Generating molecules with optimized aqueous solubility using iterative graph translation
Abstract
We present a generative modeling framework that can be used to discover new, optimal molecules. Our method involves iteratively 1) training a translation model, and 2) translating all molecules in the training dataset.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jan 01, 2022
- Source ID
- 10.1039/d1re00315a
Entities
People
- Camille L Bilodeau
- Hongyun Xu
- Jillian A Emerson
- Klavs F. Jensen
- Regina Barzilay
- Sukrit Mukhopadhyay
- Thomas H. Kalantar
- Tommi S. Jaakkola
- Wengong Jin
Organizations
- Defense Advanced Research Projects Agency
- Defense Threat Reduction Agency
- Dow Chemical Company
- Massachusetts Institute of Technology