Sign in with Facebook
Bharath Ramsundar’s Followers (1)
Bharath Ramsundar
* Note: these are all the books on Goodreads for this author. To add more, click here.
“It begins with the siRNA binding to a collection of proteins called the RNA-induced silencing complex (RISC). The RISC uses the siRNA as a template to search out matching mRNAs in the cell and degrade them. This serves both as a mechanism for regulating gene expression and as a defense against viruses. It also is a powerful tool for biology and medicine. It lets you temporarily “turn off” any gene you want. You can use it to treat a disease, or to study what happens when a gene is disabled. Just identify the mRNA you want to block, select any short segment of it, and create a siRNA molecule with the complementary sequence.”
― Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More
― Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More
“Proteins often bind to small molecules. Sometimes that binding behavior is central to the protein’s function: the main role for a given protein can involve binding to particular molecules. For example, signaling transduction in cells often passes messages via the mechanism of a protein binding to another molecule. Other times, the molecule binding to the protein is foreign: possibly a drug we’ve created to manipulate the protein, possibly a toxin that interferes with its function.”
― Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More
― Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More
“There are two main approaches to predicting protein structures. The first is called homology modeling. Protein sequences and structures are the product of billions of years of evolution. If two proteins are near relatives (the technical term is “homologs”) that only recently diverged from each other, they probably have similar structures. To predict a protein’s structure by homology modeling, you first look for a homolog whose structure is already known, then try to adjust it based on differences between the sequences of the two proteins. Homology modeling works reasonably well for determining the overall shape of a protein, but it often gets details wrong. And of course, it requires that you already know the structure of a homologous protein. The other main approach is physical modeling. Using knowledge of the laws of physics, you try to explore many different conformations the protein might take on and predict which one will be most stable. This method requires enormous amounts of computing time. Until about a decade ago, it simply was impossible. Even today it is only practical for small, fast-folding proteins. Furthermore, it requires physical approximations to speed up the calculation, and those reduce the accuracy of the result. Physical modeling will often predict the right structure, but not always.”
― Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More
― Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More
Is this you? Let us know. If not, help out and invite Bharath to Goodreads.
