Spectral clustering independent component analysis for tissue classification from brain MRI

A spectral angle based feature extraction method, Spectral Clustering Independent Component Analysis (SC-ICA), is proposed in this work to improve the brain tissue classification from Magnetic Resonance Images (MRI). SC-ICA provides equal priority to global and local features; thereby it tries to resolve the inefficiency of conventional approaches in abnormal tissue extraction. First, input multispectral MRI is divided into different clusters by a spectral distance based clustering. Then, Independent Component Analysis (ICA) is applied on the clustered data, in conjunction with Support Vector Machines (SVM) for brain tissue analysis. Normal and abnormal datasets, consisting of real and synthetic T1-weighted, T2-weighted and proton density/fluid-attenuated inversion recovery images, were used to evaluate the performance of the new method. Comparative analysis with ICA based SVM and other conventional classifiers established the stability and efficiency of SC-ICA based classification, especially in reproduction of small abnormalities. Clinical abnormal case analysis demonstrated it through the highest Tanimoto Index/accuracy values, 0.75/98.8%, observed against ICA based SVM results, 0.17/96.1%, for reproduced lesions. Experimental results recommend the proposed method as a promising approach in clinical and pathological studies of brain diseases.     

A robust biomarker discovery pipeline for high-performance mass spectrometry data

A high-throughput software pipeline for analyzing high-performance mass spectral data sets has been developed to facilitate rapid and accurate biomarker determination. The software exploits the mass precision and resolution of high-performance instrumentation, bypasses peak-finding steps, and instead uses discrete m/z data points to identify putative biomarkers. The technique is insensitive to peak shape, and works on overlapping and non-Gaussian peaks which can confound peak-finding algorithms. Methods are presented to assess data set quality and the suitability of groups of m/z values that map to peaks as potential biomarkers. The algorithm is demonstrated with serum mass spectra from patients with and without ovarian cancer. Biomarker candidates are identified and ranked by their ability to discriminate between cancer and noncancer conditions. Their discriminating power is tested by classifying unknowns using a simple distance calculation, and a sensitivity of 95.6% and a specificity of 97.1% are obtained. In contrast, the sensitivity of the ovarian cancer blood marker CA125 is approximately 50% for stage I/II and approximately 80% for stage III/IV cancers. While the generalizability of these markers is currently unknown, we have demonstrated the ability of our analytical package to extract biomarker candidates from high-performance mass spectral data.     

Gene expression data classification using consensus independent component analysis

We propose a new method for tumor classification from gene expression data, which mainly contains three steps. Firstly, the original DNA microarray gene expression data are modeled by independent component analysis （ICA）. Secondly, the most discriminant eigenassays extracted by ICA are selected by the sequential floating forward selection technique. Finally, support vector machine is used to classify the modeling data. To show the validity of the proposed method, we applied it to classify three DNA microarray datasets involving various human normal and tumor tissue samples. The experimental results show that the method is efficient and feasible.     

Multiclass cancer classification and biomarker discovery using GA-based algorithms

MOTIVATION: The development of microarray-based high-throughput gene profiling has led to the hope that this technology could provide an efficient and accurate means of diagnosing and classifying tumors, as well as predicting prognoses and effective treatments. However, the large amount of data generated by microarrays requires effective reduction of discriminant gene features into reliable sets of tumor biomarkers for such multiclass tumor discrimination. The availability of reliable sets of biomarkers, especially serum biomarkers, should have a major impact on our understanding and treatment of cancer. RESULTS: We have combined genetic algorithm (GA) and all paired (AP) support vector machine (SVM) methods for multiclass cancer categorization. Predictive features can be automatically determined through iterative GA/SVM, leading to very compact sets of non-redundant cancer-relevant genes with the best classification performance reported to date. Interestingly, these different classifier sets harbor only modest overlapping gene features but have similar levels of accuracy in leave-one-out cross-validations (LOOCV). Further characterization of these optimal tumor discriminant features, including the use of nearest shrunken centroids (NSC), analysis of annotations and literature text mining, reveals previously unappreciated tumor subclasses and a series of genes that could be used as cancer biomarkers. With this approach, we believe that microarray-based multiclass molecular analysis can be an effective tool for cancer biomarker discovery and subsequent molecular cancer diagnosis.     

