Artificial Intelligence Research Laboratory Department of Computer Science Iowa State University

An Agent-Based Environment for Integrating and Analyzing Plant Genomic Databases
   Personnel   Project Summary   Funding   Publications   Additional Information   Projects   AI Lab  

• Dr. Vasant Honavar, Principal Investigator.
• Drena Dobbs, Co-Principal Investigator.
• Pat Schnable, Collaborator.
• Ms. Doina Caragea, Ph.D. Student.
• Mr. Adrian Silvescu, Ph.D. Student.
• Ms. Taru Trivedi, Ph.D. Student.
• Dake Wang, M.S. Student

Project Summary

Recent advances in high throughput (and often automated or semi-automated) data acquisition technologies, digital storage technologies, computers and communications have made it possible to gather and store large amounts of data on plants. As a result, research groups are generating large volumes of data. In order to translate these advances in high-throughput data acquisition into fundamental gains in scientific understanding calls for development of software tools that allow integrated retrieval and analysis of the individual databases. The design and implementation of such tools has to address several challenges in computer and information sciences:

• In many instances, the data sources are physically distributed (e.g., at multiple laboratories and data repositories). This calls for the use of information assistants or software agents for intelligent, selective, and context-sensitive data gathering, information extraction, and data assimilation prior to large scale data analysis. Since scientific data sources are dynamic (i.e., they change rapidly as data items are added or modified), there is a need to monitor the data sources, propagate the changes, and trigger the necessary updates in the affected data and knowledge repositories. For example, as experimental data about mRNA expression and localization are gathered using microarray technology and in situ hybridization, it would be extremely beneficial to annotate the corresponding DNA sequences in an automated or semi-automated fashion. Since the information of interest is user, problem, and context-dependent, such tools have to be customizable.
• , Given the large volumes of data involved, it is desirable to perform as much analysis as feasible at the sites where the data is located and transmit only the results of analysis rather than flooding the network with data. This calls for the use of mobile software agents that can transport themselves to appropriate sites, carry out the computation on site, and return with useful results.
• Since the data sources are often autonomously owned and operated, and reside on heterogeneous hardware and software platforms, their effective use requires a sufficient degree of interoperability among the different data sources (despite their heterogeneity). For example, specific bioinformatics applications might have to access and use data from multiple genome or protein data banks.
• The data sources contain multiple types of data (text, images, relational databases, sequence data, spectrograms, protein structures, etc.) This calls for sophisticated tools for extracting, transforming, and assimilating relevant information from heterogeneous data sources into a data warehouse where it can be further analyzed to faciliate knowledge discovery.
• The large volumes of data, the range of scientifically relevant but complex interrelationships that need to be discovered, and the diversity of data sources challenge state-of-the-art approaches to data mining and knowledge discovery. In particular, current statistical and artificial intelligence tools have to be extended and new efficient algorithms developed to handle data-driven knowledge acquisition and incremental theory refinement from multiple heterogeneous, structured as well as semi-structured scientific data and knowledge sources.

This research is closely integrated with the training of graduate students in Bioinformatics and Computer Science at Iowa State University.

Funding

• An Agent-Based Environment for Integrating and Analysing Plant Genome Databases. Pioneer Hi-Bred International, Inc. 2000-2001. Vasant Honavar, Drena Dobbs, and Les Miller. $40,000.
• Distributed Knowledge Networks, John Deere Foundation, 1999-2000. Vasant Honavar. $30,000.

Publications

• Honavar, V. (1999). Distributed Knowledge Networks. Invited Talk. Artificial Intelligence for Distributed Information Networks (AiDIN '99) Workshop held during the 1999 National Confere nce on Artificial Intelligence (AAAI 99), Orlando, Florida. July 1999.
• Caragea, D., Silvescu, A., and Honavar, V. (1999). Incremental Distributed Support Vector Induction. To appear.
• Vander Velden, K., Andreotti, A., Dobbs, D., Honavar, V., and Miller, M. (1999). Protein Secondary Structure Prediction: New results and Some Observations. To appear.
• Yang, J., Parekh, R., Honavar, V., and Dobbs, D. (1999). Data-Driven Theory Refinement Algorithms for Bioinformatics. In: Proceedings of the International Joint Conference on Neural Networks. Washington, D.C.
• Balakrishnan, K. and Honavar, V. (1998). Intelligent Diagnosis Systems. Journal of Intelligent Systems.
• Yang, J. and Honavar, V. (1998). DistAl: An Inter-Pattern Distance Based Constructive Neural Network Learning Algorithm. . Intelligent Data Analysis
• Yang, J. and Honavar, V. (1998). Feature Subset Selection Using a Genetic Algorithm. IEEE Intelligent Systems (Special Issue on Feature Transformation and Subset Selection). vol. 13. pp. 44-49.
• Yang, J. (1999). Adaptive Agents For Information Retrieval and Data-Driven Knowledge Acquisition. Doctoral Dissertation. Department of Computer Science. Iowa State University.
• Honavar, V., Miller, L. and Wong, J. (1998). Distributed Knowledge Networks. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Helmer, G., Wong, J., Honavar, V. and Miller, L. (1998). Intelligent Agents for Intrusion Detection. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Miller, L., Honavar, V. and Wong, J. (1998). Object-Oriented Data Warehouse for Information Fusion from Heterogeneous Data and Knowledge Sources. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Yang, J., Pai, P., Honavar, V., and Miller, L. (1998). Mobile Intelligent Agents for Document Classification and Retrieval: A Machine Learning Approach. In: Proceedings of the European Symposium on Cybernetics and Systems Research.
• Yang, J., Havaldar, R., Honavar, V., Miller, L. and Wong, J. (1998). Coordination and Control of Distributed Knowledge Networks Using the Contract Net Protocol. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.

Additional Information

To appear.

© Vasant Honavar, 1999.