Enhancing Intra-Continental Biogeographical Ancestry Prediction Through a Machine Learning Marker Selection Method
Authors:
- Theresa MaurerTMTheresa Maurer
- Lennart PuruckerLPLennart Purucker
- Frank HutterFHFrank Hutter
- Peter PfaffelhuberPPPeter Pfaffelhuber
- Carola Sophia HeinzelCHCarola Sophia Heinzel
Preprint
Abstract
While classifiers such as TabPFN (Hollmann et al., 2025) and SNIPPER (Phillips et al., 2007a) achieve strong intercontinental performance (Heinzel et al., 2025), their accuracy in classifying individuals within Europe remains low. One major factor contributing to this limitation is the set of genetic markers used for classification. Marker panels such as the VISAGE Enhanced Tool (Xavier et al., 2022) are commonly employed in forensic genetics because they contain ancestry-informative markers (AIMs) that distinguish very well between major continental populations. However, these panels are often not optimized for fine-scale differentiation within continents, where genetic variation is more subtle and population structure is rather continuous. We apply machine learning to select informative markers for intra-European classification, using data from Consortium et al. (2015). Compared with the VISAGE Enhanced Tool and allele frequency–based approaches (Phillips et al., 2007b; Kosoy et al., 2009; Nassir et al., 2009; Kidd et al., 2014; Phillips et al., 2014a), our marker sets achieve substantially higher accuracy within Europe: For four European populations, accuracy improves from 68.2% (VISAGE, 104 markers) to 73.7% (100 new markers) and 82.3% (200 new markers). For five populations, accuracy rises from 56.1% (VISAGE) to 64.5% (100 new markers). Our results show that tailored marker selection markedly improves intra-continental classification. While optimized here for Europe, the method can be applied to any region with sufficient training data.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (499552394)
- Deutsche Forschungsgemeinschaft (417962828)
- Hector Foundation
This publication has 37 references indexed in Scilit:
- Forensic biogeographical ancestry inference: recent insights and current trendsGenes & Genomics, 2023
- Unsupervised discovery of ancestry-informative markers and genetic admixture proportions in biobank-scale datasetsThe American Journal of Human Genetics, 2023
- Benchmark for filter methods for feature selection in high-dimensional classification dataComputational Statistics & Data Analysis, 2020
- Prediction of biogeographical ancestry from genotype: a comparison of classifiersInternational journal of legal medicine, 2016
- A computationally fast variable importance test for random forests for high-dimensional dataAdvances in Data Analysis and Classification, 2016
- The Fundamental Nature of the Log Loss Function2015
- Inference of biogeographical ancestry across central regions of EurasiaInternational journal of legal medicine, 2015
- Ancestry informative marker sets for determining continental origin and admixture proportions in common populations in AmericaHuman Mutation, 2008
- Information on ancestry from genetic markersGenetic Epidemiology, 2004
- Racial background is a determinant factor in the maintenance dosage of WarfarinInternational Journal of Hematology, 2003