Speaker: Dibyendu Mondal
Topic: AlphaFold: a solution to a 50-year-old grand challenge in biology
Date & Time: Thursday, 7th October 2021 at 4:00 PM through MICROSOFT TEAMS.
Microsoft Teams Link:
Proteins are essential for life, and the working principles of a protein are embedded in its three dimensional structure. Extensive experimental efforts have been devoted to achieve a Protein Data Bank (PDB) of almost 0.1 million unique 3D structures of proteins. However, the number of available 3D structures is still a fraction of the billions of known protein sequences. Predicting the 3D structure of a protein solely based on its amino acid sequence is a challenging problem in ‘protein folding’, for more than 50 years.1, 2
In this talk, I will discuss AlphaFold, a computational method that uses a deep learning algorithm that includes physical and biological knowledge of protein structures in the form of multiple sequence alignment, for its design. AlphaFold is capable of predicting protein structures at atomic accuracy even in the absence of a similar structure in the database.1, 2, 3
- Jumper, J., Evans, R., Pritzel, A. Et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).
- Senior, A.W., Evans, R., Jumper, J. Et al. Improved protein structure prediction using potentials from deep learning. Nature 577, 706–710 (2020).
- Cramer, P. AlphaFold2 and the future of structural biology. Nat Struct Mol Biol 28, 704–705 (2021).