Class-imbalanced classifiers for high-dimensional data.

A class-imbalanced classifier is a decision rule to predict the class membership of new samples from an available data set where the class sizes differ considerably. When the class sizes are very different, most standard classification algorithms may favor the larger (majority) class resulting in poor accuracy in the minority class prediction. A class-imbalanced classifier typically modifies a standard classifier by a correction strategy or by incorporating a new strategy in the training phase to account for differential class sizes. This article reviews and evaluates some most important methods for class prediction of high-dimensional imbalanced data. The evaluation addresses the fundamental issues of the class-imbalanced classification problem: imbalance ratio, small disjuncts and overlap complexity, lack of data and feature selection. Four class-imbalanced classifiers are considered. The four classifiers include three standard classification algorithms each coupled with an ensemble correction strategy and one support vector machines (SVM)-based correction classifier. The three algorithms are (i) diagonal linear discriminant analysis (DLDA), (ii) random forests (RFs) and (ii) SVMs. The SVM-based correction classifier is SVM threshold adjustment (SVM-THR). A Monte-Carlo simulation and five genomic data sets were used to illustrate the analysis and address the issues. The SVM-ensemble classifier appears to perform the best when the class imbalance is not too severe. The SVM-THR performs well if the imbalance is severe and predictors are highly correlated. The DLDA with a feature selection can perform well without using the ensemble correction.

Data mining tools for Salmonella characterization: application to gel-based fingerprinting analysis.

BACKGROUND: Pulsed field gel electrophoresis (PFGE) is currently the most widely and routinely used method by the Centers for Disease Control and Prevention (CDC) and state health labs in the United States for Salmonella surveillance and outbreak tracking. Major drawbacks of commercially available PFGE analysis programs have been their difficulty in dealing with large datasets and the limited availability of analysis tools. There exists a need to develop new analytical tools for PFGE data mining in order to make full use of valuable data in large surveillance databases. RESULTS: In this study, a software package was developed consisting of five types of bioinformatics approaches exploring and implementing for the analysis and visualization of PFGE fingerprinting. The approaches include PFGE band standardization, Salmonella serotype prediction, hierarchical cluster analysis, distance matrix analysis and two-way hierarchical cluster analysis. PFGE band standardization makes it possible for cross-group large dataset analysis. The Salmonella serotype prediction approach allows users to predict serotypes of Salmonella isolates based on their PFGE patterns. The hierarchical cluster analysis approach could be used to clarify subtypes and phylogenetic relationships among groups of PFGE patterns. The distance matrix and two-way hierarchical cluster analysis tools allow users to directly visualize the similarities/dissimilarities of any two individual patterns and the inter- and intra-serotype relationships of two or more serotypes, and provide a summary of the overall relationships between user-selected serotypes as well as the distinguishable band markers of these serotypes. The functionalities of these tools were illustrated on PFGE fingerprinting data from PulseNet of CDC. CONCLUSIONS: The bioinformatics approaches included in the software package developed in this study were integrated with the PFGE database to enhance the data mining of PFGE fingerprints. Fast and accurate prediction makes it possible to elucidate Salmonella serotype information before conventional serological methods are pursued. The development of bioinformatics tools to distinguish the PFGE markers and serotype specific patterns will enhance PFGE data retrieval, interpretation and serotype identification and will likely accelerate source tracking to identify the Salmonella isolates implicated in foodborne diseases.

Prediction system for rapid identification of Salmonella serotypes based on pulsed-field gel electrophoresis fingerprints.

A classification model is presented for rapid identification of Salmonella serotypes based on pulsed-field gel electrophoresis (PFGE) fingerprints. The classification model was developed using random forest and support vector machine algorithms and was then applied to a database of 45,923 PFGE patterns, randomly selected from all submissions to CDC PulseNet from 2005 to 2010. The patterns selected included the top 20 most frequent serotypes and 12 less frequent serotypes from various sources. The prediction accuracies for the 32 serotypes ranged from 68.8% to 99.9%, with an overall accuracy of 96.0% for the random forest classification, and ranged from 67.8% to 100.0%, with an overall accuracy of 96.1% for the support vector machine classification. The prediction system improves reliability and accuracy and provides a new tool for early and fast screening and source tracking of outbreak isolates. It is especially useful to get serotype information before the conventional methods are done. Additionally, this system also works well for isolates that are serotyped as "unknown" by conventional methods, and it is useful for a laboratory where standard serotyping is not available.

