高等学校化学学报

高等学校化学学报 ›› 1995, Vol. 16 ›› Issue (9): 1360.

• 论文 • 上一篇    下一篇

人工神经网络法预测核苷及核酸碱基的疏水分配系数

张向东1, 刘祁涛1, 张士国2   

  1. 1. 辽宁大学化学系, 沈阳, 110036;
    2. 滨州师范专科学校化学系
  • 收稿日期:1994-09-29 修回日期:1995-01-07 出版日期:1995-09-24 发布日期:1995-09-24
  • 通讯作者: 张向东,男,31岁,硕士,讲师.
  • 作者简介:张向东,男,31岁,硕士,讲师.

Prediction of Hydrophobic Partition Coefficients of Nucleosides and Nucleoside Bases by Artificial Neural Network

ZHANG Xing-Dong1, Liu Qi-Tao1, ZHANG Shi-Guo2   

  1. 1. Department of Chemistry, Liaoning Universty, Shenyang, 10036;
    2. Department of Chemistry, Binzhou Teacher Training College, Binzhou
  • Received:1994-09-29 Revised:1995-01-07 Online:1995-09-24 Published:1995-09-24

PDF (PC)

被引次数

5

摘要： 用人工神经网络方法预测核苷及核酸碱基一类化合物的lgP值(P:1-辛醇/水分配系数),预测精度显著优于BlgP法、ClgP法和AlgP法。根据预测结果讨论了分子内氢键及分子构象柔顺性对这类化合物疏水性的影响。

关键词: 人工神经网络, 分配系数, 核苷, 核酸碱基

Abstract: A back-propagation artificial neural network (ANN) was trained on the Gramer's parameters to predict the lgP (logarithm of "1-octanol to water" partition coefficients) of nucleosides and nucleoside bases. The prediction results show that the ANN method is betterthan other methods (BlgP, ClgP, AlgP) for this class of compounds.The effect of conformational flexibility or intramolecular hydrogen bonding on the lgPof nucleoside compounds is discussed.

Key words: ANN, Partition coefficients, Nucleoside, Nucleoside base

TrendMD: