Citation: Chaoqin Chu, Qinkun Xiao, Chaozheng He, Chen Chen, Lu Li, Junyan Zhao, Jinzhou Zheng, Yinhuan Zhang. A novel method for atomization energy prediction based on natural-parameter network[J]. Chinese Chemical Letters, ;2024, 35(1): 109186. doi: 10.1016/j.cclet.2023.109186 shu

A novel method for atomization energy prediction based on natural-parameter network

Chaoqin Chu ^a ,
Qinkun Xiao ^{a, b, **,} ,
Chaozheng He ^{c, *,} ,
Chen Chen ^b ,
Lu Li ^a ,
Junyan Zhao ^b ,
Jinzhou Zheng ^c ,
Yinhuan Zhang ^a

a.
School of Mechanical and Electrical Engineering, Xi'an Technological University, Xi'an 710021, China
b.
School of Electrical and Information Engineering, Xi'an Technological University, Xi'an 710021, China
c.
School of Materials Science and Chemical Engineering, Xi'an Technological University, Xi'an 710021, China

^**

xiaoqinkun10000@163.com

hecz2019@xatu.edu.cn

Received Date: 31 August 2023
Revised Date: 7 October 2023
Accepted Date: 9 October 2023
Available Online: 17 October 2023

Figures(4)

