Much of the recent hype around ai has focused on fascinating digital content generated from simple prompts, along with concerns about its ability to decimate the workforce and make malicious propaganda much more convincing. (Fun!) However, some of the most promising (and potentially much less sinister) work in ai is in medicine. A new update to Google's AlphaFold software could lead to new advances in disease research and treatment.
AlphaFold software, from Google DeepMind and Isomorphic Labs (also owned by Alphabet), has already shown that it can predict how proteins fold with surprising accuracy. A staggering 200 million known proteins are cataloged, and Google says millions of researchers have used earlier versions to make discoveries in areas such as malaria vaccines, cancer treatments and enzyme designs.
Knowing the shape and structure of a protein determines how it interacts with the human body, allowing scientists to create new drugs or improve existing ones. But the new version, AlphaFold 3, can model other crucial molecules, including DNA. It can also map interactions between drugs and diseases, which could open interesting new doors for researchers. And Google says it does so with 50 percent greater accuracy than existing models.
“AlphaFold 3 takes us beyond proteins to a broad spectrum of biomolecules,” Google DeepMind research team technology/ai/google-deepmind-isomorphic-alphafold-3-ai-model/#drug-discovery” rel=”nofollow noopener” target=”_blank” data-ylk=”slk:wrote in a blog post;elm:context_link;elmt:doNotAffiliate;cpos:9;pos:1;itc:0;sec:content-canvas”>he wrote in a blog post. “This leap could unlock more transformative science, from developing biorenewable materials and more resilient crops to accelerating drug design and genomics research.”
“How do proteins respond to DNA damage? How do they find it and repair it? John Jumper, Google DeepMind project leader ai-protein-structure-dna/” rel=”nofollow noopener” target=”_blank” data-ylk=”slk:told;elm:context_link;elmt:doNotAffiliate;cpos:10;pos:1;itc:0;sec:content-canvas”>said cabling. “We can begin to answer these questions.”
Before ai, scientists could only study protein structures through electron microscopes and elaborate methods like x-ray crystallography. Machine learning streamlines much of that process by using recognized patterns in its training (a often imperceptible to humans and our standard instruments) to predict protein shapes based on their amino acids.
Google says part of AlphaFold 3's advances come from applying diffusion models to its molecular predictions. Diffusion models are centerpieces of ai imagers like Midjourney, Google's Gemini, and OpenAI's DALL-E 3. The incorporation of these algorithms in AlphaFold “sharpens the molecular structures generated by the software,” such as cabling ai-protein-structure-dna/” rel=”nofollow noopener” target=”_blank” data-ylk=”slk:explains;elm:context_link;elmt:doNotAffiliate;cpos:16;pos:1;itc:0;sec:content-canvas”>Explain. In other words, it takes training that seems confusing or vague and makes very educated guesses based on patterns in your training data to clarify it.
“This is a big breakthrough for us,” said Google DeepMind CEO Demis Hassabis. cabling. “This is exactly what is needed for drug discovery: you have to see how a small molecule will bind to a drug, how strongly and also what else it might bind to.”
AlphaFold 3 uses a color-coded scale to label your level of confidence in your prediction, allowing researchers to take appropriate caution with results that are less likely to be accurate. Blue means high confidence; Red means it is less secure.
Google is manufacturing AlphaFold 3 free for researchers to use for non-commercial research. However, unlike previous versions, the company is not open-sourcing the project. A prominent researcher who makes similar software, Professor David Baker of the University of Washington, expressed his disappointment at cabling that Google chose that route. However, he was also impressed by the software's capabilities. “The structure prediction performance of AlphaFold 3 is very impressive,” he said.
As for what's next, Google says: “Isomorphic Labs is already collaborating with pharmaceutical companies to apply it to real-world drug design challenges and ultimately develop new, life-changing treatments for patients.”
