First AI-Based Method for Dating Ancient Genomes Is Created
Complete the form below to unlock access to ALL audio articles.
A new study published in Cell Reports Methods outlines how artificial intelligence (AI) can support DNA analysis of ancient human remains.
Ancient DNA uncovers history of humankind
Advances in next-generation sequencing (NGS) technologies are enabling scientists to analyze samples that contain extremely small amounts of DNA. The application of these technologies to ancient samples, where DNA is significantly degraded, has helped researchers study and understand the history human evolution and our planet.
A critical aspect of piecing together historical events is the ability to date ancient samples. The traditional “gold standard” method for dating in archelogy is radiocarbon dating.
What is radiocarbon dating?
The premise behind radiocarbon dating is that all living organisms absorb carbon from the environment around them – including stable carbon 12 (12C) and radioactive carbon-14 (14C). When organisms die, this absorption stops, the level of 12C at time of death remains, and 14C starts to decay. The rate of this decay can be used as a “clock” to determine when the organism died. As levels of atmospheric carbon shift over time, the method requires reliable historical records of carbon variation levels.
Issues with radiocarbon dating accuracy – and how AI might offer a solution
While radiocarbon dating arguably “revolutionized” the field of archaeological science, it isn’t without its flaws, including accuracy, which scientists have been working to improve. “Unreliable dating is a major problem, resulting in vague and contradictory results,” says Dr. Eran Elhaik, associate professor in molecular cell biology at Lund University.
Elhaik is part of a research team that has developed a novel dating method for ancient genome data, using modern AI technology. The method is called Temporal Population Structure – or TPS – and is an example of supervised machine learning (SML) technology.
“The rationale of TPS is that because most human variation is within continental populations and is subjected to processes such as selection and genetic drift that modulate the allele frequencies over time, there exist markers that exhibit substantially different allele frequencies between different periods, irrespective of geography, that can be used to estimate temporal trends. We called these markers time informative markers (TIMs),” the authors write in the publication outlining their research.
Changes in allelic frequencies – be it via genetic drift or natural selection – create “unique allelic combinations” that characterize the historical period when individuals lived, the research team explains. They call these frequency combinations “temporal components”.
“Due to their association with time, temporal components can be harnessed to convert genomic data into time and predict the age of a sample solely from genotype data,” Elhaik and colleagues say. TPS is trained on the temporal components of thousands of ancient – and modern – genomes and “learns” how to predict their age.
The research team tested their method by analyzing ~5,000 human remains from the Late Mesothilic period (approximately 10,000–8,000 BC) to the present day. When compared to the samples’ known dates, the dates obtained using TPS correlated with “high accuracy”.
“We show that information about the period in which people lived is encoded in the genetic material. By figuring out how to interpret it and position it in time, we managed to date it with the help of AI,” says Elhaik.
The researchers emphasize that TPS will not eradicate the use of radiocarbon dating but can rather be used as a complementary tool for analysis, particularly when there is ambiguity surrounding a radiocarbon dating prediction.
“Radiocarbon dating can be very unstable and is affected by the quality of the material being examined. Our method is based on DNA, which makes it very solid. Now we can seriously begin to trace the origins of ancient people and map their migration routes,” concludes Elhaik.
This article is a rework of a press release issued by the Lund University. Material has been edited for length and content.
Reference: Behnamian S, Esposito U, Holland G, et al. Temporal population structure, a genetic dating method for ancient Eurasian genomes from the past 10,000 years. Cell Rep. Methods. 2022;2(8). doi: 10.1016/j.crmeth.2022.100270.
