QSAR models have attracted broad scientific interest, particularly in the pharmaceutical industry for drug discovery and in toxicology and environmental science for risk assessment. QSAR models are currently regarded as a scientifically reliable tool for predicting and classifying properties of untested chemicals. QSARs are based on the assumption that the structure of a molecule (for example, its geometric, steric and electronic properties) must contain the features responsible for its physical, chemical, and biological properties and on the ability to capture these features into one or more numerical descriptors.

In recent years, a growing interest in QSAR has been generated by REACH that explicitly states that at chemical registration level the registrant should include information from alternative sources (e.g. from QSARs, etc.) that may assist in identifying the presence or absence of hazardous properties of the substance and that can, in certain cases, replace the results of animal tests.

The REACH Regulation states that "Information on intrinsic properties of substances may be generated by means other than in vivo tests". QSAR models can diminish the requirement of experimental tests by means of in-silico property predictions so that in vivo tests can be performed only when it is necessary.

Obviously, for the purposes of the REACH legislation, it is essential to use QSAR models that produce reliable estimates, and, in this regard, model validation and evaluation of applicability domain to avoid data extrapolation have become of primary concern to the QSAR development process along with the use of advanced modeling methods able to deal with the huge chemical information currently available.

Two of the major research topics of Milano Chemometrics and QSAR Research Group have always been QSARs and molecular descriptors. In the past years, new QSAR models were developed to predict chemico-phisical, toxicological and eco-toxicological properties. New strategies to define applicability domain and to evaluate the predictive capabilities of QSAR models were evaluated, and new theoretically-based molecular descriptors for the modelling of different biological and environmental responses were proposed. Moreover, Milano Chemometrics and QSAR Research Group has been involved in several projects related to the use of QSAR for the REACH registration of chemicals. If you are interested in collaboration on these topics, please contact us.