From alien water worlds to the origin of life on Earth, life needs to withstand harsh conditions like extreme cold and heat, radiation, and massive underwater pressure.
For humans, exploring environments outside our narrow ranges — think oxygen, pressure, toxins — can be close to impossible, let alone the support systems we need like food, water, and mental fitness for long voyages into the unknown.
But these are problems that artificial intelligence does not have, and John Hopkins University has been exploring how AI can be used to reveal life in distant worlds, or in extreme areas of our own blue marble.
Key Takeaways
- Life can survive in extreme conditions like heat, cold, radiation, and high pressure — but humans face limitations in exploring these environments and need complex support systems.
- AI can bypass these challenges, helping to study life in extreme conditions on Earth and beyond.
- Johns Hopkins scientists are using AI to simulate deep ocean conditions, studying and discovering how proteins evolve under pressure.
- This research shows AI’s potential to accelerate understanding of life’s origins and possibilities on other planets.
AI Simulation Explores Proteins under Deep Ocean Pressure
Using a free and public artificial intelligence application, John Hopkins scientists have simulated deep ocean conditions and observed how proteins — the building block of life — evolve down there.
The findings, published in PRX Life, serve as a successful case study on how AI was able to accelerate research by decades.
The study found how a heat-loving microbe, Thermus thermophilus, can withstand immense pressures in the deepest ocean trenches. Researchers discovered that these proteins possess a unique flexibility that allows them to compress without collapsing, providing valuable insights into how life might adapt to extreme environments.
The John Hopkins study suggests that life on other planets might thrive in high-pressure environments, such as deep oceans. This research has significant implications for understanding the evolution of life on Earth and potentially on other planets.
Johns Hopkins University Chemist, Stephen Fried, who co-led the research, spoke to Techopedia about the study and its implications.
“This work gives us a better idea of how you might design a new protein to withstand stress and new clues into what types of proteins would be more likely to exist in high-pressure environments like those at the bottom of the ocean or on a different planet.”
Fried’s team subjected Thermus thermophilus — a microorganism widely used in scientific experiments owing to its ability to withstand heat — to lab-simulated pressures mimicking those of the Mariana Trench.
The tests revealed some of its proteins resist those stress levels because they have a built-in flexibility with extra space between their atomic structures, a design that allows them to compress without collapsing.
Fried explained that two scenarios are commonly discussed for origins on earth — warm little ponds and deep hydrothermal vents.
“Each has some advantages from a prebiotic chemistry perspective,” Fried said.
“Warm little ponds would have made the emergence of first biopolymers easier; Hydrothermal vents would have provided easier access to energy and thermodynamic gradients before the development of modern metabolism.”
Hydrothermal vents tend to be deep, so the ‘Origin of Life’ connection is to better understand how and if proteins could have worked deep under the sea.
“I think my main conclusion (on the study) would be to say that many proteins could have been stable at high pressures, and so being deep under the ocean would likely not preclude the emergence of proteins.”
Fried recognized that the study probably has deeper implications for astrobiology than for the ‘Origin of Life’ science.
“Because there are many ocean worlds where life — if it were there — would definitely have to be living under high hydrostatic pressure.”
‘A Leap In Scientific Innovation Using Google’s AlphaFold AI’
Sid Rao, CEO and co-founder of Positron Networks, an AI-driven platform for scientific computing and accelerated research, told Techopedia that the Johns Hopkins’ study has demonstrated a remarkable leap in scientific innovation driven by the power of AI.
“The Johns Hopkins team has successfully utilized Alphabet’s AlphaFold model to simulate early Earth conditions, revealing how specialized AI models can revolutionize our understanding of complex processes, such as protein folding,” Rao said.
Professor Fried from John Hopkins explained that the team used AlphaFold2-v4, a notable free and public tool, for every protein,.
The team did not retrain the model. But they did find a new way to use AlphaFold.
Surprisingly, despite its sophisticated computations, AlphaFold2 is not a generative AI, but a model that Fried compared to ‘older’ generations.
“AlphaFold 2 is designed specifically for protein structure prediction, not for general content generation, ” Fried said.
“And while AlphaFold 2 does generate 3D protein structures, it’s based on existing protein sequences rather than creating novel content from scratch.
“I think our project highlights how powerful these types of models are and the importance of releasing results and making them available on databases.”
Roa from Positron Networks said the study represents an achievement that underscores a vital point — while much attention is given to generative AI chatbots, the true impact of large language models like Alpha Fold is found in their specialized applications.
How Proteins Life Functions Buckle Under Pressure
The study found that 60% of the proteins in the bacteria resisted the pressure while the rest “buckled under it and their shapes became deformed” at points known to be of important biochemical function.
The insights could help explain how other organisms thrive under extreme pressures that would kill most living things.
Johns Hopkins chemist Haley Moran, who studies “extreme” organisms, spoke about the findings of the study.
“A lot of people predict if we are going to find extraterrestrial life, we’re going to find it deep in the ocean of some planet or moon. But we don’t fully understand life in our own ocean, where there are many different species that don’t just tolerate what would kill us, they love it and thrive in it.”
“We are taking proteins, one of the building blocks of life, and putting them under these extreme conditions to see how they may adapt to push the bounds of life.”
A proteome-wide view of protein structural deformation under pressure. Image John Hopkins.
The Johns Hopkins team already has plans for a new study and experiments on other organisms, specifically species that thrive under high pressures in the deep ocean. Fried spoke about what exactly they will investigate and why.
“We want to look at piezophiles, organisms that actually live in the deep ocean. This project looked at an organism that is not a piezophile, and where some of its proteins do deform under high pressure. But what about an organism that lives in the deep… would we find that its protein deforms when pressure is removed?”
The Bottom Line
Where does life come from, is there life in worlds beyond our own, how do species evolve and thrive despite being subject to the constant pounding of extreme environments? These and many others continue to be unanswered questions.
John Hopkins’ study not only provides initial exploratory evidence to take on these issues but proves that AI has a vital role to play in accelerating and enhancing scientific research.
There are endless simulations that can be created today with specialized AI technologies that are not expensive. This opens the doors to exciting possibilities, the exploration of life and the unknown.
References
- PRX Life 2, 033011 (2024) – Proteome-Wide Assessment of Protein Structural Perturbations under High Pressure (Journals.aps)
- Krieger School of Arts & Sciences | Johns Hopkins University (Krieger.jhu)
- Stephen Fried | Department of Chemistry | Johns Hopkins University (Chemistry.jhu)
- Sid Rao – Positron Networks | LinkedIn (Linkedin)
- Positron: AI-Driven Scientific Computing for Innovation (Positronnetworks)
- AlphaFold – Google DeepMind (Deepmind)
- AlphaFold Protein Structure Database (Alphafold.ebi.ac)
- Team — The Fried Lab (Friedlab)