Search

PurposeInformation analysis tools enhance the possibilities of firm competition in terms of knowledge management. However, the generalization of decision support systems (DSS) is still far away from everyday use by managers and academicians. This paper aims to present a framework of analysis based on Bayesian networks (BN) whose accuracy is measured in order to assess scientific evidence.Design/methodology/approachDifferent learning algorithms based on BN are applied to extract relevant information about the relationship between operations strategy and flexibility in a sample of engineering consulting firms. Feature selection algorithms automatically are able to improve the accuracy of these classifiers.FindingsResults show that the behaviors of the firms can be reduced to different rules that help in the decision‐making process about investments in technology and production resources.Originality/valueContrasting with methods from the classic statistics, Bayesian classifiers are able to model a variety of relationships between the variables affecting the dependent variable. Contrasting with other methods from the artificial intelligence field, such as neural networks or support vector machines, Bayesian classifiers are white‐box models that can directly be interpreted. Together with feature selection techniques from the machine learning field, they are able to automatically learn a model that accurately fits the data.

Inferring haplotype phase is a subject of interest, and given the increasing number of GWAS and related applications, like genetic profiling, it is necessary for phasing algorithms to provide a good performance even when processing large DNA fragments. Most of studies focus on genomic regions of limited length, therefore, we propose to test the most common statistics with genetic regions of variable length. We have found that one of the most used, the switch error, is insufficient when considering long distances: it converges to a constant value which does not truly shows the quality of the inferred phase. Furthermore, the IGP (incorrect genotype percentage) is a much more precise measure of the quality of the algorithm. New phasing algorithms should not care only about the number of switches, because in some cases (classifiers to assess genetic risks, for example) is important to distinguish the haplotype of each parent to obtain better results.

The quantity and quality of genome-wide association studies for several diseases are constantly increasing. As a consequence, molecular biologists from different laboratories demand new visualization tools for them to explore results by view and formulate new conjectures to work on. Although nowadays most studies are not able to reconstruct individual haplotypes, the next generation sequencying technologies will allow to obtain individual haplotypes in most studies conducted in the next few years. As evolutionary analysis of the haplotypes can be an invaluable information to biomedical researchers to build hypotheses of genetic variation by considering haplotype evolution, we have build a web-based tool for biomedical researchers to build and visualize risk haplotype trees along a chromosome so that they can perform a visual online exploration of the genetic factors associated with complex diseases.

The exponential increment in the production of biomedical data is forcing a higher level of automatization to analyze it. Therefore, biomedical researchers have to entrust bioinformaticians to develop software able to process a huge amount of data on high performance unix-based servers. However, most of the software is developed with a very basic, text-based, user interface, usually because of a lack of time. In addition the applications are developed as independent tools yielding to a set of specific software tools with very different ways of use. This implies that final users continuously need developer support. Even worse, in many situations only developers themselves are able to run the software every time is required. In this contribution we present a Web-based user interface that homogenizes the way users interact with the applications installed in a server. This way, authorized users can add their applications to the Web site at a very low cost. Therefore, researchers with no special computational skills will perform analysis by themselves, gaining independence to run applications whenever they want at the cost of a very little effort. The application is portable to any unix-like system with a php+mysql server.

Tree-based transmission-disequilibrium tests are valuable tools to perform fine-mapping in the search of genetic factors for complex diseases, as they use evolutionary information to relate haplotypes affecting the disease. However, the number of different haplotype trees exponentially increases with the number of markers used, leading to spurious associations due to sample overfitting. If the usual Bonferroni correction is applied to avoid those spurious associations, true risk variants may also be missed. In this work we considered a different solution to avoid sample overfitting of haplotype trees. It consists of dividing the data set into at least two parts and using one of them to choose the haplotype tree which models the disease, and the other one to assess the statistical significance. As a practical example to evaluate the performance of our proposal, we modified the TreeDT algorithm and observed a significant improvement in reproducibility while reducing the type I errors.

Due to the high pace that algorithms for scanning genome-wide datasets are produced, most of the software is quickly released. As a consequence, they usually lack in system portability and only provide a text-based user interface. BioCASE is an open-source tool developed to assist bioinformaticians in the task of producing software to perform any kind of computationally-expensive genome-wide scanning. BioCASE will produce efficient software with some other added features such as to be portable, to have a graphical user interface (GUI) and to be easily set up. A first version of BioCASE (http://bios.ugr.es/biocase) has been completed and it is being currently used in the design of a genome- wide tool to perform variable selection of genotype data sets based on multivariate association and transmission-disequilibrium tests.

Missing values in genetic data are a common issue. In this paper we explore several machine learning techniques for creating models that can be used to impute the missing genotypes using multiple genetic markers. We map the machine learning techniques to different patterns of transmission and, in particular, we contrast the effect of short and long range disequilibrium between markers. The assumption of short range disequilibrium implies that only physically close genetic variants are informative for reconstructing missing genotypes, while this assumption is relaxed in long range disequilibrium and physically distant genetic variants become informative for imputation. We evaluate the accuracy of a flexible feature selection model that fits both patterns of transmission using six real datasets of single nucleotide polymorphisms (SNP). The results show an increased accuracy compared to standard imputation models.

Compared with expert systems for specific disease diagnosis, knowledge-based systems to assist decision making in triage usually try to cover a much wider domain but can use a smaller set of variables due to time restrictions, many of them subjective so that accurate models are difficult to build. In this paper, we first study criteria that most affect the performance of systems for triage assistance. Such criteria include whether principled approaches from machine learning can be used to increase accuracy and robustness and to represent uncertainty, whether data and model integration can be performed or whether temporal evolution can be modeled to implement retriage or represent medication responses. Following the most important criteria, we explore current systems and identify some missing features that, if added, may yield to more accurate triage systems.

The interaction of human experts with machine learning and data mining tools leads to improved results in decision-making support systems. In marketing decisions related to market segmentation, the use of only one technique does not guarantee an optimal solution, as such a solution may not even be achievable. In this paper, we analyse the market segmentation decisions in the performing arts through a combination of expert opinions and machine learning algorithms in order to obtain a consensual model that allows a better understanding of market preferences together with a deep knowledge about reliability in the obtained results. The results and data were applied to build a model of market segmentation of students based on their attendance in, attitudes towards, and intentions in attending opera and ballet performances.