International Journal on Artificial Intelligence Tools

Multiple matching algorithms are used to locate the occurrences of patterns from a finite pattern set in a large input string. Aho–Corasick and Wu–Manber, two of the most well known algorithms for multiple matching require an increased computing power, particularly in cases where large-size datasets must be processed, as is common in computational biology applications. Over the past years, Graphics Processing Units (GPUs) have evolved to powerful parallel processors outperforming Central Processing Units (CPUs) in scientific calculations. Moreover, multiple GPUs can be used in parallel, forming hybrid computer cluster configurations to achieve an even higher processing throughput. This paper evaluates the speedup of the parallel implementation of the Aho–Corasick and Wu–Manber algorithms on a hybrid GPU cluster, when used to process a snapshot of the Expressed Sequence Tags of the human genome and for different problem parameters.

According to the central dogma of Biology it was commonly accepted that most of the genetic information was transacted by proteins. Recent experimental techniques revealed that the majority of mammalian genomes and other complex organisms are in fact transcribed into non-coding RNAs. Typically, non-coding RNAs are small nucleotide sequences that are not transcribed into proteins and have a profound regulatory role. Present advances in computational biosciences linked their abnormal functionality to many diseases and re-stated the principles of basic therapeutic strategies. The effective identification of non-coding RNAs and their biological role emerges as a new and challenging bioinformatics problem. ncRNAclass (http://biotools.ceid.upatras.gr/ncrnaclass/) is a web platform that allows for efficient computation of a set of features that can describe effectively the broad class of non-coding RNAs. Moreover, it enables the calculation of features that include information about the targeting behavior of miRNAs. The tool operates under a user-friendly interface and its pilot implementation incorporates prediction models for the well-known class of microRNAs and for prediction their mRNA targets. The prediction models are based on two novel evolutionary Machine Learning algorithms that achieve very high classification performance in comparison with existing methods. The platform is also equipped with a data warehouse, with manually curated sequences, that enables fast information retrieval and data mining utilities.

In the wake of gene-oriented data analysis in large-scale bioinformatics studies, focus in research is currently shifting towards the analysis of the functional association of genes, namely the metabolic pathways in which genes participate. The goal of this paper is to attempt to identify the core genes in a specific pathway, based on a user-defined selection of genomes. To this end, a novel algorithm has been developed that uses data from the KEGG database, and through the application of the MCL clustering algorithm, identifies clusters that correspond to different “layers” of genes, either on a phylogenetic or a functional level. The algorithm's complexity, evaluated experimentally, is presented and the results on three characteristic case studies are discussed.

Nowadays, people frequently use search engines in order to find the information they need on the Web. Especially, Web search constitutes of a basic tool used by million researchers in their everyday work. A very popular indexing engine, concerning life sciences and biomedical research, is PubMed. PubMed is a free database accessing primarily the MEDLINE database of references and abstracts on life sciences and biomedical topics. The present search engines usually return search results in a global ranking, making it difficult for the users to browse in different topics or subtopics.

In this work we propose a novel system to address the issues of clustering biomedical search engine results according to their topic. A methodology that exploits semantic text clustering techniques in order to group biomedical document collections in homogeneous topics, is presented and evaluated. In order to provide more accurate clustering results, we utilize various biomedical ontologies, likeMeSH and GeneOntology. Finally, we embed the proposed methodology in an online system that post-processes the PubMed online database so as to provide users the retrieved results according to well formed topics. So as to expose our method as an online real-time service with reasonable response times, we performed a wide range of engineering optimizations along with experimentation on preprocessing time to precision of results trade off.

This paper presents the SECu-SVM algorithm for solving classification problems. It allows for a significant acceleration of the standard SVM implementations by transferring the most time-consuming computations from the standard CPU to the Graphics Processor Units (GPU). In addition, highly efficient Sliced EllR-T sparse matrix format was used for storing the dataset in GPU memory, which requires a very low memory footprint and is also well adapted to parallel processing. Performed experiments demonstrate an acceleration of 4–100 times over LibSVM. Moreover, in the majority of cases the SECu-SVM is less time-consuming than the best sparse GPU implementations and allows for handling significantly larger classification datasets.

