RT Journal Article
T1 Predicting haplogroups using a versatile machine learning program (PredYMaLe) on a new mutationally balanced 32 Y-STR multiplex (CombYplex): unlocking the full potential of the human STR mutation rate spectrum to estimate forensic parameters
A1 Bouakaze, Caroline
A1 Delehelle, Franklin
A1 Saenz-Oyhéréguy, Nancy
A1 Moreira, Andreia
A1 Schiavinato, Stéphanie
A1 Croze, Myriam
A1 Delon, Solène
A1 Fortes-Lima, César
A1 Gibert, Morgane
A1 Bujan, Louis
A1 Huyghe, Eric
A1 Bellis, Gil
A1 Calderón Fernández, María Del Rosario
A1 Hernández, Candela
A1 Avendaño-Tamayo, Efren
A1 Bedoya, Gabriel
A1 Salas, Antonio
A1 Mazières, Stéphane
A1 Chiaroni, Jacques
A1 Migot-Nabias, Florence
A1 Ruiz-Linares, Andres
A1 Dugoujon, Jean-Michel
A1 Théves, Catherine
A1 Mollereau-Manaute, Catherine
A1 Nôus, Camille
A1 Poulet, Nicolas
A1 King, Turi
A1 D'Amato, Maria Eugenia
A1 Balaresque, Patricia
AB We developed a new mutationally well-balanced 32 Y-STR multiplex (CombYplex) together with a machine learning (ML) program PredYMaLe to assess the impact of STR mutability on haplogourp prediction, while respecting forensic community criteria (high DC/HD). We designed CombYplex around two sub-panels M1 and M2 characterized by average and high-mutation STR panels. Using these two sub-panels, we tested how our program PredYmale reacts to mutability when considering basal branches and, moving down, terminal branches. We tested first the discrimination capacity of CombYplex on 996 human samples using various forensic and statistical parameters and showed that its resolution is sufficient to separate haplogroup classes. In parallel, PredYMaLe was designed and used to test whether a ML approach can predict haplogroup classes fromY-STR profiles. Applied to our kit, SVM and Random Forest classifiers perform very well (average 97%), better than Neural Network (average 91%) and Bayesian methods (<90%). We observe heterogeneity in haplogroup assignation accuracy among classes, with most haplogroups having high prediction scores (99-100%) and two (E1b1b and G) having lower scores (67%). The small sample sizes of these classes explain the high tendency to misclassify the Y-profiles of these haplogroups; results were measurably improved as soon as more training data were added. We provide evidence that our ML approach is a robust method to accurately predict haplogroups when it is combined with a sufficient number of markers, well-balanced mutation rate Y-STR panels, and large ML training sets. Further research on confounding factors (such as gene conversion) and ideal STR panels in regard to the branches analysed can be developed to help classifiers further optimize prediction scores.
PB Science Direct
SN 1872-4973
YR 2020
FD 2020
LK https://hdl.handle.net/20.500.14352/98074
UL https://hdl.handle.net/20.500.14352/98074
LA eng
NO Bouakaze C, Delehelle F, Saenz-Oyhéréguy N, Moreira A, Schiavinato S, Croze M, Delon S, Fortes-Lima C, Gibert M, Bujan L, Huyghe E, Bellis G, Calderon R, Hernández CL, Avendaño-Tamayo E, Bedoya G, Salas A, Mazières S, Charioni J, Migot-Nabias F, Ruiz-Linares A, Dugoujon JM, Thèves C, Mollereau-Manaute C, Noûs C, Poulet N, King T, D'Amato ME, Balaresque P. Predicting haplogroups using a versatile machine learning program (PredYMaLe) on a new mutationally balanced 32 Y-STR multiplex (CombYplex): Unlocking the full potential of the human STR mutation rate spectrum to estimate forensic parameters. Forensic Sci Int Genet. 2020 Sep;48:102342.
NO University Toulouse III
NO Ministerio de Economía y Competitividad (España)
NO Observatory Man-Environment Haut-Vicdessos (France)
NO National Research Foundation
DS Docta Complutense
RD 8 abr 2025