header image
Home arrow Tutorial arrow Statistical Molecular Design, part 1
Statistical Molecular Design, part 1 PDF Print E-mail
Written by Lennart Eriksson, Per M Andersson, Erik Johansson and Torbjörn Lundstedt   
In pharmaceutical industry one important goal is to identify new chemical entities (NCE), which have the potential for becoming approved drugs. Quantitative structure-activity relationship (QSAR) modeling is one efficient tool in this exercise. QSARs provide a rational basis for understanding mechanisms of biological and pharmacological performance and how to alter chemical structures to achieve improved performance.
However, in the quest for accomplishing a valid and reliable QSAR model, several critical stages will be encountered that have to be dealt with in a proper manner. Chemometric techniques are very purposeful in modern QSAR analysis and will help the inexperienced QSAR analyst avoiding the most trivial mistakes. The chemometric QSAR strategy, applicable both in drug design and environmentally related sciences, highlights some of the most crucial steps. These steps involve
· how to design the training set,
· how to account for chemical and biological properties of compounds,
· how to relate these to each other, and
· how to finally validate the relevance of an established QSAR model.
To accomplish a QSAR model of good predictive power, it is mandatory to have a sufficiently informative training set. It is difficult to create an informative set by a random or an arbitrary selection of compounds. An efficient selection strategy is clearly warranted. In this first episode of our five-fold editorial we will review and illustrate the concept of statistical molecular design (SMD). We will show how this methodology can be applied in QSAR modelling and combinatorial technologies to enable informative sets of molecules, substituents and building blocks.
< Prev   Next >
Search website

Editorial flash
Can we use the regression coefficient profile for selecting PLS components?
The linear model y=Xb + f is often used in chemometrics. Unfortunately, we have put too much emphasis on the importance of the regression coefficient profile b, and mistakenly assumed or believed that it should be a good estimate of the "pure profile". This is not true, and I will argue why in later editorials. But this time, I want to address an earlier question that was posed in relation to the regression coefficient profile.
Read more...
News flash
The NIPALS mountain, revisited
Some doubts have been expressed about the real existence of the NIPALS mountain. To lay these doubts to rest, a second expedition was organized recently in the form of the two gentlemen Fredrik Östman and Jonas Utterström from Umetrics AB in Umea.
Read more...
Tutorial flash
Chemometrics in Metabonomics and Metabolomics

In the post-genomics era, the use of methodologies that enable transcriptomic,proteomic and metabolomic data to be analysed in detail have revolutionized biological investigations. One of the major advantages with metabolomics investigations compared to traditional target metabolite analysis is that metabolomics data can give an unbiased view of changes in metabolism during environmental,genetic or developmental changes. Instead of tracking only a few metabolites, changes in relative amounts in 300 to 1000 or even more metabolites can be recorded and analysed, covering all major metabolic pathways.

This development has accentuated the need to apply and further develop chemometric methodology.
Read more...