A new machine learning algorithm can distinguish between biological and non-biological samples with up to 90% accuracy. Scientists have created a program toArtificial intelligence AI can detect alien life in physical samples, but although a new machine learning algorithm — trained using living cells, fossils, meteorites, and lab-made chemicals — can distinguish between samples of biological and non-biological origin 90% of the time. -According to the scientists who built it-but its inner workings remain a mystery.
Use the test
Scientists say the new test can be used almost immediately, and will search for life on Mars by analyzing data on Martian rocks collected by the Curiosity spacecraft, in addition to the possibility of revealing the origins of mysterious and ancient rocks found on Earth. The team has published the results that… It was reported on September 25 in the journal PNAS.
“These results mean that we may be able to find a life form from another planet, even if it is very different from the life we know on Earth,” says the study’s lead author Robert Hazen, an astrobiologist at the Carnegie Institution for Studies, as told to Science magazine. In Washington, D.C., in a statement, “And if we find signs of life elsewhere, we can find out whether life on Earth and other planets derives from a common or different origin.”
amino acids
Molecular biomarkers of life on Earth are relatively easy to discover, but we cannot assume that alien life would use DNA, amino acids, etc. The study’s scientists explain that their method searches for patterns of life within different elements, as scientists already know that mixing chemicals and keeping them at primordial sea temperatures can generate organic molecules such as amino acids (the basic protein building blocks of life). They have also found evidence of these structural elements on meteorites and even on a distant asteroid.
But if alien hunters want to prove they’ve found extraterrestrial life, they need to answer a simple question: How do we know if the things we find are of biological origin, or if they were formed by the random chance of space chemistry?
Since organic molecules tend to decompose over time, it is difficult for humans to answer this question on their own. So the researchers set out to build a machine learning algorithm that could help.
method used
Scientists began using a method already used on NASA spacecraft: pyrolysis, or airless heating of a sample to separate it into gas and biochar. The decomposed parts of the sample are then arranged by a technique called chromatography, before its atoms are transcribed into data about Mass spectroscopy method.
After receiving data from 134 carbon-rich samples of known origin, the machine learning algorithm distinguished between products of modern and ancient life (such as shells, teeth, bones, coal and amber) and organic compounds of non-biological origins (such as synthetic amino acids) with 90% accuracy.
Mysterious processes
AI systems are largely black box models — viewed only in terms of their inputs and outputs — so researchers aren’t entirely sure what mysterious processes their system goes through to produce its answers, but they said they provide important evidence that the chemistry of life follows different fundamental rules. About those in the inanimate world.
“The implications of this new research are many, but there are three main points,” Jim Cleaves, the study’s lead author, a chemist at the Carnegie Institution for Science, said in the statement. “First, at a deep level, biochemistry is different from abiotic organic chemistry; Second, we can look at ancient Mars and Earth samples to see if they were once alive; “Third, this new method could potentially distinguish alternative biospheres from those found on Earth,” with major implications for future astrobiology missions.
What happens to cancer cells after they die due to treatments?
The future of transportation in the Kingdom.. What will it be like and what will come after the completion of the projects?
The Kingdom is on the way… countries that are moving to increase reliance on nuclear energy