The genetic toxicity of methylphenidate: a review of the current literature.

Attention deficit/hyperactivity disorder (ADHD), a common children's behavioral disorder, is characterized by inattention, hyperactivity and impulsivity. The disorder is thought to stem from abnormalities in the catecholamine pathway and the symptoms of the disorder have been successfully treated with methylphenidate (MPH) since the FDA approved the drug in the 1950s. MPH underwent the appropriate safety testing as part of the FDA approval process; however, a publication in 2005 that reported significant increases in cytogenetic damage in the lymphocytes of MPH-treated pediatric patients caused concern for patients and their families, the pharmaceutical industry and regulatory agencies. This communication will review the many studies that were subsequently initiated worldwide to address the genetic safety of MPH in both animal models and human subjects. Animal experiments broadened the study protocols used in the 2005 investigation to include a wider dose-range, a longer treatment period and automated scoring of biological endpoints, where possible, to reduce observer bias. The human subject studies replicated the experimental design used in the 2005 study, but increased the treatment periods and the sizes of the study populations. Neither the laboratory animal nor human subject studies found an increase in any of the measures of genetic damage that were evaluated. Taken together, these new studies are consistent with the original safety evaluation of the FDA and do not support the hypothesis that MPH treatment increases the risk of genetic damage in ADHD patients. Published 2012. This article is a US Government work and is in the public domain in the USA.

Possible impacts of the predominant Bacillus bacteria on the Ophiocordyceps unilateralis s. l. in its infected ant cadavers.

Animal hosts infected and killed by parasitoid fungi become nutrient-rich cadavers for saprophytes. Bacteria adapted to colonization of parasitoid fungi can be selected and can predominate in the cadavers, actions that consequently impact the fitness of the parasitoid fungi. In Taiwan, the zombie fungus, Ophiocordyceps unilateralis sensu lato (Clavicipitaceae: Hypocreales), was found to parasitize eight ant species, with preference for a principal host, Polyrhachis moesta. In this study, ant cadavers grew a fungal stroma that was predominated by Bacillus cereus/thuringiensis. The bacterial diversity in the principal ant host was found to be lower than the bacterial diversity in alternative hosts, a situation that might enhance the impact of B. cereus/thuringiensis on the sympatric fungus. The B. cereus/thuringiensis isolates from fungal stroma displayed higher resistance to a specific naphthoquinone (plumbagin) than sympatric bacteria from the environment. Naphthoquinones are known to be produced by O. unilateralis s. l., and hence the resistance displayed by B. cereus/thuringiensis isolates to these compounds suggests an advantage to B. cereus/thuringiensis to grow in the ant cadaver. Bacteria proliferating in the ant cadaver inevitably compete for resources with the fungus. However, the B. cereus/thuringiensis isolates displayed in vitro capabilities of hemolysis, production of hydrolytic enzymes, and antagonistic effects to co-cultured nematodes and entomopathogenic fungi. Thus, co-infection with B. cereus/thuringiensis offers potential benefits to the zombie fungus in killing the host under favorable conditions for reproduction, digesting the host tissue, and protecting the cadaver from being taken over by other consumers. With these potential benefits, the synergistic effect of B. cereus/thuringiensis on O. unilateralis infection is noteworthy given the competitive relationship of these two organisms sharing the same resource.

Power and sample size estimation in microarray studies.

