Efficient Selection of Gaussian Kernel SVM Parameters for Imbalanced Data.

For medical data mining, the development of a class prediction model has been widely used to deal with various kinds of data classification problems. Classification models especially for high-dimensional gene expression datasets have attracted many researchers in order to identify marker genes for distinguishing any type of cancer cells from their corresponding normal cells. However, skewed class distributions often occur in the medical datasets in which at least one of the classes has a relatively small number of observations. A classifier induced by such an imbalanced dataset typically has a high accuracy for the majority class and poor prediction for the minority class. In this study, we focus on an SVM classifier with a Gaussian radial basis kernel for a binary classification problem. In order to take advantage of an SVM and to achieve the best generalization ability for improving the classification performance, we will address two important problems: the class imbalance and parameter selection during SVM parameter optimization. First of all, we proposed a novel adjustment method called b-SVM, for adjusting the cutoff threshold of the SVM. Second, we proposed a fast and simple approach, called the Min-max gamma selection, to optimize the model parameters of SVMs without carrying out an extensive k-fold cross validation. An extensive comparison with a standard SVM and well-known existing methods are carried out to evaluate the performance of our proposed algorithms using simulated and real datasets. The experimental results show that our proposed algorithms outperform the over-sampling techniques and existing SVM-based solutions. This study also shows that the proposed Min-max gamma selection is at least 10 times faster than the cross-validation selection based on the average running time on six real datasets.

Development of predictive signatures for treatment selection in precision medicine with survival outcomes.

For survival endpoints in subgroup selection, a score conversion model is often used to convert the set of biomarkers for each patient into a univariate score and using the median of the univariate scores to divide the patients into biomarker-positive and biomarker-negative subgroups. However, this may lead to bias in patient subgroup identification regarding the 2 issues: (1) treatment is equally effective for all patients and/or there is no subgroup difference; (2) the median value of the univariate scores as a cutoff may be inappropriate if the sizes of the 2 subgroups are differ substantially. We utilize a univariate composite score method to convert the set of patient's candidate biomarkers to a univariate response score. We propose applying the likelihood ratio test (LRT) to assess homogeneity of the sampled patients to address the first issue. In the context of identification of the subgroup of responders in adaptive design to demonstrate improvement of treatment efficacy (adaptive power), we suggest that subgroup selection is carried out if the LRT is significant. For the second issue, we utilize a likelihood-based change-point algorithm to find an optimal cutoff. Our simulation study shows that type I error generally is controlled, while the overall adaptive power to detect treatment effects sacrifices approximately 4.5% for the simulation designs considered by performing the LRT; furthermore, the change-point algorithm outperforms the median cutoff considerably when the subgroup sizes differ substantially.

An Exhaustive Scan Method for SNP Main Effects and SNP × SNP Interactions Over Highly Homozygous Genomes.

Genome-wide association studies (GWAS) have been a powerful tool for exploring potential relationships between single-nucleotide polymorphisms (SNPs) and biological traits. For screening out important genetic variants, it is desired to perform an exhaustive scan over a whole genome. However, this is usually a challenging and daunting task in computation, due mainly to the large number of SNPs in GWAS. In this article, we propose a computationally effective algorithm for highly homozygous genomes. Pseudo standard error (PSE) is known to be a highly efficient and robust estimator for the standard deviation of a quantitative trait. We thus develop a statistical testing procedure for determining significant SNP main effects and SNP × SNP interactions associated with a quantitative trait based on PSE. A simulation study is first conducted to evaluate its empirical size and power. It is shown that the proposed PSE-based method can generally maintain the empirical size sufficiently close to the nominal significance level. However, the power investigation indicates that the PSE-based method might lack power in identifying significant effects for low-frequency variants if their true effect sizes are not large enough. A software is provided for implementing the proposed algorithm and its computational efficiency is evaluated through another simulation study. An exhaustive scan is usually done within a very reasonable runtime and a rice genome data set is analyzed by the software.

