SOTAVerified

Single-step retrosynthesis

Papers

Showing 125 of 34 papers

TitleStatusHype
RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis0
Accelerating the inference of string generation-based chemical reaction models for industrial applications0
RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetsCode2
UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES AlignmentCode1
Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step RetrosynthesisCode1
RetroBridge: Modeling Retrosynthesis with Markov BridgesCode1
Models Matter: The Impact of Single-Step Retrosynthesis on Synthesis Planning0
G-MATT: Single-step Retrosynthesis Prediction using Molecular Grammar Tree Transformer0
O-GNN: Incorporating Ring Priors into Molecular ModelingCode1
Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Prediction0
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic PlanningCode1
MARS: A Motif-based Autoregressive Model for Retrosynthesis Prediction0
Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent VariablesCode1
G2GT: Retrosynthesis Prediction with Graph to Graph Attention Neural Network and Self-TrainingCode0
Root-aligned SMILES: A Tight Representation for Chemical Reaction PredictionCode1
Chemformer: a pre-trained transformer for computational chemistryCode2
Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield NetworksCode1
RetroComposer: Composing Templates for Template-Based Retrosynthesis PredictionCode0
Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction predictionCode1
Human-in-the-loop for a Disconnection Aware Retrosynthesis0
RetroPrime: A Diverse, plausible and Transformer-based method for Single-Step retrosynthesis predictionsCode1
Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global AttentionCode1
Dual-view Molecule Pre-trainingCode1
Learning Graph Models for Template-Free Retrosynthesis0
Modern Hopfield Networks for Few- and Zero-Shot Reaction Template PredictionCode1
Show:102550
← PrevPage 1 of 2Next →

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