BACKGROUND: Before conducting a microarray experiment, one important issue that needs to be determined is the number of arrays required in order to have adequate power to identify differentially expressed genes. This paper discusses some crucial issues in the problem formulation, parameter specifications, and approaches that are commonly proposed for sample size estimation in microarray experiments. Common methods for sample size estimation are formulated as the minimum sample size necessary to achieve a specified sensitivity (proportion of detected truly differentially expressed genes) on average at a specified false discovery rate (FDR) level and specified expected proportion (pi1) of the true differentially expression genes in the array. Unfortunately, the probability of detecting the specified sensitivity in such a formulation can be low. We formulate the sample size problem as the number of arrays needed to achieve a specified sensitivity with 95% probability at the specified significance level. A permutation method using a small pilot dataset to estimate sample size is proposed. This method accounts for correlation and effect size heterogeneity among genes. RESULTS: A sample size estimate based on the common formulation, to achieve the desired sensitivity on average, can be calculated using a univariate method without taking the correlation among genes into consideration. This formulation of sample size problem is inadequate because the probability of detecting the specified sensitivity can be lower than 50%. On the other hand, the needed sample size calculated by the proposed permutation method will ensure detecting at least the desired sensitivity with 95% probability. The method is shown to perform well for a real example dataset using a small pilot dataset with 4-6 samples per group. CONCLUSIONS: We recommend that the sample size problem should be formulated to detect a specified proportion of differentially expressed genes with 95% probability. This formulation ensures finding the desired proportion of true positives with high probability. The proposed permutation method takes the correlation structure and effect size heterogeneity into consideration and works well using only a small pilot dataset.

Evaluation of pulsed-field gel electrophoresis profiles for identification of Salmonella serotypes.

Pulsed-field gel electrophoresis (PFGE) is a standard typing method for isolates from Salmonella outbreaks and epidemiological investigations. Eight hundred sixty-six Salmonella enterica isolates from eight serotypes, including Heidelberg (n = 323), Javiana (n = 200), Typhimurium (n = 163), Newport (n = 93), Enteritidis (n = 45), Dublin (n = 25), Pullorum (n = 9), and Choleraesuis (n = 8), were subjected to PFGE, and their profiles were analyzed by random forest classification and compared to conventional hierarchical cluster analysis to determine potential predictive relationships between PFGE banding patterns and particular serotypes. Cluster analysis displayed only the underlying similarities and relationships of the isolates from the eight serotypes. However, for serotype prediction of a nonserotyped Salmonella isolate from its PFGE pattern, random forest classification provided better accuracy than conventional cluster analysis. Discriminatory DNA band class markers were identified for distinguishing Salmonella serotype Heidelberg, Javiana, Typhimurium, and Newport isolates.

Effects of auxin derivatives on phenotypic plasticity and stress tolerance in five species of the green alga Desmodesmus (Chlorophyceae, Chlorophyta).

Green microalgae of the genus Desmodesmus are characterized by a high degree of phenotypic plasticity (i.e. colony morphology), allowing them to be truly cosmopolitan and withstand environmental fluctuations. This flexibility enables Desmodesmus to produce a phenotype-environment match across a range of environments broader compared to algae with more fixed phenotypes. Indoles and their derivatives are a well-known crucial class of heterocyclic compounds and are widespread in different species of plants, animals, and microorganisms. Indole-3-acetic acid (IAA) is the most common, naturally occurring plant hormone of the auxin class. IAA may behave as a signaling molecule in microorganisms, and the physiological cues of IAA may also trigger phenotypic plasticity responses in Desmodesmus. In this study, we demonstrated that the changes in colonial morphs (cells per coenobium) of five species of the green alga Desmodesmus were specific to IAA but not to the chemically more stable synthetic auxins, naphthalene-1-acetic acid and 2,4-dichlorophenoxyacetic acid. Moreover, inhibitors of auxin biosynthesis and polar auxin transport inhibited cell division. Notably, different algal species (even different intraspecific strains) exhibited phenotypic plasticity different to that correlated to IAA. Thus, the plasticity involving individual-level heterogeneity in morphological characteristics may be crucial for microalgae to adapt to changing or novel conditions, and IAA treatment potentially increases the tolerance of Desmodesmus algae to several stress conditions. In summary, our results provide circumstantial evidence for the hypothesized role of IAA as a diffusible signal in the communication between the microalga and microorganisms. This information is crucial for elucidation of the role of plant hormones in plankton ecology.

