EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Structure Modeling Protocols for Protein Multimer and RNA in CASP16 With Enhanced MSAs , Model Ranking, and Deep Learning

Yuki Kagaya iD, Tsukasa Nakamura, Jacob Verburgt, Anika Jain, Genki Terashi, Pranav Punuru, Emilia Tugolukova, Joon Hong Park, Anouka Saha, David Huang, Daisuke Kihara iD

Proteins: Structure, Function, and Bioinformatics · 2026-01 · 94 (1) · 167-182

DOI: 10.1002/prot.70033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proteins: Structure, Function, and Bioinformatics, 2025-08. Verfasst von Yuki Kagaya und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biological Sciences, Purdue University, West Lafayette, Indiana, USA. Hauptthemen laut MEDLINE: Deep Learning, RNA, Computational Biology, Proteins. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, National Science Foundation, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present the methods and results of our protein complex and RNA structure predictions at CASP16. Our approach integrated multiple state‐of‐the‐art deep learning models with a consensus‐based scoring method. To enhance the depth of multiple sequence alignments (MSAs), we employed a large metagenomic sequence database. Model ranking was performed with a state‐of‐the‐art consensus ranking method, to which we added more scoring terms. These predictions were further refined manually based on literature evidence. For RNA, we adopted an ensemble approach that incorporated multiple state‐of‐the‐art methods, centered around our NuFold framework. As a result, our KiharaLab group ranked first in protein complex prediction and third in RNA structure prediction. A detailed analysis of targets that significantly differed from those of other groups highlighted both the strengths of our MSA and scoring strategies, as well as areas requiring further improvement.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningRNAComputational BiologyProteinsModels, MolecularSequence AlignmentNucleic Acid ConformationSoftwareDatabases, ProteinProtein ConformationProtein MultimerizationAlgorithms

Stichwörter der Autor:innen

CASPCASP16MSARNA structure predictionkiharalabmodel rankingprotein structure prediction

Substanzen

RNAProteins

Autor:innen und Institutionen

  • Department of Biological Sciences, Purdue University, West Lafayette, Indiana, USA.
  • Department of Computer Science, Purdue University, West Lafayette, Indiana, USA.
  • Department of Mathematics, The University of Texas, Austin, Texas, USA.

ORCID-Profile: Yuki Kagaya, Daisuke Kihara

Förderung

  • NIH HHS
  • National Science Foundation
  • NIGMS NIH HHS
  • National Institutes of Health
  • National Institute of General Medical Sciences

Zitieren

APA

Kagaya, Y., Nakamura, T., Verburgt, J., Jain, A., Terashi, G., Punuru, P., Tugolukova, E., Park, J. H., Saha, A., Huang, D., & Kihara, D. (2026). Structure Modeling Protocols for Protein Multimer and RNA in CASP16 With Enhanced MSAs , Model Ranking, and Deep Learning. Proteins: Structure, Function, and Bioinformatics, 94(1), 167-182. https://doi.org/10.1002/prot.70033

Vancouver

Kagaya Y, Nakamura T, Verburgt J, Jain A, Terashi G, Punuru P, et al. Structure Modeling Protocols for Protein Multimer and RNA in CASP16 With Enhanced MSAs , Model Ranking, and Deep Learning. Proteins: Structure, Function, and Bioinformatics. 2026;94(1):167-182. doi:10.1002/prot.70033

BibTeX
@article{Kagaya2026,
  author = {Kagaya, Yuki and Nakamura, Tsukasa and Verburgt, Jacob and Jain, Anika and Terashi, Genki and Punuru, Pranav and Tugolukova, Emilia and Park, Joon Hong and Saha, Anouka and Huang, David and Kihara, Daisuke},
  title = {Structure Modeling Protocols for Protein Multimer and RNA in CASP16 With Enhanced MSAs , Model Ranking, and Deep Learning},
  journal = {Proteins: Structure, Function, and Bioinformatics},
  year = {2026},
  volume = {94},
  number = {1},
  pages = {167--182},
  doi = {10.1002/prot.70033}
}
Kostenlos starten →