Leveraging Uncertainty in Machine Learning Accelerates Biological Discovery and Design
Name
1-s2.0-S2405471220303641-main.pdf
Description
Published version
Size
3.88 MB
Format
Adobe PDF
Checksum (MD5)
5aa1399fabe2983bacae56129253e8d0
Author(s)
Hie, Brian
Bryson, Bryan D
Berger, Bonnie
Date Issued
2020
Journal
Cell Systems
Publisher
Elsevier BV
Version
Final published version
Abstract
© 2020 The Author(s) A machine learning algorithm that also reports its certainty about a prediction can help a researcher design new experiments. Algorithms called Gaussian processes trained with modern data can make accurate predictions with informative uncertainty. We leverage this approach to find nanomolar kinase binders, Mycobacterium tuberculosis inhibitors, mutations that enhance protein fluorescence, and genes important for cell development.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Biological Engineering
Ragon Institute of MGH, MIT and Harvard
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs License
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/J.CELS.2020.09.007
