Powerful molecule generation with simple ConvNet.
Journal:
Bioinformatics (Oxford, England)
Published Date:
Jun 27, 2022
Abstract
MOTIVATION: Automated molecule generation is a crucial step in in-silico drug discovery. Graph-based generation algorithms have seen significant progress over recent years. However, they are often complex to implement, hard to train and can under-perform when generating long-sequence molecules. The development of a simple and powerful alternative can help improve practicality of automated drug discovery method.