A team of researchers has announced that AI has helped provide new clues that could help solve a longstanding ancient human mystery involving a mysterious set of ancient human female remains.
In 2018, the discovery sparked curiosity–and controversy–within the anthropological community. Belonging to a teenage girl who lived approximately 50,000 years ago, the remains displayed features that scientists were unable to pinpoint, causing the identity of the ancient early human type she represented to remain in question.
Now, employing artificial intelligence to analyze the prehistory of humankind helped lead one team to the discovery of an unknown human ancestor species that modern humans encountered millennia ago. The findings could also help explain the features of the “hybrid” teenage girl and open the doors for re-discovering new ancient populations that were long forgotten.
Background: AI and The origins of modern humans
About 80,000 years ago, probably due to climate fluctuations, a part of the human population started migrating from the African continent to other continents, in an event we call “Out of Africa”. These massive human migrations led to the colonization of the entire planet and the formation of all current populations.
The migrating groups were composed of modern humans and other extinct hominids from other species and tended to breed with each other. Up until recently, scientists thought that modern humans had only bred with Neanderthals and Denisovans.
This study, however, identified a third companion, long isolated in the DNA of Eurasian populations, by using a new AI technology that sifted through ancient and modern human genetic code.
Analysis: A prehistoric three-way
By combining deep learning algorithms and a statistical method called Bayesian inference, the research team found evidence of what they call a “third introgression”, meaning that a third unknown, ancient population interbred with modern humans during the “Out of Africa” expansion.
“This population is either related to the Neanderthal-Denisova clade or diverged early from the Denisova lineage”, the original paper states. This means that there’s a possibility that this third population could even be a mixture of Neanderthals and Denisovans.
It’s possible that the new AI discovery could explain the appearance and unique features of the teenage girl hybrid fossil that was found in 2018, but the research projects aren’t linked, and a lot more work needs to be done to prove that theory. “Our theory coincides with the hybrid specimen discovered recently in Denisova, although as yet we cannot rule out other possibilities”, genomicist Mayukh Mondal from the University of Tartu in Estonia, said in a press statement at the time of the discovery.
Following these incredible findings, more results are bound to come through in no time, so we might not have to wait for much longer to see this mystery resolved.
Outlook: Unknown third-party
This is the first time that this sort of AI tech was used in the field of human ancestry to account for human evolution, and the fossil evidence available is scarce, but this research allowed the scientific team to uncover a new process of introgression, which ultimately leads us to know a bit more about who we are today.
“So, we thought we’d try to find these places of high divergence in the genome, see which are Neanderthal and which are Denisovan, and then see whether these explain the whole picture,” Bertranpetit told The Smithsonian. “As it happens, if you subtract the Neanderthal and Denisovan parts, there is still something in the genome that is highly divergent.”
Bertranpetit believes that using this type of AI, and other future advances in deep learning technology, is going to help uncover other lost chapters in human history. “This kind of method of analysis is going to have all kinds of new results”, he says. “I am sure that people working in Africa will find extinct groups that are not recognized yet. No doubt Africa is going to show us surprising things in the future”.
The study, published in Nature Communications, is sure to pave the way for the application of this kind of new technology in the fields of biology, genomics, and evolution.