Universität zu Köln

Katsara, Maria-Alexandra, Branicki, Wojciech ORCID: 0000-0002-7412-5733, Walsh, Susan ORCID: 0000-0002-7064-1589, Kayser, Manfred and Nothnagel, Michael (2021). Evaluation of supervised machine-learning methods for predicting appearance traits from DNA. Forensic Sci. Int.-Genet., 53. CLARE: ELSEVIER IRELAND LTD. ISSN 1878-0326

Full text not available from this repository.

Abstract

The prediction of human externally visible characteristics (EVCs) based solely on DNA information has become an established approach in forensic and anthropological genetics in recent years. While for a large set of EVCs, predictive models have already been established using multinomial logistic regression (MLR), the prediction performances of other possible classification methods have not been thoroughly investigated thus far. Motivated by the question to identify a potential classifier that outperforms these specific trait models, we conducted a systematic comparison between the widely used MLR and three popular machine learning (ML) classifiers, namely support vector machines (SVM), random forest (RF) and artificial neural networks (ANN), that have shown good performance outside EVC prediction. As examples, we used eye, hair and skin color categories as phenotypes and genotypes based on the previously established IrisPlex, HIrisPlex, and HIrisPlex-S DNA markers. We compared and assessed the performances of each of the four methods, complemented by detailed hyperparameter tuning that was applied to some of the methods in order to maximize their performance. Overall, we observed that all four classification methods showed rather similar performance, with no method being substantially superior to the others for any of the traits, although performances varied slightly across the different traits and more so across the trait categories. Hence, based on our findings, none of the ML methods applied here provide any advantage on appearance prediction, at least when it comes to the categorical pigmentation traits and the selected DNA markers used here.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Katsara, Maria-Alexandra UNSPECIFIED UNSPECIFIED UNSPECIFIED Branicki, Wojciech UNSPECIFIED orcid.org/0000-0002-7412-5733 UNSPECIFIED Walsh, Susan UNSPECIFIED orcid.org/0000-0002-7064-1589 UNSPECIFIED Kayser, Manfred UNSPECIFIED UNSPECIFIED UNSPECIFIED Nothnagel, Michael UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-593337
DOI:	10.1016/j.fsigen.2021.102507
Journal or Publication Title:	Forensic Sci. Int.-Genet.
Volume:	53
Date:	2021
Publisher:	ELSEVIER IRELAND LTD
Place of Publication:	CLARE
ISSN:	1878-0326
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language GENOME-WIDE ASSOCIATION; SKIN COLOR PREDICTION; EYE COLOR; GENETIC-DETERMINANTS; PIGMENTATION; HAIR; SYSTEM; ORGANIZATION; COMPLEX; MODEL Multiple languages Genetics & Heredity; Medicine, Legal Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/59333