J. Stuart Aitken

Feature selection and classification for microarray data analysis: Evolutionary methods for identifying predictive genes

BackgroundIn the clinical context, samples assayed by microarray are often classified by cell line or tumour type and it is of interest to discover a set of genes that can be used as class predictors. The leukemia dataset of Golub et al. [1] and the NCI60 dataset of Ross et al. [2] present multiclass classification problems where three tumour types and nine cell lines respectively must be identified. We apply an evolutionary algorithm to identify the near-optimal set of predictive genes that classify the data. We also examine the initial gene selection step whereby the most informative genes are selected from the genes assayed.ResultsIn the absence of feature selection, classification accuracy on the training data is typically good, but not replicated on the testing data. Gene selection using the RankGene software [3] is shown to significantly improve performance on the testing data. Further, we show that the choice of feature selection criteria can have a significant effect on accuracy. The evolutionary algorithm is shown to perform stably across the space of possible parameter settings – indicating the robustness of the approach. We assess performance using a low variance estimation technique, and present an analysis of the genes most often selected as predictors.ConclusionThe computational methods we have developed perform robustly and accurately, and yield results in accord with clinical knowledge: A Z-score analysis of the genes most frequently selected identifies genes known to discriminate AML and Pre-T ALL leukemia. This study also confirms that significantly different sets of genes are found to be most discriminatory as the sample classes are refined.

Review: learning bayesian networks: Approaches and issues

Bayesian networks have become a widely used method in the modelling of uncertain knowledge. Owing to the difficulty domain experts have in specifying them, techniques that learn Bayesian networks from data have become indispensable. Recently, however, there have been many important new developments in this field. This work takes a broad look at the literature on learning Bayesian networks-in particular their structure-from data. Specific topics are not focused on in detail, but it is hoped that all the major fields in the area are covered. This article is not intended to be a tutorial-for this, there are many books on the topic, which will be presented. However, an effort has been made to locate all the relevant publications, so that this paper can be used as a ready reference to find the works on particular sub-topics.

COBrA: a bio-ontology editor

COBrA is a Java-based ontology editor for bio-ontologies that distinguishes itself from other editors by supporting the linking of concepts between two ontologies, and providing sophisticated analysis and verification functions. In addition to the Gene Ontology and Open Biology Ontologies formats, COBrA can import and export ontologies in the Semantic Web formats RDF, RDFS and OWL.

A semantically guided and domain-independent evolutionary model for knowledge discovery from texts

We present a novel evolutionary model for knowledge discovery from texts (KDTs), which deals with issues concerning shallow text representation and processing for mining purposes in an integrated way. Its aims is to look for novel and interesting explanatory knowledge across text documents. The approach uses natural language technology and genetic algorithms to produce explanatory novel hypotheses. The proposed approach is interdisciplinary, involving concepts not only from evolutionary algorithms but also from many kinds of text mining methods. Accordingly, new kinds of genetic operations suitable for text mining are proposed. The principles behind the representation and a new proposal for using multiobjective evaluation at the semantic level are described. Some promising results and their assessment by human experts are also discussed which indicate the plausibility of the model for effective KDT.

Inferring gene regulatory networks from classified microarray data: Initial results

Using a method of selecting genes on the basis of their utility for classification [2], we apply optimal gene network inference to the 24 most highly-ranked genes in a leukemia data set [1]. In order to have confidence in the resulting Bayesian gene networks, we first validate the network inference methodology on synthetic data and establish that the methodology has very high specificity, i.e. if an edge is inferred then it is highly likely to be correct. However, we are unable to confidently predict directed edges in the network.

Formalizing concepts of species, sex and developmental stage in anatomical ontologies

MOTIVATION Anatomy ontologies have a growing role in bioinformatics-for example, in indexing gene expression data in model organisms. To relate or draw conclusions from data so indexed, anatomy ontologies must be equipped with the formal vocabulary that would allow statements about meronomy to be qualified by constraints such as part of the male or part at the embryonic stage. Lacking such a vocabulary, anatomists have built this information into the structure of the ontology or into anatomical terms. For example, in the FlyBase anatomy for drosophila, the term larval abdominal segment encodes the stage in the term, while the terms male genital disc and female genital disc encode the sex. It remains implicit that a fly has one and only one of these parts during its larval stage. Such indicators of context can and should be represented explicitly in the ontology. RESULTS The framework we have defined for anatomical ontologies allows the canonical anatomy structures of a given species to be those common to all sexes, and to have either male, female or hermaphrodite parts--but not combinations of the latter. Temporal aspects of development are addressed by associating a stage with organism parts and requiring a connected anatomy to have parts that exist at a common stage. Both sex and anatomical stage are represented by attributes. This formalization clarifies ontological structure and meaning and increases the capacity for formal reasoning about anatomy. The framework also supports generalizations such as vertebrate and invertebrate, thereby allowing the representation of anatomical structures that are common across a sub-phylum.

A Process Ontology

This paper describes an ontology for process representation. The ontology provides a vocabulary of classes and relations at a level above the primitive event-instance, object-instance and timepoint description. The design of this ontology balances two main concerns: to provide a concise set of useful abstractions of process, and to provide an adequate formal semantics for these abstractions. The aim of conciseness is to support knowledge authoring - ideally a domain expert should be able to author knowledge in the ontology - providing a sufficiently advanced toolset and interface has been implemented to support this task.

OBO Explorer

MOTIVATION To clarify the semantics, and take advantage of tools and algorithms developed for the Semantic Web, a mapping from the Open Biomedical Ontologies (OBO) format to the Web Ontology Language (OWL) has been established. We present an ontology editor that allows end users to work directly with this OWL representation of OBO format ontologies. AVAILABILITY http://www.aiai.ed.ac.uk/project/cobra-ct.

Using Higher-Order Dynamic Bayesian Networks to Model Periodic Data from the Circadian Clock of Arabidopsis Thaliana

Modelling gene regulatory networks in organisms is an important task that has recently become possible due to large scale assays using technologies such as microarrays. In this paper, the circadian clock of Arabidopsis thaliana is modelled by fitting dynamic Bayesian networks to luminescence data gathered from experiments. This work differs from previous modelling attempts by using higher-order dynamic Bayesian networks to explicitly model the time lag between the various genes being expressed. In order to achieve this goal, new techniques in preprocessing the data and in evaluating a learned model are proposed. It is shown that it is possible, to some extent, to model these time delays using a higher-order dynamic Bayesian network.

Automated Terminological and Structural Analysis of Human-Mouse Anatomical Ontology Mappings

Anatomical information is crucial to human biomedical research but not all research is based on human tissues. However, exploiting discoveries in model organisms such as the mouse at a systems level, involving metabolic and developmental networks in tissues, requires the identification of the links between human and model organism anatomies. The question is: can we exploit similarities between mouse and human to automatically associate data between them?