Addressing Loss of Efficiency Due to Misclassification Error in Enriched Clinical Trials for the Evaluation of Targeted Therapies Based on the Cox Proportional Hazards Model.

A key feature of precision medicine is that it takes individual variability at the genetic or molecular level into account in determining the best treatment for patients diagnosed with diseases detected by recently developed novel biotechnologies. The enrichment design is an efficient design that enrolls only the patients testing positive for specific molecular targets and randomly assigns them for the targeted treatment or the concurrent control. However there is no diagnostic device with perfect accuracy and precision for detecting molecular targets. In particular, the positive predictive value (PPV) can be quite low for rare diseases with low prevalence. Under the enrichment design, some patients testing positive for specific molecular targets may not have the molecular targets. The efficacy of the targeted therapy may be underestimated in the patients that actually do have the molecular targets. To address the loss of efficiency due to misclassification error, we apply the discrete mixture modeling for time-to-event data proposed by Eng and Hanlon [8] to develop an inferential procedure, based on the Cox proportional hazard model, for treatment effects of the targeted treatment effect for the true-positive patients with the molecular targets. Our proposed procedure incorporates both inaccuracy of diagnostic devices and uncertainty of estimated accuracy measures. We employed the expectation-maximization algorithm in conjunction with the bootstrap technique for estimation of the hazard ratio and its estimated variance. We report the results of simulation studies which empirically investigated the performance of the proposed method. Our proposed method is illustrated by a numerical example.

Gene set analysis using sufficient dimension reduction.

BACKGROUND: Gene set analysis (GSA) aims to evaluate the association between the expression of biological pathways, or a priori defined gene sets, and a particular phenotype. Numerous GSA methods have been proposed to assess the enrichment of sets of genes. However, most methods are developed with respect to a specific alternative scenario, such as a differential mean pattern or a differential coexpression. Moreover, a very limited number of methods can handle either binary, categorical, or continuous phenotypes. In this paper, we develop two novel GSA tests, called SDRs, based on the sufficient dimension reduction technique, which aims to capture sufficient information about the relationship between genes and the phenotype. The advantages of our proposed methods are that they allow for categorical and continuous phenotypes, and they are also able to identify a variety of enriched gene sets. RESULTS: Through simulation studies, we compared the type I error and power of SDRs with existing GSA methods for binary, triple, and continuous phenotypes. We found that SDR methods adequately control the type I error rate at the pre-specified nominal level, and they have a satisfactory power to detect gene sets with differential coexpression and to test non-linear associations between gene sets and a continuous phenotype. In addition, the SDR methods were compared with seven widely-used GSA methods using two real microarray datasets for illustration. CONCLUSIONS: We concluded that the SDR methods outperform the others because of their flexibility with regard to handling different kinds of phenotypes and their power to detect a wide range of alternative scenarios. Our real data analysis highlights the differences between GSA methods for detecting enriched gene sets.

MAVTgsa: an R package for gene set (enrichment) analysis.

Gene set analysis methods aim to determine whether an a priori defined set of genes shows statistically significant difference in expression on either categorical or continuous outcomes. Although many methods for gene set analysis have been proposed, a systematic analysis tool for identification of different types of gene set significance modules has not been developed previously. This work presents an R package, called MAVTgsa, which includes three different methods for integrated gene set enrichment analysis. (1) The one-sided OLS (ordinary least squares) test detects coordinated changes of genes in gene set in one direction, either up- or downregulation. (2) The two-sided MANOVA (multivariate analysis variance) detects changes both up- and downregulation for studying two or more experimental conditions. (3) A random forests-based procedure is to identify gene sets that can accurately predict samples from different experimental conditions or are associated with the continuous phenotypes. MAVTgsa computes the P values and FDR (false discovery rate) q-value for all gene sets in the study. Furthermore, MAVTgsa provides several visualization outputs to support and interpret the enrichment results. This package is available online.

An approximate approach to sample size determination in bioequivalence testing with multiple pharmacokinetic responses.

