View in EDS

Predicting epistasis across proteins by structural logic.

Saved in:
Bibliographic Details
Title: Predicting epistasis across proteins by structural logic.
Authors: Tang, Michelle1, Cromie, Gareth A.1, Kabir, Anowarul2, Timour, Martin S.1, Ashmead, Julee1, Lo, Russell S.1, Corley, Nathaniel3, DiMaio, Frank3,4, Morizono, Hiroki5,6, Caldovic, Ljubica5,6, Mew, Nicholas Ah5,6, Gropman, Andrea7,8, Shehu, Amarda2, Dudley, Aimée M.1 aimee.dudley@gmail.com
Source: Proceedings of the National Academy of Sciences of the United States of America. 1/20/2026, Vol. 123 Issue 3, p1-10. 10p.
Subjects: Complementation (Genetics), Genetic variation, Machine learning, Proteins, Individualized medicine, Enzymes
Abstract: Accurately predicting the phenotypic consequences of genetic variation is a major challenge for precision medicine. The problem is exacerbated by epistatic interactions, nonadditive effects between genetic variants that produce unexpected phenotypes. Here, we explore an understudied form of positive epistasis: intragenic complementation, in which pairs of loss-of-function variants restore near wild-type protein function. Using mutational scanning in yeast, we identify thousands of such interactions in a clinically important enzyme, human argininosuccinate lyase (ASL). Restoration of protein function is not due to the biochemical properties of the substituted amino acids, but rather to a structural feature of the protein, the active site assembly. We develop a machine learning algorithm that uses protein language model embeddings to predict intragenic complementation in ASL with 99.6% accuracy. Additionally, the model trained on ASL generalizes to a structurally related but sequence-divergent enzyme, fumarase, with accuracy over 90%. Our findings reveal a structural basis for this form of epistasis and provide a predictive framework that could extend to at least 4% of human proteins. [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: 191190671
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Predicting epistasis across proteins by structural logic.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Tang%2C+Michelle%22">Tang, Michelle</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Cromie%2C+Gareth+A%2E%22">Cromie, Gareth A.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Kabir%2C+Anowarul%22">Kabir, Anowarul</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Timour%2C+Martin+S%2E%22">Timour, Martin S.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Ashmead%2C+Julee%22">Ashmead, Julee</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Lo%2C+Russell+S%2E%22">Lo, Russell S.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Corley%2C+Nathaniel%22">Corley, Nathaniel</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22DiMaio%2C+Frank%22">DiMaio, Frank</searchLink><relatesTo>3,4</relatesTo><br /><searchLink fieldCode="AR" term="%22Morizono%2C+Hiroki%22">Morizono, Hiroki</searchLink><relatesTo>5,6</relatesTo><br /><searchLink fieldCode="AR" term="%22Caldovic%2C+Ljubica%22">Caldovic, Ljubica</searchLink><relatesTo>5,6</relatesTo><br /><searchLink fieldCode="AR" term="%22Mew%2C+Nicholas+Ah%22">Mew, Nicholas Ah</searchLink><relatesTo>5,6</relatesTo><br /><searchLink fieldCode="AR" term="%22Gropman%2C+Andrea%22">Gropman, Andrea</searchLink><relatesTo>7,8</relatesTo><br /><searchLink fieldCode="AR" term="%22Shehu%2C+Amarda%22">Shehu, Amarda</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Dudley%2C+Aimée+M%2E%22">Dudley, Aimée M.</searchLink><relatesTo>1</relatesTo><i> aimee.dudley@gmail.com</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>. 1/20/2026, Vol. 123 Issue 3, p1-10. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Complementation+%28Genetics%29%22">Complementation (Genetics)</searchLink><br /><searchLink fieldCode="DE" term="%22Genetic+variation%22">Genetic variation</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Proteins%22">Proteins</searchLink><br /><searchLink fieldCode="DE" term="%22Individualized+medicine%22">Individualized medicine</searchLink><br /><searchLink fieldCode="DE" term="%22Enzymes%22">Enzymes</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurately predicting the phenotypic consequences of genetic variation is a major challenge for precision medicine. The problem is exacerbated by epistatic interactions, nonadditive effects between genetic variants that produce unexpected phenotypes. Here, we explore an understudied form of positive epistasis: intragenic complementation, in which pairs of loss-of-function variants restore near wild-type protein function. Using mutational scanning in yeast, we identify thousands of such interactions in a clinically important enzyme, human argininosuccinate lyase (ASL). Restoration of protein function is not due to the biochemical properties of the substituted amino acids, but rather to a structural feature of the protein, the active site assembly. We develop a machine learning algorithm that uses protein language model embeddings to predict intragenic complementation in ASL with 99.6% accuracy. Additionally, the model trained on ASL generalizes to a structurally related but sequence-divergent enzyme, fumarase, with accuracy over 90%. Our findings reveal a structural basis for this form of epistasis and provide a predictive framework that could extend to at least 4% of human proteins. [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=191190671
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1073/pnas.2516291123
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 1
    Subjects:
      – SubjectFull: Complementation (Genetics)
        Type: general
      – SubjectFull: Genetic variation
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Proteins
        Type: general
      – SubjectFull: Individualized medicine
        Type: general
      – SubjectFull: Enzymes
        Type: general
    Titles:
      – TitleFull: Predicting epistasis across proteins by structural logic.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Tang, Michelle
      – PersonEntity:
          Name:
            NameFull: Cromie, Gareth A.
      – PersonEntity:
          Name:
            NameFull: Kabir, Anowarul
      – PersonEntity:
          Name:
            NameFull: Timour, Martin S.
      – PersonEntity:
          Name:
            NameFull: Ashmead, Julee
      – PersonEntity:
          Name:
            NameFull: Lo, Russell S.
      – PersonEntity:
          Name:
            NameFull: Corley, Nathaniel
      – PersonEntity:
          Name:
            NameFull: DiMaio, Frank
      – PersonEntity:
          Name:
            NameFull: Morizono, Hiroki
      – PersonEntity:
          Name:
            NameFull: Caldovic, Ljubica
      – PersonEntity:
          Name:
            NameFull: Mew, Nicholas Ah
      – PersonEntity:
          Name:
            NameFull: Gropman, Andrea
      – PersonEntity:
          Name:
            NameFull: Shehu, Amarda
      – PersonEntity:
          Name:
            NameFull: Dudley, Aimée M.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 20
              M: 01
              Text: 1/20/2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 00278424
          Numbering:
            – Type: volume
              Value: 123
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Proceedings of the National Academy of Sciences of the United States of America
              Type: main
ResultId 1