Papers › SemiRetro: Semi-template framework boosts deep retrosynthesis prediction
SemiRetro: Semi-template framework boosts deep retrosynthesis prediction
Zhangyang Gao, Cheng Tan, Lirong Wu, Stan Z. Li
Recently, template-based (TB) and template-free (TF) molecule graph learning methods have shown promising results to retrosynthesis. TB methods are more accurate using pre-encoded reaction templates, and TF methods are more scalable by decomposing retrosynthesis into subproblems, i.e., center identification and synthon completion. To combine both advantages of TB and TF, we suggest breaking a full-template into several semi-templates and embedding them into the two-step TF framework. Since many semi-templates are reduplicative, the template redundancy can be reduced while the essential chemical knowledge is still preserved to facilitate synthon completion. We call our method SemiRetro, introduce a new GNN layer (DRGAT) to enhance center identification, and propose a novel self-correcting module to improve semi-template classification. Experimental results show that SemiRetro significantly outperforms both existing TB and TF methods. In scalability, SemiRetro covers 98.9\% data using 150 semi-templates, while previous template-based GLN requires 11,647 templates to cover 93.3\% data. In top-1 accuracy, SemiRetro exceeds template-free G2G 4.8\% (class known) and 6.0\% (class unknown). Besides, SemiRetro has better training efficiency than existing methods.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | SemiRetro (reaction class as prior) | Top-1 accuracy | 65.8 | #5 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | SemiRetro (reaction class as prior) | Top-10 accuracy | 92.8 | #5 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | SemiRetro (reaction class as prior) | Top-3 accuracy | 85.7 | #5 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | SemiRetro (reaction class as prior) | Top-5 accuracy | 89.8 | #5 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | SemiRetro (reaction class unknown) | Top-1 accuracy | 54.9 | #14 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | SemiRetro (reaction class unknown) | Top-10 accuracy | 84.1 | #14 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | SemiRetro (reaction class unknown) | Top-3 accuracy | 75.3 | #14 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | SemiRetro (reaction class unknown) | Top-5 accuracy | 80.4 | #14 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.
Methods
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