RSscore: Reaction superiority learned from reaction mapping hypergraph

doi:10.1016/j.cjche.2024.06.017

Chinese Journal of Chemical Engineering ›› 2024, Vol. 74 ›› Issue (10): 203-215.DOI: 10.1016/j.cjche.2024.06.017

Previous Articles Next Articles

RSscore: Reaction superiority learned from reaction mapping hypergraph

Chenyang Xu¹, Lijuan Guo¹, Kang Zhou², Hai Yu², Chaoliang Wei², Fengqi Fan², Lei Zhang¹

1 State Key Laboratory of Fine Chemicals, Frontiers Science Center for Smart Materials Oriented Chemical Engineering, Institute of Chemical Process Systems Engineering, School of Chemical Engineering, Dalian University of Technology, Dalian 116024, China;
2 PetroChina Lanzhou Lubricating Oil Research & Development Institute, Lanzhou 730060, China

Received:2024-05-16 Revised:2024-06-15 Accepted:2024-06-16 Online:2024-07-29 Published:2024-10-28
Contact: Lei Zhang,E-mail:keleiz@dlut.edu.cn
Supported by:
The authors are grateful for the financial support of the National Natural Science Foundation of China (22078041, 22278053), Dalian High-level Talents Innovation Support Program (2021RQ105) and the Fundamental Research Funds for China Central Universities (DUT22QN209, DUT22LAB608).

RSscore: Reaction superiority learned from reaction mapping hypergraph

Chenyang Xu¹, Lijuan Guo¹, Kang Zhou², Hai Yu², Chaoliang Wei², Fengqi Fan², Lei Zhang¹

1 State Key Laboratory of Fine Chemicals, Frontiers Science Center for Smart Materials Oriented Chemical Engineering, Institute of Chemical Process Systems Engineering, School of Chemical Engineering, Dalian University of Technology, Dalian 116024, China;
2 PetroChina Lanzhou Lubricating Oil Research & Development Institute, Lanzhou 730060, China

通讯作者: Lei Zhang,E-mail:keleiz@dlut.edu.cn
基金资助:
The authors are grateful for the financial support of the National Natural Science Foundation of China (22078041, 22278053), Dalian High-level Talents Innovation Support Program (2021RQ105) and the Fundamental Research Funds for China Central Universities (DUT22QN209, DUT22LAB608).

Abstract

Abstract: The selection of chemical reactions is directly related to the quality of synthesis pathways, so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways. Since reaction conditions also need to be considered in synthesis pathway design, a reaction metric that combines reaction time, temperature, and yield is required for chemical reactions of different reaction agents. In this study, a chemical reaction graph descriptor which includes the atom-atom mapping relationship is proposed to effectively describe reactions. Then, through pre-training using graph contrastive learning and fine-tuning through supervised learning, we establish a model for generating the probability of reaction superiority (RSscore). Finally, to validate the effectiveness of the current evaluation index, RSscore is applied in two applications, namely reaction evaluation and synthesis routes analysis, which proves that the RSscore provides an important agents-considered evaluation criterion for computer-aided synthesis planning (CASP).

Key words: Computer-aided synthesis planning, Neural networks, Reaction evaluation indicator, Reaction graph, Graph contractive learning

摘要： The selection of chemical reactions is directly related to the quality of synthesis pathways, so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways. Since reaction conditions also need to be considered in synthesis pathway design, a reaction metric that combines reaction time, temperature, and yield is required for chemical reactions of different reaction agents. In this study, a chemical reaction graph descriptor which includes the atom-atom mapping relationship is proposed to effectively describe reactions. Then, through pre-training using graph contrastive learning and fine-tuning through supervised learning, we establish a model for generating the probability of reaction superiority (RSscore). Finally, to validate the effectiveness of the current evaluation index, RSscore is applied in two applications, namely reaction evaluation and synthesis routes analysis, which proves that the RSscore provides an important agents-considered evaluation criterion for computer-aided synthesis planning (CASP).

关键词: Computer-aided synthesis planning, Neural networks, Reaction evaluation indicator, Reaction graph, Graph contractive learning

Chenyang Xu, Lijuan Guo, Kang Zhou, Hai Yu, Chaoliang Wei, Fengqi Fan, Lei Zhang. RSscore: Reaction superiority learned from reaction mapping hypergraph[J]. Chinese Journal of Chemical Engineering, 2024, 74(10): 203-215.

