Computer

1. Abstract

The explosion of online scientific data resulted from DNA microarray experiments and other high-throughput techniques in molecular biology has threatened to overwhelm the ability of researchers to take full advantage of available information. This problem is particularly severe in the rapidly expanding area of gene and cancer research. The project is devoted to the document clustering of documents and papers regarding gene and breast cancer research. A few clustering algorithms will be explored and evaluated to determine the ¡§best¡¨ algorithm for use in clustering breast cancer related documents. With the clustering technique, it hopes to help researchers in gaining valuable information from the immense amount of textual documents.
2. Introduction

Biologists and scientists need to know the most updated information of the gene-cancer research at any stage of their project or research. Although some popular bio-informatics web sites, such as OMIM and GeneCard, ge...