IMPROVED ANN SEARCH ENGINE FOR CCRC NET 1H NMR XYLOGLUCAN DATABASE

改进的 CCRC NET 1H NMR XYLOGLUCAN 数据库的人工神经网络搜索引擎

• 批准号: 6653525
• 负责人: FARAMARZ VALAFAR
• 金额: $ 28.8万
• 依托单位: UNIVERSITY OF GEORGIA
• 依托单位国家: 美国
• 财政年份: 2002
• 资助国家: 美国
• 起止时间: 2002-08-01 至 2003-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/6653525
• 关键词: biological products; biomedical resource; carbohydrates; computers; informatics; model design /development; technology /technique

The ANN search engine of CCRC-Net's database of 1H-NMR spectra of xyloglucan oligosaccharides was replaced with an improved ANN engine. The new engine was trained with a greater number of duplicate spectra per structure to increase its pattern-matching accuracy. The new engine is much more robust and delivers far fewer "false-positive" matches than the original search engine. The new engine can also handle spectra that have half the signal-to-noise ratio of those spectra that could be handled by the previous engine. Also, the 1H-NMR spectra for a new xyloglucan database have been recorded; a new database and search engine is planned for these structures.

CCRC-Net 1H-NMR 谱数据库的 ANN 搜索引擎 木葡聚糖寡糖被改进的 ANN 引擎取代。 新引擎接受了更多重复光谱的训练 每个结构以提高其模式匹配精度。 新的 引擎更加强大并且提供更少的“误报” 比原来的搜索引擎更匹配。 新发动机还可以 处理信噪比一半的光谱 以前的引擎可以处理的光谱。 另外， 已记录新木葡聚糖数据库的 1H-NMR 谱；一个新的 数据库和搜索引擎是为这些结构规划的。