Chenyang Xu, Lijuan Guo, Kang Zhou, Hai Yu, Chaoliang Wei, Fengqi Fan, Lei Zhang. RSscore: Reaction superiority learned from reaction mapping hypergraph[J]. 中国化学工程学报, 2024, 74(10): 203-215.

References

[1] H.C. Wang, T.F. Fu, Y.Q. Du, W.H. Gao, K.X. Huang, Z.M. Liu, P. Chandak, S.C. Liu, P. Van Katwyk, A. Deac, A. Anandkumar, K. Bergen, C.P. Gomes, S. Ho, P. Kohli, J. Lasenby, J. Leskovec, T.Y. Liu, A. Manrai, D. Marks, B. Ramsundar, L. Song, J.M. Sun, J. Tang, P. Velickovic, M. Welling, L.F. Zhang, C.W. Coley, Y. Bengio, M. Zitnik, Scientific discovery in the age of artificial intelligence, Nature 620 (7972) (2023) 47-60.
[2] W.D. Ihlenfeldt, J. Gasteiger, Computer-assisted planning of organic syntheses: the second generation of programs, Angew. Chem. Int. Ed. 34 (23-24) (1996) 2613-2633.
[3] O. Engkvist, P.O. Norrby, N. Selmi, Y.H. Lam, Z.W. Peng, E.C. Sherer, W. Amberg, T. Erhard, L.A. Smyth, Computational prediction of chemical reactions: current status and outlook, Drug Discov. Today 23 (6) (2018) 1203-1218.
[4] I.I. Baskin, T.I. Madzhidov, I.S. Antipin, A.A. Varnek, Artificial intelligence in synthetic chemistry: achievements and prospects, Russ. Chem. Rev. 86 (11) (2017) 1127-1156.
[5] C.W. Coley, W.H. Green, K.F. Jensen, Machine learning in computer-aided synthesis planning, Acc Chem Res 51 (5) (2018) 1281-1289.
[6] S. Szymkuc, E.P. Gajewska, T. Klucznik, K. Molga, P. Dittwald, M. Startek, M. Bajczyk, B.A. Grzybowski, Computer-assisted synthetic planning: the end of the beginning, Angew Chem Int Ed Engl 55 (20) (2016) 5904-5937.
[7] F.Y. Qiu, Strategic efficiency-The new thrust for synthetic organic chemists, Can. J. Chem. 86 (9) (2008) 903-906.
[8] S. Ito, Y. Baba, T. Isomura, H. Kashima, Synthetic accessibility assessment using auxiliary responses, Expert Syst. Appl. 145 (2020) 113106.
[9] P. Ertl, A. Schuffenhauer, Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions, J. Cheminform. 1 (1) (2009) 8.
[10] D. Rogers, M. Hahn, Extended-connectivity fingerprints, J. Chem. Inf. Model. 50 (5) (2010) 742-754.
[11] S. Kim, J. Chen, T.J. Cheng, A. Gindulyte, J. He, S.Q. He, Q.L. Li, B.A. Shoemaker, P.A. Thiessen, B. Yu, L. Zaslavsky, J. Zhang, E.E. Bolton, PubChem 2019 update: improved access to chemical data, Nucleic Acids Res. 47 (D1) (2019) D1102-D1109.
[12] W.L. Wang, Q.L. Liu, L. Zhang, Y.C. Dong, J. Du, RetroSynX: a retrosynthetic analysis framework using hybrid reaction templates and group contribution-based thermodynamic models, Chem. Eng. Sci. 248 (2022) 117208.
[13] W.H. Gao, C.W. Coley, The synthesizability of molecules proposed by generative models, J. Chem. Inf. Model. 60 (12) (2020) 5714-5723.
[14] C.W. Coley, L. Rogers, W.H. Green, K.F. Jensen, SCScore: synthetic complexity learned from a reaction corpus, J. Chem. Inf. Model. 58 (2) (2018) 252-261.
[15] M. Vorsilak, M. Kolar, I. Cmelo, D. Svozil, SYBA: Bayesian estimation of synthetic accessibility of organic compounds, J. Cheminform. 12 (1) (2020) 35.
[16] C.H. Liu, M. Korablyov, S. Jastrzebski, P. Wlodarczyk-Pruszynski, Y. Bengio, M. Segler, RetroGNN: fast estimation of synthesizability for virtual screening and de novo design by learning from slow retrosynthesis software, J. Chem. Inf. Model. 62 (10) (2022) 2293-2300.
[17] A. Thakkar, V. Chadimova, E.J. Bjerrum, O. Engkvist, J.L. Reymond, Retrosynthetic accessibility score (RAscore)-rapid machine learned synthesizability classification from AI driven retrosynthetic planning, Chem. Sci. 12 (9) (2021) 3339-3349.
[18] J.H. Yu, J.K. Wang, H. Zhao, J.B. Gao, Y. Kang, D.S. Cao, Z. Wang, T.J. Hou, Organic compound synthetic accessibility prediction based on the graph attention mechanism, J. Chem. Inf. Model. 62 (12) (2022) 2973-2986.