Evaluating the tradeoffs of a generalist parasitoid fungus, Ophiocordyceps unilateralis, on different sympatric ant hosts.

It is essential for the survival and reproduction of parasitoids to adapt to the fluctuating host resources. Phenotypic plasticity may enable a parasitoid species to successfully achieve its control over a range of host species to maximize fitness in different hosts that may each require dissimilar, possibly conflicting, specific adaptations. However, there is limited information on how the fitness effects of host switching partition into costs due to the novelty of host species, where unfamiliarity with host physiological and morphological changes and its anti-parasite defenses reduces parasitoid growth, survivorship and/or reproductive success. In this study, the parasitoid fungus Ophiocordyceps unilateralis sensu lato was found to sympatrically infect a principal host ant species and other alternative sympatric hosts in the forest of central Taiwan. We herein report that the occurrence of ant infections by O. unilateralis s.l. shows spatial and temporal variation patterns on different host species. Results showed that the height from the ground to the leaf where the infected ants grip on, perithecia-forming ability, and growth rate of the stroma of the parasitoid fungus were dissimilar on different host species. These host range expansions not only related the fitness of O. unilateralis s.l. but also influenced the expression of extended phenotypic traits. Our findings revealed that a generalist parasitoid fungus suffered an evolutionary tradeoff between host breadth expansion and host-use efficiency.

Indole-3-acetic-acid-induced phenotypic plasticity in Desmodesmus algae.

Phenotypic plasticity is the ability of a single genotype of an organism to exhibit variable phenotypes in response to fluctuating environments. It plays a crucial role in their evolutionary success. In natural environments, the importance of interactions between microalgae and other microorganisms is generally well appreciated, but the effects of these interactions on algal phenotypic plasticity has not been investigated. In this study, it revealed that indole-3-acetic acid (IAA), the most common naturally occurring plant hormone, can exert stimulatory at low concentrations and inhibitory effects at high concentrations on the growth of the green alga Desmodesmus. The morphological characteristics of Desmodesmus changed drastically under exposure to IAA compared with the algae in the control environment. The proportion of Desmodesmus unicells in monocultures increased with the IAA concentration, and these unicells exhibited less possibility of sedimentation than large cells. Furthermore, we discovered that lipid droplets accumulated in algal cells grown at a high IAA concentration. Results also demonstrated that the presence of algal competitor further stimulated inducible morphological changes in Desmodesmus populations. The relative abundance of competitors influenced the proportion of induced morphological changes. The results indicate that phenotypic plasticity in microalgae can be a response to fluctuating environments, in which algae optimize the cost-benefit ratio.

Predictive biomarkers for treatment selection: statistical considerations.

Predictive biomarkers are developed for treatment selection to identify patients who are likely to benefit from a particular therapy. This review describes statistical methods and discusses issues in the development of predictive biomarkers to enhance study efficiency for detection of treatment effect on the selected responder patients in clinical studies. The statistical procedure for treatment selection consists of three components: biomarker identification, subgroup selection and clinical utility assessment. Major statistical issues discussed include biomarker designs, procedures to identify predictive biomarkers, classification models for subgroup selection, subgroup analysis and multiple testing for clinical utility assessment and evaluation.

Pharmacogenomic biomarkers for personalized medicine.

Pharmacogenomics examines how the benefits and adverse effects of a drug vary among patients in a target population by analyzing genomic profiles of individual patients. Personalized medicine prescribes specific therapeutics that best suit an individual patient. Much current research focuses on developing genomic biomarkers to identify patients, to identify which patients would benefit from a treatment, have an adverse response, or no response at all, prior to treatment according to relevant differences in risk factors, disease types and/or responses to therapy. This review describes the use of the two personalized medicine biomarkers, prognostic and predictive, to classify patients into subgroups for treatment recommendation.

Meta-analysis of pulsed-field gel electrophoresis fingerprints based on a constructed Salmonella database.