The approval of generic drugs requires the evidence of average bioequivalence (ABE) on both the area under the concentration-time curve and the peak concentration Cmax . The bioequivalence (BE) hypothesis can be decomposed into the non-inferiority (NI) and non-superiority (NS) hypothesis. Most of regulatory agencies employ the two one-sided tests (TOST) procedure to test ABE between two formulations. As it is based on the intersection-union principle, the TOST procedure is conservative in terms of the type I error rate. However, the type II error rate is the sum of the type II error rates with respect to each null hypothesis of NI and NS hypotheses. When the difference in population means between two treatments is not 0, no close-form solution for the sample size for the BE hypothesis is available. Current methods provide the sample sizes with either insufficient power or unnecessarily excessive power. We suggest an approximate method for sample size determination, which can also provide the type II rate for each of NI and NS hypotheses. In addition, the proposed method is flexible to allow extension from one pharmacokinetic (PK) response to determination of the sample size required for multiple PK responses. We report the results of a numerical study. An R code is provided to calculate the sample size for BE testing based on the proposed methods.

Asymptomatic ratio for seasonal H1N1 influenza infection among schoolchildren in Taiwan.

BACKGROUND: Studies indicate that asymptomatic infections do indeed occur frequently for both seasonal and pandemic influenza, accounting for about one-third of influenza infections. Studies carried out during the 2009 pH1N1 pandemic have found significant antibody response against seasonal H1N1 and H3N2 vaccine strains in schoolchildren receiving only pandemic H1N1 monovalent vaccine, yet reported either no symptoms or only mild symptoms. METHODS: Serum samples of 255 schoolchildren, who had not received vaccination and had pre-season HI Ab serotiters <40, were collected from urban, rural areas and an isolated island in Taiwan during the 2005-2006 influenza season. Their hemagglutination inhibition antibody (HI Ab) serotiters against the 2005 A/New Caledonia/20/99 (H1N1) vaccine strain at pre-season and post-season were measured to determine the symptoms with the highest correlation with infection, as defined by 4-fold rise in HI titer. We estimate the asymptomatic ratio, or the proportion of asymptomatic infections, for schoolchildren during the 2005-6 influenza season when this vaccine strain was found to be antigenically related to the circulating H1N1 strain. RESULTS: Fever has the highest correlation with the 2005-06 seasonal influenza A(H1N1) infection, followed by headache, cough, vomiting, and sore throat. Asymptomatic ratio for the schoolchildren is found to range between 55.6% (95% CI: 44.7-66.4)-77.9% (68.8-87.0) using different sets of predictive symptoms. Moreover, the asymptomatic ratio was 66.9% (56.6-77.2) when using US-CDC criterion of fever + (cough/sore throat), and 73.0 (63.3-82.8) when under Taiwan CDC definition of Fever + (cough or sore throat or nose) + ( headache or pain or fatigue). CONCLUSIONS: Asymptomatic ratio for children is found to be substantially higher than that of the general population in literature. In providing reasonable quantification of the asymptomatic infected children spreading pathogens to others in a seasonal epidemic or a pandemic, our estimates of symptomatic ratio of infected children has important clinical and public health implications.

Identifying gene set association enrichment using the coefficient of intrinsic dependence.

Gene set testing problem has become the focus of microarray data analysis. A gene set is a group of genes that are defined by a priori biological knowledge. Several statistical methods have been proposed to determine whether functional gene sets express differentially (enrichment and/or deletion) in variations of phenotypes. However, little attention has been given to analyzing the dependence structure among gene sets. In this study, we have proposed a novel statistical method of gene set association analysis to identify significantly associated gene sets using the coefficient of intrinsic dependence. The simulation studies show that the proposed method outperforms the conventional methods to detect general forms of association in terms of control of type I error and power. The correlation of intrinsic dependence has been applied to a breast cancer microarray dataset to quantify the un-supervised relationship between two sets of genes in the tumor and non-tumor samples. It was observed that the existence of gene-set association differed across various clinical cohorts. In addition, a supervised learning was employed to illustrate how gene sets, in signaling transduction pathways or subnetworks regulated by a set of transcription factors, can be discovered using microarray data. In conclusion, the coefficient of intrinsic dependence provides a powerful tool for detecting general types of association. Hence, it can be useful to associate gene sets using microarray expression data. Through connecting relevant gene sets, our approach has the potential to reveal underlying associations by drawing a statistically relevant network in a given population, and it can also be used to complement the conventional gene set analysis.