[19] B.H. Chen, C.T. Li, H.J. Dai, L. Song, Retro*: learning retrosynthetic planning with neural guided A^* search, arXiv:2006.15820vl.
[20] S. Genheden, A. Thakkar, V. Chadimova, J.L. Reymond, O. Engkvist, E. Bjerrum, AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning, J. Cheminform. 12 (1) (2020) 70.
[21] T. Badowski, K. Molga, B.A. Grzybowski, Selection of cost-effective yet chemically diverse pathways from the networks of computer-generated retrosynthetic plans, Chem. Sci. 10 (17) (2019) 4640-4651.
[22] M.H.S. Segler, M. Preuss, M.P. Waller, Planning chemical syntheses with deep neural networks and symbolic AI, Nature 555 (7698) (2018) 604-610.
[23] C.W. Coley, D.A. Thomas 3rd, J.A.M. Lummiss, J.N. Jaworski, C.P. Breen, V. Schultz, T. Hart, J.S. Fishman, L. Rogers, H.Y. Gao, R.W. Hicklin, P.P. Plehiers, J. Byington, J.S. Piotti, W.H. Green, A.J. Hart, T.F. Jamison, K.F. Jensen, A robotic platform for flow synthesis of organic compounds informed by AI planning, Science 365 (6453) (2019) eaax1566.
[24] T. Fuji, S. Nakazawa, K.Ito, Feasible-metabolic-pathway-exploration technique using chemical latent space， Bioinformatics. 36(Suppl.2)(2020)i770-i778.
[25] R. Sun, H. Dai, L. Li, S. Kearnes, B. Dai. Towards understanding retrosynthesis by energy-based models, Advances in Neural Information Processing Systems 34(2021)10186-10194.
[26] M.H. Lin, Z.K. Tu, C.W. Coley, Improving the performance of models for one-step retrosynthesis through re-ranking, J. Cheminf. 14 (1) (2022) 15.
[27] J. Gilmer, S.S. Schoenholz, P.F. Riley, O. Vinyals, G.E. Dahl, Neural message passing for quantum chemistry, In: International Conference on Machine Learning (ICML), Sydney, Australia,2017.
[28] K.T. Schutt, H.E. Sauceda, P.J. Kindermans, A. Tkatchenko, K.R. Muller, SchNet - A deep learning architecture for molecules and materials, J. Chem. Phys. 148 (24) (2018) 241722.
[29] J.H. Yang, Z. Liu, S.T. Xiao, C.Z. Li, D.F. Lian, S. Agrawal, A. Singh, G.Z. Sun, X. Xie, GraphFormers: GNN-nested transformers for representation learning on textual graph, (2021): 2105.02605.
[30] Z.R. Shui, G. Karypis, Heterogeneous molecular graph neural networks for predicting molecule properties, 2020 IEEE International Conference on Data Mining (ICDM). Sorrento, Italy. IEEE, (2020) 492-500.
[31] Y.B. Li, L.R. Zhang, Z.M. Liu, Multi-objective de novo drug design with conditional graph generative model, (2018): 1801.07299.
[32] Y.J. Li, O. Vinyals, C. Dyer, R. Pascanu, P. Battaglia, Learning deep generative models of graphs, (2018): 1803.03324.
[33] J.X. You, B.W. Liu, R. Ying, V. Pande, J. Leskovec, Graph convolutional policy network for goal-directed molecular graph generation, (2018): 1806.02473.
[34] G.A. Pinheiro, J.L.F. Da Silva, M.G. Quiles, SMICLR: contrastive learning on multiple molecular representations for semisupervised and unsupervised representation learning, J. Chem. Inf. Model. 62 (17) (2022) 3948-3960.
[35] Y.Y. Wang, J.R. Wang, Z.L. Cao, A. Barati Farimani, Molecular contrastive learning of representations via graph neural networks, Nat. Mach. Intell. 4 (2022) 279-287.
[36] S.L. Li, J.B. Zhou, T. Xu, D.J. Dou, H. Xiong, GeomGCL: geometric graph contrastive learning for molecular property prediction, (2021): 2109.11730.
[37] M. Sun, J. Xing, H. Wang, B. Chen, J. Zhou, MoCL: data-driven molecular fingerprint via knowledge-aware contrastive learning from molecular graph, KDD 2021 (2021) 3585-3594.