A database was constructed consisting of 45,923 Salmonella pulsed-field gel electrophoresis (PFGE) patterns. The patterns, randomly selected from all submissions to CDC PulseNet during 2005 to 2010, included the 20 most frequent serotypes and 12 less frequent serotypes. Meta-analysis was applied to all of the PFGE patterns in the database. In the range of 20 to 1100 kb, serotype Enteritidis averaged the fewest bands at 12 bands and Paratyphi A the most with 19, with most serotypes in the 13-15 range among the 32 serptypes. The 10 most frequent bands for each of the 32 serotypes were sorted and distinguished, and the results were in concordance with those from distance matrix and two-way hierarchical cluster analyses of the patterns in the database. The hierarchical cluster analysis divided the 32 serotypes into three major groups according to dissimilarity measures, and revealed for the first time the similarities among the PFGE patterns of serotype Saintpaul to serotypes Typhimurium, Typhimurium var. 5-, and I 4,[5],12:i:-; of serotype Hadar to serotype Infantis; and of serotype Muenchen to serotype Newport. The results of the meta-analysis indicated that the pattern similarities/dissimilarities determined the serotype discrimination of PFGE method, and that the possible PFGE markers may have utility for serotype identification. The presence of distinct, serotype specific patterns may provide useful information to aid in the distribution of serotypes in the population and potentially reduce the need for laborious analyses, such as traditional serotyping.

Biomarker classifiers for identifying susceptible subpopulations for treatment decisions.

AIM: A main goal of pharmacogenomics is to develop genomic signatures to predict patients' responses to a drug or therapy for treatment decisions. Identification of patients who would have no beneficial effect or have the risk of developing adverse effects from an unnecessary treatment could save enormous cost in the healthcare system and clinical trials. This article presents an approach for developing a biomarker classifier for identifying a fraction of susceptible patients, who should be spared unnecessary treatment prior to treatment. MATERIALS & METHODS: The identification of susceptible patients involves two steps. The first step is to identify biomarkers of susceptibility from a mixture of biomarkers of susceptibility and biomarkers of response; the second step is to develop a classifier using an ensemble classification algorithm, as the number of susceptible patients is generally much smaller than the number of nonsusceptible patients. RESULTS: Selection of the biomarkers of susceptibility is essential to achieve good prediction accuracy. The ensemble algorithm significantly improves the prediction accuracy compared with the standard classifiers. CONCLUSION: The study shows that classifiers developed based on the biomarkers obtained by comparing the genomic profiles of responders to those of nonresponders may lead to a high misclassification error rate. Classifiers to identify a small fraction of the subpopulation should take imbalanced class sizes into consideration. A large sample size may be needed in order to ensure detection of a sufficient number of biomarkers and a sufficient number of susceptible subjects for classifier development and validation.

An approach to identifying preclinical biomarkers of susceptibility to drug-induced toxicity.

AIM: Drug-induced toxicity that leads to termination of candidate drugs or postmarketing removal of approved drugs can potentially be explained by the existence of susceptible subpopulations. If the susceptible subpopulations are identified in advance, the drug's benefits could be maximized by optimal treatment decisions. This article presents a statistical model and an approach for identifying pharmacogenomic biomarkers of susceptibility to drug-induced toxicity for detecting the susceptible subpopulations. MATERIALS & METHODS: Biomarkers are categorized into three disjoint sets: biomarkers of both susceptibility and exposure (A); biomarkers of susceptibility only (B); and biomarkers of exposure only (C). Set B contains the most useful biomarkers to identify susceptible subpopulations prior to drug exposure; these markers demonstrate no change in response before and after drug exposure. We present a sample size analysis to illustrate the issues and challenges facing identifying biomarker set B. RESULTS: The required sample size increases as the proportion of the susceptible subpopulation decreases. The examples demonstrated that at least 75 subjects per group are needed for a population with a 5% susceptible subpopulation and more than 1000 are often necessary. CONCLUSION: This study demonstrates that the biomarkers identified by common methods are a mixture of biomarkers of exposure and susceptibility (A and C), it further demonstrates that the proposed approach could be used to identify biomarkers of susceptibility (B), where a large sample size may be required for adequate power and low false-positive rate. Original submitted 14 October 2010; Revision submitted 8 December 2010.