Analysis Of Heterogeneous Data Sets Research Articles

Research of methods of analysis of heterogeneous data sets

Research of methods of analysis of heterogeneous data sets

A multilevel approach to big data analysis using analytic tools and actor network theory

Background: Over the years, big data analytics has been statically carried out in a programmed way, which does not allow for translation of data sets from a subjective perspective. This approach affects an understanding of why and how data sets manifest themselves into various forms in the way that they do. This has a negative impact on the accuracy, redundancy and usefulness of data sets, which in turn affects the value of operations and the competitive effectiveness of an organisation. Also, the current single approach lacks a detailed examination of data sets, which big data deserve in order to improve purposefulness and usefulness.Objective: The purpose of this study was to propose a multilevel approach to big data analysis. This includes examining how a sociotechnical theory, the actor network theory (ANT), can be complementarily used with analytic tools for big data analysis.Method: In the study, the qualitative methods were employed from the interpretivist approach perspective.Results: From the findings, a framework that offers big data analytics at two levels, micro- (strategic) and macro- (operational) levels, was developed. Based on the framework, a model was developed, which can be used to guide the analysis of heterogeneous data sets that exist within networks.Conclusion: The multilevel approach ensures a fully detailed analysis, which is intended to increase accuracy, reduce redundancy and put the manipulation and manifestation of data sets into perspectives for improved organisations’ competitiveness.

Data Fusion in Metabolomics Using Coupled Matrix and Tensor Factorizations

With a goal of identifying biomarkers/patterns related to certain conditions or diseases, metabolomics focuses on the detection of chemical substances in biological samples such as urine and blood using a number of analytical techniques, including nuclear magnetic resonance (NMR) spectroscopy, liquid chromatography-mass spectrometry (LC–MS), and fluorescence spectroscopy. Data sets measured using these methods provide partly complementary information, and their joint analysis has the potential to reveal underlying structures, which are, otherwise, difficult to extract. While we can collect vast amounts of data using different analytical methods, data fusion remains a challenging task, in particular, when the goal is to capture the underlying factors and use them for interpretation, e.g., for biomarker identification. Furthermore, many data fusion applications require joint analysis of heterogeneous (i.e., in the form of higher order tensors and matrices) data sets with shared/unshared factors. In order to jointly analyze such heterogeneous data sets, we formulate data fusion as a coupled matrix and tensor factorization (CMTF) problem, which has already proved useful in many data mining applications, and discuss its extension to a structure-revealing data fusion model, i.e., a data fusion model that can identify shared and unshared factors. The traditional methods commonly used for data fusion in the presence of shared/unshared factors are matrix factorization-based methods. Using both simulations and prototypical experimental coupled data sets, we assess the performance of various state-of-the-art data fusion methods and demonstrate that while matrix factorization-based approaches have limitations when used for joint analysis of heterogeneous data sets, the structure-revealing CMTF model can successfully capture the underlying factors by exploiting the low-rank structure of higher order data sets.

Chapter 1: Biomedical Knowledge Integration

The modern biomedical research and healthcare delivery domains have seen an unparalleled increase in the rate of innovation and novel technologies over the past several decades. Catalyzed by paradigm-shifting public and private programs focusing upon the formation and delivery of genomic and personalized medicine, the need for high-throughput and integrative approaches to the collection, management, and analysis of heterogeneous data sets has become imperative. This need is particularly pressing in the translational bioinformatics domain, where many fundamental research questions require the integration of large scale, multi-dimensional clinical phenotype and bio-molecular data sets. Modern biomedical informatics theory and practice has demonstrated the distinct benefits associated with the use of knowledge-based systems in such contexts. A knowledge-based system can be defined as an intelligent agent that employs a computationally tractable knowledge base or repository in order to reason upon data in a targeted domain and reproduce expert performance relative to such reasoning operations. The ultimate goal of the design and use of such agents is to increase the reproducibility, scalability, and accessibility of complex reasoning tasks. Examples of the application of knowledge-based systems in biomedicine span a broad spectrum, from the execution of clinical decision support, to epidemiologic surveillance of public data sets for the purposes of detecting emerging infectious diseases, to the discovery of novel hypotheses in large-scale research data sets. In this chapter, we will review the basic theoretical frameworks that define core knowledge types and reasoning operations with particular emphasis on the applicability of such conceptual models within the biomedical domain, and then go on to introduce a number of prototypical data integration requirements and patterns relevant to the conduct of translational bioinformatics that can be addressed via the design and use of knowledge-based systems.

