AlphaFold has changed science. 5 years later, it’s still evolving

For example, researchers at Imperial College have been investigating how some “pirate phages” – those wonderful viruses that hijack other viruses – manage to break into bacteria. Understanding these mechanisms could open entirely new ways to treat drug-resistant infections, which constitute a huge global health challenge.

What the co-scientist brought to this work was the ability to quickly analyze decades of published research and independently come up with a hypothesis about bacterial gene transfer mechanisms that matches what the Imperial team spent years developing and experimentally validating.

What we’re really seeing is that the system can dramatically compress the hypothesis generation phase — quickly accumulating massive amounts of literature — while human researchers are still designing trials and understanding what the results actually mean for patients.

Looking ahead to the next five years, beyond proteins and materials, what is the “unsolved problem” that keeps you up at night that these tools can help solve?

What really excites me is understanding how cells function as complete systems, and deciphering the genome is key to achieving this.

DNA is the recipe book of life, and proteins are the ingredients. If we can truly understand what makes us different genetically and what happens when DNA changes, we open up extraordinary new possibilities. This is not just limited to personalized medicine, but it is possible to design new enzymes to address climate change and have other applications that extend beyond health care.

However, mimicking an entire cell is one of the main goals of biology, but it remains elusive. As a first step, we need to understand the deeper structure of the cell, its nucleus: specifically where each piece of genetic code is read, and how the signaling molecules that ultimately lead to the assembly of proteins are produced. Once we explore the core, we can work our way from the inside out. We are working on this, but it will take several more years.

If we can reliably mimic cells, we could transform medicine and biology. We can computationally test drug candidates before they are manufactured, understand disease mechanisms at a fundamental level, and design personalized treatments. This is actually the bridge between biomimetics and clinical reality that you’re asking about, which is moving from computational predictions to actual treatments that help patients.

This story originally appeared in WIRED Italia and was translated from Italian.