Atomization energy (AE) is an important indicator for measuring material stability and reactivity, which refers to the energy change when a polyatomic molecule decomposes into its constituent atoms. Predicting AE based on the structural information of molecules has been a focus of researchers, but existing methods have limitations such as being time-consuming or requiring complex preprocessing and large amounts of training data. Deep learning (DL), a new branch of machine learning (ML), has shown promise in learning internal rules and hierarchical representations of sample data, making it a potential solution for AE prediction. To address this problem, we propose a natural-parameter network (NPN) approach for AE prediction. This method establishes a clearer statistical interpretation of the relationship between the network's output and the given data. We use the Coulomb matrix (CM) method to represent each compound as a structural information matrix. Furthermore, we also designed an end-to-end predictive model. Experimental results demonstrate that our method achieves excellent performance on the QM7 and BC2P datasets, and the mean absolute error (MAE) obtained on the QM7 test set ranges from 0.2 kcal/mol to 3 kcal/mol. The optimal result of our method is approximately an order of magnitude higher than the accuracy of 3 kcal/mol in published works. Additionally, our approach significantly accelerates the prediction time. Overall, this study presents a promising approach to accelerate the process of predicting structures using DL, and provides a valuable contribution to the field of chemical energy prediction.
- Structure prediction,
- Atomization energy,
- Deep learning,
- Coulomb matrix,
- NPN,
- End-to-end
1. [1]
  G. Montavon, M. Rupp, V. Gobre, et al., New J. Phys. 15 (2013) 095003. doi: 10.1088/1367-2630/15/9/095003
2. [2]
  E. Tuca, G. DiLabio, A. Otero-de-la-Roza, J. Chem. Inf. Model. 62 (2022) 4107–4121. doi: 10.1021/acs.jcim.2c00656
3. [3]
  D. Yang, L. Wang, P. Yuan, et al., Chin. Chem. Lett. 34 (2023) 107964. doi: 10.1016/j.cclet.2022.107964
4. [4]
  Q. Tong, L. Xue, J. Lv, et al., Faraday Discuss 211 (2018) 31–43. doi: 10.1039/C8FD00055G
5. [5]
  P. Gao, S. Wang, J. Lv, et al., RSC Adv. 7 (2017) 39869–39876. doi: 10.1039/C7RA07461A
6. [6]
  X. Wei, C. Zhou, X. Shen, et al., J. Jilin Univ. 51 (2021) 667–676.
7. [7]
  L. Torres, J.P. Arrais, B. Ribeiro, Neural Comput. Appl. 35 (2023) 13167–13185. doi: 10.1007/s00521-023-08403-5
8. [8]
  M. Sumanto, M.A. Martoprawiro, A.L. Ivansyah, J. Phys. Conf. Ser. 2072 (2021) 012005. doi: 10.1088/1742-6596/2072/1/012005
9. [9]
  G.A. Pinheiro, J. Mucelini, M.D. Soares, et al., J. Phys. Chem. A 124 (2020) 9854–9866. doi: 10.1021/acs.jpca.0c05969
10. [10]
  M. Tsubaki, T. Mizoguchi, Phys. Rev. Lett. 125 (2020) 206401. doi: 10.1103/PhysRevLett.125.206401
11. [11]
  P. Reddy, A.B. Bhattacherjee, Mach. Learn. Sci. Technol. (2) (2021) 025019. doi: 10.1088/2632-2153/abd486
12. [12]
  N. Dandu, L. Ward, R.S. Assary, et al., J. Phys. Chem. A 124 (2020) 5804–5811. doi: 10.1021/acs.jpca.0c01777
13. [13]
  L. Ward, B. Blaiszik, I. Foster, et al., MRS Commun. 9 (2019) 891–899. doi: 10.1557/mrc.2019.107
14. [14]
  Hansen K, G. Montavon, F. Biegler, et al., J. Chem. Theory Comput. 9 (2013) 3404–3419. doi: 10.1021/ct400195d
15. [15]
  A. Jussupow, V.R.I. Kaila, J. Chem. Theory Comput. 19 (2023) 1965–1975. doi: 10.1021/acs.jctc.2c01027
16. [16]
  B. Selvaratnam, R.T. Koodali, P. Miró, J. Phys. Chem. 60 (2020) 1928–1935.
17. [17]
  M. Rupp, A. Tkatchenko, K.R. Müller, et al., J. Cheminf. 4 (2012) 1. doi: 10.1186/1758-2946-4-1
18. [18]
  A.K. Gupta, K. Raghavachari, J. Chem. Theory Comput. 18 (2022) 2132–2143. doi: 10.1021/acs.jctc.1c00504
19. [19]
  E.M. Collins, K. Raghavachari, J. Comput. Chem. 19 (2023) 2804–2810.
20. [20]
  M. Kilgour, J. Rogal, M. Tuckerman, J. Chem. Theory Comput. (2023). arXiv: 2303.10140.
21. [21]
  H. Wang, X. Shi, D.Y. Yeung, Adv. Neural Inf. Process. Syst. (2016) 118–126.
22. [22]
  G. Montavon, K. Hansen, S. Fazli, et al., Adv. Neural Inf. Process. Syst. 1 (2012) 449–457.
23. [23]
  J. Hoja, L. Medrano Sandonas, B.G. Ernst, et al., Sci. Data 8 (2021) 43.
24. [24]
  D.P. Kingma, J. Ba, Learning (2014). arXiv: 1412.6980[cs. LG].
25. [25]
  C. Chu, Q. Xiao, Y. Zhang, et al., Int. J. Pattern Recognit. Artif. Intell. 36 (2022) 2250036. doi: 10.1142/S0218001422500367
26. [26]
  M. Rupp, A. Tkatchenko, K.R. Müller, et al., Phys. Rev. Lett. 108 (2012) 058301. doi: 10.1103/PhysRevLett.108.058301
27. [27]
  M. Krykunov, T.K. Woo, J. Chem. Theory Comput. 14 (2018) 5229–5237. doi: 10.1021/acs.jctc.8b00788
28. [28]
  S. Laghuvarapu, Y. Pathak, U.D. Priyakumar, J. Comput. Chem. 41 (2020) 790–799. doi: 10.1002/jcc.26128
29. [29]
  A.B. Tchagang, J.J. Valdés, Prediction of the Atomization Energy of Molecules Using Coulomb Matrix and Atomic Composition in a Bayesian Regularized Neural Networks, ICANN, 2019, pp. 793–803.
30. [30]
  S. Wengert, G. Csányi, K. Reuter, et al., J. Chem. Theory Comput. 18 (7) (2022) 4586–4593. doi: 10.1021/acs.jctc.2c00343
