Algorithms
Browse retrosynthesis algorithms and their model versions
| Name | Description | Versions |
|---|---|---|
| Version | Instance Name | Description | Prediction Runs | Date Added |
|---|---|---|---|---|
| Version | Instance Name | Description | Prediction Runs | Date Added |
|---|---|---|---|---|
The most comprehensive (feature-wise) open-source suite for multistep planning from MIT.
Current state-of-the-art achieved by any version of this algorithm.
95% CI: [3.1%, 10.0%]
Top-1 Accuracy achieved by ASKCOS (v2.0.0)
95% CI: [13.1%, 25.6%]
Top-10 Accuracy achieved by ASKCOS (v2.0.0)
95% CI: [4.2%, 8.4%]
Top-1 Accuracy achieved by ASKCOS (v2.0.0)
95% CI: [13.2%, 19.6%]
Top-10 Accuracy achieved by ASKCOS (v2.0.0)
| version | slug | description | prediction runs | date added |
|---|---|---|---|---|
v2.0.0 | askcos-v2-0-0 | — | 8 runs | 2 days ago |
if you use this model in your work, cite it as
@article{askcos_2025,
author = {Tu, Zhengkai and Choure, Sourabh J. and Fong, Mun Hong and Roh, Jihye and Levin, Itai and Yu, Kevin and Joung, Joonyoung F. and Morgan, Nathan and Li, Shih-Cheng and Sun, Xiaoqi and Lin, Huiqian and Murnin, Mark and Liles, Jordan P. and Struble, Thomas J. and Fortunato, Michael E. and Liu, Mengjie and Green, William H. and Jensen, Klavs F. and Coley, Connor W.},
title = {ASKCOS: Open-Source, Data-Driven Synthesis Planning},
journal = {Accounts of Chemical Research},
volume = {58},
number = {11},
pages = {1764-1775},
year = {2025},
doi = {10.1021/acs.accounts.5c00155},
note ={PMID: 40397546},
URL = {https://doi.org/10.1021/acs.accounts.5c00155},
}