Pharmaceutical Chemistry

QSAR in Pharmaceutical Chemistry

Submit Abstract Register Now

Quantitative structure–activity relationship models (QSAR models) square measure regression or classification models employed in the chemical and biological sciences and engineering. Like alternative regression models, QSAR regression models relate a collection of "predictor" variables (X) to the efficiency of the response variable (Y), whereas classification QSAR models relate the predictor variables to a categorical price of the response variable. In QSAR modelling, the predictors contains physico-chemical properties or theoretical molecular descriptors of chemicals; the QSAR response-variable may be a biological activity of the chemicals. QSAR models initial summarize a supposed relationship between chemical structures and biological activity in an exceedingly data-set of chemicals. Second, QSAR models predict the activities of recent chemicals.

Related terms embody quantitative structure–property relationships (QSPR) once a property is modelled because the response variable. As associate degree example, biological activity may be expressed quantitatively because the concentration of a substance needed to relinquish an explicit biological response. in addition, once chemical science properties or structures square measure expressed by numbers, one will notice a mathematical relationship, or quantitative structure-activity relationship, between the 2. The mathematical expression, if fastidiously valid will then be wont to predict the modelled response of alternative chemical structures.

A QSAR has the shape of a mathematical model:

Activity = f(physiochemical properties and/or structural properties) + error

The error includes model error (bias) and data-based variability, that is, the variability in observations even on an accurate model.