Artificial intelligence will help scientists soon know if there was life on Mars

The artificial intelligence has provided a new simple and reliable test to detect signs of past or present life on other planets, what they call ‘the holy grail of astrobiology’.

A seven-member team, funded by the John Templeton Foundation and led by Jim Cleaves and Robert Hazen of the Carnegie Institution for Science, reports in the Proceedings of the National Academy of Sciences that, with an accuracy of 90%its method based on artificial intelligence distinguished modern and ancient biological samples from those of abiotic origin.

LOOK: The chatbot with artificial intelligence ChatGPT is updated and now I could “see, hear and speak”

“This routine analytical method has the potential to revolutionize the search for extraterrestrial life and deepen our understanding of both the origin and chemistry of the most primitive life on Earth. -says Dr. Hazen-. “It paves the way for the use of smart sensors in robotic spacecraft, landers and rovers to search for signs of life before samples return to Earth.”.

More immediately, the new test could reveal the history of mysterious, ancient rocks on Earth, and possibly that of samples already collected by the Sample Analysis at Mars (SAM) instrument on the Mars Curiosity rover. These latest tests could be performed with an onboard analytical instrument dubbed SAM (for Sample Analysis at Mars.

“We will have to adjust our method to match SAM protocols, but we may already have data in hand to determine if there are molecules on Mars coming from a Martian organic biosphere.”he comments.

“The search for extraterrestrial life remains one of the most tantalizing endeavors of modern science.”adds lead author Jim Cleaves of the Earth and Planet Laboratory at the Carnegie Institution for Science.

Probing Martian rocks with the Perseverance rover. (POT/)

“The implications of this new research are many, but there are three big conclusions, he emphasizes: First, at some deep level, biochemistry differs from abiotic organic chemistry; second, we can look at samples from Mars and ancient Earth to see if they were ever alive; and third, it is likely that this new method can distinguish alternative biospheres from those of Earth, with significant implications for future astrobiology missions.”

The innovative analytical method is not based simply on the identification of a specific molecule or group of compounds in a sample.

Instead, Researchers showed that AI can differentiate biotic from abiotic samples by detecting subtle differences in the molecular patterns of a samplerevealed by pyrolysis gas chromatography analysis (which separates and identifies the components of a sample), followed by mass spectrometry (which determines the molecular weights of those components).

LOOK: Opportunity or threat? How journalists view artificial intelligence according to a study

Extensive multidimensional data from molecular analyzes of 134 known carbon-rich abiotic or biotic samples were used to train the AI ​​to predict the origin of a new sample. With an approximate accuracy of 90%, the AI ​​successfully identified samples originating from living beings, such as modern shells, teeth, bones, insects, leaves, rice, human hair and cells preserved in fine-grained rocks; remains of ancient life altered by geological processes (e.g., coal, oil, amber, and carbon-rich fossils), and samples of abiotic origin, such as pure laboratory chemicals (e.g., amino acids) and carbon-rich meteorites.

The authors add that until now it has been difficult to determine the origin of many ancient carbon-rich samples because collections of organic molecules, whether biotic or abiotic, tend to degrade over time.

Surprisingly, despite the significant decomposition and alteration, The new analytical method detected signs of biology preserved in some cases for hundreds of millions of years.

“We started 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 points out –. If we could deduce those rules, we could use them to guide our efforts to model the origins of life or detect subtle signs of life on other worlds.”

“These results mean that perhaps we can find a form of life from another planet, another biosphere, even if it is very different from the life we ​​know on Earth,” he suggests. And, if we find signs of life elsewhere, we will be able to know if life on Earth and on other planets derived from a common or different origin.”.

“In other words, the method should be able to detect alien biochemistry as well as terrestrial life. This is very important because it is relatively easy to detect the molecular biomarkers of terrestrial life, but we cannot assume that extraterrestrial life will use DNA, amino acids, etc. -he highlights-. Our method looks for patterns in molecular distributions that arise from life’s demand for “functional” molecules.”.

“What really amazed us was that we trained our machine learning model to predict only two types of samples, biotic or abiotic, but the method discovered three distinct populations: abiotic, living biotic, and fossil biotic,” he continues. In other words, he could distinguish the most recent biological samples from the fossil ones: a freshly plucked leaf or vegetable, for example, from something that died a long time ago. “This surprising finding makes us optimistic about the possibility of also distinguishing other attributes, such as photosynthetic life or eukaryotes (cells with a nucleus).”.

Technique could soon solve several Earth scientific mysteries, such as the origin of Western Australia’s 3.5 billion-year-old black sediments, much-discussed rocks that some researchers say harbor the oldest fossil microbes on Earth, while others claim they lack signs of life. And other ancient rock samples from northern Canada, South Africa and China spark similar debates.

“We are now applying our methods to answer these long-standing questions about the biogenicity of the organic material in these rocks,” confirms Hazen, and new ideas have emerged about the possible contributions of this new approach in other fields such as biology, paleontology and archaeology.

“If AI can easily distinguish biotic from abiotic, as well as modern life from ancient life, what other insights might we gain? For example, could we find out if an ancient fossil cell had a nucleus or was photosynthetic? -Hazen wonders-. Could you analyze charred remains and discriminate different types of wood from an archaeological site? It’s like we’re just dipping our toes in the water of a vast ocean of possibilities.”.

Source: Elcomercio