What is it about?
QSAR (quantitative structure-activity relationship) is a method used to generate predictive models in various fields including agriculture, biology, environmental, food, and materials sciences. In medicinal chemistry, it has been used to assist in the process of drug design. We applied a machine-learning automated QSAR protocol to the datasets of previously published QSAR models to demonstrate that the approach can perform similarly or better than experienced practitioners in the field. Furthermore, a great diversity of models were produced in a much-reduced amount time.
Featured Image
Why is it important?
In this time and age of 'big data', Automated QSAR is particularly relevant to speed up the process of model generation for various uses. The approach has shown to produced quality models with minimum human interference.
Perspectives
There is still lack of confidence in the community that machines can produce models of similar or better quality than those generated by experts, which is clearly not the case as shown in our contribution. We hope that increasingly more people will use similar approaches to generate their models. Another key aspect of AutoQSAR is the democratization of access to the method to the benefit especially of non-experts.
Marcelo Tavares
Universidade de São Paulo
Read the Original
This page is a summary of: On the virtues of automated quantitative structure–activity relationship: the new kid on the block, Future Medicinal Chemistry, February 2018, Future Science,
DOI: 10.4155/fmc-2017-0170.
You can read the full text:
Contributors
The following have contributed to this page
