Learning local languages and its application to protein /spl alpha/-chain identification
Learning local languages and its application to protein /spl alpha/-chain identification
复制标题
学习当地语言及其在蛋白质/spl α/链识别中的应用
DOI：
10.1109/hicss.1994.323560
复制
发表时间：
1994
期刊：
影响因子：
--
通讯作者：
Satoshi Kobayashi
中科院分区：
文献类型：
--
作者：
T. Yokomori;Nobuyuki Ishida;Satoshi Kobayashi
研究了一种从正数据中学习一种特殊类型的正则语言——局部可测试语言的有效算法，并将其应用于氨基酸序列中蛋白质/spl α /-链区域的识别。首先，我们提出了一种线性时间算法，给定一种局部可测试的语言，仅从正数据中学习（识别）其极限的确定性有限状态自动机。这为符号分析的特定领域提供了一种实用而有效的学习方法。然后描述了使用该学习算法的几个实验结果。根据理论观察，强烈表明某种类型的氨基酸序列可以用局部可测试的语言表达，我们将学习算法应用于血红蛋白氨基酸序列中的蛋白质/spl α /-链区域的识别。实验分数显示，正面数据的正确识别成功率为95%，负面数据的正确识别成功率为96%。<<ETX>>
Concerns an efficient algorithm for learning in the limit a special type of regular language called a locally testable language from positive data, and its application to identifying the protein /spl alpha/-chain region in amino acid sequences. First, we present a linear-time algorithm that, given a locally testable language, learns (identifies) its deterministic finite state automaton in the limit from only positive data. This provides a practical and efficient learning method for a specific domain of symbolic analysis. We then describe several experimental results using the learning algorithm. Following a theoretical observation which strongly suggests that a certain type of amino acid sequence can be expressed by a locally testable language, we apply the learning algorithm to identifying the protein /spl alpha/-chain region in amino acid sequences for hemoglobin. Experimental scores show an overall success rate of 95% correct identification for positive data and 96% for negative data.<<ETX>>
DOI：
10.1073/pnas.84.13.4355
发表时间：
1987-07-01
影响因子：
11.1
作者：
GRIBSKOV, M;MCLACHLAN, AD;EISENBERG, D
通讯作者：
EISENBERG, D
DOI：
10.1073/pnas.86.4.1183
发表时间：
1989-02-01
影响因子：
11.1
作者：
STORMO, GD;HARTZELL, GW
通讯作者：
HARTZELL, GW