fbpx
New AI Tools Open the Door for Greater Astrobiology Research New AI Tools Open the Door for Greater Astrobiology Research
AI has been making waves in multiple fields for its ability to detect patterns more efficiently than humans. In one such... New AI Tools Open the Door for Greater Astrobiology Research

AI has been making waves in multiple fields for its ability to detect patterns more efficiently than humans. In one such field, Astrobiology, new deep learning techniques are poised to discover a treasure trove of new protein families that could help unlock new mysteries.

In a study published in Nature, a research team at the University of Basel and the SIB Swiss Institute of Bioinformatics have used deep learning to make these discoveries and help push the envelope of protein science.

This was all made possible by AlphaFold, which made waves by discovering almost every known protein on Earth. The tool which was trained on protein data collected by life scientists over the past half century, can predict the three-dimensional shapes of proteins with a high level of accuracy.

Because of AlphaFold’s success, the team was able to model 215 million proteins. This massive number is providing them with insights into the possible shape of almost any protein. This is quite useful because it allows for the study of proteins that have not yet been studied experimentally.

Joana Pereira, the leader of the study said, “There are now many sources of protein information, enclosing valuable insights into how proteins evolve and work.” One of the issues that had to be handled before AI tools such as AlphaFold was the sheer amount of data.

This data, though valuable, proves difficult to sift through over time without large numbers of human labor. But with AlphaFold, it’s now viable. During the study, the researchers constructed an interactive network of 53 million proteins with high-quality AlphaFold structures.

Dr. Janani Durairaj, the first author said, “This network serves as a valuable source for theoretically predicting unknown protein families and their functions on a large scale.” The team was able to identify 290 new protein families and one new protein fold that looks to resemble the basic shape of a flower.

For fields such as Astrobiology, AlphaFold can unlock new possibilities never thought possible for proteins. Providing new insights on possible paths of evolution, which if proven over time, should showcase the diverse nature of life in the cosmos.

Janani Durairaj concludes, “We hope this resource will help not only researchers and curators but also students and teachers by providing a new platform for learning about protein diversity, from structure, to function, to evolution.”

But it’s not just in Astrobiology where AlphaFold shining. Researchers have leaned on AlphaFold in the past to also help accurate drug discovery and other medical advancements.

ODSC Team

ODSC Team

ODSC gathers the attendees, presenters, and companies that are shaping the present and future of data science and AI. ODSC hosts one of the largest gatherings of professional data scientists with major conferences in USA, Europe, and Asia.

1