[38] Y. Fang, Q.Zhang, H.Yang, X.Zhuang, S.Deng, W.Zhang, M.Qin, Z.Chen, X.Fan, H.Chen, Molecular contrastive learning with chemical element knowledge graph. In: Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada, 2022.
[39] Y. Kwon, D. Lee, Y.S. Choi, S. Kang, Uncertainty-aware prediction of chemical reaction yields with graph neural networks, J. Cheminform. 14 (1) (2022) 2.
[40] S. M. Kearnes, M. R. Maser, M. Wleklinski, A. Kast, A. G. Doyle, S. D. Dreher, J. M. Hawkins, K. F. Jensen, C. W. Coley, The open reaction database. Journal of the American Chemical Society, 143 (45) (2021) 18820-18826.
[41] M.S. Sigman, K.C. Harper, E.N. Bess, A. Milo, The development of multidimensional analysis tools for asymmetric catalysis and beyond, Acc. Chem. Res. 49 (6) (2016) 1292-1301.
[42] W. Hu, B. Liu, J. Gomes, M. Zitnik, P. Liang, V. Pande, J. Leskovec, Strategies for pre-training graph neural networks, arXiv:1905 (2019)12265.
[43] A.C. Vaucher, F. Zipoli, J. Geluykens, V.H. Nair, P. Schwaller, T. Laino, Automated extraction of chemical synthesis actions from experimental procedures, Nat. Commun. 11 (1) (2020) 3601.
[44] D. Fooshee, A. Andronico, P. Baldi, ReactionMap: an efficient atom-mapping algorithm for chemical reactions, J. Chem. Inf. Model. 53 (11) (2013) 2812-2819.
[45] G. Landrum, Rdkit: Open-source chemoinformatics and machine learning. Accessed August 19, 2023. http://rdkit.org.
[46] T. Chen, S. Kornblith, M. Norouzi, G. Hinton, A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, 2020.
[47] Deep graph library, https://www.dgl.ai. Accessed 19 August (2023).
[48] W.T. Zhang, Z.A. Sheng, Z.Q. Yin, Y. Jiang, Y.K. Xia, J. Gao, Z. Yang, B. Cui, Model Degradation Hinders Deep Graph Neural NetworksProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Washington DC USA. ACM, 2022.
[49] T. Y. Lin, P. Goyal, R. Girshick, K. He, P.Dollar, Focal loss for dense object detection, In: Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 2017.
[50] S. Ruder, An overview of gradient descent optimization algorithms, arXiv:1609.04747(2016).
[51] A. Liaw, M. Wiener, Classification and regression by randomForest. R news, 2 (3) (2002) 18-22.
[52] J. Friedman, R. Tibshirani, T.Hastie, Additive logistic regression: a statistical view of boosting - Rejoinder. The Annals of Statistics, (2)(2000)28.
[53] T.Chen, C. Guestrin, XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd Acm SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, USA.2016.
[54] L. McInnes, J. Healy, J. Melville, UMAP: uniform manifold approximation and projection for dimension reduction, (2018): 1802.03426.
[55] Y.Q. Guan, H.R. Yang, W.Q. Chen, F. Li, Z.Y. Liao. Study on Synthesis of Paracetamolum. Journal of Guangdong University of Technology. (02) (1997) 43-46.
[56] G. Li, X.J Xu. Study on the Preparation of Para-aminophenol from Nitrobenzene by Reduction. Guizhou Chemical Industry, (04) (2003) 14-15.
[57] M. Zhang, J.S. Yang, C.D. Wang. The direct synthesis of p-aminophenol by the reduction of nitrobenzene. Journal of Yangzhou Univensity: Nataral Science Edition, (2) (1999) 19-20+39.
[58] S.Y. Li, Y.Z. Liu, Q.L. Zhang, M. Bai. Review on preparation methods of p-aminophenol. Fine and Specialty Chemicals, 19(12) (2011) 52-54.
[59] A.V. Kumar, S.D. Kiritkumar, P.R. Kantibhai, P.B. Rajendrakumar, T.N. Mansukhlal, U.A. Rameshchandra. Process for preparing clobazam using novel intermediates. world intellectual property organization, WO-2016193482-A1 (2016).
[60] Y. Fang, Y.M. Du, A method for the Preparation of Clobazam, China Pat., CN201710166922.3 (2017).
[61] H. Zhou, C. Peng, Q. Liu, Z. Zhang, Z. Liao, A Method for the Industrial Production of Clobazam, China Pat., CN202110084477.2 (2021).

