Virus-PLoc: a fusion classifier for predicting the subcellular localization of viral proteins within host and virus-infected cells

Viruses can reproduce their progenies only within a host cell, and their actions depend both on its destructive tendencies toward a specific host cell and on environmental conditions. Therefore, knowledge of the subcellular localization of viral proteins in a host cell or virus-infected cell is very useful for in-depth studying of their functions and mechanisms as well as designing antiviral drugs. An analysis on the Swiss-Prot database (version 50.0, released on May 30, 2006) indicates that only 23.5% of viral protein entries are annotated for their subcellular locations in this regard. As for the gene ontology database, the corresponding percentage is 23.8%. Such a gap calls for the development of high throughput tools for timely annotating the localization of viral proteins within host and virus-infected cells. In this article, a predictor called "Virus-PLoc" has been developed that is featured by fusing many basic classifiers with each engineered according to the K-nearest neighbor rule. The overall jackknife success rate obtained by Virus-PLoc in identifying the subcellular compartments of viral proteins was 80% for a benchmark dataset in which none of proteins has more than 25% sequence identity to any other in a same location site. Virus-PLoc will be freely available as a web-server at http://202.120.37.186/bioinf/virus for the public usage. Furthermore, Virus-PLoc has been used to provide large-scale predictions of all viral protein entries in Swiss-Prot database that do not have subcellular location annotations or are annotated as being uncertain. The results thus obtained have been deposited in a downloadable file prepared with Microsoft Excel and named "Tab_Virus-PLoc.xls." This file is available at the same website and will be updated twice a year to include the new entries of viral proteins and reflect the continuous development of Virus-PLoc.     

The management of vegetation classifications with fuzzy clustering

Questions: Does fuzzy clustering provide an appropriate numerical framework to manage vegetation classifications? What is the best fuzzy clustering method to achieve this? Material: We used 531 relevés from Catalonia (Spain), belonging to two syntaxonomic alliances of mesophytic and xerophytic montane pastures, and originally classified by experts into nine and 13 associations, respectively. Methods: We compared the performance of fuzzy C‐means (FCM), noise clustering (NC) and possibilistic C‐means (PCM) on four different management tasks: (1) assigning new relevé data to existing types; (2) updating types incorporating new data; (3) defining new types with unclassified relevés; and (4) reviewing traditional vegetation classifications. Results: As fuzzy classifiers, FCM fails to indicate when a given relevé does not belong to any of the existing types; NC might leave too many relevés unclassified; and PCM membership values cannot be compared. As unsupervised clustering methods, FCM is more sensitive than NC to transitional relevés and therefore produces fuzzier classifications. PCM looks for dense regions in the space of species composition, but these are scarce when vegetation data contain many transitional relevés. Conclusions: All three models have advantages and disadvantages, although the NC model may be a good compromise between the restricted FCM model and the robust but impractical PCM model. In our opinion, fuzzy clustering might provide a suitable framework to manage vegetation classifications using a consistent operational definition of vegetation type. Regardless of the framework chosen, national/regional vegetation classification panels should promote methodological standards for classification practices with numerical tools.     

Developing an indicator system for local governments to evaluate transport sustainability strategies

This study proposed an indicator system for measuring and monitoring transport sustainability at the county (or city) level. Twenty-one indicators were grouped into economy, environment, society, and energy aspects. A committee comprised of government officials from Taipei City and New Taipei City proposed transport solutions to improve the transport sustainability of the Taipei metropolitan area. Ten key indicators were selected to measure the sustainable transport strategies. This study applied Fuzzy Cognitive Maps (FCMs) and the Analytic Hierarchy Process (AHP) to construct the cause–effect relationships between these key indicators and to evaluate sustainable transport strategies. The evaluation results showed that the strategy of expanding mass rapid transit (MRT) lines was predicted to produce the most significant improvements; the strategy of integrating bus exclusive lanes would provide the least improvement; and the strategies of promoting cleaner vehicles and integrating Fu-Kang bus resources would perform similarly to each other in improving transport sustainability.     

Autonomic resource management in virtualized data centers using fuzzy logic-based approaches

Data centers, as resource providers, are expected to deliver on performance guarantees while optimizing resource utilization to reduce cost. Virtualization techniques provide the opportunity of consolidating multiple separately managed containers of virtual resources on underutilized physical servers. A key challenge that comes with virtualization is the simultaneous on-demand provisioning of shared physical resources to virtual containers and the management of their capacities to meet service-quality targets at the least cost. This paper proposes a two-level resource management system to dynamically allocate resources to individual virtual containers. It uses local controllers at the virtual-container level and a global controller at the resource-pool level. An important advantage of this two-level control architecture is that it allows independent controller designs for separately optimizing the performance of applications and the use of resources. Autonomic resource allocation is realized through the interaction of the local and global controllers. A novelty of the local controller designs is their use of fuzzy logic-based approaches to efficiently and robustly deal with the complexity and uncertainties of dynamically changing workloads and resource usage. The global controller determines the resource allocation based on a proposed profit model, with the goal of maximizing the total profit of the data center. Experimental results obtained through a prototype implementation demonstrate that, for the scenarios under consideration, the proposed resource management system can significantly reduce resource consumption while still achieving application performance targets.

