AncesTrees: ancestry estimation with randomized decision trees

Abstract

In forensic anthropology, ancestry estimation is essential in establishing the individual biological profile. The aim of this study is to present a new program--AncesTrees--developed for assessing ancestry based on metric analysis. AncesTrees relies on a machine learning ensemble algorithm, random forest, to classify the human skull. In the ensemble learning paradigm, several models are generated and co-jointly used to arrive at the final decision. The random forest algorithm creates ensembles of decision trees classifiers, a non-linear and non-parametric classification technique. The database used in AncesTrees is composed by 23 craniometric variables from 1,734 individuals, representative of six major ancestral groups and selected from the Howells' craniometric series. The program was tested in 128 adult crania from the following collections: the African slaves' skeletal collection of Valle da Gafaria; the Medical School Skull Collection and the Identified Skeletal Collection of 21st Century, both curated at the University of Coimbra. The first step of the test analysis was to perform ancestry estimation including all the ancestral groups of the database. The second stage of our test analysis was to conduct ancestry estimation including only the European and the African ancestral groups. In the first test analysis, 75% of the individuals of African ancestry and 79.2% of the individuals of European ancestry were correctly identified. The model involving only African and European ancestral groups had a better performance: 93.8% of all individuals were correctly classified. The obtained results show that AncesTrees can be a valuable tool in forensic anthropology.

Discarded in the trash: Burials of African enslaved individuals in Valle da Gafaria, Lagos, Portugal (15th–17th centuries)

“…The osteological collection of African‐enslaved individuals of Lagos is composed of 158 individuals: 50 non‐adults, 107 adults (30 males, 58 females, 19 of unknown sex), and one individual whose poor state of preservation prevented the estimation of his/her biological profile. Ancestry estimation was performed based on morphometric (Coelho et al, ; Navega et al, ) and genetic (Martiniano et al, ) analyses. Age at death of non‐adults was achieved on the basis of dental development (i.e., dental calcification and sequence of formation and eruption of teeth) and skeletal development (i.e., long bones' lengths; Wasterlain et al, ).…”

“…Anthropological analyses of the human skeletons revealed a morphology characteristic of African ancestry (Coelho, Navega, Cunha, Ferreira, & Wasterlain, ; Navega et al, ), as well as the presence of intentional tooth modifications in many individuals (Wasterlain, Neves, & Ferreira, ). The genetic study of four skeletons confirmed their African ancestry affinity with Bantu‐speaking groups (Martiniano et al, ).…”

Growth faltering in a skeletal sample of enslaved nonadult Africans found at Lagos, Portugal (15th–17th centuries)

“…An archaeological excavation performed in Valle da Gafaria (Lagos, Portugal) led to the discovery of a deposit of urban waste dated from the 15th to 17th centuries, from which the skeletons of 158 individuals were exhumed (Wasterlain, Neves, & Ferreira, ). Evidence suggests that these individuals were African slaves: their cadavers were thrown into the trash; there were African objects associated with the skeletons; their morphometric traits were indicative of an African ancestry (Coelho, Navega, Cunha, Ferreira, & Wasterlain, ; Navega et al, ); 63 individuals (14 of which were nonadults) exhibited intentionally modified teeth, a cultural practice commonly performed in Africa (Wasterlain et al, ); and the historical sources testify the importance of Lagos as a harbour where slaves arrived from Africa and from which were redistributed to the Kingdom of Portugal, the Mediterranean Sea, and Northern Europe (Caldeira, ; Fonseca, ). In fact, the “Lagos Company” for trade with the African coast was founded in 1443 (Mendes, ).…”

Is north Indian population changing it craniofacial form? A study of secular trends in craniometric indices and its relation to sex and ancestry estimation

“…FORDISC [24] CRANID [25] and ANCESTREES [26] to estimate ancestry of unknown crania using software based programs. The CRANID used 29 parameters of the craniofacial region to compare unknown crania to 74 geographical samples that are from a collection of 3,163 crania from 39 different populations from around the world.…”