Hey, I have a few new publications I want to bring your attention to.


d’Oliveira Coelho J, Curate F. 2019. CADOES: An interactive machine-learning approach for sex estimation with the pelvis. Forensic Science International, 302:109873.

CADOES employs powerful graphical devices, flexible variable selection, robust cross-validation mechanisms, and 12 machine learning algorithms for estimating sex in skeletal remains using the pelvis.

Landmarks defining the variables used.

The app is available at Osteomics.

New paper is available here.

There was media coverage about CADOES in Observador, Exame Informática, among many other portuguese magazines.

Ammer-Coelho simulator

Ammer S, d’Oliveira Coelho J, Cunha E. 2019. Outline Shape Analysis on the Trochlear Constriction and Olecranon Fossa of the Humerus: Insights for Sex Estimation and a New Computational Tool. Journal of Forensic Sciences, 64(6):1788–1795.

The easiest way to understand what we did here, is to grab a humerus, look at its distal (and posterior) end, and try to estimate its sex through outline shape simulation, using our app! I think this is the easiest-to-apply method based in geometric morphometrics ever. Well at least to my knowledge. I created the software back in 2017, so I am glad to see the paper out finally. Check it here!

PCA separation
PCA morphospace mined by an LDA algorithm for sex estimation

Paper available here.


Vilas-Boas D, Wasterlain SN, d’Oliveira Coelho J, Navega D, Gonçalves D. 2019. SPINNE: An app for human vertebral height estimation based on artificial neural networks. Forensic Science International. 298:121–130.

The SPINNE webapp together with raxter allow for a complete back-to-end protocol for anatomical stature estimation, even if some vertebras are missing in your individual. This is the most complete solution yet for the stature estimation problem in bioarchaeological or forensic anthropology scenarios. SPINNE uses a neural network regression approach to fill the missing values, similar to what we did previously in DXAGE. The paper is available here!

correlation matrix
Correlation Matrix with all the variables.

New biological profile data for the Lagos skeletons

Ferreira MT, Coelho C, d’Oliveira Coelho J, Navega D, Wasterlain SN. 2018. New data about sex and age-at-death based on the postcranial skeleton of the enslaved adult Africans found at Lagos, Portugal (15th-17th centuries). Cadernos do GEEvH, 7(1):7–16.

158 individuals of sub-saharan origin were excavated in an archaeological urban dump in Algarve. We re-analysed sex and age-at-death for adults (roughly 60% of the sample) using combinations of multiple methods. We provide all the dataset and results in this open access publication available at Cadernos do Grupo de Estudos de Evolução Humana.

Our research team was featured on El País!

One of the individuals from the Lagos excavations.

Mandibular paleopathology case

Silva A, Tomé T, Cunha C, d’Oliveira Coelho J, Valera A, Filipe V, Scott GR. 2018. Unilateral absence of mandibular condyle in a Bronze Age male skeleton from Portugal. International Journal of Paleopathology, 22: 168–172.

I contributed with some quantitative landmark-based analyses and 3D modelling for this paper.

dice view
I did this 3D model of the mandible using a NextEngine Scanner.

The paper described a pathological absence of the left mandibular condyle and its possible diagnoses, including subcondylar fracture, cystic defect, congenital absence, condylar aplasia and mandibular condylysis. The most likely explanation for the pathological alteration is subcondylar fracture with non-union. This mandible was likely functional, as can be inferred from dental wear and muscle attachment sites. This trauma probably occurred before adult age (male individual) when remodelling capacity is still high. Read more about it here.

à bientôt.

ZGA X DEL - Directrizes e Métodos de Transcendência


Lines from 2008 up to 2018 get hyperdimensionally rebuilt into the ultimate origami by DEL while ZGA brings all the genres into a supernova darwinian competition in a spheric battlefield of lost clouds of electrons.

  4. RA.RAR
  9. PSICONAUTA (feat. zer-0)
  11. GRAVIDADE MAIOR (feat. Momentum II)
ZGA X DEL inside out
ZGA X DEL inside out

Raps and lyrics by DEL
Beats, production, mastering, 1st verses and chorus on track 2, 2nd verse and chorus on track 10, adlibs on track 7 by Z G A
2nd verse on track 9 by zer-0
Piano and adlib on track 11 by Momemtum II

ZGA X DEL outside in
ZGA X DEL outside in

There is a hidden track in the physical version of the CD as well. Shhhh!
(Trumpet in hidden track by ORLA; verses in hidden track by zer-0)

We are on Spotify, BandCamp, Amazon, Apple Music, Deezer, Google Play, Tidal, and YouTube (includes video-album and hidden track).

