EUVIMEDEUVIMED entdecken
Crossref

A biogeographical ancestry inference pipeline using PCA-XGBoost model and its application in Asian populations

Chunnain Wang, Shuaiqi Wang, Yiru Zhao, Jun Liu, Deqin Zhang, Fuyang Wang, Hong Fan, Caixia Li, Li Jiang

Forensic Science International: Genetics · 2025-04 · 77 · 103239

DOI: 10.1016/j.fsigen.2025.103239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forensic Science International: Genetics, 2025-04. Verfasst von Chunnain Wang und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Shaanxi Normal University, Xian, Shaanxi 710119, China; Key Laboratory of Forensic Genetics, Beijing Engineering Research…. Hauptthemen laut MEDLINE: Principal Component Analysis, Genetics, Population, Asian People, Models, Genetic. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: Shaanxi Province Natural Science Foundation, National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Biogeographical ancestry (BGA) inference plays a crucial role in genetics, anthropology, forensic science, and medical research. Current methods like principal component analysis (PCA) and ADMIXTURE, based on single nucleotide polymorphisms, are commonly used. Here, we introduce a bio-geographical ancestry inference pipeline that integrates prior population structure and clustering. Our pipeline first analyzes genetic structure on cleaned data to obtain optimal parameters and classification model labels. An XGBoost (eXtreme Gradient Boosting) classification model is constructed using principal components from PCA, and model predictions are evaluated with LR (likelihood ratio). The pipeline was applied to a dataset of Asian populations, with a first prediction accuracy of 96.27 % achieved. The LR-based evaluation accuracy reached 98.96 %, showing an improvement of 2.69 % with the introduction of LR assessment. This highlights the robust predictive capability of our pipeline and the improved accuracy in evaluation with LR. This successful application will benefit genetic research, human history studies, and criminal investigations. Additionally, the pipeline's versatility allows application to new datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Principal Component AnalysisGenetics, PopulationAsian PeopleModels, GeneticHumansPolymorphism, Single NucleotideLikelihood FunctionsBoosting Machine Learning Algorithms

Stichwörter der Autor:innen

Biogeographical ancestry inferenceLikelihood ratio assessmentPipelinePrincipal component analysis

Autor:innen und Institutionen

  • School of Computer Science, Shaanxi Normal University, Xian, Shaanxi 710119, China; Key Laboratory of Forensic Genetics, Beijing Engineering Research Center of Crime Scene Evidence Examination, National Engineering Labo…
  • Key Laboratory of Forensic Genetics, Beijing Engineering Research Center of Crime Scene Evidence Examination, National Engineering Laboratory for Forensic Science, Institute of Forensic Science, Beijing 100038, China; S…
  • Key Laboratory of Forensic Genetics, Beijing Engineering Research Center of Crime Scene Evidence Examination, National Engineering Laboratory for Forensic Science, Institute of Forensic Science, Beijing 100038, China; J…
  • Key Laboratory of Forensic Genetics, Beijing Engineering Research Center of Crime Scene Evidence Examination, National Engineering Laboratory for Forensic Science, Institute of Forensic Science, Beijing 100038, China; I…
  • Key Laboratory of Forensic Genetics, Beijing Engineering Research Center of Crime Scene Evidence Examination, National Engineering Laboratory for Forensic Science, Institute of Forensic Science, Beijing 100038, China.
  • School of Computer Science, Shaanxi Normal University, Xian, Shaanxi 710119, China. Electronic address: fanhong@snnu.edu.cn.

Förderung

  • Shaanxi Province Natural Science Foundation
  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Institute of Forensic Science, Ministry of Public Security

Zitieren

APA

Wang, C., Wang, S., Zhao, Y., Liu, J., Zhang, D., Wang, F., Fan, H., Li, C., & Jiang, L. (2025). A biogeographical ancestry inference pipeline using PCA-XGBoost model and its application in Asian populations. Forensic Science International: Genetics, 77, 103239. https://doi.org/10.1016/j.fsigen.2025.103239

Vancouver

Wang C, Wang S, Zhao Y, Liu J, Zhang D, Wang F, et al. A biogeographical ancestry inference pipeline using PCA-XGBoost model and its application in Asian populations. Forensic Science International: Genetics. 2025;77:103239. doi:10.1016/j.fsigen.2025.103239

BibTeX
@article{Wang2025,
  author = {Wang, Chunnain and Wang, Shuaiqi and Zhao, Yiru and Liu, Jun and Zhang, Deqin and Wang, Fuyang and Fan, Hong and Li, Caixia and Jiang, Li},
  title = {A biogeographical ancestry inference pipeline using PCA-XGBoost model and its application in Asian populations},
  journal = {Forensic Science International: Genetics},
  year = {2025},
  volume = {77},
  pages = {103239},
  doi = {10.1016/j.fsigen.2025.103239}
}
Kostenlos starten →