EUVIMEDEUVIMED entdecken
Open Access

Exploring the Terra incognita of AI ‐based domain classifications

Jimin Pei iD, Antonina Andreeva iD, Tiago Grego iD, Sara Chuguransky iD, Beatriz Lázaro Pinto iD, Nicole Morvelli Flores iD, Typhaine Paysan-Lafosse iD, Richard Dustin Schaeffer iD, Alex Bateman iD, Qian Cong iD, Nick V Grishin

Protein Science · 2025

DOI: 10.1002/pro.70392 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Protein Science, 2025. Verfasst von Jimin Pei und 10 weiteren Autor:innen. Beteiligte Einrichtung: Eugene McDermott Center for Human Growth and Development, University of Texas Southwestern Medical Center, Dallas, Texas, USA. Hauptthemen laut MEDLINE: Proteins, Computational Biology. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Science Foundation, NIH HHS, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The classification of novel protein folds remains a central challenge in structural bioinformatics, particularly as deep learning models like AlphaFold2 dramatically expand the universe of predicted protein structures. In this study, we investigated 664 candidate novel fold (CNF) domains from the TED database that both TED and DPAM methods had classified with low confidence. These CNFs span a structurally diverse and largely non‐redundant set of domains, most of which lack clear sequence or structural similarity to known folds. Many CNFs appear as insertions into known transmembrane or enzymatic domains, while others occur in modular architectures, co‐occurring with interaction or catalytic folds such as β‐barrels, zinc fingers, or Rossmann‐like domains. Although some CNFs resemble known folds that have undergone topological rearrangements or circular permutations, others result from errors in domain boundary prediction, often due to truncated sequences or tightly packed domain duplications. Our analyses led to the creation of 190 new Pfam families, many classified as domains of unknown function (DUFs), and revealed intriguing cases of zinc‐binding and disulfide‐rich architectures that contribute to fold space expansion. A small subset of CNFs helped define new superfamilies by linking previously unclassified but structurally related domains. Taken together, this work underscores the importance of integrating structural, evolutionary, and contextual information to resolve challenging fold assignments and provides a roadmap for extending protein classification frameworks into previously uncharted structural territory.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologyProtein FoldingDatabases, ProteinProtein DomainsModels, Molecular

Stichwörter der Autor:innen

DPAMPfam familyTEDcandidate novel folddisulfide‐rich domainsdomain of unknown function (DUF)protein domain classificationzinc finger domains

Substanzen

Proteins

Autor:innen und Institutionen

  • Eugene McDermott Center for Human Growth and Development, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
  • Department of Biophysics, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
  • Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
  • European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, UK.
  • Department of Biochemistry, University of Texas Southwestern Medical Center, Dallas, Texas, USA.

ORCID-Profile: Jimin Pei, Antonina Andreeva, Tiago Grego, Sara Chuguransky, Beatriz Lázaro Pinto, Nicole Morvelli Flores, Typhaine Paysan-Lafosse, Richard Dustin Schaeffer, Alex Bateman, Qian Cong

Förderung

  • National Science Foundation
  • NIH HHS
  • NIGMS NIH HHS
  • Biotechnology and Biological Sciences Research Council
  • Welch Foundation
  • National Institutes of Health

Zitieren

APA

Pei, J., Andreeva, A., Grego, T., Chuguransky, S., Pinto, B. L., Flores, N. M., Paysan-Lafosse, T., Schaeffer, R. D., Bateman, A., Cong, Q., & Grishin, N. V. (2025). Exploring the Terra incognita of AI ‐based domain classifications. Protein Science. https://doi.org/10.1002/pro.70392

Vancouver

Pei J, Andreeva A, Grego T, Chuguransky S, Pinto BL, Flores NM, et al. Exploring the Terra incognita of AI ‐based domain classifications. Protein Science. 2025. doi:10.1002/pro.70392

BibTeX
@article{Pei2025,
  author = {Pei, Jimin and Andreeva, Antonina and Grego, Tiago and Chuguransky, Sara and Pinto, Beatriz Lázaro and Flores, Nicole Morvelli and Paysan-Lafosse, Typhaine and Schaeffer, Richard Dustin and Bateman, Alex and Cong, Qian and Grishin, Nick V},
  title = {Exploring the Terra incognita of AI ‐based domain classifications},
  journal = {Protein Science},
  year = {2025},
  doi = {10.1002/pro.70392}
}
Kostenlos starten →