University of Washington (UW) researchers have developed a model they say can predict which genetic mutations significantly change how genes splice.
The researchers say the model is the first to train a machine-learning algorithm on vast amounts of genetic data created with synthetic biology techniques.
"This model can help you narrow down the universe--hugely--of the mutations that might be most likely to cause disease," says UW doctoral student Alexander Rosenberg.
The team tested the model on several well-understood mutations, such as those in the BRCA2 gene that have been linked to breast and ovarian cancer. The researchers say compared to previously published models, the approach is three times more accurate in predicting how a mutation will cause genetic material to be included or excluded in the protein-making process.
Using common molecular biology methods, the UW team created a library of more than 2 million synthetic "mini-genes" by including random DNA sequences, and then determining how each random sequence element affected where genes spliced and what types of RNA were produced. UW professor Georg Seelig says that larger library of synthetic data teaches the model to become smarter.
The researchers have made a Web tool available to the public, and they plan to expand the approach beyond alternative splicing to other processes that determine how genes are expressed.
From University of Washington News and Information
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found