EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

XGBoost-SHAP analysis prioritizes lower-frequency variants predicted to affect HNF4A binding motifs in pancreatic progenitors

Kelly A Frazer, Benjamin Henson, Jennifer P Nguyen, Wilfredo G Gonzalez Rivera iD, Matteo D'Antonio iD

PLOS Genetics · 04.11.2026 · 22 (11) · e1012361

DOI: 10.1371/journal.pgen.1012361 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Genetics, online erschienen am 04.11.2026. Verfasst von Kelly A Frazer und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Genomic Medicine, University of California San Diego, Gilman Dr, La Jolla, California, United States of America. Hauptthemen laut MEDLINE: Hepatocyte Nuclear Factor 4, Pancreas. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDDK NIH HHS, NHGRI NIH HHS, NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Noncoding genetic variants underlie many complex traits, yet predicting their regulatory impact in cell type-specific contexts remains a major challenge. Transcription factor binding is a primary mechanism through which noncoding variants influence gene regulation, but the relationships among chromatin accessibility, variant frequency, and transcription factor binding are complex and nonlinear, limiting the performance of traditional linear models.

Methods

We generated single-nucleus ATAC sequencing data from seven induced pluripotent stem cell-derived pancreatic progenitor cell samples and identified 93,803 heterozygous single nucleotide polymorphisms overlapping accessible chromatin regions. Allele-specific effects (ASE) were quantified for each variant via binomial tests. We trained XGBoost, logistic regression, and regularized logistic regression models to predict allele-specific effects via chromatin read depth, peak score, variant minor allele frequency (MAF), and transcription factor binding prediction for five pancreatic transcription factors: HNF4A, HNF1A, NEUROD1, NKX6-1, and PDX1. Model performance was assessed by the area under the receiver operating characteristic curve (AUC) via fivefold cross-validation as well as using test and validation SNP sets. Shapley (SHAP) value analysis was used to interpret model predictions and to cluster variants on the basis of their regulatory feature contributions.

Results

XGBoost significantly outperformed linear models, particularly at stringent allele-specific effect thresholds, consistent with its ability to capture nonlinear interactions among features. Chromatin read depth, peak score, and minor allele frequency were the strongest predictors. Stratification by read-depth and MAF deciles showed that XGBoost retained better overall predictive performance across deciles than the linear models, indicating that its advantage was not explained by these variables alone. Dimensionality reduction of variants on the basis of Shapley value profiles revealed seven clusters with distinct chromatin states and variant allele frequencies. These findings were supported by highly significant pairwise differences in allele frequency distributions across the seven clusters. One cluster was enriched for lower-MAF SNPs showing strong predicted interactions with HNF4A binding motifs. Because MAF and its SHAP contribution were inputs to the embedding, the lower-MAF identity of this cluster was expected; its high ASE enrichment and distinctive HNF4A interaction structure were the biologically informative findings. Combined Annotation Dependent Depletion (CADD) analyses further supported a stronger relationship between HNF4A-related predictions and predicted deleteriousness in this cluster.

Conclusions

Integration of single-nucleus chromatin accessibility data with an interpretable XGBoost-SHAP framework provides a method for prioritizing noncoding variants and identifying nonlinear regulatory relationships in a specific developmental context. Within this framework, the stronger relationship between HNF4A-related predictions and CADD-predicted deleteriousness in the lower-MAF cluster is consistent with selective constraint on HNF4A-bound regulatory elements and suggests a hypothesis for how lower-frequency noncoding variation may contribute to intrafamilial phenotypic variability in HNF4A-related Maturity-Onset Diabetes of the Young (MODY1).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hepatocyte Nuclear Factor 4PancreasPolymorphism, Single NucleotideHumansChromatinGene FrequencyBoosting Machine Learning AlgorithmsAllelesTranscription FactorsBinding SitesStem Cells

Substanzen

Hepatocyte Nuclear Factor 4ChromatinHNF4A protein, humanTranscription Factors

Autor:innen und Institutionen

  • Institute of Genomic Medicine, University of California San Diego, Gilman Dr, La Jolla, California, United States of America.
  • Department of Pediatrics, University of California, San Diego, La Jolla, California, United States of America.
  • Bioinformatics and Systems Biology Graduate Program, University of California, San Diego, La Jolla, California, United States of America.
  • Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, United States of America.
  • Department of Medicine, Division of Metabolism, Endocrinology and Nutrition and UW Medicine Diabetes Institute, University of Washington, Seattle, Washington, United States of America.

ORCID-Profile: Wilfredo G Gonzalez Rivera, Matteo D'Antonio

Förderung

  • NIDDK NIH HHS
  • NHGRI NIH HHS
  • NHLBI NIH HHS
  • NIH HHS
  • NLM NIH HHS
  • National Institute of Diabetes and Digestive and Kidney Diseases
  • National Heart, Lung, and Blood Institute
  • National Human Genome Research Institute

Zitieren

APA

Frazer, K. A., Henson, B., Nguyen, J. P., Gonzalez Rivera, W. G., & D'Antonio, M. (2026). XGBoost-SHAP analysis prioritizes lower-frequency variants predicted to affect HNF4A binding motifs in pancreatic progenitors. PLOS Genetics, 22(11), e1012361. https://doi.org/10.1371/journal.pgen.1012361

Vancouver

Frazer KA, Henson B, Nguyen JP, Gonzalez Rivera WG, D'Antonio M. XGBoost-SHAP analysis prioritizes lower-frequency variants predicted to affect HNF4A binding motifs in pancreatic progenitors. PLOS Genetics. 2026;22(11):e1012361. doi:10.1371/journal.pgen.1012361

BibTeX
@article{Frazer2026,
  author = {Frazer, Kelly A and Henson, Benjamin and Nguyen, Jennifer P and Gonzalez Rivera, Wilfredo G and D'Antonio, Matteo},
  title = {XGBoost-SHAP analysis prioritizes lower-frequency variants predicted to affect HNF4A binding motifs in pancreatic progenitors},
  journal = {PLOS Genetics},
  year = {2026},
  volume = {22},
  number = {11},
  pages = {e1012361},
  doi = {10.1371/journal.pgen.1012361}
}
Kostenlos starten →