Scientists develop AI tool to hunt for hidden signals of past lives they reckon could help search for extraterrestrial organisms on other planets
A new ‘bot could find alien life, experts say. Scientists have developed tech to hunt for hidden signals of past lives. They reckon it could assist in the search for extraterrestrial organisms on other planets.
Pairing cutting-edge chemical techniques with artificial intelligence researchers found evidence of ancient life in 3.3-billion-year-old rocks from Earth.
They hope the same approach could be applied to samples from Mars or icy ocean worlds such as Jupiter’s moon Europa. Research published in Proceedings of the National Academy of Sciences involved analysis of more than 400 samples from ancient sediments, fossils, modern plants and animals, fungi, and meteorites to stress-test the new detection model.
Experts found it was capable of distinguishing material left behind by life from non-biological samples with more than 90% accuracy.
Astrobiologists and planetary scientist Dr Michael Wong said: “This represents an inspiring example of how modern technology can shine a light on the planet’s most ancient stories and could reshape how we search for ancient life on Earth and other worlds. This is a powerful new tool for astrobiology.”
The team used a technique called pyrolysis-gas chromatography-mass spectrometry to uncover faint chemical fingerprints left behind by ancient organisms.
Complex chemical patterns of molecular fragments released from rock samples were analysed using a machine-learning model to identify biosignatures that would otherwise be too degraded to interpret.
Dr Wong’s co-author Dr Robert Hazen said the process represented a ‘paradigm shift’ because the algorithm was not looking for specific molecules – such as DNA – that could be evidence of past life.
Instead it was looking at the distribution of what was present to see if that hinted there may once have been life.
Dr Hazen told the BBC: “For the very first time we’re just looking for a distribution function. That allows us to be much more general when examining highly degraded samples with very little information.”
The oldest biosignature signal detected dated back 3.3 billion years – almost twice as old as the previous limit of 1.7 billion years.
The team also found evidence photosynthesis – in which green plants, algae and bacteria use sunlight, water, and carbon dioxide to create their own glucose food releasing oxygen as a by-product – was occurring at least 2.5 billion years ago.
That is 800 million years earlier than previously thought.
Scientists have previously traced life back 3.5 billion years using two main types of evidence. One involved ancient rock structures created by communities of microbes that grew in sticky, layered ‘mats’ leaving behind mound-like formations known as stromatolites.
The other evidence was telltale shifts in the ratios of isotopes in the rocks. But suitable samples for such detections are rare.
The new machine-learning approach avoids the need for intact fossils or surviving biomolecules offering a complementary line of evidence that can be applied to a far wider range of rocks. It also goes beyond a simple life-versus-no-life test.
The algorithm can distinguish photosynthetic from non-photosynthetic organisms and separate broad groups of cells known as eukaryotes and prokaryotes.
Dr Hazen said the system found ‘very distinct differences’ between samples containing life and no life. That ability could prove crucial on Mars where scientists are not sure what life may have looked like if it existed.
If retrieving samples from Mars proves too expensive Dr Hazen said an instrument-carrying rover could carry out the analysis on the Red Planet’s surface.
His team has received NASA funding to develop such an instrument package. Co-author Dr Anirudh Prabhu said: “What’s exciting is that this approach doesn’t rely on finding recognisable fossils.
“AI didn’t just help us analyse data faster, it allowed us to make sense of messy, degraded chemical data. It opens the door to exploring ancient and alien environments with a fresh lens guided by patterns we might not even know to look for ourselves.”
The authors said the process could become a key analytical tool in terrestrial and planetary science.
Co-author and paleobiologist Professor Andrew Knoll said: “For decades we’ve searched ancient rocks for traces of life using a limited set of tools.
“What’s remarkable about this study is that it adds whole new dimensions – not just better instruments, but better questions.
“Machine learning helps us uncover biological signals that were effectively invisible before. It’s a leap forward in our ability to read the deep-time record of life.”