With an increasing global population that is rapidly ageing,our society faces challenges that impact health,environment,and energy demand.With this ageing comes an accumulation of cellular changes that lead to the development of diseases and susceptibility to infections.This impacts not only the health system,but also the global economy.As the population increases,so does the demand for energy and the emission of pollutants,leading to a progressive degradation of our environment.This in turn impacts health through reduced access to arable land,clean water,and breathable air.New monitoring approaches to assist in environmental control and minimize the impact on health are urgently needed,leading to the development of new sensor technologies that are highly sensitive,rapid,and low-cost.Nanopore sensing is a new technology that helps to meet this purpose,with the potential to provide rapid point-of-care medical diagnosis,real-time on-site pollutant monitoring systems to manage environmental health,as well as integrated sensors to increase the efficiency and storage capacity of renewable energy sources.In this review we discuss how the powerful approach of nanopore based single-molecule,or particle,electrical promises to overcome existing and emerging societal challenges,providing new opportunities and tools for personalized medicine,localized environmental monitoring,and improved energy production and storage systems.

Polypeptide analysis for nanopore-based protein identification

Presently,proteins are identified by cleaving them with proteases,measuring the mass to charge ratio of the fragments with a mass spectrometer,and matching the fragments to segments within known proteins in databases.We earlier demonstrated that a nanometer-scale pore formed by aerolysin(AeL)can discriminate between,and therefore identify,three similar size proteins from their trypsin-cleaved polypeptide fragments.With this nanopore-protease method,the protein’s identity is instead determined from characteristic ionic current blockade patterns caused by the polypeptide fragments that enter the nanopore.The results also suggested that not all of the theoretically expected cleavage products partition into the pore.To better understand the mechanism by which polypeptide fragments are captured,and how different polypeptides reduce the pore’s ionic current,we studied the effects of 11 identical length polypeptides with different net charges and charge distributions.We show that under certain experimental conditions,negative,positive,and neutral polypeptides are driven into the AeL pore by the same applied voltage polarity.The capture rate and dwell time of polypeptides in the pore depend strongly on the ionic strength,the magnitude of the applied voltage,and the net charge and charge distribution of the polypeptides.The dwell time distribution depends nonmonotonically on the applied voltage(regardless of the polymer’s net charge),and its maximum value depends on the polypeptide net charge and charge distribution.The maximum dwell time for different polypeptides does not occur at the same applied voltage amplitude,which conceivably might complicate the detection and discrimination of some polypeptide fragments.Although additional experiments,computer simulations,and artificial intelligence research are needed to better understand how to optimize the partitioning of enzymatically cleaved fragments into the AeL nanopore,the method is still capable of accurately identifying proteins.