Multivariate classification analysis of metabolomic data for candidate biomarker discovery in type 2 diabetes mellitus

Recent advances in genomics, metabolomics and proteomics have made it possible to interrogate disease pathophysiology and drug response on a systems level. The analysis and interpretation of the complex data obtained using these techniques is potentially fertile but equally challenging. We conducted a small clinical trial to explore the application of metabolomics data in candidate biomarker discovery. Specifically, serum and urine samples from patients with type 2 diabetes mellitus (T2DM) were profiled on metabolomics platforms before and after 8 weeks of treatment with one of three commonly used oral antidiabetic agents, the sulfonyurea glyburide, the biguanide metformin, or the thiazolidinedione rosiglitazone. Multivariate classification techniques were used to detect serum or urine analytes, obtained at baseline (pre-treatment) that could predict a significant treatment response after 8 weeks. Using this approach, we identified three analytes, measured at baseline, that were associated with response to a thiazolidinedione after 8 weeks of treatment. Although larger and longer-term studies are required to validate any of the candidate biomarkers, pharmacometabolomic profiling, in combination with multivariate classification, is worthy of further exploration as an adjunct to clinical decision making regarding treatment selection and for patient stratification within clinical trials. Electronic supplementary material  The online version of this article (doi:) contains supplementary material, which is available to authorized users.     

LC-MS-based serum metabolic profiling for genitourinary cancer classification and cancer type-specific biomarker discovery

Bladder cancer (BC) and kidney cancer (KC) are the first two commonly occurring genitourinary cancers in China. In this study, a comprehensive LC-MS-based method, which utilizes both reversed phase liquid chromatography (RPLC) and hydrophilic interaction chromatography (HILIC) separations, has been carried out in conjunction with multivariate data analysis to discriminate the global serum profiles of BC, KC, and noncancer controls. An independent test set consisting of different patients has been used to objectively evaluate the predictive ability of the analysis platform. Excellent sensitivity and specificity have been achieved in detection of KC and BC. The results suggest that serum metabolic profiling could be used for different types of genitourinary cancer diagnosis. Furthermore, cancer type-specific biomarkers were found through a critical selection criterion. As a result, eicosatrienol, azaprostanoic acid, docosatrienol, retinol, and 14'-apo-beta-carotenal were found as specific biomarkers for BC; and PE(P-16:0e/0:0), glycerophosphorylcholine, ganglioside GM3 (d18:1/22:1), C17 sphinganine, and SM(d18:0/16:1(9Z)) were found as specific biomarkers for KC. Receiver operating characteristic (ROC) analysis was used for the preliminary evaluation of the biomarkers. These biomarkers have great potential to be used in the clinical diagnosis after further rigorous assessment.     

Data-driven analysis approach for biomarker discovery using molecular-profiling technologies

High-throughput molecular-profiling technologies provide rapid, efficient and systematic approaches to search for biomarkers. Supervised learning algorithms are naturally suited to analyse a large amount of data generated using these technologies in biomarker discovery efforts. The study demonstrates with two examples a data-driven analysis approach to analysis of large complicated datasets collected in high-throughput technologies in the context of biomarker discovery. The approach consists of two analytic steps: an initial unsupervised analysis to obtain accurate knowledge about sample clustering, followed by a second supervised analysis to identify a small set of putative biomarkers for further experimental characterization. By comparing the most widely applied clustering algorithms using a leukaemia DNA microarray dataset, it was established that principal component analysis-assisted projections of samples from a high-dimensional molecular feature space into a few low dimensional subspaces provides a more effective and accurate way to explore visually and identify data structures that confirm intended experimental effects based on expected group membership. A supervised analysis method, shrunken centroid algorithm, was chosen to take knowledge of sample clustering gained or confirmed by the first step of the analysis to identify a small set of molecules as candidate biomarkers for further experimentation. The approach was applied to two molecular-profiling studies. In the first study, PCA-assisted analysis of DNA microarray data revealed that discrete data structures exist in rat liver gene expression and correlated with blood clinical chemistry and liver pathological damage in response to a chemical toxicant diethylhexylphthalate, a peroxisome-proliferator-activator receptor agonist. Sixteen genes were then identified by shrunken centroid algorithm as the best candidate biomarkers for liver damage. Functional annotations of these genes revealed roles in acute phase response, lipid and fatty acid metabolism and they are functionally relevant to the observed toxicities. In the second study, 26 urine ions identified from a GC/MS spectrum, two of which were glucose fragment ions included as positive controls, showed robust changes with the development of diabetes in Zucker diabetic fatty rats. Further experiments are needed to define their chemical identities and establish functional relevancy to disease development.     

