EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine learning methods and harmonized datasets improve immunogenic neoantigen prediction

Markus Müller, Florian Huber, Marion Arnaud, Anne I Kraemer, Emma Ricart Altimiras, Justine Michaux, Marie Taillandier-Coindard, Johanna Chiffelle, Baptiste Murgues, Talita Gehret, Aymeric Auger, Brian J Stevenson und 3 weitere

Immunity · 2023-11 · 56 (11) · 2650-2663.e6

DOI: 10.1016/j.immuni.2023.09.002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Immunity, 2023-11. Verfasst von Markus Müller und 14 weiteren Autor:innen. Beteiligte Einrichtung: Ludwig Institute for Cancer Research, University of Lausanne, Agora Center Bugnon 25A, 1005 Lausanne, Switzerland; Department of Oncology, Centre hos…. Hauptthemen laut MEDLINE: Antigens, Neoplasm, Neoplasms. Die Arbeit wurde bisher 114-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Swiss Cancer Research Foundation, Fondation ISREC, Ludwig Institute for Cancer Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate selection of neoantigens that bind to class I human leukocyte antigen (HLA) and are recognized by autologous T cells is a crucial step in many cancer immunotherapy pipelines. We reprocessed whole-exome sequencing and RNA sequencing (RNA-seq) data from 120 cancer patients from two external large-scale neoantigen immunogenicity screening assays combined with an in-house dataset of 11 patients and identified 46,017 somatic single-nucleotide variant mutations and 1,781,445 neo-peptides, of which 212 mutations and 178 neo-peptides were immunogenic. Beyond features commonly used for neoantigen prioritization, factors such as the location of neo-peptides within protein HLA presentation hotspots, binding promiscuity, and the role of the mutated gene in oncogenicity were predictive for immunogenicity. The classifiers accurately predicted neoantigen immunogenicity across datasets and improved their ranking by up to 30%. Besides insights into machine learning methods for neoantigen ranking, we have provided homogenized datasets valuable for developing and benchmarking companion algorithms for neoantigen-based immunotherapies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Antigens, NeoplasmNeoplasmsHumansHistocompatibility Antigens Class IMachine LearningPeptidesImmunotherapy

Stichwörter der Autor:innen

cancer immunotherapymachine learningneoantigen prioritizationpersonalized cancer vaccine

Substanzen

Antigens, NeoplasmHistocompatibility Antigens Class IPeptides

Autor:innen und Institutionen

  • Ludwig Institute for Cancer Research, University of Lausanne, Agora Center Bugnon 25A, 1005 Lausanne, Switzerland; Department of Oncology, Centre hospitalier universitaire vaudois (CHUV), Rue du Bugnon 46, 1005 Lausanne…
  • Agora Cancer Research Centre, 1011 Lausanne, Switzerland; SIB Swiss Institute of Bioinformatics, Quartier Sorge, Bâtiment Amphipôle, 1015 Lausanne, Switzerland.

Förderung

  • Swiss Cancer Research Foundation
  • Fondation ISREC
  • Ludwig Institute for Cancer Research
  • Swiss Cancer Foundation
  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Zitieren

APA

Müller, M., Huber, F., Arnaud, M., Kraemer, A. I., Altimiras, E. R., Michaux, J., Taillandier-Coindard, M., Chiffelle, J., Murgues, B., Gehret, T., Auger, A., Stevenson, B. J., Coukos, G., Harari, A., & Bassani-Sternberg, M. (2023). Machine learning methods and harmonized datasets improve immunogenic neoantigen prediction. Immunity, 56(11), 2650-2663.e6. https://doi.org/10.1016/j.immuni.2023.09.002

Vancouver

Müller M, Huber F, Arnaud M, Kraemer AI, Altimiras ER, Michaux J, et al. Machine learning methods and harmonized datasets improve immunogenic neoantigen prediction. Immunity. 2023;56(11):2650-2663.e6. doi:10.1016/j.immuni.2023.09.002

BibTeX
@article{Mller2023,
  author = {Müller, Markus and Huber, Florian and Arnaud, Marion and Kraemer, Anne I and Altimiras, Emma Ricart and Michaux, Justine and Taillandier-Coindard, Marie and Chiffelle, Johanna and Murgues, Baptiste and Gehret, Talita and Auger, Aymeric and Stevenson, Brian J and Coukos, George and Harari, Alexandre and Bassani-Sternberg, Michal},
  title = {Machine learning methods and harmonized datasets improve immunogenic neoantigen prediction},
  journal = {Immunity},
  year = {2023},
  volume = {56},
  number = {11},
  pages = {2650--2663.e6},
  doi = {10.1016/j.immuni.2023.09.002}
}
Kostenlos starten →