EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GenoEye : A machine learning‐based framework for the prediction of intermediate eye color phenotypes

Davide Dalfovo, Giorgia Pallafacchina, Gianluca Occhi, Alberto Marino, Giovanni Vazza, Christian Faccinetto, Alessandro Romanel

Journal of Forensic Sciences · 2026

DOI: 10.1111/1556-4029.70403 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Forensic Sciences, 2026. Verfasst von Davide Dalfovo und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cellular, Computational and Integrative Biology (CIBIO), University of Trento, Trento, Italy. Hauptthemen laut MEDLINE: Eye Color, Phenotype, Machine Learning, Polymorphism, Single Nucleotide. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forensic DNA phenotyping (FDP) enables the prediction of externally visible characteristics from genetic data, providing valuable investigative leads. While current approaches achieve high accuracy for blue and brown eye color, the prediction of intermediate phenotypes such as green and hazel remains challenging, particularly in Southern European and Mediterranean populations. In this study, we developed GenoEye, an interpretable machine learning framework for three‐category eye color prediction based on an expanded SNP panel, from which a final 37‐SNP predictive signature was derived. The model was developed and evaluated on a cohort of 363 Italian individuals using a gradient boosting approach, with independent data used for performance assessment. GenoEye achieved high predictive performance for blue and brown eye color (AUC up to 0.97), while improving the classification of intermediate phenotypes (AUC = 0.79), a category where existing tools show limited sensitivity. Comparative analyses under multiple decision strategies demonstrated that GenoEye provides consistently higher sensitivity for intermediate eye color while maintaining high specificity. To support practical application, GenoEye is implemented as a web‐based tool with integrated SHAP‐based interpretability. These results indicate that GenoEye improves the resolution of intermediate eye color prediction and provides a robust and interpretable framework for forensic applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Eye ColorPhenotypeMachine LearningPolymorphism, Single NucleotideHumansPredictive Learning ModelsBoosting Machine Learning AlgorithmsForensic GeneticsPrediction Algorithms

Stichwörter der Autor:innen

SNPseye color predictionforensic DNA phenotypingintermediate eye colormachine learning

Autor:innen und Institutionen

  • Department of Cellular, Computational and Integrative Biology (CIBIO), University of Trento, Trento, Italy.
  • Neuroscience Institute, Italian National Research Council CNR, Padova, Italy.
  • Department of Biomedical Sciences, University of Padova, Padova, Italy.
  • Department of Biology, University of Padova, Padova, Italy.
  • Reparto Carabinieri Investigazioni Scientifiche di Parma, Sezione Biologia, Parma, Italy.

Zitieren

APA

Dalfovo, D., Pallafacchina, G., Occhi, G., Marino, A., Vazza, G., Faccinetto, C., & Romanel, A. (2026). GenoEye : A machine learning‐based framework for the prediction of intermediate eye color phenotypes. Journal of Forensic Sciences. https://doi.org/10.1111/1556-4029.70403

Vancouver

Dalfovo D, Pallafacchina G, Occhi G, Marino A, Vazza G, Faccinetto C, et al. GenoEye : A machine learning‐based framework for the prediction of intermediate eye color phenotypes. Journal of Forensic Sciences. 2026. doi:10.1111/1556-4029.70403

BibTeX
@article{Dalfovo2026,
  author = {Dalfovo, Davide and Pallafacchina, Giorgia and Occhi, Gianluca and Marino, Alberto and Vazza, Giovanni and Faccinetto, Christian and Romanel, Alessandro},
  title = {GenoEye : A machine learning‐based framework for the prediction of intermediate eye color phenotypes},
  journal = {Journal of Forensic Sciences},
  year = {2026},
  doi = {10.1111/1556-4029.70403}
}
Kostenlos starten →