Overlapped Partitioning for Ensemble Classifiers of P300-Based Brain-Computer Interfaces

A P300-based brain-computer interface (BCI) enables a wide range of people to control devices that improve their quality of life. Ensemble classifiers with naive partitioning were recently applied to the P300-based BCI and these classification performances were assessed. However, they were usually trained on a large amount of training data (e.g., 15300). In this study, we evaluated ensemble linear discriminant analysis (LDA) classifiers with a newly proposed overlapped partitioning method using 900 training data. In addition, the classification performances of the ensemble classifier with naive partitioning and a single LDA classifier were compared. One of three conditions for dimension reduction was applied: the stepwise method, principal component analysis (PCA), or none. The results show that an ensemble stepwise LDA (SWLDA) classifier with overlapped partitioning achieved a better performance than the commonly used single SWLDA classifier and an ensemble SWLDA classifier with naive partitioning. This result implies that the performance of the SWLDA is improved by overlapped partitioning and the ensemble classifier with overlapped partitioning requires less training data than that with naive partitioning. This study contributes towards reducing the required amount of training data and achieving better classification performance.     

Predicting potential cancer genes by integrating network properties, sequence features and functional annotations

The discovery of novel cancer genes is one of the main goals in cancer research. Bioinformatics methods can be used to accelerate cancer gene discovery, which may help in the understanding of cancer and the development of drug targets. In this paper, we describe a classifier to predict potential cancer genes that we have developed by integrating multiple biological evidence, including protein-protein interaction network properties, and sequence and functional features. We detected 55 features that were significantly different between cancer genes and non-cancer genes. Fourteen cancer-associated features were chosen to train the classifier. Four machine learning methods, logistic regression, support vector machines (SVMs), BayesNet and decision tree, were explored in the classifier models to distinguish cancer genes from non-cancer genes. The prediction power of the different models was evaluated by 5-fold cross-validation. The area under the receiver operating characteristic curve for logistic regression, SVM, Baysnet and J48 tree models was 0.834, 0.740, 0.800 and 0.782, respectively. Finally, the logistic regression classifier with multiple biological features was applied to the genes in the Entrez database, and 1976 cancer gene candidates were identified. We found that the integrated prediction model performed much better than the models based on the individual biological evidence, and the network and functional features had stronger powers than the sequence features in predicting cancer genes.     

Genus- and isolate-specific real-time PCR quantification of Erwinia on leaf surfaces of English oaks (Quercus robur L.)

In order to quantify pathogenic epiphytic bacteria on leaf surfaces of the important European forest tree Quercus robur without time-intensive cultivation and separation of microorganisms, methods were developed to selectively quantify DNA copy numbers of the genus Erwinia in DNA isolated from the leaf surface. By using the combination of the two different real-time PCR techniques SYBR-Green and TaqMan, methods were developed not only to allow quantification of the total DNA copy number of Erwinia on the oak leaf surface, but also to distinguish between two significantly different groups of Erwinia strains. In the present work, these techniques were successfully applied to quantify the copy number of the genus Erwinia and its subgroups compared with the total bacteria number in DNA samples extracted from the upper leaf surface of English oaks collected on the 4th of June 2001 (Julian day 155).     

Identification of DNA-binding Proteins Using Structural, Electrostatic and Evolutionary Features

DNA-binding proteins (DBPs) participate in various crucial processes in the life-cycle of the cells, and the identification and characterization of these proteins is of great importance. We present here a random forests classifier for identifying DBPs among proteins with known 3D structures. First, clusters of evolutionarily conserved regions (patches) on the surface of proteins were detected using the PatchFinder algorithm; earlier studies showed that these regions are typically the functionally important regions of proteins. Next, we trained a classifier using features like the electrostatic potential, cluster-based amino acid conservation patterns and the secondary structure content of the patches, as well as features of the whole protein, including its dipole moment. Using 10-fold cross-validation on a dataset of 138 DBPs and 110 proteins that do not bind DNA, the classifier achieved a sensitivity and a specificity of 0.90, which is overall better than the performance of published methods. Furthermore, when we tested five different methods on 11 new DBPs that did not appear in the original dataset, only our method annotated all correctly.The resulting classifier was applied to a collection of 757 proteins of known structure and unknown function. Of these proteins, 218 were predicted to bind DNA, and we anticipate that some of them interact with DNA using new structural motifs. The use of complementary computational tools supports the notion that at least some of them do bind DNA.     

