About us

Lab Presentation: "The Computer-Assisted Drug Design Group at ETH Zurich", MedChemWatch (2011) 12:55-57.

Schneider, G. (2012) From theory to bench experiment by computer-assisted drug design. Chimia 66:120-124.

In tight combination with chemical synthesis and biochemical activity testing, computer-generated hypotheses and methods are assessed for their practical applicability in medicinal chemistry. At the heart of our studies lies the machine-driven de novo design of both individual candidate molecules and small focused compound libraries that exhibit a desired pharmacological activity profile.

Research studies also include drug re-purposing, target profile prediction, analysis of protein structure and modulation of protein-protein interaction, virtual screening and design of natural product analogs, peptide design, and the de-orphanization of drugs and their macromolecular receptors.

We run own state-of-the-art synthesis and testing facilities as well as a service point for virtual screening (SerViS).

Pattern Recognition & Molecular Design: From Models to Molecules

We develop automated, adaptive systems and software for multi-dimensional drug design, synthesis and characterization. Smart algorithms guide an evolutionary design process that constantly adapts to the fitness landscape by integrating new test results that are fed back in iterative synthesis-and-test cycles (active learning concept). Compounds are generated from readily available building blocks by straightforward (flow)chemistry in analytical or semi-preparative amounts, and subsequently tested for target binding or "bioactivity" in vitro.

The ultimate goal is to construct an unsupervised molecular design automaton generating "leads on demand".

Inductive hypothesis generation - an example:

Which feature separates these two classes of "molecules"? Find the classifier ("structure-activity-relationship") by inductive learning, and then design a new molecule for each class.