Does your model know its limits? Leveraging uncertainties to find better compounds
If you’re using predictive models in your molecule design and optimisation, an accurate uncertainty estimate can be just as important…
In this webinar, we demonstrate how Augmented Chemistry®, a unique deep learning method, can learn from higher throughput data together with limited panel data to provide high-quality imputations for sensory properties.
- Find novel active compounds with 3D virtual screening against known actives:
- Demonstrate the imputation of sparse physicochemical and sensory data
- Compare the results with conventional quantitative structure-activity relationship (QSAR) methods
- Present robust uncertainty estimates generated by the imputation model, highlighting the most accurate predictions to guide decision making
- Show that imputation more accurately predicts activity cliffs, where small changes in compound structure result in large changes in sensory properties.
Sensory properties are subjective measures assessed by panels of trained experts in an expensive and time-consuming process. Samar Mahmoud and Tamsin Mansley were joined by Dmitriy Chekmarev, Senior Research Investigator in computational sciences at IFF, to discuss the challenges of using this sparse and noisy sensory data in predictive models.
Other webinars you may be interested in
How to perform fast and accurate 3D ligand-based affinity predictions
Binding affinity prediction continues to be a challenge in computer-aided drug design, especially in the absence of a high-quality target…
Computational and experimental integration in modern cancer drug discovery: The synthetic lethality approach
Join us for a webinar featuring experts from IDEAYA Biosciences and CDD Vault as they explore how synthetic lethality is…