Comparison of cultivation-dependent and molecular methods for studying the diversity of anoxygenic purple phototrophs in sediments of an eutrophic brackish lagoon

Phototrophic anoxygenic purple bacteria play a key role in many aquatic ecosystems by oxidizing sulfur compounds and low-molecular-weight organic compounds using light as energy source. In this study, molecular methods based upon pufM gene (photosynthetic unit forming gene) were compared with culture-dependent methods to investigate anoxygenic purple phototrophic communities in sediments of an eutrophic brackish lagoon. Thirteen strains, belonging to eight different genera of purple phototrophic bacteria were isolated with a large dominance of the metabolically versatile purple non-sulfur bacteria (eight strains), some purple sulfur bacteria (three strains) and two strains belonging to the Roseobacter clade (aerobic phototrophs). The pufM genes amplified from the isolated strains were not detected by the molecular methods [terminal-restriction fragment length polymorphism (T-RFLP)] applied on in situ communities. An environmental clone library of the pufM gene was thus constructed from sediment samples. The results showed that most of the clones probably corresponded to aerobic phototrophic bacteria. Our results demonstrate that the culture-dependent techniques remain the best experimental approach for determining the diversity of phototrophic purple non-sulfur bacteria whereas the molecular approach clearly illustrated the abundance of organisms related to the Roseobacter clade in these eutrophic sediments.     

Efficient subfractionation of gram-negative bacteria for proteomics studies

Proteomics studies of pathogenic bacteria are an important basis for biomarker discovery and for the development of antimicrobial drugs and vaccines. Especially where vaccines are concerned, it is of great interest to explore which bacterial factors are exposed on the bacterial cell surface and thus can be directly accessed by the immune system. One crucial step in proteomics studies of bacteria is an efficient subfractionation of their cellular compartments. We set out to compare and improve different protocols for the fractionation of proteins from Gram-negative bacteria into outer membrane, cytoplasmic membrane, periplasmic, and cytosolic fractions, with a focus on the outer membrane. Overall, five methods were compared, three methods for the fast isolation of outer membrane proteins and two methods for the fractionation of each cellular compartment, using Escherichia coli BL21 as a model organism. Proteins from the different fractions were prepared for further mass spectrometric analysis by SDS gel electrophoresis and consecutive in-gel tryptic digestion. Most published subfractionation protocols were not explicitly developed for proteomics applications. Thus, we evaluated not only the separation quality of the five methods but also the suitability of the samples for mass spectrometric analysis. We could obtain high quality mass spectrometry data from one-dimensional SDS-PAGE, which greatly reduces experimental time and sample amount compared to two-dimensional electrophoresis methods. We then applied the most specific fractionation technique to different Gram-negative pathogens, showing that it is efficient in separating the subcellular proteomes independent of the species and that it is capable of producing high-quality proteomics data in electrospray ionization mass spectrometry.     

Optimal approach for classification of acute leukemia subtypes based on gene expression data

The classification of cancer subtypes, which is critical for successful treatment, has been studied extensively with the use of gene expression profiles from oligonucleotide chips or cDNA microarrays. Various pattern recognition methods have been successfully applied to gene expression data. However, these methods are not optimal, rather they are high-performance classifiers that emphasize only classification accuracy. In this paper, we propose an approach for the construction of the optimal linear classifier using gene expression data. Two linear classification methods, linear discriminant analysis (LDA) and discriminant partial least-squares (DPLS), are applied to distinguish acute leukemia subtypes. These methods are shown to give satisfactory accuracy. Moreover, we determined optimally the number of genes participating in the classification (a remarkably small number compared to previous results) on the basis of the statistical significance test. Thus, the proposed method constructs the optimal classifier that is composed of a small size predictor and provides high accuracy.     

