EUVIMEDEUVIMED entdecken
Open Access

Protein NMR assignment by isotope pattern recognition

Uluk Rasulov iD, Harrison K Wang iD, Thibault Viennet iD, Maxim A Droemer iD, Srđan Matosin iD, Sebastian Schindler iD, Zhen-Yu J Sun iD, Luca Mureddu iD, Geerten W Vuister iD, Scott A Robson iD, Haribabu Arthanari iD, Ilya Kuprov iD

Science Advances · 06.09.2024 · 10 (36)

DOI: 10.1126/sciadv.ado0403 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 06.09.2024. Verfasst von Uluk Rasulov und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Chemistry, University of Southampton, University Road, Southampton SO17 1BJ, UK. Hauptthemen laut MEDLINE: Proteins. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The current standard method for amino acid signal identification in protein NMR spectra is sequential assignment using triple-resonance experiments. Good software and elaborate heuristics exist, but the process remains laboriously manual. Machine learning does help, but its training databases need millions of samples that cover all relevant physics and every kind of instrumental artifact. In this communication, we offer a solution to this problem. We propose polyadic decompositions to store millions of simulated three-dimensional NMR spectra, on-the-fly generation of artifacts during training, a probabilistic way to incorporate prior and posterior information, and integration with the industry standard CcpNmr software framework. The resulting neural nets take [ 1 H, 13 C] slices of mixed pyruvate–labeled HNCA spectra (different CA signal shapes for different residue types) and return an amino acid probability table. In combination with primary sequence information, backbones of common proteins (GB1, MBP, and INMT) are rapidly assigned from just the HNCA spectrum.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsNuclear Magnetic Resonance, BiomolecularSoftwareAmino AcidsAlgorithmsIsotopesMachine Learning

Substanzen

ProteinsAmino AcidsIsotopes

Autor:innen und Institutionen

  • School of Chemistry, University of Southampton, University Road, Southampton SO17 1BJ, UK.
  • Department of Biochemistry and Molecular Pharmacology, Harvard Medical School, Boston, MA 02115, USA.
  • Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA 02215, USA.
  • Department of Chemistry and iNANO, Aarhus University, Langelandsgade 140, 8000 Aarhus C, Denmark.
  • Faculty for Chemistry and Pharmacy, Ludwig-Maximilians-Universität München, Munich, Germany.
  • Department of Molecular and Cell Biology, Institute for Structural and Chemical Biology, University of Leicester, Lancaster Road, Leicester LE1 7HB, UK.

ORCID-Profile: Uluk Rasulov, Harrison K Wang, Thibault Viennet, Maxim A Droemer, Srđan Matosin, Sebastian Schindler, Zhen-Yu J Sun, Luca Mureddu, Geerten W Vuister, Scott A Robson, Haribabu Arthanari, Ilya Kuprov

Förderung

  • NIGMS NIH HHS

Zitieren

APA

Rasulov, U., Wang, H. K., Viennet, T., Droemer, M. A., Matosin, S., Schindler, S., Sun, Z. J., Mureddu, L., Vuister, G. W., Robson, S. A., Arthanari, H., & Kuprov, I. (2024). Protein NMR assignment by isotope pattern recognition. Science Advances, 10(36). https://doi.org/10.1126/sciadv.ado0403

Vancouver

Rasulov U, Wang HK, Viennet T, Droemer MA, Matosin S, Schindler S, et al. Protein NMR assignment by isotope pattern recognition. Science Advances. 2024;10(36). doi:10.1126/sciadv.ado0403

BibTeX
@article{Rasulov2024,
  author = {Rasulov, Uluk and Wang, Harrison K and Viennet, Thibault and Droemer, Maxim A and Matosin, Srđan and Schindler, Sebastian and Sun, Zhen-Yu J and Mureddu, Luca and Vuister, Geerten W and Robson, Scott A and Arthanari, Haribabu and Kuprov, Ilya},
  title = {Protein NMR assignment by isotope pattern recognition},
  journal = {Science Advances},
  year = {2024},
  volume = {10},
  number = {36},
  doi = {10.1126/sciadv.ado0403}
}
Kostenlos starten →