Papers › RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction

RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction

20 Dec 2021arXiv:2112.11225archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

uta-smile/retrocomposer officialmentioned in paperpytorch report

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

PredictionRetrosynthesisSingle-step retrosynthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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