Understanding the faulty proteins linked to cancer and autism — Google DeepMind Skip to main content Explore our next generation AI systems Explore models Gemini Gemini Build intelligent agents Gemini Omni Create anything from anything Nano Banana Create and edit detailed images Gemini Audio Talk, create and control audio Specialized models Veo Generate cinematic video with audio Imagen Generate high-quality images from text Lyria Generate high fidelity music and audio World models & embodied AI Genie 3 Generate and explore interactive worlds Gemini Robotics Perceive, reason, use tools and interact Open models Gemma Build responsible AI applications at scale Our latest AI breakthroughs and updates from the lab Explore research Breakthroughs SIMA 2 An agent that plays, reasons, and learns with you Genie 3 Generate and explore interactive worlds AlphaGo Mastering the game of Go Gemini Robotics Perceive, reason, use tools and interact Learn more Evals Publications Responsibility Unlocking a new era of discovery with AI Explore science Breakthroughs AlphaFold Predict protein structures with high accuracy WeatherNext Fast and accurate AI weather forecasting AlphaEarth Map our planet in unprecedented detail AlphaEvolve Design advanced algorithms for math and applications in computing Learn more Gemini for Science Experimental Tools Science Skills Our mission is to build AI responsibly to benefit humanity About Google DeepMind Responsibility Ensuring AI safety through proactive security, even against evolving threats News Discover our latest AI breakthroughs, projects, and updates Careers We’re looking for people who want to make a real, positive impact on the world Learn more Education Our National Partnerships for AI Accelerator programs The Podcast Models Explore our next generation AI systems Explore models Gemini Gemini Build intelligent agents Gemini Omni Create anything from anything Nano Banana Create and edit detailed images Gemini Audio Talk, create and control audio Specialized models Veo Generate cinematic video with audio Imagen Generate high-quality images from text Lyria Generate high fidelity music and audio World models & embodied AI Genie 3 Generate and explore interactive worlds Gemini Robotics Perceive, reason, use tools and interact Open models Gemma Build responsible AI applications at scale Research Our latest AI breakthroughs and updates from the lab Explore research Breakthroughs SIMA 2 An agent that plays, reasons, and learns with you Genie 3 Generate and explore interactive worlds AlphaGo Mastering the game of Go Gemini Robotics Perceive, reason, use tools and interact Learn more Evals Publications Responsibility Science Unlocking a new era of discovery with AI Explore science Breakthroughs AlphaFold Predict protein structures with high accuracy WeatherNext Fast and accurate AI weather forecasting AlphaEarth Map our planet in unprecedented detail AlphaEvolve Design advanced algorithms for math and applications in computing Learn more Gemini for Science Experimental Tools Science Skills About Our mission is to build AI responsibly to benefit humanity About Google DeepMind Learn more Education Our National Partnerships for AI Accelerator programs The Podcast Responsibility Ensuring AI safety through proactive security, even against evolving threats News Discover our latest AI breakthroughs, projects, and updates Careers We’re looking for people who want to make a real, positive impact on the world Build with Gemini Try Gemini Google DeepMind Google AI Learn about all our AI Google DeepMind Explore the frontier of AI Google Labs Try our AI experiments Google Research Explore our research Products and apps Gemini app Chat with Gemini Google AI Studio Build with our next-gen AI models Google Antigravity Our agentic development platform Models Research Science About Build with Gemini Try Gemini September 26, 2022 ScienceUnderstanding the faulty proteins linked to cancer and autism Share Copied AlphaFold is helping researchers uncover how protein-mutations cause disease, and how to prevent them Luigi Vitagliano is a Research Director at the Institute of Biostructures and Bioimaging in Naples, Italy. He shares his AlphaFold story. Being a structural biologist in the age of AlphaFold is like the early days of gold mining. Before this technology, everyone was doing painstaking work to find individual gold nuggets, cleaning them and looking at them one by one. Then, all of a sudden, a gold mine appeared. We couldn’t believe our luck. For 30 years, I’ve been studying the proteins encoded in our DNA. Within most human cells, there are somewhere between 20,000 and 100,000 different proteins. In certain instances, the way the string of amino acids in a protein takes its shape, also known as 'protein folding' can be full of irregularities, and these are linked to lots of diseases. Recently, I’ve been looking at a family of human proteins, known as potassium channel tetramerisation domain (KCTD) proteins, that are particularly poorly understood. What is