RSscore: Reaction superiority learned from reaction mapping hypergraph

RSscore: Reaction superiority learned from reaction mapping hypergraph

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Zongyu Yao, Qingchao Jiang, Xingsheng Gu. Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference [J]. Chinese Journal of Chemical Engineering, 2024, 73(9): 311-323.
[2]	Zhiwei Zhu, Minglei Yang, Wangli He, Renchu He, Yunmeng Zhao, Feng Qian. A deep reinforcement learning approach to gasoline blending real-time optimization under uncertainty [J]. Chinese Journal of Chemical Engineering, 2024, 71(7): 183-192.
[3]	Cheng Yang, Chao Jiang, Guo Yu, Jun Li, Cuimei Bo. Transferable adversarial slow feature extraction network for few-shot quality prediction in coal-to-ethylene glycol process [J]. Chinese Journal of Chemical Engineering, 2024, 71(7): 258-271.
[4]	Zeeshan Ikram Butt, Iftikhar Ahmad, Muhammad Shoaib, Syed Ibrar Hussain, Hira Ilyas, Muhammad Asif Zahoor Raja. Stochastic neuro-swarming intelligence paradigm for the analysis of magneto-hydrodynamic Prandtl-Eyring fluid flow with diffusive magnetic layers effect over an elongated surface [J]. Chinese Journal of Chemical Engineering, 2024, 74(10): 295-311.
[5]	Xi Luo, Xiayuan Feng, Xu Ji, Yagu Dang, Li Zhou, Kexin Bi, Yiyang Dai. Extraction and analysis of risk factors from Chinese chemical accident reports [J]. Chinese Journal of Chemical Engineering, 2023, 61(9): 68-81.
[6]	Jian Long, Kai Deng, Renchu He. Closed-loop scheduling optimization strategy based on particle swarm optimization with niche technology and soft sensor method of attributes-applied to gasoline blending process [J]. Chinese Journal of Chemical Engineering, 2023, 61(9): 43-57.
[7]	Shanwei Xiong, Li Zhou, Yiyang Dai, Xu Ji. Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis [J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 1-14.
[8]	Kun Ren, Zheng Jiao, Xiaolong Wu, Honggui Han. Multivariable identification of membrane fouling based on compacted cascade neural network [J]. Chinese Journal of Chemical Engineering, 2023, 53(1): 37-45.
[9]	Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis [J]. Chinese Journal of Chemical Engineering, 2022, 50(10): 398-411.
[10]	Qiaoyi Xu, Wenli Du, Jinjin Xu, Jikai Dong. Neural network-based source tracking of chemical leaks with obstacles [J]. Chinese Journal of Chemical Engineering, 2021, 33(5): 211-220.
[11]	Chuankun Li, Dongfeng Zhao, Shanjun Mu, Weihua Zhang, Ning Shi, Lening Li. Fault diagnosis for distillation process based on CNN–DAE [J]. Chinese Journal of Chemical Engineering, 2019, 27(3): 598-604.
[12]	Ahmad KhazaiePoul, M. Soleimani, S. Salahi. Solubility prediction of disperse dyes in supercritical carbon dioxide and ethanol as co-solvent using neural network [J]. Chin.J.Chem.Eng., 2016, 24(4): 491-498.
[13]	Qiangda Yang, Hongbo Gao, Weijun Zhang, Huimin Li. Simultaneous hybrid modeling of a nosiheptide fermentation process using particle swarm optimization [J]. Chin.J.Chem.Eng., 2016, 24(11): 1631-1639.
[14]	Yonggang Wang, Xinfu Pang, Zailin Piao, Jingjing Fang, Jun Fu, Tianyou Chai . Intelligent decoupling PID control for the forced-circulation evaporation system [J]. Chin.J.Chem.Eng., 2015, 23(12): 2075-2086.
[15]	Qunxiong Zhu, Yiwen Jia, Di Peng, Yuan Xu. Study and Application of Fault Prediction Methods with Improved Reservoir Neural Networks [J]. , 2014, 22(7): 812-819.