Alvascience: A New Software Suite for the QSAR Workflow Applied to the Blood-Brain Barrier Permeability

Area of Science:

• Computational chemistry
• cheminformatics
• Drug discovery

Background:

• Quantitative structure-activity relationship (QSAR) and quantitative structure-property relationship (QSPR) are vital for predicting molecular properties.
• Existing workflows can be complex and time-consuming.
• There is a need for integrated tools to manage the entire QSAR/QSPR process.

Purpose of the Study:

• To introduce the Alvascience software suite, an integrated platform for QSAR/QSPR modeling.
• To demonstrate the utility of the software suite in a real-world application.
• To provide accessible predictive models for endpoints like blood-brain barrier permeability.

Main Methods:

• Utilized alvaMolecule for data curation.
• Employed alvaDesc for generating molecular descriptors and fingerprints.
• Built and validated models using alvaModel.
• Deployed and applied models for prediction with alvaRunner.

Main Results:

• Successfully applied the Alvascience suite to predict blood-brain barrier permeability.
• Developed predictive models with an accuracy of 0.8 or higher.
• Bundled the predictive models into an alvaRunner project for easy access.

Conclusions:

• The Alvascience software suite offers a comprehensive solution for the entire QSAR/QSPR workflow.
• The developed models demonstrate high accuracy in predicting critical endpoints.
• The readily available alvaRunner project facilitates the application of these predictive models.