Data-driven analysis approach for biomarker discovery using molecular-profiling technologies

High-throughput molecular-profiling technologies provide rapid, efficient and systematic approaches to search for biomarkers. Supervised learning algorithms are naturally suited to analyse a large amount of data generated using these technologies in biomarker discovery efforts. The study demonstrates with two examples a data-driven analysis approach to analysis of large complicated datasets collected in high-throughput technologies in the context of biomarker discovery. The approach consists of two analytic steps: an initial unsupervised analysis to obtain accurate knowledge about sample clustering, followed by a second supervised analysis to identify a small set of putative biomarkers for further experimental characterization. By comparing the most widely applied clustering algorithms using a leukaemia DNA microarray dataset, it was established that principal component analysis-assisted projections of samples from a high-dimensional molecular feature space into a few low dimensional subspaces provides a more effective and accurate way to explore visually and identify data structures that confirm intended experimental effects based on expected group membership. A supervised analysis method, shrunken centroid algorithm, was chosen to take knowledge of sample clustering gained or confirmed by the first step of the analysis to identify a small set of molecules as candidate biomarkers for further experimentation. The approach was applied to two molecular-profiling studies. In the first study, PCA-assisted analysis of DNA microarray data revealed that discrete data structures exist in rat liver gene expression and correlated with blood clinical chemistry and liver pathological damage in response to a chemical toxicant diethylhexylphthalate, a peroxisome-proliferator-activator receptor agonist. Sixteen genes were then identified by shrunken centroid algorithm as the best candidate biomarkers for liver damage. Functional annotations of these genes revealed roles in acute phase response, lipid and fatty acid metabolism and they are functionally relevant to the observed toxicities. In the second study, 26 urine ions identified from a GC/MS spectrum, two of which were glucose fragment ions included as positive controls, showed robust changes with the development of diabetes in Zucker diabetic fatty rats. Further experiments are needed to define their chemical identities and establish functional relevancy to disease development.     

Human saliva proteome analysis and disease biomarker discovery

Human saliva is an attractive body fluid for disease diagnosis and prognosis because saliva testing is simple, safe, low-cost and noninvasive. Comprehensive analysis and identification of the proteomic content in human whole and ductal saliva will not only contribute to the understanding of oral health and disease pathogenesis, but also form a foundation for the discovery of saliva protein biomarkers for human disease detection. In this article, we have summarized the proteomic technologies for comprehensive identification of proteins in human whole and ductal saliva. We have also discussed potential quantitative proteomic approaches to the discovery of saliva protein biomarkers for human oral and systemic diseases. With the fast development of mass spectrometry and proteomic technologies, we are enthusiastic that saliva protein biomarkers will be developed for clinical diagnosis and prognosis of human diseases in the future.     

Human saliva proteome analysis and disease biomarker discovery

Human saliva is an attractive body fluid for disease diagnosis and prognosis because saliva testing is simple, safe, low-cost and noninvasive. Comprehensive analysis and identification of the proteomic content in human whole and ductal saliva will not only contribute to the understanding of oral health and disease pathogenesis, but also form a foundation for the discovery of saliva protein biomarkers for human disease detection. In this article, we have summarized the proteomic technologies for comprehensive identification of proteins in human whole and ductal saliva. We have also discussed potential quantitative proteomic approaches to the discovery of saliva protein biomarkers for human oral and systemic diseases. With the fast development of mass spectrometry and proteomic technologies, we are enthusiastic that saliva protein biomarkers will be developed for clinical diagnosis and prognosis of human diseases in the future.     