Random forests-based differential analysis of gene sets for gene expression data.

In DNA microarray studies, gene-set analysis (GSA) has become the focus of gene expression data analysis. GSA utilizes the gene expression profiles of functionally related gene sets in Gene Ontology (GO) categories or priori-defined biological classes to assess the significance of gene sets associated with clinical outcomes or phenotypes. Many statistical approaches have been proposed to determine whether such functionally related gene sets express differentially (enrichment and/or deletion) in variations of phenotypes. However, little attention has been given to the discriminatory power of gene sets and classification of patients. In this study, we propose a method of gene set analysis, in which gene sets are used to develop classifications of patients based on the Random Forest (RF) algorithm. The corresponding empirical p-value of an observed out-of-bag (OOB) error rate of the classifier is introduced to identify differentially expressed gene sets using an adequate resampling method. In addition, we discuss the impacts and correlations of genes within each gene set based on the measures of variable importance in the RF algorithm. Significant classifications are reported and visualized together with the underlying gene sets and their contribution to the phenotypes of interest. Numerical studies using both synthesized data and a series of publicly available gene expression data sets are conducted to evaluate the performance of the proposed methods. Compared with other hypothesis testing approaches, our proposed methods are reliable and successful in identifying enriched gene sets and in discovering the contributions of genes within a gene set. The classification results of identified gene sets can provide an valuable alternative to gene set testing to reveal the unknown, biologically relevant classes of samples or patients. In summary, our proposed method allows one to simultaneously assess the discriminatory ability of gene sets and the importance of genes for interpretation of data in complex biological systems. The classifications of biologically defined gene sets can reveal the underlying interactions of gene sets associated with the phenotypes, and provide an insightful complement to conventional gene set analyses.

Association of response to hepatitis B vaccination and survival in dialysis patients.

BACKGROUND: The status of immunocompromised patients is well recognized in end stage renal disease (ESRD). As described recently, this acquired immune dysfunction in the uremic milieu may be one of the main pathogenic factors for mortality in ESRD. The aim of this study was to determine the relationship between the immune response following a hepatitis B vaccination (HBV vaccination) and the survival of maintenance dialysis patients. METHODS: A total of 156 patients (103 on hemodialysis and 53 on continuous ambulatory peritoneal dialysis) were recruited. After receiving a full dose of the HBV vaccination, all patients were followed up for to 5 years to evaluate the association of patient survival, cause of mortality, and immune response. RESULTS: The response rate to the hepatitis B vaccination was 70.5%. There was no significant association between the immune response and the 5-year survival rate (p =0.600) or between the post-vaccination anti-HBs titers and the 5-year survival rate (p = 0.201). The logistic prediction model with the coefficient as non-response following HBV vaccination, diabetes mellitus, old age, and low albumin level could significantly predict infection-cause mortality (sensitivity = 0.842, specificity = 0.937). CONCLUSION: There was no significant association between the immune response to HBV vaccination and the 5-year survival rate. However, non-response following HBV vaccination might be associated with infection-cause mortality in dialysis patients.

Recursive feature selection with significant variables of support vectors.