基于分子印迹技术的细菌传感检测

分子印迹因其材料结构的稳定性及靶标物识别的特异性而被广泛应用于生化分离分析的相关领域。近年来，将具有选择性捕获、分离和富集靶标物等优势的分子印迹技术与生化传感检测技术有机结合，是目前细菌等微生物高效检测领域备受关注的研究热点。本文就分子印迹技术在细菌分析中的印迹方法、分析检测技术和典型应用等方面的最新进展进行综述。首先介绍了细菌分子印迹原理，对表面印迹的材料以及直接压印、间接印迹和电聚合等制备方法进行了总结和归纳；重点对基于荧光、电化学、石英晶体微天平（QCM）等检测模式的细菌印迹传感监测在细菌分析检测及其与微流控芯片技术耦合的应用和进展进行了综述；最后，提出了存在的挑战及发展的趋势。     

Comparison of three different methods for automated classification of cervical cells.

Over 4600 exfoliated squamous cervical cells taken from appropriate Papanicolaou samples were classified as normal, mildly dysplastic, moderately dysplastic and severely dysplastic by an experienced cytopathologist. The slides were de-stained and subsequently re-stained with Feulgen Thionin-SO2 stain. Images of the nuclei were then captured, recorded and processed employing an image cytometry device. Automated classification of the cells was carried out using three different methods--discriminant function analysis, a decision tree classifier and a neutral network classifier. The discriminant function analysis method, which combined all dysplastic cells into an abnormal group, achieved a combined error rate of less than 0.4% for moderate and severe dysplastic cells, and less than 40% for mildly dysplastic cells. All three methods yielded comparable results, which approached those of human performance.     

Whole-proteome phylogeny of large dsDNA viruses and parvoviruses through a composition vector method related to dynamical language model

Background  

The vast sequence divergence among different virus groups has presented a great challenge to alignment-based analysis of virus phylogeny. Due to the problems caused by the uncertainty in alignment, existing tools for phylogenetic analysis based on multiple alignment could not be directly applied to the whole-genome comparison and phylogenomic studies of viruses. There has been a growing interest in alignment-free methods for phylogenetic analysis using complete genome data. Among the alignment-free methods, a dynamical language (DL) method proposed by our group has successfully been applied to the phylogenetic analysis of bacteria and chloroplast genomes.     

Microbial communities in the saturated groundwater environment I: Methods of isolation and characterization of heterotrophic bacteria

In this paper we present a method of isolation and morphological and physiological characterization of groundwater bacteria based on numerical taxonomy and cluster analysis, and using a miniaturized test system (microtiter plates). Bacteria were isolated randomly on P-agar, and each strain was characterized in regard to 155 features. The media for biochemical differentiation are listed as well as methods of morphological discrimination. 246 strains of heterotrophic and oligotrophic bacteria, isolated from five water samples from different depths of the saturated groundwater area, were used for optimizing media and test reactions.     

ProLoc: prediction of protein subnuclear localization using SVM with automatic selection from physicochemical composition features

Accurate prediction methods of protein subnuclear localizations rely on the cooperation between informative features and classifier design. Support vector machine (SVM) based learning methods are shown effective for predictions of protein subcellular and subnuclear localizations. This study proposes an evolutionary support vector machine (ESVM) based classifier with automatic selection from a large set of physicochemical composition (PCC) features to design an accurate system for predicting protein subnuclear localization, named ProLoc. ESVM using an inheritable genetic algorithm combined with SVM can automatically determine the best number m of PCC features and identify m out of 526 PCC features simultaneously. To evaluate ESVM, this study uses two datasets SNL6 and SNL9, which have 504 proteins localized in 6 subnuclear compartments and 370 proteins localized in 9 subnuclear compartments. Using a leave-one-out cross-validation, ProLoc utilizing the selected m=33 and 28 PCC features has accuracies of 56.37% for SNL6 and 72.82% for SNL9, which are better than 51.4% for the SVM-based system using k-peptide composition features applied on SNL6, and 64.32% for an optimized evidence-theoretic k-nearest neighbor classifier utilizing pseudo amino acid composition applied on SNL9, respectively.     

Comparison of API 20NE and Biolog GN identification systems assessed by techniques of multivariate analyses.