Urine metabolomics analysis for adrenal incidentaloma activity detection and biomarker discovery

This study describes the development of a method suitable for the analysis of nineteen major urinary steroid metabolites in human urine. The analytes of interest were isolated from urine using solid phase extraction, subjected to enzymatic hydrolysis and again extracted applying solid phase extraction. After derivatization, methyloxime-trimethylsilyl ether derivatives of steroid hormones were identified by gas chromatography-mass spectrometry (GC/MS) and quantified by gas chromatography with flame ionization detector (GC/FID). The quantification method was validated for linearity, trueness, precision and selectivity. The limits of detection were between 6.2 and 7.2 ng/mL and limits of quantification were between 12.3 and 14.8 ng/mL. The established method was applied to analyze 28 urine samples from patients diagnosed with non-functioning adrenal incidentalomas (AIs) and 30 healthy subjects. Hierarchical cluster analysis (HCA) and principal component analysis (PCA) were employed to visualize the differences between metabolic profiles of patients and the control group and to determine possible markers of AIs activity. Both multivariate methods separated seven patients from the rest of the examined individuals. Five urinary metabolites including α-cortol, tetrahydrocorticosterone, tetrahydrocortisol, allo-tetrahydrocortisol and etiocholanolone were identified as potential biomarkers of pathological adrenal function. The altered metabolites reflected pathological metabolism mainly of cortisol and cortisone. This research proved that metabolomics is a suitable tool for disease research.     

Autoantibody microarrays for biomarker discovery

Identification of autoantigens and the detection of autoantibody reactivity are useful in biomarker discovery and for explaining the role of important biochemical pathways in disease. Despite all of their potential advantages, the main challenge to working with autoantibodies is their sensitivity. Nevertheless, proteomics may hold the key to overcoming this limitation by providing the means to multiplex. Clearly, the ability to detect multiple autoantigens using a platform such as a high-density antigen microarray would improve sensitivity and specificity of detection for autoantibody profiling. The aims of this review are to: briefly describe the current status of antigen–autoantibody microarrays; provide examples of their use in biomarker discoveries; address current limitations; and provide examples and strategies to facilitate their implementation in the clinical setting.     

Autoantibody microarrays for biomarker discovery

Identification of autoantigens and the detection of autoantibody reactivity are useful in biomarker discovery and for explaining the role of important biochemical pathways in disease. Despite all of their potential advantages, the main challenge to working with autoantibodies is their sensitivity. Nevertheless, proteomics may hold the key to overcoming this limitation by providing the means to multiplex. Clearly, the ability to detect multiple autoantigens using a platform such as a high-density antigen microarray would improve sensitivity and specificity of detection for autoantibody profiling. The aims of this review are to: briefly describe the current status of antigen-autoantibody microarrays; provide examples of their use in biomarker discoveries; address current limitations; and provide examples and strategies to facilitate their implementation in the clinical setting.     

Data-driven analysis approach for biomarker discovery using molecular-profiling technologies.

High-throughput molecular-profiling technologies provide rapid, efficient and systematic approaches to search for biomarkers. Supervised learning algorithms are naturally suited to analyse a large amount of data generated using these technologies in biomarker discovery efforts. The study demonstrates with two examples a data-driven analysis approach to analysis of large complicated datasets collected in high-throughput technologies in the context of biomarker discovery. The approach consists of two analytic steps: an initial unsupervised analysis to obtain accurate knowledge about sample clustering, followed by a second supervised analysis to identify a small set of putative biomarkers for further experimental characterization. By comparing the most widely applied clustering algorithms using a leukaemia DNA microarray dataset, it was established that principal component analysis-assisted projections of samples from a high-dimensional molecular feature space into a few low dimensional subspaces provides a more effective and accurate way to explore visually and identify data structures that confirm intended experimental effects based on expected group membership. A supervised analysis method, shrunken centroid algorithm, was chosen to take knowledge of sample clustering gained or confirmed by the first step of the analysis to identify a small set of molecules as candidate biomarkers for further experimentation. The approach was applied to two molecular-profiling studies. In the first study, PCA-assisted analysis of DNA microarray data revealed that discrete data structures exist in rat liver gene expression and correlated with blood clinical chemistry and liver pathological damage in response to a chemical toxicant diethylhexylphthalate, a peroxisome-proliferator-activator receptor agonist. Sixteen genes were then identified by shrunken centroid algorithm as the best candidate biomarkers for liver damage. Functional annotations of these genes revealed roles in acute phase response, lipid and fatty acid metabolism and they are functionally relevant to the observed toxicities. In the second study, 26 urine ions identified from a GC/MS spectrum, two of which were glucose fragment ions included as positive controls, showed robust changes with the development of diabetes in Zucker diabetic fatty rats. Further experiments are needed to define their chemical identities and establish functional relevancy to disease development.     

