Timezone: »

 
Poster
Retrosynthesis Prediction with Conditional Graph Logic Network
Hanjun Dai · Chengtao Li · Connor Coley · Bo Dai · Le Song

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #58
in Algorithms -- Structured Prediction »

Retrosynthesis is one of the fundamental problems in organic chemistry. The task is to identify reactants that can be used to synthesize a specified product molecule. Recently, computer-aided retrosynthesis is finding renewed interest from both chemistry and computer science communities. Most existing approaches rely on template-based models that define subgraph matching rules, but whether or not a chemical reaction can proceed is not defined by hard decision rules. In this work, we propose a new approach to this task using the Conditional Graph Logic Network, a conditional graphical model built upon graph neural networks that learns when rules from reaction templates should be applied, implicitly considering whether the resulting reaction would be both chemically feasible and strategic. We also propose an efficient hierarchical sampling to alleviate the computation cost. While achieving a significant improvement of 8.1% over current state-of-the-art methods on the benchmark dataset, our model also offers interpretations for the prediction.

Keywords: Embedding Approaches · Deep Learning · Algorithms -> Representation Learning; Algorithms -> Structured Prediction; Applications · Computational Biology and Bioinform
[ Paper]  [ Poster]  [ Slides] 

Author Information

Hanjun Dai (Georgia Tech)
Chengtao Li (MIT)

I'm a 4-th year PhD student at MIT working with Stefanie Jegelka and Suvrit Sra. I work in the field of machine learning and am broadly interested in generative models, approximate inference, large-scale machine learning, Markov chains and mixing times, matrix approximations, kernel methods and probabilistic numerics.

Connor Coley (MIT)
Bo Dai (Google Brain)
Le Song (Georgia Institute of Technology)

More from the Same Authors