Kulikowski C A, Muchnik I, Yun H J, Dayanik A A, Zhang D, Song Y, Montelione G T
Computer Science Department, Rutgers University, Piscataway, NJ 08903, USA.
Stud Health Technol Inform. 2001;84(Pt 2):965-9.
Domain parsing, or the detection of signals of protein structural domains from sequence data, is a complex and difficult problem. If carried out reliably it would be a powerful interpretive and predictive tool for genomic and proteomic studies. We report on a novel approach to domain parsing using consensus techniques based on Hidden Markov Models (HMMs) and BLAST searches built from a training set of 1471 continuous structural domains from the Dali Domain Dictionary (DDD). Validation on an independent test sample of family-matched structural domain sequences from the Scop database yields a consensus prediction performance rate of 75.5%, well above the 58% obtained by simple agreement of methods.
结构域解析，即从序列数据中检测蛋白质结构域的信号，是一个复杂且困难的问题。如果能够可靠地进行，它将成为基因组和蛋白质组研究中一个强大的解释和预测工具。我们报告了一种基于隐马尔可夫模型（HMM）和从达利结构域字典（DDD）的1471个连续结构域训练集构建的BLAST搜索的共识技术进行结构域解析的新方法。对来自scop数据库的家族匹配结构域序列的独立测试样本进行验证，得到的共识预测准确率为75.5%，远高于通过简单方法一致性获得的58%。