The development of DNA microarray makes researchers screen thousands of genes simultaneously and it also helps determine high- and low-expression level genes in normal and disease tissues. Selecting relevant genes for cancer classification is an important issue. Most of the gene selection methods use univariate ranking criteria and arbitrarily choose a threshold to choose genes. However, the parameter setting may not be compatible to the selected classification algorithms. In this paper, we propose a new gene selection method (SVM-t) based on the use of t-statistics embedded in support vector machine. We compared the performance to two similar SVM-based methods: SVM recursive feature elimination (SVMRFE) and recursive support vector machine (RSVM). The three methods were compared based on extensive simulation experiments and analyses of two published microarray datasets. In the simulation experiments, we found that the proposed method is more robust in selecting informative genes than SVMRFE and RSVM and capable to attain good classification performance when the variations of informative and noninformative genes are different. In the analysis of two microarray datasets, the proposed method yields better performance in identifying fewer genes with good prediction accuracy, compared to SVMRFE and RSVM.

Factors associated with infection by 2009 pandemic H1N1 influenza virus during different phases of the epidemic.

OBJECTIVE: The focus of this study was to ascertain the factors associated with 2009 pandemic influenza H1N1 (pH1N1) infection during different phases of the epidemic. METHODS: In central Taiwan, 306 persons from households with schoolchildren were followed sequentially and serum samples were taken at three sampling time-points starting in the fall of 2008, shortly after influenza vaccination. Participants who seroconverted between two consecutive blood samplings were considered as having serological evidence of infection. A generalized estimation equation (GEE) with a logistic link to account for household correlations was applied to identify factors associated with pH1N1 infections during the pre-epidemic (April-June) and epidemic (September-October) periods. RESULTS: The results showed that receiving an inactivated seasonal influenza vaccine (ISIV) and having a hemagglutination inhibition assay (HI) titer of 40 or higher resulted in a significantly lower likelihood of pH1N1 infection during the pre-epidemic period only, for both children and adults (adjusted odds ratio (OR) 0.3, 95% confidence interval (CI) 0.12-0.9). Having a previous infection by pH1N1 with a baseline titer of 20 or higher resulted in a significantly lower likelihood of infection by pH1N1 during the epidemic period (adjusted OR 0.06, 95% CI 0.02-0.16). CONCLUSIONS: Our results provide the first serological evidence to suggest a protection effect from receiving an ISIV against pH1N1 infection only when the HI titer reaches 40 or higher during the pre-epidemic period. This study gives an important insight into the control and intervention measures required for preventing infections during future influenza epidemics.

Comparison of hepatitis B surface antibody decay rates after vaccination between hemodialysis and peritoneal dialysis patients.

BACKGROUND AND OBJECTIVES: The available information about maintaining effective immunity after hepatitis B virus (HBV) vaccination in dialysis patients is limited. The aim of this study was to determine whether a difference exists in the persistence of immunity between hemodialysis (HD) and peritoneal dialysis (PD) patients. We compared the decay rate of hepatitis B surface antibody (anti-HBs) titers after HBV vaccination between HD and PD patients. DESIGN, SETTING, PARTICIPANTS, AND MEASURES: A total of 103 HD and 53 PD patients who were completely vaccinated were enrolled. We examined their anti-HBs titers at the 1st month after vaccination then annually thereafter. Changes in the anti-HBs titers were assessed by comparing annual geometric mean titers (GMTs). RESULTS: The slopes of the anti-HBs titer decay rates plotted on a logarithmic scale for the HD and PD groups were -23.41 and -31.48, respectively. The decay rate of the PD group was significantly faster than that of the HD group (P=0.0053). CONCLUSION: The decay rate of anti-HBs titers in the PD group was faster than that in the HD group. Hepatitis B vaccination could not offer long-term protection in HD or PD patients. Post-vaccination testing every 6-12 months is necessary and revaccination may be protective in dialysis patients, especially in hyper-endemic areas of hepatitis B infection.

Sarcosine therapy for obsessive compulsive disorder: a prospective, open-label study.