Meurónios Bosque!

rASUDAS is a new web-application using a statistical framework that estimates the ancestry of unknown individuals based on their suite of tooth crown and root traits. Users can choose between 21 independent traits, scored following the well-known Arizona State University Dental Anthropology System (ASUDAS). It is powered by a world-wide reference sample representing approximately 30000 individuals from seven biogeographic regions. The statistical framework and the web application were developed using the R open source programming language. The framework uses a naive Bayes classifier to assign posterior probabilities for individual group assignment. To test the application, 150 individuals were selected from the C. G. Turner II database. In a seven-group analysis, the model correctly assigned individuals to groups 51.8% of the time (chance is 14%!). In a four-group analysis (chance = 25%), classification accuracy improved to 66.7%. With three groups, accuracy was at 72.7%. It is still necessary to validate the program using forensic cases and to augment the reference sample with modern skeletal data. However, results from the current version of rASUDAS are presented as proof of concept on the potential of dental morphology in ancestry estimation in medico-legal contexts. This software has been described in the first issue of the new scientific journal Forensic Anthropology. The application is available at rASUDAS is free! You can try it osteomics.

Forensic Anthropology Journal
New scientific journal: Forensic Anthropology

Why teeth?

The incorporation of dental morphological analyses into forensic anthropological casework has several advantages:

  1. there is a robust body of literature outlining the heritability, development, evolution, and population history of dental morphology, which allows for accurate interpretations of results;
  2. teeth are not subject to plastic change over a lifetime; and
  3. teeth are often better preserved than other parts of the skeleton; Further,
  4. dental morphology represents a different aspect of the genotype and is the result of distinct evolutionary relationships that go beyond the mid-face and shape and size of the cranial vault.

The ability to incorporate more information from the skeleton when assessing ancestry is critical in creating accurate estimates of ancestry. Dental morphology couched in a statistical framework can become an integral part of the methods regularly used by forensic anthropologists in ancestry estimation.

rASUDAS is free! You can try it here.

Feel free to read the paper, here is a very cool historical snippet from it on how me and Navega were working on these kind of projects early on in 2015.

rASUDAS creation
Osteomics becoming part of forensic anthropology history!

Congrats to my colleagues,

rASUDAS: A New Web-Based Application for Estimating Ancestry from Tooth Morphology

G. Richard Scott, Marin A. Pilloud, David Navega, João d’Oliveira Coelho, Eugénia Cunha, Joel D. Irish

DOI: http://dx.doi.org/10.5744/fa.2018.0003

Bo asudas rsrsrs

We have a new scientific article out. It discusses how bone mineral density correlates with age, and thus can be used to model age at death from human remains. We employed artificial neural networks, a simple machine learning technique, to learn patterns of femur densitometric data gathered in 100 female individuals from the Coimbra Identified Skeletal Collection. The mean error of the method, depending on the variables used, ranged from 9.19 to 13.49 years. It is also the first publication about the DXAGE app that was developed with the cooperation with some team members from the Laboratory of Forensic Anthropology, UC. Despite preliminary, and only indicated for skeletal remains of adult females, it shows a very original approach for bioarchaeologists and forensic anthropologists to assess age at death.

figure 2
The neural network architecture used.

Congrats to my peers.

DXAGE: A New Method for Age at Death Estimation Based on Femoral Bone Mineral Density and Artificial Neural Networks

D. Navega, J. d’Oliveira Coelho, E. Cunha, F. Curate

DOI: http://dx.doi.org/10.1111/1556-4029.13582

Best regards, Jow-nhs


I am very pleased to announce that the HOT team has a new site:

hot bones
Click on the image to visit HOT BONES

The coolest thing I learned when developing HOT BONES was to create this beauties, using only the R programming language and a simple sheet from Excel.

Dead Weight paper is out

Besides, we published recently, with some of the team members a new paper, Dead Weight: validation of mass regression equations on experimentally burned skeletal remains to assess skeleton completeness, on Science and Justice. It tests the MassReg app on the experimentally burned skeletons of the CEIXXI available at Laboratory of Forensic Anthropology, UC. Despite MassReg being initially developed for non-burned skeletal remains, it seems to perform as well on burned skeletal remains as other techniques (e.g. comparing to references). Thus it is a new promising and useful tool to assess skeletal completeness.

Congrats to all involved!

Dead weight: Validation of mass regression equations on experimentally burned skeletal remains to assess skeleton completeness

D. Gonçalves, J. d’Oliveira Coelho, A. Amarante, C. Makhoul, I. Oliveira-Santos, D. Navega, E. Cunha

DOI: http://dx.doi.org/10.1016/j.scijus.2017.07.003

Best regards, Johny