The increasing use of commercial multitest systems for identification of environmental bacteria creates the problem of how to compare the identification results obtained from different systems. The limited use of species designations in such comparisons is caused by low usage of environmental bacteria in the development of commercial identification schemes. Two multivariate statistical methods, the Mantel's test and the co-inertia analysis, were applied to analyze data derived from the Biolog GN and the API 20NE systems of identification for 50 environmental bacterial strains. We found these two methods to be useful for revealing the relationship between the two sets of numerical taxonomic traits. Both of these methods showed that the distances according to the Biolog GN results between the studied strains were related to those derived from the API 20NE results, despite the differences in the test sets of the two systems. In addition, the co-inertia analysis allowed us to visualise the relationships between classifications of strains derived from the two identification systems and, simultaneously, to estimate the contribution of particular tests to the differentiation of bacterial strains.     

Simple alignment-free methods for protein classification: a case study from G-protein-coupled receptors

Computational methods of predicting protein functions rely on detecting similarities among proteins. However, sufficient sequence information is not always available for some protein families. For example, proteins of interest may be new members of a divergent protein family. The performance of protein classification methods could vary in such challenging situations. Using the G-protein-coupled receptor superfamily as an example, we investigated the performance of several protein classifiers. Alignment-free classifiers based on support vector machines using simple amino acid compositions were effective in remote-similarity detection even from short fragmented sequences. Although it is computationally expensive, a support vector machine classifier using local pairwise alignment scores showed very good balanced performance. More commonly used profile hidden Markov models were generally highly specific and well suited to classifying well-established protein family members. It is suggested that different types of protein classifiers should be applied to gain the optimal mining power.     

Influence of nitrate—ammonium ratio on growth and nutrition of Arabidopsis thaliana

We investigated the microbial community structure and population size of arboreal soils—including canopy and bromeliad epiphytic leaf-tank soils—and ground soils in a tropical lowland rainforest in Costa Rica using molecular and cultivation methods. PCR-DGGE analysis of 16S rRNA and 18S rRNA gene fragments and quantitative real-time PCR were applied to survey the bacteria, ammonia-oxidizing bacteria (AOB), and fungi. Bacteria from epiphytic tank soils were isolated and identified. Bacillaceae, Pseudomonadaceae and Micrococcaceae were the most abundant families. According to cluster analysis of DGGE fingerprints a significant difference among the three soil types was evident for bacterial communities. In addition, the microbial communities of canopy and tank soils clustered apart from ground soils. The fungal and AOB communities were diverse but non-specific for the soil types analyzed.     

Purple nonsulfur bacteria diversity in activated sludge and its potential phosphorus-accumulating ability under different cultivation conditions

This study investigates the diversity and the potential phosphorus-accumulating ability among the purple nonsulfur (PNS) bacteria. Traditional methods and molecular biotechniques were applied. Microscopic visualization using 4′,6-diamidino-2-phenylindole staining as well as chemical analysis demonstrated that most of the isolated PNS bacteria presented different levels of phosphorus accumulation. Four of the pure cultures, denoted as Rhodopseudomonas palustris CC1, CC7, G11, and GE1, based on their differences in the PNS’s pufM gene, exhibited higher internal phosphorus content compared to other isolated strains in this study. In addition, substantial polyphosphate accumulation was observed after the bacteria entered their stationary growth phase. Among them, the isolated R. palustris G11 could accumulate internal phosphorus up to 13%–15% of its cell dry weight under anaerobic illuminated incubation conditions. When the incubation status was switched from anaerobic to aerobic, the bacterial phosphorus content had a tendency to decrease slightly or remain about the same throughout the whole aerobic stage. The growth rate and biomass were higher when the PNS bacteria grew under photoheterotrophic conditions rather than the chemoheterotrophic ones. Furthermore, the environmental pH value could affect the contents of internal bacterial phosphate. Results of this study demonstrated that PNS bacteria are a group of the polyphosphate-accumulating organisms, of which this ability had never been properly studied. The conditions that PNS bacteria accumulating polyphosphate presented from this study were unique and showed characteristics that were different from the well-known enhanced biological phosphorus removal model.     

Application of terminal restriction fragment length polymorphism (T-RFLP) analysis to monitor effect of biocontrol agents on rhizosphere microbial community of hot pepper (<Emphasis Type="Italic">Capsicum annuum</Emphasis> L.)

