TY  - JOUR
AU  - Kloska, Anna
AU  - Giełczyk, Agata
AU  - Grzybowski, Tomasz
AU  - Płoski, Rafał
AU  - Kloska, Sylwester
AU  - Marciniak, Tomasz
AU  - Pałczynski, Krzysztof
AU  - Rogalla-Ładniak, Urszula
AU  - Malyarchuk, Boris
AU  - Derenko, Miroslava
AU  - Kovačević-Grujičić, Nataša
AU  - Stevanović, Milena
AU  - Drakulić, Danijela
AU  - Davidović, Slobodan
AU  - Spólnicka, Magdalena
AU  - Zubanska, Magdalena
AU  - Wozniak, Marcin
PY  - 2023
UR  - http://radar.ibiss.bg.ac.rs/handle/123456789/6321
AB  - 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.
PB  - Basel: MDPI
T2  - International Journal of Molecular Sciences
T1  - A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe
IS  - 20
VL  - 24
DO  - 10.3390/ijms242015095
SP  - 15095
ER  - 

@article{
author = "Kloska, Anna and Giełczyk, Agata and Grzybowski, Tomasz and Płoski, Rafał and Kloska, Sylwester and Marciniak, Tomasz and Pałczynski, Krzysztof and Rogalla-Ładniak, Urszula and Malyarchuk, Boris and Derenko, Miroslava and Kovačević-Grujičić, Nataša and Stevanović, Milena and Drakulić, Danijela and Davidović, Slobodan and Spólnicka, Magdalena and Zubanska, Magdalena and Wozniak, Marcin",
year = "2023",
abstract = "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.",
publisher = "Basel: MDPI",
journal = "International Journal of Molecular Sciences",
title = "A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe",
number = "20",
volume = "24",
doi = "10.3390/ijms242015095",
pages = "15095"
}

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

Kloska A, Giełczyk A, Grzybowski T, Płoski R, Kloska S, Marciniak T, Pałczynski K, Rogalla-Ładniak U, Malyarchuk B, Derenko M, Kovačević-Grujičić N, Stevanović M, Drakulić D, Davidović S, Spólnicka M, Zubanska M, Wozniak 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, Marciniak, Tomasz, Pałczynski, Krzysztof, Rogalla-Ładniak, Urszula, Malyarchuk, Boris, Derenko, Miroslava, Kovačević-Grujičić, Nataša, Stevanović, Milena, Drakulić, Danijela, Davidović, Slobodan, Spólnicka, Magdalena, Zubanska, Magdalena, Wozniak, 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 . .

TY  - JOUR
AU  - Davidović, Slobodan
AU  - Malyarchuk, Boris
AU  - Grzybowski, Tomasz
AU  - Aleksić, Jelena M.
AU  - Derenko, Miroslava
AU  - Litvinov, Andrey
AU  - Rogalla-Ładniak, Urszula
AU  - Stevanović, Milena
AU  - Kovačević-Grujičić, Nataša
PY  - 2020
UR  - http://link.springer.com/10.1007/s00414-020-02324-x
UR  - http://www.ncbi.nlm.nih.gov/pubmed/32504149
UR  - https://radar.ibiss.bg.ac.rs/handle/123456789/3685
AB  - Mitochondrial genome (mtDNA) is a valuable resource in resolving various human forensic casework. The usage of variability of complete mtDNA genomes increases their discriminatory power to the maximum and enables ultimate resolution of distinct maternal lineages. However, their wider employment in forensic casework is nowadays limited by the lack of appropriate reference database. In order to fill in the gap in the reference data, which, considering Slavic-speaking populations, currently comprises only mitogenomes of East and West Slavs, we present mitogenome data for 226 Serbians, representatives of South Slavs from the Balkan Peninsula. We found 143 (sub)haplogroups among which West Eurasian ones were dominant. The percentage of unique haplotypes was 85%, and the random match probability was as low as 0.53%. We support previous findings on both high levels of genetic diversity in the Serbian population and patterns of genetic differentiation among this and ten studied European populations. However, our high-resolution data supported more pronounced genetic differentiation among Serbians and two Slavic populations (Russians and Poles) as well as expansion of the Serbian population after the Last Glacial Maximum and during the Migration period (fourth to ninth century A.D.), as inferred from the Bayesian skyline analysis. Phylogenetic analysis of haplotypes found in Serbians contributed towards the improvement of the worldwide mtDNA phylogeny, which is essential for the interpretation of the mtDNA casework.
PB  - Springer
T2  - International Journal of Legal Medicine
T1  - Complete mitogenome data for the Serbian population: the contribution to high-quality forensic databases.
VL  - 134
DO  - 10.1007/s00414-020-02324-x
SP  - 1581
EP  - 1590
ER  - 

