| | | |

Artificial Intelligence Technologies

Data Mining in Functional Genomics (BioMine)

Image representing the BioMine project - Click for full view

The BioMine project was initiated in August 1999 to respond to an increasingly urgent need in the field of Bioinformatics (a field that merges computer science and biotechnology) to process and analyze vast amounts of information generated in the study of genes and protein functions. A collaborative project with NRC’s Institute for Biological Sciences (NRC-IBS), the project focuses primarily on the development of a data mining tool which will enable the fast, accurate processing of data from BioChips and protein microarrays. The project consists of three separate phases:

Phase I: preliminary investigation to identify the genomics data mining requirements and to evaluate related data mining techniques and tools currently on the market. This phase was started in August 1999 and was completed in January 2000 and did not identify any existing integrated data mining tool that could support all the BioChip data mining requirements.
Phase II: requirements analysis, research, design and implementation of a data mining tool, called BioMiner. During this phase, the architecture of the BioMiner software, which contained a unique approach to data mining in genomics, was designed and implemented. The software will also be adapted to analyze proteomic and metabolic data, two areas where increased data production rates are imminent.
Phase III: enhancements to BioMiner software, extensive research in genomics and case studies using public and private genomics data sets. The case studies will serve to further validate existing tools and to identify new functionalities. This phase started in April 2002 and will continue until March 2005.

The Biomine project recently led to a 3-year joint partnership involving the Ministry of Science and Technology (MCYT) of Spain. This collaborative effort will use the research from the Biomine project to develop a decision support system. This comprehensive knowledge base would serve as a tool to merge and cross-reference several streams of biomedical data from a variety of sources, including other experimental data, microarray data and clinical information. Ultimately the use of such a tool will result in further advances in the identification of gene and related protein functions. It will also enable medical researchers to analyze and predict the effectiveness of new drugs in the treatment of disease, and to diagnose disease earlier and with increased accuracy.

Project partners:

NRC - Institute for Biological Sciences (NRC-IBS)
NRC - Biotechnology Research Institute (NRC-BRI)
NRC - Plant Biotechnology Institute (NRC-PBI)
NRC - Institute for Marine Biosciences (NRC-IMB)
Children’s Hospital of Eastern Ontario (CHEO)
Centro Nacional de Biotecnología – Consejo Superior de Investigaciones Cientificas (CNIB-CSIC)
Centro Nacional de Investigaciones Oncológicasc (CNIO)

Research Contact

Dr. Abolfazl Famili (Fazel)
Research Officer
Integrated Reasoning
NRC Institute for Information Technology
1200 Montreal Road
Building M-50, Room 368
Ottawa, ON K1A 0R6
Telephone: +1 (613) 993-8554
Fax: +1 (613) 952-0215
E-mail: Fazel.Famili@nrc-cnrc.gc.ca

Business Contact

Dr. George Forester
Business Development Officer
Business Development Office, NCR
NRC Institute for Information Technology
1200 Montreal Road
Building M-50, Room 203
Ottawa, ON K1A 0R6
Telephone: +1 (613) 993-3478
Fax: +1 (613) 952-0074
E-mail: George.Forester@nrc-cnrc.gc.ca