Skip to content
TU Dresden
A joint project with Uni Leipzig DE EN

Teaching artificial intelligence conformational dynamics of proteins

Mentored by Jens Meiler and Sayan Mukherjee
at Institute of Drug Discovery, Leipzig University and Institute for Informatics, Leipzig University / Max Planck Institute for Mathematics in the Sciences

Proteins adopt different conformations to fulfil diverse functions. In recent years, artificial intelligence (AI) has become a valuable tool for the exploration of protein structural dynamics. In particular, the AlphaFold2 platform provides high resolution 3-D structural information with high accuracy. However, it is crucial to select and validate the generated structures through comparison with experimental data. To this end, we will develop novel AI methods which integrate experimental datasets with structural models derived from AlphaFold2 or other computational structure prediction methods.

The two principal investigators of this project, Jens Meiler and Sayan Mukherjee, are leaders in the fields of computational protein structure prediction and AI, respectively. Moreover, the Meiler group has recently developed pipelines complementing computationally derived protein conformations with experimental data, such as electron paramagnetic resonance spectroscopy which has proven its capacity for the analysis of conformational ensembles. The Mukherjee group has recently developed theory and methodology for neural networks to model 3-D shapes and dynamics. The joint effort will expand on the challenge of teaching AI about protein flexibility, which closes a wide gap between structure prediction and structure-based drug discovery.

Work environment

The Interdisciplinary Center for Bioinformatics in Leipzig and cooperate with the machine learning and AI experts at the ScaDS.AI in Leipzig and Dresden. You will have access to machine-learning HPC resources of the ScaDS.AI Center for Scalable Data Analytics and AI Leipzig, offering state-of-the-art CPU (Intel and IBM POWER 9) and GPU (Nvidia A100 and V100) resources, as well as high-performance computing and storage systems for computational experiments.


The candidate will need a solid background in bioinformatics or structural biology as well as proficiency in scientific programming with Python and an interest in data analysis.