BACKGROUND: Several lines of evidence implicate glutamatergic neurotransmission in the pathophysiology of obsessive compulsive disorder (OCD). Sarcosine is an endogenous antagonist of glycine transporter-1. By blocking glycine uptake, sarcosine may increase the availability of synaptic glycine and enhance N-methyl-d-aspartate (NMDA) subtype glutamatergic neurotransmission. In this 10-week open-label trial, we examined the potential benefit of sarcosine treatment in OCD patients. METHOD: Twenty-six outpatients with OCD and baseline Yale-Brown Obsessive Compulsive Scale (YBOCS) scores higher than 16 were enrolled. Drug-naive subjects (group 1, n = 8) and those who had discontinued serotonin reuptake inhibitors for at least 8 weeks at study entry (group 2, n = 6) received sarcosine monotherapy. The other subjects (group 3, n = 12) received sarcosine as adjunctive treatment. A flexible dosage schedule of sarcosine 500 to 2000 mg/d was applied. The primary outcome measures were Y-BOCS and Hamilton Anxiety Inventory, rated at weeks 0, 2, 4, 6, 8, and 10. Results were analyzed by repeated-measures analysis of variance. RESULTS: Data of 25 subjects were eligible for analysis. The mean ± SD Y-BOCS scores decreased from 27.6 ± 5.8 to 22.7 ± 8.7, indicating a mean decrease of 19.8% ± 21.7% (P = 0.0035). Eight (32%) subjects were regarded as responders with greater than 35% reduction of Y-BOCS scores. Five of the responders achieved the good response early by week 4. Although not statistically significant, drug-naive (group 1) subjects had more profound and sustained improvement and more responders than the subjects who had received treatment before (groups 2 and 3). Sarcosine was tolerated well; only one subject withdrew owing to transient headache. CONCLUSION: Sarcosine treatment can achieve a fast therapeutic effect in some OCD patients, particularly those who are treatment naive. The study supports the glycine transporter-1 as a novel target for developing new OCD treatment. Large-series placebo-controlled, double-blind studies are recommended.

Serological evidence of subclinical transmission of the 2009 pandemic H1N1 influenza virus outside of Mexico.

BACKGROUND: Relying on surveillance of clinical cases limits the ability to understand the full impact and severity of an epidemic, especially when subclinical cases are more likely to be present in the early stages. Little is known of the infection and transmissibility of the 2009 H1N1 pandemic influenza (pH1N1) virus outside of Mexico prior to clinical cases being reported, and of the knowledge pertaining to immunity and incidence of infection during April-June, which is essential for understanding the nature of viral transmissibility as well as for planning surveillance and intervention of future pandemics. METHODOLOGY/PRINCIPAL FINDINGS: Starting in the fall of 2008, 306 persons from households with schoolchildren in central Taiwan were followed sequentially and serum samples were taken in three sampling periods for haemagglutination inhibition (HI) assay. Age-specific incidence rates were calculated based on seroconversion of antibodies to the pH1N1 virus with an HI titre of 1:40 or more during two periods: April-June and September-October in 2009. The earliest time period with HI titer greater than 40, as well as a four-fold increase of the neutralization titer, was during April 26-May 3. The incidence rates during the pre-epidemic phase (April-June) and the first wave (July-October) of the pandemic were 14.1% and 29.7%, respectively. The transmissibility of the pH1N1 virus during the early phase of the epidemic, as measured by the effective reproductive number R(0), was 1.16 (95% confidence interval (CI): 0.98-1.34). CONCLUSIONS: Approximately one in every ten persons was infected with the 2009 pH1N1 virus during the pre-epidemic phase in April-June. The lack of age-pattern in seropositivity is unexpected, perhaps highlighting the importance of children as asymptomatic transmitters of influenza in households. Although without virological confirmation, our data raise the question of whether there was substantial pH1N1 transmission in Taiwan before June, when clinical cases were first detected by the surveillance network.

Serological response and persistence in schoolchildren with high baseline seropositive rate after receiving 2009 pandemic influenza A(H1N1) vaccine.

