,
Essential Steps in QSAR Studies
The principal steps of QSAR/QSPR include.
1) Selection of data set and extraction of structural/empirical descriptors 2. variable selection, 3. model construction, and 4. validation evaluation.
,
Evaluation of The Quality of QSAR Models
QSAR modeling produces predictive models derived from application of statistical tools correlating biological activity (including desirable therapeutic effect and undesirable side effects) or physico-chemical properties in QSPR models of chemicals (drugs/toxicants/environmental pollutants) with descriptors representative of molecular structure or p.
,
Modeling
In the literature it can be often found that chemists have a preference for partial least squares (PLS) methods,[citation needed] since it applies the feature extraction and inductionin one step.
,
SAR and The SAR Paradox
The basic assumption for all molecule-based hypotheses is that similar molecules have similar activities.
This principle is also called Structure–Activity Relationship (SAR).
The underlying problem is therefore how to define a small difference on a molecular level, since each kind of activity, e.g. reaction ability, biotransformation ability, solub.
,
,
What are the different types of QSAR methods?
The method can include:
- bagging ( Classification and Regression Trees (CART); Breiman 1996) and boosting ( Classification and Regression Trees (CART); Breiman 1998 )
Based on the nature of the response variable, QSAR approaches can be grouped into
classification, category, or continuous QSAR (see below).
,
What is a QSAR/QSPR study?
Part of the SpringerBriefs in Molecular Science book series (BRIEFSMOLECULAR) QSAR/QSPR studies are aimed at developing correlation models using a response of chemicals (activity/property) and chemical information data in a statistical approach.
,
Which metric is used for classification-based QSAR models?
Commonly applied metrics for classification-based QSAR models are illustrated below [ 20 ]:
- 1
The Wilks lambda is a metric for the testing of significance of a discriminant model function and determined as the ratio of within group sum of squares and total sum of squares, i.e., within-category to total dispersion.