It can tell difference between molecules that originate from life and those that come from non-living sources with 90% accuracy
The AI tool could be used in robotic spacecraft, landers and rovers to search for signs of life before the samples return to Earth. Photo: iStock_ A new artificial intelligence (AI) tool could potentially aid scientists in their search for signs of life on Mars and other planetary bodies, according to a new study.
This new tool can tell the difference between molecules that originate from life and those that come from non-living sources, the study published in journal PNAS stated.
“This routine analytical method has the potential to revolutionise the search for extraterrestrial life and deepen our understanding of both the origin and chemistry of the earliest life on Earth,” Robert Hazen of the Carnegie Institution for Science said in a statement.
Read more: Mars may have been less oxygen-rich than previously assumed
The AI tool could be used in robotic spacecraft, landers, and rovers to search for signs of life before the samples return to Earth, he added.
Easily recognisable signatures of life or biosignatures include body fossils and other biological samples such as shells, teeth, and bones, for example, the paper noted.There are other biosignatures, too. These include deoxyribonucleic acid (DNA), lipids, and atmospheric molecules that are generated when an organism breaks down or metabolises compounds.
Hazen explains that it is relatively easy to recognise Earth’s biosignatures. “But we cannot assume that alien life will use DNA, amino acids,” he added.
The team hypothesised that molecules derived from life follow specific patterns or rules. Deducing them would help them understand the origins of life or detect subtle signs of life in other worlds.
“We began with the idea that the chemistry of life differs fundamentally from that of the inanimate world; that there are ‘chemical rules of life’ that influence the diversity and distribution of biomolecules,” Hazen explained.
First, they used sophisticated instruments. One was used to separate and identify ingredients in 134 known non-living and living sources, while the other assisted in determining their molecular weights.
This data was then used to train AI, after which it was asked to predict the origin of new samples. These samples include extraterrestrial ones such as carbonaceous meteorites, which are the most primitive objects in the solar system.
The AI programme was 90 per cent accurate when it was tested against samples that originated from living things (modern shells, teeth, bones, insects, leaves, rice, human hair, and cells preserved in fine-grained rock), remnants of ancient life altered by geological processing (coal, oil, amber, and carbon-rich fossils), and samples with non-living origins, such as pure laboratory chemicals (amino acids) and carbon-rich meteorites, the researchers reported.
Further, the tool demonstrated its prowess in identifying samples that were hundreds of millions of years old.
Read more: Venus might have microbial life in its atmosphere, study shows
There is more — the technology could settle many questions. For instance, scientists have been debating whether 3.5 billion-year-old black sediments from Western Australia contain the remains of ancient microbes.
The team is applying their methods to address these long-standing questions, Hazen said.
“If AI can easily distinguish biotic (living) from abiotic (non-living), as well as modern from ancient life, then what other insights might we gain? For example, could we tease out whether an ancient fossil cell had a nucleus, or was photosynthetic?” Hazen added.
We are a voice to you; you have been a support to us. Together we build journalism that is independent, credible and fearless. You can further help us by making a donation. This will mean a lot for our ability to bring you news, perspectives and analysis from the ground so that we can make change together.
.png)
Comments are moderated and will be published only after the site moderator’s approval. Please use a genuine email ID and provide your name. Selected comments may also be used in the ‘Letters’ section of the Down To Earth print edition.