EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY-NC 4.0

Pathway‐Informed Machine Learning Identifies Genetic Predictors of High‐Dose Methotrexate‐Induced Mucositis in Pediatric Acute Lymphoblastic Leukemia

Xiao Yu Cindy Zhang iD, Erika N Scott iD, Hedy Maagdenberg iD, Alice Man iD, Kathy H Li, S Rod Rassekh iD, Bruce C Carleton iD, Colin J D Ross iD, Wyeth W Wasserman iD, Catrina M Loucks iD

Clinical Pharmacology & Therapeutics · 2026

DOI: 10.1002/cpt.70135 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Clinical Pharmacology & Therapeutics, 2026. Verfasst von Xiao Yu Cindy Zhang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Bioinformatics Graduate Program, University of British Columbia, Vancouver, British Columbia, Canada. Hauptthemen laut MEDLINE: Methotrexate, Precursor Cell Lymphoblastic Leukemia-Lymphoma, Mucositis, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Canadian Institutes of Health Research (CIHR) through a Canada Graduate Scholarships-Master's Program, Natural Sciences and Engineering Research Council (NSERC) Discovery Grant, BC Children's Hospital Research Institute (BCCHR) Doctoral Studentship.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High‐dose methotrexate for pediatric cancer treatment is frequently associated with mucositis, which can lead to delayed or discontinued treatment and impact survival. While individual genetic variants have been implicated, the cumulative impact of genetic variation within relevant biological pathways remains unexplored. We evaluated single nucleotide polymorphisms across 18 pathways previously identified as relevant to mucositis in 278 pediatric patients with acute lymphoblastic leukemia from six academic health centers across Canada. Pathway enrichment was assessed using the Joint Association of Genetic variants tool, and a predictive model was developed using XGBoost, a supervised machine learning algorithm based on gradient‐boosted decision trees. Pathway enrichment identified significant associations in IL6 ( P = 0.04) and WNT/β‐catenin ( P = 0.048) signaling pathways. The predictive model (area under the curve [AUC] = 0.76) highlighted single nucleotide polymorphisms associated with inflammation‐ and mucosa‐related genes, including PRKCD , IL17B , MAST3 , and CAPN9 , with both risk and protective effects. Model performance dropped by 0.15 in AUC (from 0.76 to 0.61) after removing single nucleotide polymorphism features, underscoring their predictive value. This pathway‐informed approach identifies genetic contributors to methotrexate‐induced mucositis and supports polygenic risk prediction. Our findings provide a foundation for individualized toxicity risk profiling and suggest potential therapeutic targets to mitigate treatment‐limiting mucositis in pediatric oncology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MethotrexatePrecursor Cell Lymphoblastic Leukemia-LymphomaMucositisMachine LearningAntimetabolites, AntineoplasticHumansPolymorphism, Single NucleotideChildMaleFemaleChild, PreschoolAdolescentInfantCanada

Substanzen

MethotrexateAntimetabolites, Antineoplastic

Autor:innen und Institutionen

  • Bioinformatics Graduate Program, University of British Columbia, Vancouver, British Columbia, Canada.
  • British Columbia Children's Hospital Research Institute, Vancouver, British Columbia, Canada.
  • Division of Translational Therapeutics, Department of Pediatrics, Faculty of Medicine, University of British Columbia, Vancouver, British Columbia, Canada.
  • Department of Respiratory Medicine, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, The Netherlands.
  • Division of Pharmacoepidemiology and Clinical Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Faculty of Science, Utrecht University, Utrecht, The Netherlands.
  • Department of Medicine, McMaster University, Hamilton, Ontario, Canada.

ORCID-Profile: Xiao Yu Cindy Zhang, Erika N Scott, Hedy Maagdenberg, Alice Man, S Rod Rassekh, Bruce C Carleton, Colin J D Ross, Wyeth W Wasserman, Catrina M Loucks

Förderung

  • Canadian Institutes of Health Research (CIHR) through a Canada Graduate Scholarships-Master's Program
  • Natural Sciences and Engineering Research Council (NSERC) Discovery Grant
  • BC Children's Hospital Research Institute (BCCHR) Doctoral Studentship
  • Genome Canada
  • Genome British Columbia
  • CIHR
  • British Columbia's Provincial Health Services Authority (PHSA)
  • BC Children's Hospital Foundation

Zitieren

APA

Zhang, X. Y. C., Scott, E. N., Maagdenberg, H., Man, A., Li, K. H., Rassekh, S. R., Carleton, B. C., Ross, C. J. D., Wasserman, W. W., & Loucks, C. M. (2026). Pathway‐Informed Machine Learning Identifies Genetic Predictors of High‐Dose Methotrexate‐Induced Mucositis in Pediatric Acute Lymphoblastic Leukemia. Clinical Pharmacology & Therapeutics. https://doi.org/10.1002/cpt.70135

Vancouver

Zhang XYC, Scott EN, Maagdenberg H, Man A, Li KH, Rassekh SR, et al. Pathway‐Informed Machine Learning Identifies Genetic Predictors of High‐Dose Methotrexate‐Induced Mucositis in Pediatric Acute Lymphoblastic Leukemia. Clinical Pharmacology & Therapeutics. 2026. doi:10.1002/cpt.70135

BibTeX
@article{Zhang2026,
  author = {Zhang, Xiao Yu Cindy and Scott, Erika N and Maagdenberg, Hedy and Man, Alice and Li, Kathy H and Rassekh, S Rod and Carleton, Bruce C and Ross, Colin J D and Wasserman, Wyeth W and Loucks, Catrina M},
  title = {Pathway‐Informed Machine Learning Identifies Genetic Predictors of High‐Dose Methotrexate‐Induced Mucositis in Pediatric Acute Lymphoblastic Leukemia},
  journal = {Clinical Pharmacology & Therapeutics},
  year = {2026},
  doi = {10.1002/cpt.70135}
}
Kostenlos starten →