Timezone: »

Generative modeling for protein structures
Namrata Anand · Possu Huang

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #120

Analyzing the structure and function of proteins is a key part of understanding biology at the molecular and cellular level. In addition, a major engineering challenge is to design new proteins in a principled and methodical way. Current computational modeling methods for protein design are slow and often require human oversight and intervention. Here, we apply Generative Adversarial Networks (GANs) to the task of generating protein structures, toward application in fast de novo protein design. We encode protein structures in terms of pairwise distances between alpha-carbons on the protein backbone, which eliminates the need for the generative model to learn translational and rotational symmetries. We then introduce a convex formulation of corruption-robust 3D structure recovery to fold the protein structures from generated pairwise distance maps, and solve these problems using the Alternating Direction Method of Multipliers. We test the effectiveness of our models by predicting completions of corrupted protein structures and show that the method is capable of quickly producing structurally plausible solutions.

Author Information

Namrata Anand (Stanford University)
Possu Huang (Stanford University)

More from the Same Authors

  • 2021 Workshop: Machine Learning in Structural Biology »
    Ellen Zhong · Raphael Townshend · Stephan Eismann · Namrata Anand · Roshan Rao · John Ingraham · Wouter Boomsma · Sergey Ovchinnikov · Bonnie Berger
  • 2020 Workshop: Machine Learning for Structural Biology »
    Raphael Townshend · Stephan Eismann · Ron Dror · Ellen Zhong · Namrata Anand · John Ingraham · Wouter Boomsma · Sergey Ovchinnikov · Roshan Rao · Per Greisen · Rachel Kolodny · Bonnie Berger