Microbial communities in hot pepper (Capsicum annuum L.) cultivation fields under different cultivation methods were investigated by terminal restriction fragment length polymorphism (T-RFLP) analysis. Rhizosphere soil and leaf samples were collected from control, conventional and nature-friendly cultivation fields between May and July, 2009. Two Bacillus subtilis strains were applied to nature-friendly cultivation fields as biocontrol agents during the sampling period. Relative abundances of bacteria and plant pathogenic fungi related T-RFs were also measured to monitor the effect of biocontrol agents on potential plant pathogenic fungi. In the principal component analysis (PCA) based on T-RFLP profiles, the microbial communities from rhizosphere soil samples in July, including bacteria and fungi, showed distinct difference between nature-friendly cultivation fields and other cultivation fields. However, there was no correlation between cultivation methods and leaf microbial communities at any sampling period. Changes in the abundance of bacteria related T-RF in the rhizosphere of nature-friendly cultivation fields were observed clearly two months after application of biocontrol agent, while the abundance of plant pathogenic fungi related T-RFs significantly decreased.     

‘True’ null allele detection in microsatellite loci: a comparison of methods,assessment of difficulties and survey of possible improvements

Null alleles are alleles that for various reasons fail to amplify in a PCR assay. The presence of null alleles in microsatellite data is known to bias the genetic parameter estimates. Thus, efficient detection of null alleles is crucial, but the methods available for indirect null allele detection return inconsistent results. Here, our aim was to compare different methods for null allele detection, to explain their respective performance and to provide improvements. We applied several approaches to identify the ‘true’ null alleles based on the predictions made by five different methods, used either individually or in combination. First, we introduced simulated ‘true’ null alleles into 240 population data sets and applied the methods to measure their success in detecting the simulated null alleles. The single best‐performing method was ML‐NullFreq_frequency. Furthermore, we applied different noise reduction approaches to improve the results. For instance, by combining the results of several methods, we obtained more reliable results than using a single one. Rule‐based classification was applied to identify population properties linked to the false discovery rate. Rules obtained from the classifier described which population genetic estimates and loci characteristics were linked to the success of each method. We have shown that by simulating ‘true’ null alleles into a population data set, we may define a null allele frequency threshold, related to a desired true or false discovery rate. Moreover, using such simulated data sets, the expected null allele homozygote frequency may be estimated independently of the equilibrium state of the population.     

BOX-PCR技术在微生物多样性研究中的应用

近年来在微生物多样性研究中,利用微生物基因组中广泛分布的短重复序列设计引物,选择性地扩增重复序列之间的不同基因区域,以得到大小不等的DNA扩增片段的方法日渐增多.以BOX插入因子(细菌基因组重复序列)为基础的PCR技术,具有操作简单快捷,可重复性强,容易获得较为丰富的扩增条带等特点,最初主要应用于细菌的多样性研究.目前研究发现用BoxA1R引物对微生物中的真菌、放线菌进行选择性的扩增,也能够达到很好的遗传及多样性分析的目的.本文综述了BOX-PCR指纹图谱分析技术的特点和一般步骤;结合作者对植物内生细菌的BOX-PCR指纹图谱分析体系的优化,对BOX-PCR技术的改进进行了总结:并对该技术在微生物菌株多样性研究领域的应用现状和前景进行了阐述.     

Spatial distribution and species composition of prosthecate bacteria in Lake Baĭkal

From the water column of Lake Baikal, several strains of prosthecate bacteria belonging to the genera Caulobacter and Brevundimonas were isolated. In this article, the methods applied for their isolation and cell number determination are described; the occurrence frequency and spatial distribution of these microorganisms in the lake are demonstrated. Characterization of the species composition of cultivable and uncultivable prosthecate bacteria was carried out using the methods of traditional and molecular microbiology, respectively. A comparative phylogenetic analysis of the DNA sequences of uncultivable bacteria, which showed homology to the members of the alpha subclass of proteobacteria, was carried out. It was demonstrated that the lake water column is inhabited by uncultivable alpha-proteobacteria of uncertain phylogenetic affinity, in addition to representatives of the species Caulobacter vibrioides and C. leidyi, which were detected by traditional microbiological methods.