Skip to content

Details

Deepmind achieved a major breakthrough in biology by solving Protein folding problem that has stood as a grand challenge for the past 50 years. Alphafold 2 won the protein structure prediction challenge CASP 14 with more than 90% accuracy, speeding up the field for decades. We will read the Alphafold paper published in January 2020 and understand the role of deep learning in this achievement.

Paper abstract:
Protein structure prediction is of fundamental importance as the structure of a protein largely determines its function. But protein structures can be difficult to determine experimentally. We show that we can train a neural network to make accurate predictions of the distances between pairs of residues, which convey more information about the structure than contact predictions. We construct a potential of mean force that can accurately describe the shape of a protein. We find that the resulting potential can be optimized by a simple gradient descent algorithm to generate structures. The resulting system, named AlphaFold, achieves high accuracy, even for sequences with fewer homologous sequences. In the recent Critical Assessment of Protein Structure Prediction (CASP13), AlphaFold created high-accuracy structures for 24 out of 43 free modelling domains, whereas the next best method achieved such accuracy for only 14 out of 43 domains.

Paper to read:
Senior, Andrew W., Richard Evans, John Jumper, James Kirkpatrick, Laurent Sifre, Tim Green, Chongli Qin et al. "Improved protein structure prediction using potentials from deep learning." Nature 577, no. 7792 (2020) https://go.nature.com/3mrCVFv

Deepmind blog:

  1. Jan 15, 2020, "AlphaFold: Using AI for scientific discovery" https://deepmind.com/blog/article/AlphaFold-Using-AI-for-scientific-discovery
  2. Nov 30, 2020. "AlphaFold: a solution to a 50-year-old grand challenge in biology", https://deepmind.com/blog/article/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology

Discussion leader: Junling Hu

This is part of the weekly reading series. We come together to discuss cutting-edge AI topics and papers. One paper is selected as the major discussion topic. The meeting is led by one presenter, with group discussion and participation. Your video presence is required for attending this meeting.

7-7:15pm Meet and greet
7:15-8:15pm Paper presentation and group discussion
8:15-8:30 Additional discussions

You may also like