“We specifically asked the program to learn the language of shape-changing biomolecular condensates, which are droplets of proteins found inside cells. Scientists have cancer and neurodegenerative diseases such as Alzheimer’s disease. You really need to understand in order to decipher the biological functions and dysfunctional languages that cause the disease, without being explicitly told that scientists have already discovered the language of proteins in decades of research. I found that I could learn. “
Proteins are large, complex molecules that play many important roles in the body. They do most of the work inside the cell and are required for the structure, function and regulation of body tissues and organs. Antibodies, for example, are proteins that work to protect the body.
Alzheimer’s disease, Parkinson’s disease, and Huntington’s disease are three of the most common neurodegenerative diseases, but scientists believe there are hundreds of them.
In Alzheimer’s disease, which affects 50 million people worldwide, proteins become fraudulent, forming aggregates and killing healthy nerve cells. A healthy brain has a quality control system that effectively disposes of these potentially dangerous protein masses known as aggregates.
Scientists now believe that some chaotic proteins form liquid-like droplets of proteins called condensates that do not have a membrane and fuse freely with each other. Unlike irreversible protein aggregates, protein condensates can form and reshape and are often compared to lumps of reshaping wax in lava lamps.
Professor Knowles said: “Protein condensates have recently received a lot of attention in the scientific world because they control important intracellular events such as gene expression. DNA How cells make proteins, and they are transformed into protein synthesis.
“Defects associated with these protein droplets can lead to diseases such as cancer. Protein dysfunction to allow this to correct the intracellular grammatical errors that cause the disease. That’s why it’s essential to introduce natural language processing technology into the study of molecular origins. “
Dr. Saar said: “We entered all the data held in known proteins into the algorithm so that these models could learn and predict the language of proteins in the same way they learn about human language.
“Then I was able to ask about a particular grammar that leads only a few proteins to form condensates in the cell. It’s a very challenging problem, and unleashing it makes us sick. Will help you learn the rules of the language. “
Machine learning technology is evolving rapidly due to increased data availability, increased computing power, and technological advances that have created more powerful algorithms.
Further use of machine learning can change the study of future cancers and neurodegenerative diseases. Scientists can now make discoveries beyond what they already know and speculate about the disease, and potentially beyond what the human brain can understand without the help of machine learning.
Dr. Saar explains: “Machine learning means freeing us from the restrictions that researchers consider to be the subject of scientific research and finding new connections that we haven’t even thought of yet. It’s really, very exciting.”
The developed network is now created Freely available To researchers around the world to enable more scientists to work on progress.
Reference: “Learn the Molecular Grammar of Protein Condensates from Sequencing Factors and Embeddings” Kadi L. Saar, Alexey S. Morgunov, Runzhang Qi, William E. Arter, Georg Krainer, Alpha A. Lee, Tuomas PJ Knowles, 2021 April 7, Minutes of the National Academy of Sciences..
DOI: 10.1073 / pnas.2019053118
Powerful Algorithms Used by Netflix, Amazon and Facebook Could “Crack the Language of Cancer and Alzheimer’s” Source link Powerful Algorithms Used by Netflix, Amazon and Facebook Could “Crack the Language of Cancer and Alzheimer’s”