Bob Baddeley

The Scalable Reasoning System: Lightweight visualization for distributed analytics

A central challenge in visual analytics is the creation of accessible, widely distributable analysis applications that bring the benefits of visual discovery to as broad a user base as possible. Moreover, to support the role of visualization in the knowledge creation process, it is advantageous to allow users to describe the reasoning strategies they employ while interacting with analytic environments. We introduce an application suite called the scalable reasoning system (SRS), which provides Web-based and mobile interfaces for visual analysis. The service-oriented analytic framework that underlies SRS provides a platform for deploying pervasive visual analytic environments across an enterprise. SRS represents a ldquolightweightrdquo approach to visual analytics whereby thin client analytic applications can be rapidly deployed in a platform-agnostic fashion. Client applications support multiple coordinated views while giving analysts the ability to record evidence, assumptions, hypotheses and other reasoning artifacts. We describe the capabilities of SRS in the context of a real-world deployment at a regional law enforcement organization.

XOA: Web-Enabled Cross-Ontological Analytics

We describe the development of the cross-ontological analytics (XOA) system, which implements a novel Web-enabled approach for computing similarities across gene and gene products with associated specifications of functional genomic relationships. The XOA system enables biologists to leverage combinations of hierarchical and associative data across multiple subontologies in order to reveal relationships between gene and gene products that might not otherwise be exposed by existing methods of computational analysis. We also provide examples of specific proof-of-concept applications in which XOA has been successfully tested.

Combining Hierarchical and Associative Gene Ontology Relations With Textual Evidence in Estimating Gene and Gene Product Similarity

Two approaches have recently emerged where the similarity between two genes or gene products is obtained by comparing Gene Ontology (GO) annotations associated with the genes or gene products. One approach captures GO-based similarity in terms of hierarchical relations within each gene subontology, while the other relies on associative relations across the three gene subontologies. We propose a novel methodology where the two approaches can be merged and enriched by textual evidence extracted from biomedical literature with ensuing benefits in coverage and stronger correlation with sequence-based similarity

Scalable visual reasoning: Supporting collaboration through distributed analysis

We present a visualization environment called the scalable reasoning system (SRS) that provides a suite of tools for the collection, analysis, and dissemination of reasoning products. This environment is designed to function across multiple platforms, bringing the display of visual information and the capture of reasoning associated with that information to both mobile and desktop clients. The service-oriented architecture of SRS facilitates collaboration and interaction between users regardless of their location or platform. Visualization services allow data processing to be centralized and analysis results to be collected from distributed clients in real time. We use the concept of ldquoreasoning artifactsrdquo to capture the analytic value attached to individual pieces of information and collections thereof, helping to fuse the foraging and sense-making loops in information analysis. Reasoning structures composed of these artifacts can be shared across platforms while maintaining references to the analytic activity (such as interactive visualization) that produced them.

An Adaptive Visual Analytics Platform for Mobile Devices

We present the design and implementation of InfoStar, an adaptive visual analytics platform for mobile devices such as PDAs, laptops, Tablet PCs and mobile phones. InfoStar extends the reach of visual analytics technology beyond the traditional desktop paradigm to provide ubiquitous access to interactive visualizations of information spaces. These visualizations are critical in addressing the knowledge needs of human agents operating in the field, in areas as diverse as business, homeland security, law enforcement, protective services, emergency medical services and scientific discovery. We describe an initial real world deployment of this technology, in which the InfoStar platform has been used to offer mobile access to scheduling and venue information to conference attendees at Supercomputing 2004.

The scalable reasoning system: lightweight visualization for distributed analytics

A central challenge in visual analytics is the creation of accessible, widely distributable analysis applications that bring the benefits of visual discovery to as broad a user base as possible. Moreover, to support the role of visualization in the knowledge creation process, it is advantageous to allow users to describe the reasoning strategies they employ while interacting with analytic environments. We introduce an application suite called the scalable reasoning system (SRS), which provides web-based and mobile interfaces for visual analysis. The service-oriented analytic framework that underlies SRS provides a platform for deploying pervasive visual analytic environments across an enterprise. SRS represents a ‘lightweight’ approach to visual analytics whereby thin client analytic applications can be rapidly deployed in a platform-agnostic fashion. Client applications support multiple coordinated views while giving analysts the ability to record evidence, assumptions, hypotheses and other reasoning artifacts. We describe the capabilities of SRS in the context of a real-world deployment at a regional law enforcement organization.

Cross-Ontological analytics: combining associative and hierarchical relations in the gene ontologies to assess gene product similarity

Gene and gene product similarity is a fundamental diagnostic measure in analyzing biological data and constructing predictive models for functional genomics. With the rising influence of the gene ontologies, two complementary approaches have emerged where the similarity between two genes/gene products is obtained by comparing gene ontology (GO) annotations associated with the gene/gene products. One approach captures GO-based similarity in terms of hierarchical relations within each gene ontology. The other approach identifies GO-based similarity in terms of associative relations across the three gene ontologies. We propose a novel methodology where the two approaches can be merged with ensuing benefits in coverage and accuracy.

Using the gene ontology to enrich biological pathways.

Most current approaches to automatic pathway generation are based on a reverse engineering approach in which pathway plausibility is solely derived from gene expression data and not independently validated. Alternative approaches use prior biological knowledge to validate automatically inferred pathways, but the prior knowledge is usually not sufficiently tuned to the pathology of focus. We present a novel pathway generation approach that combines insights from the reverse engineering and knowledge-based approaches to increase the biological plausibility of automatically generated regulatory networks and describe an application of this approach to transcriptional data from a mouse model of neuroprotection during stroke.

A Layered Dempster-Shafer Approach to Scenario Construction and Analysis

The ability to support creation and parallel analysis of competing scenarios is perhaps the greatest single challenge for todays intelligence analysis systems. Dempster-Shafer theory provides an evidentiary reasoning methodology for scenario construction and analysis that offers potential advantages when compared to other approaches such as Bayesian nets as it places less conceptual load on the analyst by not requiring the complete specification of joint probability distributions. This paper presents a method that can further reduce the conceptual load by taking advantage of hierarchically structured indicators. We present a novel interface for this layered, Dempster-Shafer evidentiary reasoning approach and demonstrate the utility of this interface with reference to analysis problems focusing on comparing distinct hypotheses.

Enriching regulatory networks by bootstrap learning using optimised GO-based gene similarity and gene links mined from PubMed abstracts

Increasingly, reverse engineering methods have been employed to infer transcriptional regulatory networks from gene expression data. Enrichment with independent evidence from sources such as the biomedical literature and the Gene Ontology (GO) is desirable to corroborate, annotate and expand these networks as well as manually constructed networks. In this paper, we explore a novel approach for computer-assisted enrichment of regulatory networks. GO-based gene similarity is first tuned to an initial network augmented with gene links mined from PubMed and then used to drive network construction using a bootstrapping algorithm. We describe two applications of this approach and discuss its added value in terms of corroboration, annotation and expansion of manually constructed and reversed engineered networks.