AlphaFold AI Won The Nobel Prize In Chemistry!

Dear fellow scholars, this is two minute papers with Dr. Zsolnai. The works that you are going to see today give me shivers. You see, earlier we talked about AlphaFold DeepMind's amazing paper on protein folding and I promised to get back to you to show how it is transforming the world around us today. This is not your usual 2 minute papers video, so hold on to your papers fellow scholars, and this is going to be an incredible ride. But wait, I hear you asking the question, what is protein folding? A protein is a string of amino acids. These are the building blocks of life. This is what goes in, which in reality has a 3D structure and that is protein folding. Letters go in and a 3D object comes out. So how hard is it? Well, extremely hard. It is significantly harder than chess and Go, both of which are really challenging games to master. But they have nothing on protein folding. Alright, first project. Plastics are very useful. We use them for single use, drinks, bottles, clothing and carpets and more. We all know that. But the problem with plastics start the moment we are done with them. You see, 400 million tons of it is produced every year around the world. And unfortunately, you guessed it right, most of them end up in landfills. And this project is about evolving enzymes. What kind of enzymes? Well, hold on to your papers fellow scholars, because these are enzymes that are made to be able to digest these plastics. Yes, that's right. It is breaking these plastics down, but it gets better. It even helps recycling them so they can be used over and over again infinitely like glass or tin cans. We won't need to produce more of these, which requires fossil fuels. And we can clean up these landfills with it. This sounds like a science fiction movie and it came right out of a paper that was published in 2021. I am truly out of words. Now this research group notes that experiments like these were underway for a long time. But the protein structure prediction steps took years and years. Often an entire PhD thesis took on solving a single protein structure. And now with AlphaFold, they only take a few minutes and they are super accurate. Hence biologists can run not one experiment in a few years, but they can run hundreds or even thousands of experiments at the same time, almost in real time. Now this is an AI collaborating with humans to solve important problems. They call it a complete paradigm shift. But all this is just the start. Other Alphafold based projects are also underway. For instance, this research group was wondering that if it can study living proteins, can it maybe study extinct ones too? If that would be true, that would open up amazing new techniques in paleoproteomics, the study of ancient proteins. What does this mean? Well, for instance, it helped this research group learn how an ancient bird went extinct. The problem was that they couldn't get usable DNA out of these ancient eggs, as these structures break down very quickly. Studying the proteins of the eggshell instead would be so much more convenient because they live on for 10 times longer and they also need much less of them. Hmm. Are you thinking what I am thinking? Oh yes. That is exactly what AlphaFold is for. So they have done exactly that and were able to compare those proteins to that of modern birds and and found out which one of the current birds are the most similar to it. They found out that this was a huge flightless bird, similar to an ostrich that went extinct because unfortunately, humans were looking to eat their eggs. AlphaFold helped solve this huge mystery and no doubt it will help solve many more in the future. I love how in this project AlphaFold is like a lens that helps us look back in time even further and even more accurately. This is an incredible scientific achievement. It is also currently being used to study and perhaps treat diseases that ail millions and millions of people around the world once again. All this from a paper that was published in 2021. This work is perhaps the the most important paper of the last decade and is going to change the world for the better as we know it. What a time to be alive. So what do you think? What else will AlphaFold be useful for? Let me know in the comments below. Weights and Biases provides tools to track.

Your experiments in your deep learning projects.

What you see here is their tables feature.

And the best part about it is that it is not only able to handle pretty much any kind of data.

You can throw at it, but it.

Also presents your experiments to you in a way that is easy to understand. It is used by many prestigious labs including OpenAI, Toyota Research, GitHub and more. And the best part is that Weights and Biases is free for all individuals, academics and open source projects. Make sure to Visit them through wnb.com papers or just click the link in the video description and you can get a free demo today. Our thanks to Weights and Biases for their long standing support and for helping us make better videos for you.

Thanks for watching and for your generous support and I'll see you next time.