@article{
author = "Davidović, Slobodan and Malyarchuk, Boris and Grzybowski, Tomasz and Aleksić, Jelena M. and Derenko, Miroslava and Litvinov, Andrey and Rogalla-Ładniak, Urszula and Stevanović, Milena and Kovačević-Grujičić, Nataša",
year = "2020",
abstract = "Mitochondrial genome (mtDNA) is a valuable resource in resolving various human forensic casework. The usage of variability of complete mtDNA genomes increases their discriminatory power to the maximum and enables ultimate resolution of distinct maternal lineages. However, their wider employment in forensic casework is nowadays limited by the lack of appropriate reference database. In order to fill in the gap in the reference data, which, considering Slavic-speaking populations, currently comprises only mitogenomes of East and West Slavs, we present mitogenome data for 226 Serbians, representatives of South Slavs from the Balkan Peninsula. We found 143 (sub)haplogroups among which West Eurasian ones were dominant. The percentage of unique haplotypes was 85%, and the random match probability was as low as 0.53%. We support previous findings on both high levels of genetic diversity in the Serbian population and patterns of genetic differentiation among this and ten studied European populations. However, our high-resolution data supported more pronounced genetic differentiation among Serbians and two Slavic populations (Russians and Poles) as well as expansion of the Serbian population after the Last Glacial Maximum and during the Migration period (fourth to ninth century A.D.), as inferred from the Bayesian skyline analysis. Phylogenetic analysis of haplotypes found in Serbians contributed towards the improvement of the worldwide mtDNA phylogeny, which is essential for the interpretation of the mtDNA casework.",
publisher = "Springer",
journal = "International Journal of Legal Medicine",
title = "Complete mitogenome data for the Serbian population: the contribution to high-quality forensic databases.",
volume = "134",
doi = "10.1007/s00414-020-02324-x",
pages = "1581-1590"
}

Davidović, S., Malyarchuk, B., Grzybowski, T., Aleksić, J. M., Derenko, M., Litvinov, A., Rogalla-Ładniak, U., Stevanović, M.,& Kovačević-Grujičić, N.. (2020). Complete mitogenome data for the Serbian population: the contribution to high-quality forensic databases.. in International Journal of Legal Medicine
Springer., 134, 1581-1590.
https://doi.org/10.1007/s00414-020-02324-x

Davidović S, Malyarchuk B, Grzybowski T, Aleksić JM, Derenko M, Litvinov A, Rogalla-Ładniak U, Stevanović M, Kovačević-Grujičić N. Complete mitogenome data for the Serbian population: the contribution to high-quality forensic databases.. in International Journal of Legal Medicine. 2020;134:1581-1590.
doi:10.1007/s00414-020-02324-x .

Davidović, Slobodan, Malyarchuk, Boris, Grzybowski, Tomasz, Aleksić, Jelena M., Derenko, Miroslava, Litvinov, Andrey, Rogalla-Ładniak, Urszula, Stevanović, Milena, Kovačević-Grujičić, Nataša, "Complete mitogenome data for the Serbian population: the contribution to high-quality forensic databases." in International Journal of Legal Medicine, 134 (2020):1581-1590,
https://doi.org/10.1007/s00414-020-02324-x . .