蛋白质二级结构预测样本集数据库的设计与实现

将数据库技术应用到蛋白质二级结构预测的样本集处理和分析上，建立了二级结构预测样本集数据库。以CB513样本集为例介绍了该数据库的构建模式。构建样本数据库不仅便于存储、管理和检索数据，还可以完成一些简单的序列分析工作，取代许多以往必须的编程。从而大大提高了工作效率，减少错误的发生。

Design and implementation of the database of data sets for prediction of protein secondary structures

A novel approach was introduced to process and analyze the data sets for protein secondary structure prediction based on database technologies via construcdng a Database of the prediction data sets. The schema of the database is shown taking the CB513 data set as example. The database of data sets can not only lead an easy way to store, manage and query data, but do some simple sequence analysis instead of the complicated data processing by programming as before. So that it is a much mone efficient method making work simple, quick and accurate.