TY  - JOUR
AU  - Kloska, Anna
AU  - Giełczyk, Agata
AU  - Grzybowski, Tomasz
AU  - Płoski, Rafał
AU  - Kloska, Sylwester M.
AU  - Marciniak, Tomasz
AU  - Pałczyński, Krzysztof
AU  - Rogalla-Ładniak, Urszula
AU  - Malyarchuk, Boris A.
AU  - Derenko, Miroslava V.
AU  - Kovačević-Grujičić, Nataša
AU  - Stevanović, Milena
AU  - Drakulić, Danijela
AU  - Davidović, Slobodan
AU  - Spólnicka, Magdalena
AU  - Zubańska, Magdalena
AU  - Woźniak, Marcin
PY  - 2023
UR  - https://www.mdpi.com/1422-0067/24/20/15095
UR  - https://imagine.imgge.bg.ac.rs/handle/123456789/2171
AB  - Data obtained with the use of massive parallel sequencing (MPS) can be valuable in population genetics studies. In particular, such data harbor the potential for distinguishing samples from different populations, especially from those coming from adjacent populations of common origin. Machine learning (ML) techniques seem to be especially well suited for analyzing large datasets obtained using MPS. The Slavic populations constitute about a third of the population of Europe and inhabit a large area of the continent, while being relatively closely related in population genetics terms. In this proof-of-concept study, various ML techniques were used to classify DNA samples from Slavic and non-Slavic individuals. The primary objective of this study was to empirically evaluate the feasibility of discerning the genetic provenance of individuals of Slavic descent who exhibit genetic similarity, with the overarching goal of categorizing DNA specimens derived from diverse Slavic population representatives. Raw sequencing data were pre-processed, to obtain a 1200 character-long binary vector. A total of three classifiers were used—Random Forest, Support Vector Machine (SVM), and XGBoost. The most-promising results were obtained using SVM with a linear kernel, with 99.9% accuracy and F1-scores of 0.9846–1.000 for all classes.
T2  - International Journal of Molecular Sciences
T1  - A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe
IS  - 20
SP  - 15095
VL  - 24
DO  - 10.3390/ijms242015095
ER  - 

@article{
author = "Kloska, Anna and Giełczyk, Agata and Grzybowski, Tomasz and Płoski, Rafał and Kloska, Sylwester M. and Marciniak, Tomasz and Pałczyński, Krzysztof and Rogalla-Ładniak, Urszula and Malyarchuk, Boris A. and Derenko, Miroslava V. and Kovačević-Grujičić, Nataša and Stevanović, Milena and Drakulić, Danijela and Davidović, Slobodan and Spólnicka, Magdalena and Zubańska, Magdalena and Woźniak, Marcin",
year = "2023",
abstract = "Data obtained with the use of massive parallel sequencing (MPS) can be valuable in population genetics studies. In particular, such data harbor the potential for distinguishing samples from different populations, especially from those coming from adjacent populations of common origin. Machine learning (ML) techniques seem to be especially well suited for analyzing large datasets obtained using MPS. The Slavic populations constitute about a third of the population of Europe and inhabit a large area of the continent, while being relatively closely related in population genetics terms. In this proof-of-concept study, various ML techniques were used to classify DNA samples from Slavic and non-Slavic individuals. The primary objective of this study was to empirically evaluate the feasibility of discerning the genetic provenance of individuals of Slavic descent who exhibit genetic similarity, with the overarching goal of categorizing DNA specimens derived from diverse Slavic population representatives. Raw sequencing data were pre-processed, to obtain a 1200 character-long binary vector. A total of three classifiers were used—Random Forest, Support Vector Machine (SVM), and XGBoost. The most-promising results were obtained using SVM with a linear kernel, with 99.9% accuracy and F1-scores of 0.9846–1.000 for all classes.",
journal = "International Journal of Molecular Sciences",
title = "A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe",
number = "20",
pages = "15095",
volume = "24",
doi = "10.3390/ijms242015095"
}

Kloska, A., Giełczyk, A., Grzybowski, T., Płoski, R., Kloska, S. M., Marciniak, T., Pałczyński, K., Rogalla-Ładniak, U., Malyarchuk, B. A., Derenko, M. V., Kovačević-Grujičić, N., Stevanović, M., Drakulić, D., Davidović, S., Spólnicka, M., Zubańska, M.,& Woźniak, M.. (2023). A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe. in International Journal of Molecular Sciences, 24(20), 15095.
https://doi.org/10.3390/ijms242015095

Kloska A, Giełczyk A, Grzybowski T, Płoski R, Kloska SM, Marciniak T, Pałczyński K, Rogalla-Ładniak U, Malyarchuk BA, Derenko MV, Kovačević-Grujičić N, Stevanović M, Drakulić D, Davidović S, Spólnicka M, Zubańska M, Woźniak M. A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe. in International Journal of Molecular Sciences. 2023;24(20):15095.
doi:10.3390/ijms242015095 .

Kloska, Anna, Giełczyk, Agata, Grzybowski, Tomasz, Płoski, Rafał, Kloska, Sylwester M., Marciniak, Tomasz, Pałczyński, Krzysztof, Rogalla-Ładniak, Urszula, Malyarchuk, Boris A., Derenko, Miroslava V., Kovačević-Grujičić, Nataša, Stevanović, Milena, Drakulić, Danijela, Davidović, Slobodan, Spólnicka, Magdalena, Zubańska, Magdalena, Woźniak, Marcin, "A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe" in International Journal of Molecular Sciences, 24, no. 20 (2023):15095,
https://doi.org/10.3390/ijms242015095 . .