Illumina AI - ChatGPT for your genome...

Key Takeaways

so alumina unveils AI software to predict disease-causing genetic mutations in patients the AI boom has been mostly sent around the big AI companies and video Google Microsoft open AI Etc that's the space that everyone's watching that's where all the money is Flowing but there's something else Brewing just out of sight in order to understand what's happening it's important to understand how Google's deepmind solved protein folding if you're already familiar with this use the video chapters to skip ahead in 2020 deepmind's Alpha fold 2 solved a 50 year old biology challenge this is one of the biggest advancements in Ai and structural biology in decades in this video I will explain simply what this means and what advancements we can expect next the first thing to understand is that there are amino acids which are the basic building blocks of life think of them like Lego blocks with those Lego blocks we can build proteins so amino acids and proteins are both the building blocks of life but they are also the machines that make life work it's what allows us to see light to move to breathe and to metabolize the things we eat each protein has an intricate shape that defines what it does and how it works we know of over 200 million of proteins and that number is going up as we discover more and more but humans have been pretty bad at understanding the exact 3D shapes of all of these so if we're looking at a Lego castle we know which Lego pieces are used to build it and we kind of know what the castle looks like we just can't build an exact replica of it unravel approach made up of 20 different types of amino acids interactions between these amino acids make the protein fold as it finds its shape out of almost Limitless possibilities for decades a community of scientists have been working on a way to figure out a protein shake just from its string of amino acids this is a major challenge in our understanding of biology our ability to understand protein folding would allow us to understand the actual Machinery that makes life function the sequence of amino acids is folded into unique and specific 3D structure which determines the protein's function it's important to understand that a string of amino acids can fold in many different ways in fact that's an understatement to give you an idea the number of atoms in the universe is 10 to the 82nd power yet the number of unique ways a protein can fold is 10 to the 143rd power these are unimaginably large numbers so basically it would take an enormously long time to go through all the possible configurations yet proteins can fold in seconds or less this by the way is called the 11th house Paradox so out of the 200 plus million of proteins that we are aware of we were able to determine the exact 3D structure of about 170 000 of them we did that using x-ray crystallography which by the way was what Walter White from Breaking Bad was really good at his breakthroughs in x-ray crystallographies would allowed that multi-billion dollar company gray matter to form that's completely unrelated to anything here I just thought I would throw that in anyway Alpha fold is able to take our existing data set of proteins whose structure we know and then predict the 3D structure of other proteins that we do not know this is an important thing to understand without AI it takes us hundreds of thousands of dollars and years to map out these 3D structures it's slow it's expensive and it's very limited but with AI we are able to have it predict new protein structures with ever increasing accuracy as it predicts more protein structures our data sets grow and allow us to improve the ai's ability why is this important how will we use this newfound understanding in the real world well the ability to understand protein function would allow us to know the unknown functions of proteins in our DNA as well as quickly designed new proteins that alter the functions of other proteins this would be massive for pharmaceutical development or our ability to understand and to change the genome this would allow us to treat many diseases create biomaterials that we can use in building as well as agriculture tissue and organ regeneration might be possible as well as supplements for health and anti-aging in the long term it would allow us to create biological simulations and potentially lead to being able to engineer biological life as well as many many more things that we probably can't even think of right now [Music] areas imagine a future where we can understand diseases more quickly and develop drugs to fight them or one where we could use enzymes to break down plastic waste or even to capture carbon from the atmosphere all with the help of proteins there's a lot more work to be done but unlocking the shapes of these building blocks could help scientists better understand the natural world and perhaps expand our knowledge of life itself and people aren't noticing this more and more attention is being paid to the biotech companies where neural networks can be used to accelerate progress people in the space believe that massive progress will be unlocked at the intersection of AI and genetics neural networks are great at swallowing large unmanageable amounts of raw data and spitting out valuable insights and that's what a big part of genomics is it's vast amounts of data that brings us back to Illumina it's a massive company that is a global leader in genomic sequencing genomic sequencing is very basically the process of making DNA readable so let's say you have a blood sample or a spit sample you run it through a machine to sequence it and on the other side you get the exact structure of your DNA the actual data that you can read print out on a piece of paper or feed into a database and there are now global efforts to sequence everyone and use AI to process the data and there are some smart people taking note of this Peter Thiel is a german-american billionaire entrepreneur co-founder of PayPal palantir Technologies and Founders fund he was the first outside investor in Facebook the guy made a lot of money and he's investing in Ultima genomics a competitor to Illumina ultimate genomics is coming out of stealth mode after raising 600 million from investors including and recent Horowitz Peter thiel's founder fund Etc that was in 2022 Carl Icahn the billionaire corporate Raider launched an attack on Illumina buying up shares and trying to land some board seats that was 2023 Stanley druckenmiller who is considered to be one of the best investors of all time recently added 25 million of Illumina to his portfolio this was May 2023 but that number might be a lot higher since there's a delay before they have to disclose their positions with that said I feel like we're going to start seeing a lot more action in this space specifically biotech where AI can play a big role will start growing at a faster rate genomics personalized medicine modified organisms Etc keep in mind that with things like crispr we can pretty much modify DNA in any way that we like for those who are not familiar crispr operates as a kind of molecular scissors allowing researchers to precisely cut a DNA molecule at a desired location either to disrupt a specific gene or to introduce a new genetic sequence so just like we can edit text in a Word document we can edit human genes easy peasy there's just one problem we have no idea what we're doing we have a very tiny understanding of what the code does and how it all works together we can edit the code we just can't edit it safely and we have no idea what it's going to do AI neural Nets seem like they would be the perfect thing to make sense of all this potentially giving us a much stronger ability to control our health as well as develop biological materials and potentially even create bacteria that can eat Plastics or produce biofuel but all this is still borderline science fiction we know it's possible we have some idea of how to do it but nothing that is functional at scale at least right now with that let's get back to that article about illuminaire so Illumina unveils AI software to predict disease-causing genetic mutations in patients it's exciting to see primate AI 3D that's the name of the AI that they're using and the latest in AI technology combined with the most advanced DNA sequencing capability said Francis de Souza Chief Executive Officer of Illumina helping clinicians and researchers keep up with the vast quantities of genomic data now being generated from our platforms holds the potential to exponentially accelerate the critical work underway to better serve patients according to the National Institute of Health the amount of genomic data being generated is approaching 40 billion gigabytes each year the ability to share analyze and interpret genomic data is critical to unlocking discoveries that will advance understanding of human health and improve Precision medicine to achieve its state-of-the-art performance primate AI 3D utilizes deep neural network architecture similar to Chad gbt and Alpha fold but is trained on genome sequences rather than human language they note here that unlike Chad GPT where you know we know what the text says it's a little bit harder of DNA because we don't know what a lot of it is and to overcome this primate AI 3D effectively uses natural selection to train the parameters of the deep neural network using millions of benign genetic variants identified through the sequencing of 233 diverse primate species the largest such sequencing effort of non-human primate species to date the result is a deep neural network that has been shown to identify disease-causing variants with Superior accuracy in all six clinical cohorts that were tested and the big deal here is the accuracy of genetic risk prediction and their elimination of accessory bias this testing is going to be very personalized if you don't fit a certain group of people that's okay because a lot of this is going to be tailored to you and the application of the latest advances in AI to genomics opens tremendous opportunities for Illumina in both genetic risk prediction and Drug Target Discovery by decoding the basis of complex genetic diseases such as diabetes heart disease and autoimmune diseases so what do you think is this kind of a big deal is this the next AI Frontier or is this still way too early to be talking about this let me know in the comments and thank you for watching