Papers › RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction
RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction
Chaochao Yan, Peilin Zhao, Chan Lu, Yang Yu, Junzhou Huang
The main target of retrosynthesis is to recursively decompose desired molecules into available building blocks. Existing template-based retrosynthesis methods follow a template selection stereotype and suffer from limited training templates, which prevents them from discovering novel reactions. To overcome this limitation, we propose an innovative retrosynthesis prediction framework that can compose novel templates beyond training templates. As far as we know, this is the first method that uses machine learning to compose reaction templates for retrosynthesis prediction. Besides, we propose an effective reactant candidate scoring model that can capture atom-level transformations, which helps our method outperform previous methods on the USPTO-50K dataset. Experimental results show that our method can produce novel templates for 15 USPTO-50K test reactions that are not covered by training templates. We have released our source implementation.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class as prior) | Top-1 accuracy | 65.9 | #4 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class as prior) | Top-10 accuracy | 91.5 | #4 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class as prior) | Top-3 accuracy | 85.8 | #4 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class as prior) | Top-5 accuracy | 89.5 | #4 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class unknown) | Top-1 accuracy | 54.4 | #16 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class unknown) | Top-10 accuracy | 87.7 | #16 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class unknown) | Top-3 accuracy | 77.2 | #16 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroComposer (reaction class unknown) | Top-5 accuracy | 83.2 | #16 of 35 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections