File(s) under permanent embargo
Graph transformation policy network for chemical reaction prediction
conference contribution
posted on 2019-01-01, 00:00 authored by Kien DoKien Do, Truyen TranTruyen Tran, Svetha VenkateshSvetha Venkatesh© 2019 Copyright held by the owner/author(s). We address a fundamental problem in chemistry known as chemical reaction product prediction. Our main insight is that the input reactant and reagent molecules can be jointly represented as graphs, and the process of generating product molecules from reactant molecules can be formulated as a set of graph transformations. To this end, we propose Graph Transformation Policy Network (GTPN) - a novel generic method that combines the strengths of graph neural networks and reinforcement learning to learn reactions directly from data with minimal chemical knowledge. Compared to previous methods, GTPN has some appealing properties such as: end-to-end learning, and making no assumption about the length or the order of graph transformations. In order to guide our model search through the complex discrete space of sets of graph transformations effectively, we extend the standard policy gradient loss by adding useful constraints. Evaluation results show that GTPN improves the top-1 accuracy over the current state-of-the-art method by about 3% on the large USPTO dataset.
History
Event
Knowledge Discovery & Data Mining. International Conference (25th : 2019 : Anchorage, Alaska)Pagination
750 - 760Publisher
ACMLocation
Anchorage, AlaskaPlace of publication
New York, N.Y.Publisher DOI
Start date
2019-08-04End date
2019-08-08ISBN-13
9781450362016Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2019, The AuthorsTitle of proceedings
KDD 2019 : Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC