Thema der Dissertation:
Machine Learning for Kinase Drug Discovery Thema der Disputation:
Virtual screening in computer-aided drug discovery: molecular encodings and deep learning models
Machine Learning for Kinase Drug Discovery Thema der Disputation:
Virtual screening in computer-aided drug discovery: molecular encodings and deep learning models
Abstract: Drug design is a time-consuming and expensive process that requires several iterations in the "design-make-test-analyse" cycle. In order to save time, costs, and reduce animal testing, computer-aided drug design (CADD) can be helpful in assisting diverse stages of drug campaigns.
In this talk, I will explain how virtual screening (VS), a mature CADD technique, can be applied to prioritize promising compounds. Since VS pipelines require a computational representation of molecular entities, I will describe methods to numerically encode molecular information, from the ligand, protein, and protein-ligand complex perspectives. Special focus will be given to protein kinases, a well-studied family of drug targets. Deep learning models in VS will be presented and open challenges in CADD will be discussed.
In this talk, I will explain how virtual screening (VS), a mature CADD technique, can be applied to prioritize promising compounds. Since VS pipelines require a computational representation of molecular entities, I will describe methods to numerically encode molecular information, from the ligand, protein, and protein-ligand complex perspectives. Special focus will be given to protein kinases, a well-studied family of drug targets. Deep learning models in VS will be presented and open challenges in CADD will be discussed.
Zeit & Ort
13.02.2023 | 13:00