Papers › Computer-Assisted Retrosynthesis Based on Molecular Similarity
Computer-Assisted Retrosynthesis Based on Molecular Similarity
Connor W. Coley, Luke Rogers, William H. Green, and Klavs F. Jensen
We demonstrate molecular similarity to be a surprisingly effective metric for proposing and ranking one-step retrosynthetic disconnections based on analogy to precedent reactions. The developed approach mimics the retrosynthetic strategy defined implicitly by a corpus of known reactions without the need to encode any chemical knowledge. Using 40 000 reactions from the patent literature as a knowledge base, the recorded reactants are among the top 10 proposed precursors in 74.1% of 5000 test reactions, providing strong quantitative support for our methodology. Extension of the one-step strategy to multistep pathway planning is demonstrated and discussed for two exemplary drug products.
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 | RetroSim (reaction class as prior) | Top-1 accuracy | 52.9 | #25 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroSim (reaction class as prior) | Top-10 accuracy | 88.1 | #25 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroSim (reaction class as prior) | Top-3 accuracy | 73.8 | #25 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroSim (reaction class as prior) | Top-5 accuracy | 81.2 | #25 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroSim (reaction class unknown) | Top-1 accuracy | 37.3 | #34 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroSim (reaction class unknown) | Top-10 accuracy | 74.1 | #34 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroSim (reaction class unknown) | Top-3 accuracy | 54.7 | #34 of 35 | Archive leaderboard | report |
| Single-step retrosynthesis | USPTO-50k | RetroSim (reaction class unknown) | Top-5 accuracy | 63.3 | #34 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