Evolutionary algorithms (EAs) can be used to find solutions in dynamic environments. In such cases, after a change in the environment, EAs can either be restarted or they can take advantage of previous knowledge to resume the evolutionary process. The second option tends to be faster and demands less computational effort. The preservation or growth of population diversity is one of the strategies used to advance the evolutionary process after modifications to the environment. We propose a new adaptive method to control population diversity based on a model-reference. The EA evolves the population whereas a control strategy, independently, handles the population diversity. Thus, the adaptive EA evolves a population that follows a diversity-reference model. The proposed model, called the Diversity-Reference Adaptive Control Evolutionary Algorithm (DRAC), aims to maintain or increase the population diversity, thus avoiding premature convergence, and assuring exploration of the solution space during the whole evolutionary process. We also propose a diversity models based on the dynamics of heterozygosity of the population, as models to be tracked by the diversity control. The performance of DRAC showed promising results when compared with the standard genetic algorithm and six other adaptive evolutionary algorithms in 14 different experiments with three different types of environments.

Web service composition is a significant problem as the number of available web services increases; however, manual composition is not an efficient option. Automated web service composition can be performed using AI Planning techniques, utilizing descriptions of available atomic web services, enhanced with semantic awareness and relaxation. This paper discusses a unified, semantically aware approach, handling both semantic (OWL-S & SAWSDL) and non-semantic (WSDL) web service descriptions. In the first case, ontology analysis is adopted to semantically enhance the planning domains and problems, in order to deal with cases where exact syntactic input-to-output matching is not feasible. In the non-semantic descriptions case, semantic information is acquired utilizing alternative sources such as lexical thesauri. Concept similarity measures are applied and utilized to achieve the desired degree of semantic relaxation. The solution to a web service composition problem is a plan describing the desired composite service. To support the proposed approach, the PORSCE framework has been implemented. The framework is modular, integrating discrete web service description languages and semantic relaxation techniques. Based on the similarity measures suggested in the paper, performance issues are also explored.

Sequential pattern mining has become one of the most important topics in data mining. It has broad applications such as analyzing customer purchase data, Web access patterns, network traffic data, DNA sequencing, and so on. Previous studies have concentrated on reducing redundant patterns among the sequential patterns, and on finding meaningful patterns from huge datasets. In sequential pattern mining, closed sequential pattern mining and weighted sequential pattern mining are the two main approaches to perform mining tasks. This is because closed sequential pattern mining finds representative sequential patterns which show exactly the same knowledge as the complete set of frequent sequential patterns, and weight-based sequential pattern mining discovers important sequential patterns by considering the importance of each sequential pattern. In this paper, we study the problem of mining robust closed weighted sequential patterns by integrating two paradigms from large sequence databases. We first show that the joining order between the weight constraints and the closure property in sequential pattern mining leads to different sets of results. From our analysis of joining orders, we suggest robust closed weighted sequential pattern mining without information loss, and present how to discover representative important sequential patterns without information loss. Through performance tests, we show that our approach gives high performance in terms of efficiency, effectiveness, memory usage, and scalability.

A framework for constructing robust classification models is proposed in the paper. An assumption about importance of one of the classes in comparison with other classes is incorporated into the models. It often takes place in the real application, for example, in reliability, in medical diagnostic, etc. A main idea underlying the models is to consider a set of probability distributions on training examples produced by the imprecise probability models such as linear-vacuous mixture and constant odd-ratio contaminated models. Extreme points of the sets of probability distributions are a main tool for constructing the robust classifiers. It is shown that algorithms for computing optimal classification parameters are reduced to a finite number of weighted support vector machines with weights determined by the extreme points. Experimental results with synthetic and real data illustrate the proposed models.