molecule-one / megan

Code for "Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits"

molecule-one/megan Issues

Lower results for forward-synthesis on USPTO-MIT
Updated 8 months ago2
Question about the evaluation metrics
Closed 8 months ago1
CUDA out of memory
Closed 8 months ago2
Speedup for training
Closed a year ago2
Is there any args for evaluating with reaction class unknown?
Closed 2 years ago1
Your model can process the multi-edits?
Closed 2 years ago3
Are the data split exactly the same as those in GLN and G2Gs?
Closed 3 years ago6
Segmentation error (core dumped)
Closed 3 years ago1
Nice work - are you aware of the USPTO data leak? (+ training issue on HPC)
Closed 3 years ago10
License
Closed 3 years ago1