Toward an integrated assessment of the ecological and chemical status of european river basins

Here, recommendations to improve ecological and chemical status assessments in accordance with the European Water Framework Directive (WFD) are made on the basis of experience gained from the MODELKEY project database, linking existing biological and chemical monitoring data of 3 case study river basins (Elbe, Scheldt, and Llobregat). The data analysis within and across river basins revealed major obstacles to be tackled, including scarcity of matching ecological and chemical monitoring sites for cause-effect relationships as well as a general lack of stressor-specific metrics for single biological quality elements (BQE) to enable a comprehensive risk assessment of all predominant stressors, including toxicity. An example of such a metric, which is recommended for the BQE of benthic macroinvertebrates, is the trait-based species-at-risk index (SPEAR) that correlated well with a respective measure for toxic stress, referred to as toxic units, based on simple mixture toxicity concepts. Surprisingly, the assessment of chemical status of a total of 695 monitoring sites for 2000 to 2004 showed that environmental quality standards (EQSs) were exceeded for at least 1 of the currently 41 priority pollutants (PPs) in 92% to 98% of the cases in all 3 of the river basins, which, according to definition, indicates potential effects on ecological status. A comparison of compliance with EQSs for 41 PPs with a respective effect threshold (derived for benthic macroinvertebrates) revealed that the rather conservative concept of chemical status is most likely not protective in all cases. Furthermore, to account for the many other compounds that are detected frequently in European surface waters and that may also have ecotoxicological effects, we introduced a provisional predicted no-effect concentration that is in accordance with the EQS methodology and is suggested to identify potential emerging compounds for which no or insufficient toxicity data exist. In conclusion, this study aims to support the implementation of the WFD by drawing conclusions from the analysis of heterogeneous data sets of various member states and by introducing new tools to move toward an integrated European assessment of ecological and chemical status.

PAML 4: Phylogenetic Analysis by Maximum Likelihood

PAML, currently in version 4, is a package of programs for phylogenetic analyses of DNA and protein sequences using maximum likelihood (ML). The programs may be used to compare and test phylogenetic trees, but their main strengths lie in the rich repertoire of evolutionary models implemented, which can be used to estimate parameters in models of sequence evolution and to test interesting biological hypotheses. Uses of the programs include estimation of synonymous and nonsynonymous rates (d(N) and d(S)) between two protein-coding DNA sequences, inference of positive Darwinian selection through phylogenetic comparison of protein-coding genes, reconstruction of ancestral genes and proteins for molecular restoration studies of extinct life forms, combined analysis of heterogeneous data sets from multiple gene loci, and estimation of species divergence times incorporating uncertainties in fossil calibrations. This note discusses some of the major applications of the package, which includes example data sets to demonstrate their use. The package is written in ANSI C, and runs under Windows, Mac OSX, and UNIX systems. It is available at -- (http://abacus.gene.ucl.ac.uk/software/paml.html).

Data merging for integrated microarray and proteomic analysis

The functioning of even a simple biological system is much more complicated than the sum of its genes, proteins and metabolites. A premise of systems biology is that molecular profiling will facilitate the discovery and characterization of important disease pathways. However, as multiple levels of effector pathway regulation appear to be the norm rather than the exception, a significant challenge presented by high-throughput genomics and proteomics technologies is the extraction of the biological implications of complex data. Thus, integration of heterogeneous types of data generated from diverse global technology platforms represents the first challenge in developing the necessary foundational databases needed for predictive modelling of cell and tissue responses. Given the apparent difficulty in defining the correspondence between gene expression and protein abundance measured in several systems to date, how do we make sense of these data and design the next experiment? In this review, we highlight current approaches and challenges associated with integration and analysis of heterogeneous data sets, focusing on global analysis obtained from high-throughput technologies.

Tectonic analysis of fault slip data sets

Using data that include the direction and the sense of motion on individual fault surfaces determined by slickenside lineations, it is possible to reconstruct reduced stress tensors that correspond to the orientation of stress axes and to the ratio ϕ = (σ2−σ3)/(σ1−σ3) between principal stress values (σ1≥σ2≥σ3, compression being positive). No assumption is made concerning the orientation of fault planes relative to stress axes, so that reactived faults are taken into account as well as newly created ones. Qualitative and quantitative methods for analysis of fault slip data were developed during the last 10 years. The practical limitation of the methods and the necessity for critical field observations are emphasized. These methods can be applied to focal mechanisms of earthquakes. A more complex analysis of heterogeneous data sets, involving an iterative separation of different stress systems, is also discussed. This analysis enables one to distinguish successive faulting events. Careful qualitative study in the field is in all cases essential.