Communications of the ACM
System Can Generate AI Models for Biology Research
The BioAutoMATED AutoML system can select and build an appropriate model for a given dataset.
Credit: Unsplash
Is it possible to build machine-learning models without machine-learning expertise?
Jim Collins, a professor in the Department of Biological Engineering at MIT, and colleagues tackled this problem and built a platform to automate machine-learning for biological sequence analysis. They describe their proposed solution, called BioAutoMATED, in an article published in Cell Systems.
BioAutoMATED is an automated machine-learning system that can select and build an appropriate model for a given dataset and even take care of the laborious task of data preprocessing, whittling down a months-long process to just a few hours.
The open-source code is publicly available and easy to run, the researchers say. "What we would love to see is for people to take our code, improve it, and collaborate with larger communities to make it a tool for all," says co-author Luis Soenksen, a postdoc researcher at the Abdul Latif Jameel Clinic for Machine Learning in Health.
From MIT News
View Full Article
No entries found