Using AI to detect how humans have adapted to recent diseases

Artificial intelligence can help spot traces of natural selection.

In the natural selection process, beneficial gene mutations are preserved from generation to generation until they become dominant in our genomes. The protection against pathogens drives the process.

However, gene mutations that are protective against one pathogen could make people susceptible to new diseases whenever there is a change in the environment.

Familial Mediterranean Fever (FMF) is one example of such disease. It is an autoimmune disease that has emerged over the past 20,000 years in southern Europe, the Middle East, and northern Africa. Around 50 percent of the people in the region today carry a gene mutation that makes them more susceptible to the disease.

This prevalence of a seemingly detrimental gene mutation could be the consequence of two distinct kinds of natural selection. One choice is ‘incomplete sweep’, where the gene mutation for vulnerability is currently being eliminated from the populace. However, it has not yet been destroyed. For this situation, natural selection is ongoing.

The other option is ‘balancing selection, where some potentially detrimental gene mutations for one condition are preserved in the population because they confer some protection against different diseases. In this case, the gene for FMF susceptibility has been associated with protection against the bacteria Yersinia pestis, which causes the plague.

To determine which version of natural selection is at play in FMF, scientists used advanced AI and large genomic data sets. They trained their algorithm on datasets that have known values to test their ability to spot patterns.

Scientists ran their algorithm on the database for the 1000 genomes project, which holds genomic data for 2,504 individuals from 26 populations, including the relevant ones around the Mediterranean. They discovered that the FMF gene mutations are still prevalent due to ongoing selection; they haven’t reached an equilibrium yet, and natural selection is still acting.

Lead researcher Dr. Matteo Fumagalli, from the Department of Life Sciences at Imperial, said“This is the first tool to test the difference between different types of natural selection, finding signals in the genome that have previously been inaccessible.

“Now we have proven that AI can be used to search genomes for subtle patterns of selection, we can use it to investigate further how humans have both adapted to old diseases, like the plague, and relatively new diseases, like FMF.”

Journal Reference:
  1. Ulas Isildak et al. Distinguishing between recent balancing selection and incomplete sweep using deep neural networks. DOI: 10.1111/1755-0998.13379

See stories of the future in your inbox every morning.