Data Driven Design of Protein Function

Abstract

Our research first focused on a design task: designing mini-proteins that are stable, without requiring them to be functional. This work involved designing, testing, and learning from hundreds of thousands of mini-proteins, and resulted in machine learning (ML) models that are predictive of stability, as well as improvements to Rosetta's energy function. In the last two years, we have advanced to substantially more difficult tasks: designing proteins that are both stable and bind to a protein or DNA target. This work involved testing hundreds of thousands of binders, has resulted in dramatic increases to our success rates, and has provided several high-throughput datasets for future learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 24, 2022
Accession Number
AD1164648

Entities

People

  • David Baker
  • Hugh Haddox
  • Ian C Haydon
  • Kristina Herrera
  • Lance Stewart

Organizations

  • University of Washington

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Acids
  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Amino Acids
  • Chemical Reactions
  • Computer Programs
  • Covid-19
  • Deoxyribonucleic Acids
  • Disease Outbreaks
  • Diseases And Disorders
  • Hydrophobic Properties
  • Infection
  • Infectious Diseases
  • Learning
  • Machine Learning
  • Manufacturing
  • Mrna Vaccines
  • Sars
  • Standards
  • Throughput
  • Vaccines
  • Viruses

Fields of Study

  • Computer science

Readers

  • Molecular Genetics
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks