Exploring the Terra incognita of AI ‐based domain classifications
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.
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)
Stichwörter der Autor:innen
Substanzen
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}
}
EUVIMED