View in EDS

Rapid and automated design of two-component protein nanomaterials using ProteinMPNN.

Saved in:
Bibliographic Details
Title: Rapid and automated design of two-component protein nanomaterials using ProteinMPNN.
Authors: de Haas, Robbert J.1, Brunette, Natalie2,3, Goodson, Alex2,3, Dauparas, Justas2,3, Yi, Sue Y.2,3, Yang, Erin C.2,3, Dowling, Quinton2,3, Nguyen, Hannah2,3, Kang, Alex2,3, Bera, Asim K.2,3, Sankaran, Banumathi4, de Vries, Renko1, Baker, David2,3,5, King, Neil P.2,3 neilking@uw.edu
Source: Proceedings of the National Academy of Sciences of the United States of America. 3/26/2024, Vol. 121 Issue 13, p1-9. 36p.
Subjects: Protein engineering, Learning ability testing, Protein biotechnology, Nanostructured materials, Amino acid sequence
Abstract: The design of protein-protein interfaces using physics-based design methods such as Rosetta requires substantial computational resources and manual refinement by expert structural biologists. Deep learning methods promise to simplify protein--protein interface design and enable its application to a wide variety of problems by researchers from various scientific disciplines. Here, we test the ability of a deep learning method for protein sequence design, ProteinMPNN, to design two-component tetrahedral protein nanomaterials and benchmark its performance against Rosetta. ProteinMPNN had a similar success rate to Rosetta, yielding 13 new experimentally confirmed assemblies, but required orders of magnitude less computation and no manual refinement. The interfaces designed by ProteinMPNN were substantially more polar than those designed by Rosetta, which facilitated in vitro assembly of the designed nanomaterials from independently purified components. Crystal structures of several of the assemblies confirmed the accuracy of the design method at high resolution. Our results showcase the potential of deep learning--based methods to unlock the widespread application of designed protein--protein interfaces and self-assembling protein nanomaterials in biotechnology. [ABSTRACT FROM AUTHOR]
Copyright of Proceedings of the National Academy of Sciences of the United States of America is the property of National Academy of Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 176568119
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Rapid and automated design of two-component protein nanomaterials using ProteinMPNN.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22de+Haas%2C+Robbert+J%2E%22">de Haas, Robbert J.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Brunette%2C+Natalie%22">Brunette, Natalie</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Goodson%2C+Alex%22">Goodson, Alex</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Dauparas%2C+Justas%22">Dauparas, Justas</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Yi%2C+Sue+Y%2E%22">Yi, Sue Y.</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Yang%2C+Erin+C%2E%22">Yang, Erin C.</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Dowling%2C+Quinton%22">Dowling, Quinton</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Nguyen%2C+Hannah%22">Nguyen, Hannah</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Kang%2C+Alex%22">Kang, Alex</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Bera%2C+Asim+K%2E%22">Bera, Asim K.</searchLink><relatesTo>2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Sankaran%2C+Banumathi%22">Sankaran, Banumathi</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22de+Vries%2C+Renko%22">de Vries, Renko</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Baker%2C+David%22">Baker, David</searchLink><relatesTo>2,3,5</relatesTo><br /><searchLink fieldCode="AR" term="%22King%2C+Neil+P%2E%22">King, Neil P.</searchLink><relatesTo>2,3</relatesTo><i> neilking@uw.edu</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Proceedings+of+the+National+Academy+of+Sciences+of+the+United+States+of+America%22">Proceedings of the National Academy of Sciences of the United States of America</searchLink>. 3/26/2024, Vol. 121 Issue 13, p1-9. 36p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Protein+engineering%22">Protein engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Learning+ability+testing%22">Learning ability testing</searchLink><br /><searchLink fieldCode="DE" term="%22Protein+biotechnology%22">Protein biotechnology</searchLink><br /><searchLink fieldCode="DE" term="%22Nanostructured+materials%22">Nanostructured materials</searchLink><br /><searchLink fieldCode="DE" term="%22Amino+acid+sequence%22">Amino acid sequence</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The design of protein-protein interfaces using physics-based design methods such as Rosetta requires substantial computational resources and manual refinement by expert structural biologists. Deep learning methods promise to simplify protein--protein interface design and enable its application to a wide variety of problems by researchers from various scientific disciplines. Here, we test the ability of a deep learning method for protein sequence design, ProteinMPNN, to design two-component tetrahedral protein nanomaterials and benchmark its performance against Rosetta. ProteinMPNN had a similar success rate to Rosetta, yielding 13 new experimentally confirmed assemblies, but required orders of magnitude less computation and no manual refinement. The interfaces designed by ProteinMPNN were substantially more polar than those designed by Rosetta, which facilitated in vitro assembly of the designed nanomaterials from independently purified components. Crystal structures of several of the assemblies confirmed the accuracy of the design method at high resolution. Our results showcase the potential of deep learning--based methods to unlock the widespread application of designed protein--protein interfaces and self-assembling protein nanomaterials in biotechnology. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Proceedings of the National Academy of Sciences of the United States of America is the property of National Academy of Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=176568119
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1073/pnas.2314646121
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 36
        StartPage: 1
    Subjects:
      – SubjectFull: Protein engineering
        Type: general
      – SubjectFull: Learning ability testing
        Type: general
      – SubjectFull: Protein biotechnology
        Type: general
      – SubjectFull: Nanostructured materials
        Type: general
      – SubjectFull: Amino acid sequence
        Type: general
    Titles:
      – TitleFull: Rapid and automated design of two-component protein nanomaterials using ProteinMPNN.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: de Haas, Robbert J.
      – PersonEntity:
          Name:
            NameFull: Brunette, Natalie
      – PersonEntity:
          Name:
            NameFull: Goodson, Alex
      – PersonEntity:
          Name:
            NameFull: Dauparas, Justas
      – PersonEntity:
          Name:
            NameFull: Yi, Sue Y.
      – PersonEntity:
          Name:
            NameFull: Yang, Erin C.
      – PersonEntity:
          Name:
            NameFull: Dowling, Quinton
      – PersonEntity:
          Name:
            NameFull: Nguyen, Hannah
      – PersonEntity:
          Name:
            NameFull: Kang, Alex
      – PersonEntity:
          Name:
            NameFull: Bera, Asim K.
      – PersonEntity:
          Name:
            NameFull: Sankaran, Banumathi
      – PersonEntity:
          Name:
            NameFull: de Vries, Renko
      – PersonEntity:
          Name:
            NameFull: Baker, David
      – PersonEntity:
          Name:
            NameFull: King, Neil P.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 26
              M: 03
              Text: 3/26/2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 00278424
          Numbering:
            – Type: volume
              Value: 121
            – Type: issue
              Value: 13
          Titles:
            – TitleFull: Proceedings of the National Academy of Sciences of the United States of America
              Type: main
ResultId 1