Bridging the Gap between Chemical Reaction Pretraining and Conditional Molecule Generation with a Unified Model

arXiv:2303.06965v4 Announce Type: replace
Abstract: Chemical reactions are the fundamental building blocks of drug design and organic chemistry research. In recent years, there has been a growing need for a large-scale deep-learning framework that can efficiently capture the basic rules of chemical reactions. In this paper, we have proposed a unified framework that addresses both the reaction representation learning and molecule generation tasks, which allows for a more holistic approach. Inspired by the organic chemistry mechanism, we develop a novel …

abstract arxiv basic building chemistry cs.lg design drug design framework gap pretraining q-bio.bm research rules scale type unified model