particularly interesting about mutations in these proteins - caused by genetic mutations - is the range of diseases that they are linked to: from schizophrenia to autism, and leukaemia to colorectal cancers, as well as brain and movement disorders. As new proteins are constantly being made inside cells, old or defective ones need to be removed. There are 25 kinds of KCTD proteins in humans, and four-fifths of them seek out other proteins and mark them for degradation and destruction. This process is called ubiquitination and it is essential for keeping cells healthy and helping to prevent disease. When KCTD proteins don’t work properly, the consequences can be debilitating to our health. However there’s a lot we don’t understand about them, too. About one-fifth of KCTD proteins inside cells were mysteries to scientists like me: we had no idea what they do, and therefore how to prevent them mutating and causing disease. Until now, we’ve had very little structural information on them, which has been a major barrier to KCTD research. Entire generations of eminent scientists have been unable to solve this problem. Then, almost miraculously, a solution appeared. Luigi Vitagliano Research Director The structures predicted by AlphaFold revealed that over the course of evolution their structures have remained very similar despite having very different genetic codes. This was a significant breakthrough. Previously, we’ve relied on genetics to assess the similarities or differences between proteins. Based on genes alone, we thought these proteins would be very different. Using AlphaFold, we were able to build a new evolutionary family tree based on the shape of these proteins rather than their genetic sequence. Evolutionary trees are usually built using genetic information, but they don’t take structural similarities into account. Structure relates to function, so using this approach is thrilling – it could reveal all kinds of mysteries about which KCTD proteins have similar functions and how these functions evolved over time. I used AlphaFold to look at and compare the structure of all 25 KCTD proteins for similarities and differences, to identify which parts of these proteins are important. To our delight, AlphaFold's predicted structures appeared to be very accurate. For example, we already knew that one section of the KCTD proteins – the BTB domain – was similar amongst all family members, and so we presumed this was the most important part. AlphaFold has revealed many more additional structural similarities amongst these proteins and has opened up an entirely new realm of exploration. For 60 years – including the 30 years that I’ve been working in this field – we’ve tried and failed to find the connection between sequences and structures. Entire generations of eminent scientists have been unable to solve this problem. Then, almost miraculously, this solution appeared. All of our data, the structural information for all members of the KCTD family, has come from AlphaFold. Without it, this study couldn’t have been done at all. My feeling was that AlphaFold was a dream. If somebody had told me that in two years we will have over 200 million protein structures, I wouldn’t have believed them. Now, what lies in the decades ahead is finding out exactly what these proteins do. There’s a lot more excitement and discovery ahead. Related posts AlphaFold Learn more Tracing the evolution of proteins back to the origin of life July 2022Science Learn more The race to cure a billion people from a deadly parasitic disease July 2022Science Learn more Creating plastic-eating enzymes that could save us from pollution July 2022Science Learn more Accelerating the race against antibiotic resistance July 2022Science Learn more Fighting osteoporosis before it starts September 2022Science Learn more Solving the mystery of how an ancient bird went extinct September 2022Science Learn more Stopping malaria in its tracks October 2022Science Learn more AlphaFold transforms biology for millions around the world July 2022Science Learn more AlphaFold unlocks one of the greatest puzzles in biology July 2022Science Learn more Targeting early-onset Parkinson’s with AI September 2022Science Learn more Breeding healthier and stronger honeybees November 2025Science Learn more Advancing discovery of better drugs and medicine July 2022Science Learn more Follow us Sign up for updates on our latest innovations I accept Google's Terms and Conditions and acknowledge that my information will be used in accordance with Google's Privacy Policy. Sign up Build AI responsibly to benefit humanity Models Gemini Gemini Omni Nano Banana Gemini Audio Gemma Genie Lyria Veo Research Gemini Robotics Breakthroughs Evals Publications Responsibility Science AlphaFold AlphaGenome WeatherNext AlphaEarth AlphaEvolve Products Gemini app Google AI Studio Google Antigravity Learn more About News Careers National Partnerships for AI Accelerator programs The Podcast About Google Google products Privacy Terms Cookies management controls