Placenta proteome analysis from Down syndrome pregnancies for biomarker discovery

Down syndrome is one of the most frequent chromosomal disorders, with a prevalence of approximately 1/500 to 1/800, depending on the maternal age distribution of the pregnant population. However, few reliable protein biomarkers have been used in the diagnosis of this disease. Recent progress in quantitative proteomics has offered opportunities to discover biomarkers for tracking the progression and for understanding the molecular mechanisms of Down syndrome. In the present study, placental samples were analyzed by fluorescence two-dimensional differential gel electrophoresis (2D-DIGE) and differentially expressed proteins were identified by matrix assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS). In total, 101 proteins have been firmly identified representing 80 unique gene products. These proteins mainly function in cytoskeleton structure and regulation (such as vimentin and Profilin-1). Additionally, our quantitative proteomics approach has identified numerous previously reported Down syndrome markers, such as myelin protein. Here we present several Down syndrome biomarkers including galectin-1, ataxin-3 and sprouty-related EVH1 domain-containing protein 2 (SPRED2), which have not been reported elsewhere and may be associated with the progression and development of the disease. In summary, we report a comprehensive placenta-based proteomics approach for the identification of potential biomarkers for Down syndrome, in which serum amyloid P-component (APCS) and ataxin-3 have been shown to be up-regulated in the maternal peripheral plasma of Down syndrome cases. The potential of utilizing these markers for the prognosis and screening of Down syndrome warrants further investigation.     

Comparison between principal component analysis and independent component analysis in electroencephalograms modelling

Principal Component Analysis (PCA) is a classical technique in statistical data analysis, feature extraction and data reduction, aiming at explaining observed signals as a linear combination of orthogonal principal components. Independent Component Analysis (ICA) is a technique of array processing and data analysis, aiming at recovering unobserved signals or 'sources' from observed mixtures, exploiting only the assumption of mutual independence between the signals. The separation of the sources by ICA has great potential in applications such as the separation of sound signals (like voices mixed in simultaneous multiple records, for example), in telecommunication or in the treatment of medical signals. However, ICA is not yet often used by statisticians. In this paper, we shall present ICA in a statistical framework and compare this method with PCA for electroencephalograms (EEG) analysis.We shall see that ICA provides a more useful data representation than PCA, for instance, for the representation of a particular characteristic of the EEG named event-related potential (ERP).     

Opportunities for pharmacoproteomics in biomarker discovery

Proteomic data are a uniquely valuable resource for drug response prediction and biomarker discovery because most drugs interact directly with proteins in target cells rather than with DNA or RNA. Recent advances in mass spectrometry and associated processing methods have enabled the generation of large-scale proteomic datasets. Here we review the significant opportunities that currently exist to combine large-scale proteomic data with drug-related research, a field termed pharmacoproteomics. We describe successful applications of drug response prediction using molecular data, with an emphasis on oncology. We focus on technical advances in data-independent acquisition mass spectrometry (DIA-MS) that can facilitate the discovery of protein biomarkers for drug responses, alongside the increased availability of big biomedical data. We spotlight new opportunities for machine learning in pharmacoproteomics, driven by the combination of these large datasets and improved high-performance computing. Finally, we explore the value of pre-clinical models for pharmacoproteomic studies and the accompanying challenges of clinical validation. We propose that pharmacoproteomics offers the potential for novel discovery and innovation within the cancer landscape.     

Nutrition proteomics and biomarker discovery

Baukje de Roos is a principal investigator at the University of Aberdeen, Rowett Institute of Nutrition and Health. She investigates mechanisms through which dietary fats and fatty acids, and also polyphenols, affect parameters involved in the development of heart disease in vivo. This is achieved not only by measuring their effect on conventional risk markers for heart disease but also by assessing their effect on new markers that are being developed through proteomic and mass spectrometry methods. She obtained her PhD in Human Nutrition at Wageningen University, The Netherlands, in January 2000, after which she was appointed as a post-doctoral research fellow at the Department of Vascular Biochemistry, Glasgow Royal Infirmary, in collaboration with GlaxoSmithKline. In June 2001 she joined the Rowett Research Institute in Aberdeen. She is currently working for the University of Aberdeen, where her research is funded by the Scottish Government Rural and Environment Research and Analysis Directorate (RERAD). She is an active member of the European Nutrigenomics Organisation (NuGO), an EU-funded Network of Excellence, which merges the nutrigenomics activities of its 23 partners across Europe.