- First Package To Include Bicluster, Super-paramagnetic and Percolation Algorithms -

ITHACA, NY - November 6, 2001 - At the International Conference on Systems Biology, Gene Network Sciences (GNS) today announced the launch of BioMine™, an integrated software package that allows users of microarray data to quickly and accurately extract the maximum information from their experiments.

Currently under evaluation at more than 30 pharmaceutical companies, biotechs and academic institutions, BioMine is the only commercial product with the proprietary BiCluster™ algorithm, which directly links genes to conditions, and sophisticated clustering algorithms including super-paramagnetic and percolation. These algorithms are complemented by non-parametric statistical analysis tools, which do not assume a normal distribution of the data, and correct normalization for Affymetrix® GeneChip® and other data sets. In addition, BioMine offers advanced visualization techniques and an experiment design tool.

"For years, I've been calling for more solid statistical foundations and advanced clustering algorithms in the analysis of gene expression matrices. Finally, someone listened to my ranting and delivered a product that doesn't dodge the hard problems," said Zoltan Szallasi, M.D., Children's Hospital Informatics Program, Harvard Medical School. "BiCluster holds the promise of solving some of the most immediate needs in gene expression analysis -- finding marker genes for cancer sub-types or identifying therapeutic targets for novel treatment strategies."

GNS is offering a free trial download of BioMine via its Web site: www.gnsbiotech.com. Interested parties can view the software, run up to five test sessions, and walk through an on-line tutorial.

How BioMine Works

Once researchers run experiments using DNA chips or cDNA microarrays and complete the image processing step, the resulting data files are imported to BioMine for normalization, processing and filtering. Researchers then have the option of running one of BioMine's 14 clustering algorithms. At any point, BioMine's five statistical tools, which include non-parametric tests that do not assume normal data distribution, can be tapped to provide validation and determine the P-value of relationships.

BioMine's advanced visualization techniques, including 3D PCA, projection pursuit, parallel coordinates and self-self plots, can be used throughout the process to provide clear pictures of the data. In addition, BioMine offers an experiment design tool that helps researchers save time and reduce expenses by delivering the exact number of replicates needed for a given confidence level.

"The ultimate objective of microarray analysis is to link genes to conditions. Our proprietary BiCluster algorithm does this in one step, going directly from normalization to correlation," says Colin Hill, CEO of GNS. "In addition to providing sophisticated new algorithms, another priority when designing BioMine was to address the most common complaints about existing packages -- inadequate normalization, statistical tools that assume a normal distribution of the data, and a lack of help in designing experiments. By solving these critical problems, BioMine leapfrogs the current packages on the market and sets a new standard for microarray analysis."

 
About Gene Network Sciences

Founded in August 2000, Gene Network Sciences (www.gnsbiotech.com) is a privately held biotech company headquartered in Ithaca, New York. A pioneer in the field of systems biology, GNS integrates biological and chemical data to create accurate and robust computer models of cell function and human biology. GNS helps pharmaceutical companies better understand the complex human biological systems that they seek to affect. The company's technology will ultimately increase clinical trial success rates and help bring better drugs to market faster.

Return to top