Research map / Probabilistic and scientific modeling / Molecules and proteins
Graph models for retrosynthesis
Predict retrosynthesis using graph-based generation and attention.
10 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2020–2026) · an approach in Molecules and proteins, keyword cluster “molecules · drug · chemical”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
1 papers in 2023–24 and 4 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 0.2% to 0.4%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2020 · A Graph to Graphs Framework for Retrosynthesis Prediction (ICML 2020 · 84 citations)
- 2021 · Learning Graph Models for Retrosynthesis Prediction (NeurIPS 2021 · 71 citations)
- 2023 · Matching receptor to odorant with protein language and graph neural networks (ICLR 2023)
- 2025 · GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation (AAAI 2025 · 4 citations)
- 2026 · TRACE: Transformation-Aware Graph Refinement for Reaction Condition Prediction (AAAI 2026 · 0 citations)
Earliest papers here
- A Graph to Graphs Framework for Retrosynthesis Prediction (ICML 2020 · 84 citations)
- RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist (NeurIPS 2020 · 51 citations)
- Learning Graph Models for Retrosynthesis Prediction (NeurIPS 2021 · 71 citations)
What has been tried
7 papers here report 64 measured changes (a component added, removed or swapped, compared with a baseline): helped 84%, no clear effect 5%, hurt 9%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add dual graphs to the reaction center model | USPTO-50k reaction center prediction, unknown class · top-1 accuracy | 81.4 -> 86.2 | Helped | GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation (AAAI 2025 · 4 citations) |
| use Cross-Entropy instead of VLB | USPTO-50k test · top-1 exact-match accuracy | 56.2 -> 58.3 | Helped | Advancing Retrosynthesis with Retrieval-Augmented Graph Generation (AAAI 2025 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 10 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Structure-based 3D molecule generation (107 papers)
- Diffusion for molecular conformations (67 papers)
- Machine-learned interatomic potentials (74 papers)
- Structure-based molecule design with diffusion (48 papers)
Elsewhere in the topic
- Generative protein structure design (142 papers)
- Prediction-powered and conformal inference (129 papers)
- Statistical analysis of ML practice (122 papers)
- Neuro-symbolic probabilistic layers (120 papers)
- Sparse graphical and tensor models (97 papers)
- Flow matching generative modeling (97 papers)
- Machine learning for physical simulation (96 papers)
- Multimodal trajectory prediction (95 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).