Several Statistical Models In Quantitative Structure Activity Relationships

Quantitative Quantitative Structure-Activity Relationship (QSAR), which investigates the quantitative relationship between the molecular structural parameters and biological activities or dependent functions, is one of the most important fundamental fields in pure and applied chemistry and pharmacy. As an important field for basic research and application of modern chemistry,it has become the hotspot of research on organic chemistry, pharmacological chemistry, environment chemistry, chemometrics, molecular biology and immunology.Structural description is a key step in the QSAR studies. Whether the structural descriptors can reflect the structural variations determines the success of QSAR studies. In this paper, suah as Molecular electro-negativity distance vectors (MEDV) , Molecular Electronegativity Interaction Vector(VMEI) were further Studied.The modeling methods and related techniques are also important for the success of QSAR studies. The modeling methods such as multiple linear regression (MLR), Artificial Neural Network, Genetic Algorithms(GA ) were studied in this paper. applied with the Structural descriptions, Establishing the QSAR models of Drug's structure and their Activity,and made a equivalent or better results then References.The main contents can be divided into three as follows:1. First of all, systematically studied on Several Statistical Models which important in Quantitative Structure Activity Relationship research.2. Secondly,MEDV /VMEI were employed to characterize molecular structure of active components on Pharmaceutical,and has made some investigation on MEDV /VMEI as the extended and improved.3. Finally , Establishing QSAR models of several kinds of Pharmaceutical or compounds,which are two sets of anti-HIV agents ,three Series of peptide,three types of estrogen,Promoter of DNA and several kinds of Persistent Organic Pollutants and Alkanes.The QSAR methods which studied in this paper has made a good result , and as a new way for Pharmaceutical exploitation and design research., will have a bright further.