Deep learning in life science 1000-2M23DLS

Introduction:
1. Intro and Mathematical foundation to DL
2. Convolutional and Recurrent neural networks
3. Autoencoders and variational autoencoders
4. Attention mechanisms and transformers
Genomics:
5. Transformers and RNN for sequence analysis
6. Models for multimodal data integration
7. VAE in single-cell genomics
Protein Structure:
8. AlphaFold, EMSFold to predict structure of proteins
9. RNN, CNN models for topology/graph analysis in biopolymers
10. Deep learning models for protein-ligand binding site prediction
11. Diffusion models for protein design
BioImage analysis:
12.Intro to BioImage Analysis and Deep Learning Utilization
13.Deep Architectures for sampling macromolecules
14. Deep learning for segmentation

The credits for the course are granted based on homeworks done throughout the semester. The best students will be able to go in June to the hackathon in Heidelberg.