Communications of the ACM
Google, Stanford Use Machine Learning on 37.8m Data Points For Drug Discovery
Researchers at Google and Stanford University have used machine-learning techniques to identify effective treatments for a variety of diseases.
Credit: CIO Australia
Researchers at Stanford University and Google have used machine-learning techniques, including deep learning and multitask networks, to find effective drug treatments for a variety of diseases. The researchers worked with 259 publicly available datasets on biological processes, containing 37.8 million data points for 1.6 million compounds.
"Because of our large scale, we were able to carefully probe the sensitivity of these models to a variety of changes in model structure and input data," the researchers wrote on the Google Research Blog.
The goal was to quantify how the amount and diversity of screening data from a variety of diseases with very different biological processes can be used to improve the virtual drug-screening predictions. "Our models are able to utilize data from many different experiments to increase prediction accuracy across many diseases," the researchers wrote.
The learning models were evaluated using "area under the receiver operating characteristic curve," a measure for classification accuracy.
The researchers noted a key finding of their work was that multitask networks allow for significantly more accurate predictions than single-task methods, and their predictive capability improves as more tasks and data is added to the models.
From CIO Australia
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found