Big data produced during decades of research was fed into a computer-oriented language model to ascertain if AI can make more advanced discoveries than humans.
Their ground-breaking study has been published within the scientific journal PNAS and will be utilized in the longer term to correct the grammatical mistakes inside cells that cause disease.
Professor Tuomas Knowles, the first author of the paper and a Fellow at St John’s College, said: “Bringing machine-learning technology into research into brain atrophy diseases and cancer is an absolute game-changer. Ultimately, the aim is going to be to use AI to develop targeted drugs to dramatically ease symptoms or to stop dementia happening in the least .”
Similar algorithms are employed by many video streaming applications just like Netflix. Whenever the app suggests a replacement video to observe that supports your history of video streaming, it uses an equivalent method to form highly educated guesses.
Similarly, when the social site Facebook asks you to befriend some people, it uses an equivalent algorithm. Voice assistants like Alexa and Siri, used by some tech giants, can even recognize individual people and instantly have a conversation with you.
Dr. Kadi Liis Saar, the primary author of the paper and a search Fellow at St John’s College said, “We specifically asked the program to find out the language of shapeshifting biomolecular condensates — droplets of proteins found in cells — that scientists actually need to know to crack the language of biological function and malfunction that cause cancer and neurodegenerative diseases like Alzheimer’s. We found it could learn, without being told, what scientists have already discovered about the language of proteins over decades of research.”
Proteins are the most building blocks of the body. They are doing most of the add cells and are required for the structure, function, and regulation of the body’s tissues and organs. Scientists now think that some disordered proteins also form liquid-like droplets of proteins called condensates that do not have a membrane and merge freely with one another.
These condensates are under tons of attention within the scientific world because they command key events within the cell-like organic phenomena, how our DNA is converted into proteins, and how protein is synthesized in our body.
The algorithm is fed all of the knowledge of the persisted known proteins so it could learn and predict the language of proteins within the same way these models study human language and the way WhatsApp knows the way to suggest words for you to use.
Further use of machine learning could transform future research in cancer and neurodegenerative disease. Discoveries might be made beyond what scientists currently already know and speculate about diseases and potentially even beyond what the human brain can understand without the assistance of machine learning.
Also Read: A Surge In Fire Accidents Amid The Pandemic
