共 11 条
STRUCTURE DESIGN - AN ARTIFICIAL INTELLIGENCE-BASED METHOD FOR THE DESIGN OF MOLECULES UNDER GEOMETRICAL CONSTRAINTS
被引:3
作者:
COHEN, AA
SHATZMILLER, SE
机构:
[1] Tel-Aviv University, School of Chemistry, Ramat-Aviv
来源:
JOURNAL OF MOLECULAR GRAPHICS
|
1993年
/
11卷
/
03期
关键词:
DRUG DESIGN;
STRUCTURE GENERATION;
ARTIFICIAL INTELLIGENCE;
MOLECULAR GRAPHS;
D O I:
10.1016/0263-7855(93)80068-3
中图分类号:
Q5 [生物化学];
学科分类号:
071010 ;
081704 ;
摘要:
This study presents an algorithm that implements artificial-intelligence1 techniques for automated, and site-directed drug design. The aim of the method is to link two or more predetermined functional groups into a sensible molecular structure. The proposed designing process mimics the classical manual design method, in which the drug designer sits in front of the computer screen and with the aid of computer graphics attempts to design the new drug. Therefore, the key principle of the algorithm is the parameterization of some criteria that affect the decision-making process carried out by the drug designer. This parameterization is based on the generation of weighting factors that reflect the knowledge and knowledge-based intuition of the drug designer, and thus add further rationalization to the drug design process. The proposed algorithm has been shown to yield a large variety of different structures, of which the drug designer may choose the most sensible. Performance tests indicate that with the proper set of parameters, the method generates a new structure within a short time.
引用
收藏
页码:166 / 173
页数:8
相关论文