Drug Discovery and development is a multidisciplinary, expensive and decade long research endeavor from idea to treatment of patients. ML and application of modern neural networks has the potential to speed up the process and we work with developing and applying the newest algorithms to accelerate the discovery of new drug candidates. Using natural language architectures and a sequential molecular notation, SMILES, we can teach the computer to design new molecules with desirable properties. Several design methodologies and specialized architectures have been invented in our department, with the newest trends going towards creating unified self-supervised architectures for solving diverse chemical tasks. To help with the process of finding synthetic pathways to the novel molecules, we apply neural network enhanced game algorithms to find plausible synthetic plans.
About the speaker: Esben Jannik Bjerrum completed his PhD in Computational Chemistry at Copenhagen University in 2008. He has since worked both in academia as a post.doc, in industry as an IT specialist as well as an self-employed IT consultant. In 2017 his independent research resulted in several contributions to the chemistry deep learning renaissance. He joined Astrazeneca in 2018 where he currently works with development of de novo design algorithms and deep learning assisted retrosynthetic planning. He’s the lead blogger of cheminformania.com.
Published: Wed 27 Apr 2022.
Please fill in a message
Thanks! We have received your message. If you have left your email address, you will receive a response from the editor-in-chief within 2-3 working days.