Single-step retrosynthesis
1개 벤치마크 · 논문 43편 · 이 태스크의 논문 보기 →
Benchmarks
USPTO-50k
Most implemented
RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNets
UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment
Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesis
RetroBridge: Modeling Retrosynthesis with Markov Bridges
O-GNN: Incorporating Ring Priors into Molecular Modeling
Papers
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this,…
Single-step retrosynthesisAccurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically exp…
Single-step retrosynthesisAugmenting Molecular Language Models with Local $n$-gram Memory
Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn local syntax at the expens…
Unconditional Molecule GenerationForward reaction predictionSingle-step retrosynthesisRETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking
Single-step retrosynthesis needs both accurate first-ranked suggestions and candidate lists that are rich enough for downstream selection. We study this as a proposal-selection decomposition. Our system, RETROSPECT, comb…
Single-step retrosynthesisRepresentation-Guided Discrete Molecular Graph Retrosynthesis
Stochastic process-based molecular graph generators have become the state of the art for template-free single-step retrosynthesis. However, these models are typically trained only on product-reactant pairs, thereby acqui…
Single-step retrosynthesisConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis
Template based single step retrosynthesis predicts reactants by selecting and applying an explicit reaction template, making each prediction traceable to a chemical transformation rule. This is useful for synthesis plann…
Single-step retrosynthesis