|
IBM and Celestar Lexico-Sciences Develops New Text Mining Technology To Support Scientific Discovery
Tokyo, September 5, 2002--- Celestar Lexico-Sciences Inc. (CLS), a biotech venture company, and IBM Japan, today announced the development of new text mining technology for life sciences research, using IBM's Text Analysis and Knowledge Mining solution and IBM's eServer system as the core technology. CLS has implemented the new text mining technology, the first implementation in the world.
CLS develops predictive algorithms that identify genes and protein properties related to such diseases as cancer, circulatory disorders, dementia, and infection, for use by major pharmaceutical companies for drug development. The new text mining technology will be used in conjunction with other analysis applications to help CLS strengthen its services to customers.
CLS researchers will use the new advanced text mining technology to analyze and mine more than 11 million potential sources of important research data found in MEDLINE®, the U.S. National Library of Medicine's premier bibliographic database of references to 4,500 biomedical journals published in the United States and 70 foreign countries.
"Life Sciences researchers need to sift through large amounts of data in order to extract valuable scientific information," said Dr. Hirofumi Doi, president and CEO of Celestar Lexico-Sciences, Inc. Central to these efforts is the expanding role of new technologies to quickly integrate the available information in useful forms. The new text mining technology will help to accelerate Life Sciences research by making text search and analysis efforts more efficient."
IBM's Text Analysis and Knowledge Mining solution, the core technology of the new text mining technology, was developed at IBM's Tokyo Research Laboratory, using Natural Language Processing technologies to extract important information including technical terms with a predefined set of categories and relationships between them. It provides sophisticated information retrieval, analysis and browsing capabilities through views from various types of aspects, including word frequency distribution, relative word frequency distribution, topic extraction, 2-dimensional analysis, and timeline analysis.
CLS has selected the IBM eServer p690 system, running AIX, IBM's UNIX operating system, to support its research and run predictive algorithms. The eServer p690 system is based on IBM's next-generation POWER4 microprocessor -- the first "server on a chip," containing two one-gigahertz-plus processors -- and includes self-healing technologies that help provide uninterrupted operation, even through major power outages and system failures.
About Celestar Lexico-Sciences, Inc.
Celestar Lexico-Sciences, Inc. (CLS) is a biotech venture company formed in August 2000, with core technologies in bioinformatics and comparative genomics. The company has 50 employees.
IBM Life Sciences
IBM Life Sciences brings together IBM resources, from research, services and e-business expertise to data and storage management and high-performance computing, to offer new solutions for the life sciences market, including biotechnology, genomic, e-health, pharmaceutical, and agri-science industries. The fastest way to get more information about IBM Life Sciences is through its Web site, http://www.ibm.com/solutions/lifesciences
IBM is a trademark of IBM Corporation in the United States and/or other countries.
MEDLINE is a registered trademark of the US National Library of Medicine.
The IBM eServer brand consists of the established IBM e-business logo with the following descriptive term "server" following it. IBM, the e-business logo, AIX, and pSeries are trademarks of IBM Corporation in the United States and/or other countries.
UNIX is a registered trademark in the United States and other countries licensed exclusively through The Open Group.
|
