Computational neural network analysis of the affinity of N-n-alkylnicotinium salts for the alpha4beta2* nicotinic acetylcholine receptor.
Computational neural network analysis of the affinity of N-n-alkylnicotinium salts for the alpha4beta2* nicotinic acetylcholine receptor.
复制标题
N-n-烷基烟碱盐对 α4β2* 烟碱乙酰胆碱受体的亲和力的计算神经网络分析。
DOI：
10.1080/14756360801945648
复制
发表时间：
2009
影响因子：
5.6
通讯作者：
Crooks,PeterA
中科院分区：
文献类型：
--
作者：
Zheng,Fang;Zheng,Guangrong;Deaciuc,AGabriela;Zhan,Chang-Guo;Dwoskin,LindaP;Crooks,PeterA
基于85个分子数据库，采用不同大小数据集的线性回归和人工神经网络方法建立数学关系，拟合大鼠纹状体膜制剂[3H]尼古丁结合试验中获得的一系列单季铵盐和双季铵盐的亲和值（Ki）。利用拟合结果分析了一组n- n-烷基镍类似物从1个碳增加到20个碳的实验值之间的规律。这些正烷基nicoinium化合物的亲和力随着正烷基链上碳原子数量的增加呈抛物线型变化，其中C4（正丁基）类似物的亲和力最小。在c12和c13之间也观察到inKivalue的降低。85个实验值的最佳神经网络拟合统计结果为r2= 0.84, rmsd = 0.39；Rcv2 = 0.68, loormsd = 0.56。生成的具有85个分子训练集的神经网络模型也可能对新的虚拟化合物的kivalues的未来预测有价值，然后可以识别，随后合成和实验测试。
Based on an 85 molecule database, linear regression with different size datasets and an artificial neural network approach have been used to build mathematical relationships to fit experimentally obtained affinity values (Ki) of a series ofmono- andbis-quaternary ammonium salts from [3H]nicotine binding assays using rat striatal membrane preparations. The fitted results were then used to analyze the pattern among the experimentalKivalues of a set ofN-n-alkylnicotinium analogs with increasing n-alkyl chain length from 1 to 20 carbons. The affinity of theseN-n-alkylnicotinium compounds was shown to parabolically vary with increasing numbers of carbon atoms in the n-alkyl chain, with a local minimum for the C4(n-butyl) analogue. A decrease inKivalue between C12and C13was also observed. The statistical results for the best neural network fit of the 85 experimentalKivalues are r2= 0.84, rmsd = 0.39; rcv2= 0.68, and loormsd = 0.56. The generated neural network model with the 85 molecule training set may also be of value for future predictions ofKivalues for new virtual compounds, which can then be identified, subsequently synthesized, and tested experimentally.