Fuzzy knowledge- and data-based models of damage to reeds by grazing of Greylag Geese

This paper describes a fuzzy and neuro-fuzzy approach to modelling feeding intensity of Greylag Geese on reed. As a consequence of the presence of some non-measurable or random factors and the heterogeneity of reed and goose behaviour, the relationships between the model variables are often not well known and the data collected have a high degree of uncertainty. A fuzzy approach was selected which can be applied with vague knowledge and data of high uncertainty. Fuzzy logic can be used to handle inexact reasoning in knowledge-based models with fuzzy rules and fuzzy sets to handle uncertainty in data. The neural network technique was applied to develop the fuzzy data-based models. For training, several dataset combinations of three lakes in North Germany were used. The generalisation capability of these models was checked for other lakes. The performance of these models was compared with the results of the fuzzy knowledge-based model developed in the next step. The knowledge base of this model contains the Mamdani-type rules formulated by a domain expert. All models were implemented using the Fuzzy Logic Toolbox of MATLAB^®.     

Decision errors in evaluating tipping points for ecosystem resilience

When an ecosystem reaches tipping points for selected indicators, resilience to further changes in external drivers can decrease, regime shifts can occur that diminish the capacity of the ecosystem to provide ecosystem services, and the ecosystem is more vulnerable to collapse. Evaluating tipping points for resilience using crisp decision rules can result in decision errors about whether or not resilience has been compromised. The source and nature of those errors are described and a fuzzy decision rule is proposed for evaluating resilience. Decision errors are evaluated for four cases. Cases 1 through 3 (or case 4) derive conditions for evaluating decision errors when there is a single (or multiple) indicator(s). The primary sources of decision errors for the four cases are discrepancies between measured (or established) and true values of the indicators (or tipping points) and using a crisp decision rule to reach conclusions about whether or not resilience has been compromised. A fuzzy decision rule, based on fuzzy TOPSIS, is proposed that evaluates the extent to which an ecosystem is resilient. Although crisp decision rules provide unambiguous conclusions about resilience, those conclusions can be faulty, particularly when measured indicators and established tipping points deviate substantially from their true values. In contrast, the conclusions from the fuzzy decision rule are less susceptible to the decision errors and, hence, faulty decisions.     

Bis-class: a new classification tool of methylation status using bayes classifier and local methylation information

Background

Whole genome sequencing of bisulfite converted DNA (‘methylC-seq’) method provides comprehensive information of DNA methylation. An important application of these whole genome methylation maps is classifying each position as a methylated versus non-methylated nucleotide. A widely used current method for this purpose, the so-called binomial method, is intuitive and straightforward, but lacks power when the sequence coverage and the genome-wide methylation level are low. These problems present a particular challenge when analyzing sparsely methylated genomes, such as those of many invertebrates and plants.

Results

We demonstrate that the number of sequence reads per position from methylC-seq data displays a large variance and can be modeled as a shifted negative binomial distribution. We also show that DNA methylation levels of adjacent CpG sites are correlated, and this similarity in local DNA methylation levels extends several kilobases. Taking these observations into account, we propose a new method based on Bayesian classification to infer DNA methylation status while considering the neighborhood DNA methylation levels of a specific site. We show that our approach has higher sensitivity and better classification performance than the binomial method via multiple analyses, including computational simulations, Area Under Curve (AUC) analyses, and improved consistencies across biological replicates. This method is especially advantageous in the analyses of sparsely methylated genomes with low coverage.

Conclusions

Our method improves the existing binomial method for binary methylation calls by utilizing a posterior odds framework and incorporating local methylation information. This method should be widely applicable to the analyses of methylC-seq data from diverse sparsely methylated genomes. Bis-Class and example data are provided at a dedicated website (http://bibs.snu.ac.kr/software/Bisclass).

Electronic supplementary material

The online version of this article (doi:10.1186/1471-2164-15-608) contains supplementary material, which is available to authorized users.     

Predicting the Risk of Suicide by Analyzing the Text of Clinical Notes

We developed linguistics-driven prediction models to estimate the risk of suicide. These models were generated from unstructured clinical notes taken from a national sample of U.S. Veterans Administration (VA) medical records. We created three matched cohorts: veterans who committed suicide, veterans who used mental health services and did not commit suicide, and veterans who did not use mental health services and did not commit suicide during the observation period (n = 70 in each group). From the clinical notes, we generated datasets of single keywords and multi-word phrases, and constructed prediction models using a machine-learning algorithm based on a genetic programming framework. The resulting inference accuracy was consistently 65% or more. Our data therefore suggests that computerized text analytics can be applied to unstructured medical records to estimate the risk of suicide. The resulting system could allow clinicians to potentially screen seemingly healthy patients at the primary care level, and to continuously evaluate the suicide risk among psychiatric patients.