EUVIMEDEUVIMED entdecken
Open Access

Discovery of unconventional and nonintuitive self-assembling peptide materials using experiment-driven machine learning

Y Nissi Talluri iD, Subramanian Krs Sankaranarayanan iD, H Christopher Fry, Rohit Batra iD

Science Advances · 13.06.2025 · 11 (24)

DOI: 10.1126/sciadv.adt9466 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 13.06.2025. Verfasst von Y Nissi Talluri und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Metallurgical and Materials Engineering, Indian Institute of Technology Madras, Chennai 600036, India. Hauptthemen laut MEDLINE: Machine Learning, Peptides. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prediction of peptide secondary structure is challenging because of complex molecular interactions, sequence-specific behavior, and environmental factors. Traditional design strategies, based on hydrophobicity and structural propensity, can be biased and could indeed prevent discovery of interesting, diverse, and unconventional peptides with desired nanostructure assembly. Using β sheet formation in pentapeptides as a case study, we used an integrated high-throughput experimental workflow and an artificial intelligence–driven active learning framework to improve prediction accuracy of self-assembly. By focusing on sequences where machine learning (ML) predictions deviate from conventional design strategies, we synthesized and tested 268 pentapeptides, successfully finding 96 forming β sheet assemblies, including unconventional sequences (e.g., ILFSM, LMISI, MITIY, MISIW, and WKIYI) not predicted by traditional methods. Our ML models outperformed conventional β sheet propensity tables, revealing useful chemical design rules. A web interface is provided to facilitate community access to these models. This work highlights the value of ML-driven approaches in overcoming the limitations of current peptide design strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPeptidesHydrophobic and Hydrophilic InteractionsProtein Conformation, beta-StrandAmino Acid Sequence

Substanzen

Peptides

Autor:innen und Institutionen

  • Department of Metallurgical and Materials Engineering, Indian Institute of Technology Madras, Chennai 600036, India.
  • Center for Nanoscale Materials, Argonne National Laboratory, Lemont, IL 60439, USA.
  • Department of Mechanical and Industrial Engineering, University of Illinois, Chicago, IL 60607, USA.
  • Center for Atomistic Modelling and Materials Design, IIT Madras, Chennai 600036, India.

ORCID-Profile: Y Nissi Talluri, Subramanian Krs Sankaranarayanan, Rohit Batra

Zitieren

APA

Talluri, Y. N., Sankaranarayanan, S. K., Fry, H. C., & Batra, R. (2025). Discovery of unconventional and nonintuitive self-assembling peptide materials using experiment-driven machine learning. Science Advances, 11(24). https://doi.org/10.1126/sciadv.adt9466

Vancouver

Talluri YN, Sankaranarayanan SK, Fry HC, Batra R. Discovery of unconventional and nonintuitive self-assembling peptide materials using experiment-driven machine learning. Science Advances. 2025;11(24). doi:10.1126/sciadv.adt9466

BibTeX
@article{Talluri2025,
  author = {Talluri, Y Nissi and Sankaranarayanan, Subramanian Krs and Fry, H Christopher and Batra, Rohit},
  title = {Discovery of unconventional and nonintuitive self-assembling peptide materials using experiment-driven machine learning},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {24},
  doi = {10.1126/sciadv.adt9466}
}
Kostenlos starten →