The serological response of the current 2009 H1N1 pandemic influenza monovalent vaccine in children exhibiting high baseline seropositive rate was evaluated though a community-based household study. Seroprotection rate of >90% and seroconversion rate of >50% were observed in children one month after receiving the pandemic vaccine. Among children with low baseline antibody titer, a significant lower seroconversion rate (55%) was observed in children who received seasonal trivalent inactivated vaccine (TIV) prior to pandemic vaccine, when compared with those receiving the pandemic vaccine only (86%). Persistence of antibody against the pandemic influenza virus was observed 6 months after vaccination in >80% of children presenting seroprotective antibody levels.

Development of biomarker classifiers from high-dimensional data.

Recent development of high-throughput technology has accelerated interest in the development of molecular biomarker classifiers for safety assessment, disease diagnostics and prognostics, and prediction of response for patient assignment. This article reviews and evaluates some important aspects and key issues in the development of biomarker classifiers. Development of a biomarker classifier for high-throughput data involves two components: (i) model building and (ii) performance assessment. This article focuses on feature selection in model building and cross validation for performance assessment. A 'frequency' approach to feature selection is presented and compared to the 'conventional' approach in terms of the predictive accuracy and stability of the selected feature set. The two approaches are compared based on four biomarker classifiers, each with a different feature selection method and well-known classification algorithm. In each of the four classifiers the feature predictor set selected by the frequency approach is more stable than the feature set selected by the conventional approach.

Multivariate analysis of variance test for gene set analysis.

MOTIVATION: Gene class testing (GCT) or gene set analysis (GSA) is a statistical approach to determine whether some functionally predefined sets of genes express differently under different experimental conditions. Shortcomings of the Fisher's exact test for the overrepresentation analysis are illustrated by an example. Most alternative GSA methods are developed for data collected from two experimental conditions, and most is based on a univariate gene-by-gene test statistic or assume independence among genes in the gene set. A multivariate analysis of variance (MANOVA) approach is proposed for studies with two or more experimental conditions. RESULTS: When the number of genes in the gene set is greater than the number of samples, the sample covariance matrix is singular and ill-condition. The use of standard multivariate methods can result in biases in the analysis. The proposed MANOVA test uses a shrinkage covariance matrix estimator for the sample covariance matrix. The MANOVA test and six other GSA published methods, principal component analysis, SAM-GS, analysis of covariance, Global, GSEA and MaxMean, are evaluated using simulation. The MANOVA test appears to perform the best in terms of control of type I error and power under the models considered in the simulation. Several publicly available microarray datasets under two and three experimental conditions are analyzed for illustrations of GSA. Most methods, except for GSEA and MaxMean, generally are comparable in terms of power of identification of significant gene sets. AVAILABILITY: A free R-code to perform MANOVA test is available at http://mail.cmu.edu.tw/~catsai/research.htm. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Multispectra CWT-based algorithm (MCWT) in mass spectra for peak extraction.

An important objective in mass spectrometry (MS) is to identify a set of biomarkers that can be used to potentially distinguish patients between distinct treatments (or conditions) from tens or hundreds of spectra. A common two-step approach involving peak extraction and quantification is employed to identify the features of scientific interest. The selected features are then used for further investigation to understand underlying biological mechanism of individual protein or for development of genomic biomarkers to early diagnosis. However, the use of inadequate or ineffective peak detection and peak alignment algorithms in peak extraction step may lead to a high rate of false positives. Also, it is crucial to reduce the false positive rate in detecting biomarkers from ten or hundreds of spectra. Here a new procedure is introduced for feature extraction in mass spectrometry data that extends the continuous wavelet transform-based (CWT-based) algorithm to multiple spectra. The proposed multispectra CWT-based algorithm (MCWT) not only can perform peak detection for multiple spectra but also carry out peak alignment at the same time. The author' MCWT algorithm constructs a reference, which integrates information of multiple raw spectra, for feature extraction. The algorithm is applied to a SELDI-TOF mass spectra data set provided by CAMDA 2006 with known polypeptide m/z positions. This new approach is easy to implement and it outperforms the existing peak extraction method from the Bioconductor PROcess package.