% pubman genre = article
@article{item_3334258,
title = {{Prediction of eye, hair and skin colour in Latin Americans}},
author = {Palmal, Sagnik and Adhikari, Kaustubh and Mendoza-Revilla, Javier and Fuentes-Guajardo, Macarena and Cerqueira, Silva and Cesar, Caio and Bonfante, Betty and Chac{\'o}n-Duque, Juan Camilo and Sohail, Anood and Hurtado, Malena and Villegas, Valeria and Granja, Vanessa and Jaramillo, Claudia and Arias, William and Barquera Lozano, Rodrigo Jos{\'e} and Everardo-Mart{\'\i}nez, Paola and G{\'o}mez-Vald{\'e}s, Jorge and Villamil-Ram{\'\i}rez, Hugo and H{\"u}nemeier, T{\'a}bita and Ramallo, Virginia and Parolin, Maria-Laura and Gonzalez-Jos{\'e}, Rolando and Sch{\"u}ler-Faccini, Lavinia and Bortolini, Maria-C{\'a}tira and Acu{\~n}a-Alonzo, Victor and Canizales-Quinteros, Samuel and Gallo, Carla and Poletti, Giovanni and Bedoya, Gabriel and Rothhammer, Francisco and Balding, David and Faux, Pierre and Ruiz-Linares, Andr{\'e}s},
language = {eng},
issn = {1872-4973},
doi = {10.1016/j.fsigen.2021.102517},
publisher = {Elsevier Science},
address = {Amsterdam},
year = {2021},
date = {2021-07},
abstract = {{Here we evaluate the accuracy of prediction for eye, hair and skin pigmentation in a dataset of {\textgreater} 6500 individuals from Mexico, Colombia, Peru, Chile and Brazil (including genome-wide SNP data and quantitative/categorical pigmentation phenotypes - the CANDELA dataset CAN). We evaluated accuracy in relation to different analytical methods and various phenotypic predictors. As expected from statistical principles, we observe that quantitative traits are more sensitive to changes in the prediction models than categorical traits. We find that Random Forest or Linear Regression are generally the best performing methods. We also compare the prediction accuracy of SNP sets defined in the CAN dataset (including 56, 101 and 120 SNPs for eye, hair and skin colour prediction, respectively) to the well-established HIrisPlex-S SNP set (including 6, 22 and 36 SNPs for eye, hair and skin colour prediction respectively). When training prediction models on the CAN data, we observe remarkably similar performances for HIrisPlex-S and the larger CAN SNP sets for the prediction of hair (categorical) and eye (both categorical and quantitative), while the CAN sets outperform HIrisPlex-S for quantitative, but not for categorical skin pigmentation prediction. The performance of HIrisPlex-S, when models are trained in a world-wide sample (although consisting of 80{\textpercent} Europeans, https://hirisplex.erasmusmc.nl), is lower relative to training in the CAN data (particularly for hair and skin colour). Altogether, our observations are consistent with common variation of eye and hair colour having a relatively simple genetic architecture, which is well captured by HIrisPlex-S, even in admixed Latin Americans (with partial European ancestry). By contrast, since skin pigmentation is a more polygenic trait, accuracy is more sensitive to prediction SNP set size, although here this effect was only apparent for a quantitative measure of skin pigmentation. Our results support the use of HIrisPlex-S in the prediction of categorical pigmentation traits for forensic purposes in Latin America, while illustrating the impact of training datasets on its accuracy.}},
contents = {1. Introduction 2. Materials and methods 2.1. Study sample: phenotypes, genetic data and covariates 2.2. Pigmentation SNP sets used for prediction 2.3. Prediction methods and models evaluated 2.4. Evaluation of prediction accuracy 2.5. Comparison with prediction accuracy from HIrisPlex-S-online 2.6. Prediction of MI in Native American individuals of unknown phenotype 3. Results 3.1. Prediction accuracy in relation to models, methods and pigmentation SNP sets 3.2. Prediction accuracy at varying levels of European/Native American ancestry 3.3. Prediction accuracy in CANDELA relative to other population samples 3.4. Portability of models for pigmentation prediction in individuals with high Native Ancestry 3.5. Prediction of skin pigmentation in Native Americans 4. Discussion},
journal = {{Forensic Science International: Genetics}},
volume = {53},
eid = {102517},
}