Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

Postal Subscription Code 80-970

2018 Impact Factor: 1.129

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Comput. Sci.    2024, Vol. 18 Issue (2) : 182906    https://doi.org/10.1007/s11704-023-3103-z
Interdisciplinary
A multi-stream network for retrosynthesis prediction
Qiang ZHANG1, Juan LIU1(), Wen ZHANG2(), Feng YANG1, Zhihui YANG1, Xiaolei ZHANG1
1. Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan 430072, China
2. College of Informatics, Huazhong Agricultural University, Wuhan 430072, China
 Download: PDF(852 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Corresponding Author(s): Juan LIU,Wen ZHANG   
Issue Date: 19 July 2023
 Cite this article:   
Qiang ZHANG,Juan LIU,Wen ZHANG, et al. A multi-stream network for retrosynthesis prediction[J]. Front. Comput. Sci., 2024, 18(2): 182906.
 URL:  
https://academic.hep.com.cn/fcs/EN/10.1007/s11704-023-3103-z
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I2/182906
Fig.1  Pipeline of multi-stream network for retrosynthesis (MSNR)
Method Top-1 Top-3 Top-5 Top-10
RetroSim [1] 37.3 54.7 63.3 74.1
NeuralSym [2] 44.4 65.3 72.4 78.9
G2Gs [7] 48.9 67.6 72.5 75.5
Transformer [7] 37.9 57.3 62.7 /
Syntax Correction [3] 43.7 60.0 65.2 68.7
Latent model, l=1 [8] 44.8 62.6 67.7 71.7
Latent model, l=5 [8] 40.5 65.1 72.8 79.4
MSNR 53.0 68.4 72.2 75.6
MSNR+ 63.9 83.1 87.6 91.3
Tab.1  Top-k exact match accuracy in USPTO-50k dataset
Methods USPTO-50k USPTO-full
Top-1 Top-10 Top-1 Top-10
Retrosim [1] 37.3 74.1 32.8 56.1
Neuralsym [2] 44.4 78.9 35.8 60.8
MSNR 53.0 75.6 37.7 56.7
MSNR+ 63.9 91.3 51.8 79.0
Tab.2  Top-k exact match accuracy in USPTO-full dataset
1 C W, Coley L, Rogers W H, Green K F Jensen . Computer-assisted retrosynthesis based on molecular similarity. ACS Central Science, 2017, 3( 12): 1237–1245
2 M H S, Segler M P Waller . Neural-symbolic machine learning for retrosynthesis and reaction prediction. Chemistry-A European Journal, 2017, 23( 25): 5966–5971
3 Zheng S, Rao J, Zhang Z, Xu J, Yang Y. Predicting retrosynthetic reactions using self-corrected transformer neural networks. Journal of Chemical Information and Modeling, 2022, 60 (1): 47 − 55
4 D Weininger . SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. Journal of Chemical Information & Computer Sciences, 1988, 28( 1): 31–36
5 X B, Ye Q, Guan W, Luo L, Fang Z R, Lai J Wang . Molecular substructure graph attention network for molecular property identification in drug discovery. Pattern Recognition, 2022, 128: 108659
6 B, Liu B, Ramsundar P, Kawthekar J, Shi J, Gomes Q L, Nguyen S, Ho J, Sloane P, Wender V Pande . Retrosynthetic reaction prediction using neural sequence-to-sequence models. ACS Central Science, 2017, 3( 10): 1103–1113
7 Shi C, Xu M, Guo H, Zhang M, Tang J. A graph to graphs framework for retrosynthesis prediction. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 818
8 Chen B, Shen T, Jaakkola T S, Barzilay R. Learning to make generalizable and diverse predictions for retrosynthesis. 2019, arXiv preprint arXiv: 1910.09688
[1] FCS-23103-OF-QZ_suppl_1 Download
[2] FCS-23103-OF-QZ_suppl_2 Download
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed