SOTAVerified

Single-step retrosynthesis

Papers

Showing 110 of 34 papers

TitleStatusHype
Chemformer: a pre-trained transformer for computational chemistryCode2
RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetsCode2
State-of-the-Art Augmented NLP Transformer models for direct and single-step retrosynthesisCode1
Modern Hopfield Networks for Few- and Zero-Shot Reaction Template PredictionCode1
Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global AttentionCode1
Dual-view Molecule Pre-trainingCode1
Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield NetworksCode1
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic PlanningCode1
Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent VariablesCode1
Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph EditsCode1
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NAG2G (reaction class as prior)Top-1 accuracy67.2Unverified
2UAlign (reaction class as prior)Top-1 accuracy66.4Unverified
3MARS (reaction class as prior)Top-1 accuracy66.2Unverified
4RetroComposer (reaction class as prior)Top-1 accuracy65.9Unverified
5SemiRetro (reaction class as prior)Top-1 accuracy65.8Unverified
6O-GNN (reaction class as prior)Top-1 accuracy65.7Unverified
7Dual-TF (reaction class as prior)Top-1 accuracy65.7Unverified
8GraphRetro (reaction class as prior)Top-1 accuracy63.9Unverified
9LocalRetro (reaction class as prior)Top-1 accuracy63.9Unverified
10MEGAN (reaction class as prior)Top-1 accuracy60.7Unverified