Karel Berka and Marian Novotný - Alphafoldology - Machine Learning revolution in structural biology

Karel Berka (PřF UPOL) and Marian Novotný (PřF UK) presents Alphafoldology - Machine Learning revolution in structural biology

An algorithm Alphafold has been named by Science journal a scientific breakthrough of the year 2021 - the Alphafold algorithm predicted 3D structures of proteins from sequence better than its competitors in CATH competition in a quality indistinguishable from the experimental structure.

Since late 2020, Alphafold has been used to predict 3D structures under various scenarios, including those it has not been trained for at all. A database of Alphafold models has been built for common use in July 2021 and other tools have been adopted to a new reality of having a powerful tool to predict 3D structure from literally any protein sequence.

We slowly start to gather answers to the following questions:
- How does Alphafold actually work?
- How difficult is it to run Alphafold with my data?
- How to interpret the Alphafold models?
- What tasks are still difficult for Alphafold?
- Would we still need experimental protein structure determination?

In our lecture, we will try to address these questions as much as we can say based on our hands-on experience with protein structure models.

Keywords: AlphaFold Database (13181), Alphafold, Structures (structures), protein-3D-structure, Machine learning

Status: Active

Authors: Karel Berka, Marian Novotny

Scientific topics: Structure prediction, Structural biology, Machine learning

Activity log