31. [31]
  Y.H. Tang, W.A. de Jong, J. Chem. Phys. 150 (2019) 044107. doi: 10.1063/1.5078640
32. [32]
  M. Tsubaki, T. Mizoguchi, J. Chem. Theory Comput. 17 (2021) 7814–7821. doi: 10.1021/acs.jctc.1c00568
33. [33]
  X. Fu, X. Cheng, C. He, et al., Phys. Chem. Chem. Phys. 25 (2023) 2430–2438. doi: 10.1039/D2CP04941D
1. [1]
  Run-Han Li , Tian-Yi Dang , Wei Guan , Jiang Liu , Ya-Qian Lan , Zhong-Min Su . Evolution exploration and structure prediction of Keggin-type group IVB metal-oxo clusters. Chinese Chemical Letters, 2024, 35(5): 108805-. doi: 10.1016/j.cclet.2023.108805
2. [2]
  Lingna Wang , Chenxin Tian , Ruobin Dai , Zhiwei Wang . Eco-friendly regeneration of end-of-life PVDF membrane with triethyl phosphate: Efficiency and mechanism. Chinese Chemical Letters, 2024, 35(9): 109356-. doi: 10.1016/j.cclet.2023.109356
3. [3]
  Yijia Jiao , Yuzhu Li , Yuting Zhou , Peipei Cen , Yi Ding , Yan Guo , Xiangyu Liu . Structural evolution and zero-field SMM behaviour in ferromagnetically-coupled disk-type Co₇ clusters bearing exclusively end-on azido bridges. Chinese Chemical Letters, 2024, 35(8): 109082-. doi: 10.1016/j.cclet.2023.109082
4. [4]
  Shihong Wu , Ronghui Zhou , Hang Zhao , Peng Wu . Sonoafterglow luminescence for in vivo deep-tissue imaging. Chinese Chemical Letters, 2024, 35(10): 110026-. doi: 10.1016/j.cclet.2024.110026
5. [5]
  Dian-Xue Ma , Yu-Wu Zhong . Achieving highly-efficient room-temperature phosphorescence with a nylon matrix. Chinese Journal of Structural Chemistry, 2024, 43(9): 100391-100391. doi: 10.1016/j.cjsc.2024.100391
6. [6]
  Zixing Xu , Ruiying Chen , Chuanming Hao , Qionghong Xie , Chunhui Deng , Nianrong Sun . Peptidome data-driven comprehensive individualized monitoring of membranous nephropathy with machine learning. Chinese Chemical Letters, 2024, 35(5): 108975-. doi: 10.1016/j.cclet.2023.108975
7. [7]
  Dan Ouyang , Huan Huang , Yanting He , Jiajing Chen , Jiali Lin , Zhuling Chen , Zongwei Cai , Zian Lin . Utilization of hydralazine as a reactive matrix for enhanced detection and on-MALDI-target derivatization of saccharides. Chinese Chemical Letters, 2024, 35(5): 108885-. doi: 10.1016/j.cclet.2023.108885
8. [8]
  Boran Cheng , Lei Cao , Chen Li , Fang-Yi Huo , Qian-Fang Meng , Ganglin Tong , Xuan Wu , Lin-Lin Bu , Lang Rao , Shubin Wang . Fluorine-doped carbon quantum dots with deep-red emission for hypochlorite determination and cancer cell imaging. Chinese Chemical Letters, 2024, 35(6): 108969-. doi: 10.1016/j.cclet.2023.108969
9. [9]
  Yuxiang Zhang , Jia Zhao , Sen Lin . Nitrogen doping retrofits the coordination environment of copper single-atom catalysts for deep CO2 reduction. Chinese Journal of Structural Chemistry, 2024, 43(11): 100415-100415. doi: 10.1016/j.cjsc.2024.100415
10. [10]
  Hualei Xu , Manman Han , Haiqiang Liu , Liang Qin , Lulu Chen , Hao Hu , Ran Wu , Chenyu Yang , Hua Guo , Jinrong Li , Jinxiang Fu , Qichen Hao , Yijun Zhou , Jinchao Feng , Xiaodong Wang . 4-Nitrocatechol as a novel matrix for low-molecular-weight compounds in situ detection and imaging in biological tissues by MALDI-MSI. Chinese Chemical Letters, 2024, 35(6): 109095-. doi: 10.1016/j.cclet.2023.109095
11. [11]
  Zhao Li , Huimin Yang , Wenjing Cheng , Lin Tian . Recent progress of in situ/operando characterization techniques for electrocatalytic energy conversion reaction. Chinese Chemical Letters, 2024, 35(9): 109237-. doi: 10.1016/j.cclet.2023.109237
12. [12]
  Peng Wang , Daijie Deng , Suqin Wu , Li Xu . Cobalt-based deep eutectic solvent modified nitrogen-doped carbon catalyst for boosting oxygen reduction reaction in zinc-air batteries. Chinese Journal of Structural Chemistry, 2024, 43(1): 100199-100199. doi: 10.1016/j.cjsc.2023.100199
13. [13]
  Zhao-Xia Lian , Xue-Zhi Wang , Chuang-Wei Zhou , Jiayu Li , Ming-De Li , Xiao-Ping Zhou , Dan Li . Producing circularly polarized luminescence by radiative energy transfer from achiral metal-organic cage to chiral organic molecules. Chinese Chemical Letters, 2024, 35(8): 109063-. doi: 10.1016/j.cclet.2023.109063
14. [14]
  Feibin Wei , Yongfang Rao , Yu Huang , Wei Wang , Hui Mei . The new challenges for the development of NH₃-SCR catalysts under new situation of energy transition in power generation industry. Chinese Chemical Letters, 2024, 35(6): 108931-. doi: 10.1016/j.cclet.2023.108931
15. [15]
  Xinyu Ren , Hong Liu , Jingang Wang , Jiayuan Yu . Electrospinning-derived functional carbon-based materials for energy conversion and storage. Chinese Chemical Letters, 2024, 35(6): 109282-. doi: 10.1016/j.cclet.2023.109282
16. [16]
  Chaoqun Ma , Yuebo Wang , Ning Han , Rongzhen Zhang , Hui Liu , Xiaofeng Sun , Lingbao Xing . Carbon dot-based artificial light-harvesting systems with sequential energy transfer and white light emission for photocatalysis. Chinese Chemical Letters, 2024, 35(4): 108632-. doi: 10.1016/j.cclet.2023.108632
17. [17]
  Chao Ma , Cong Lin , Jian Li . MicroED as a powerful technique for the structure determination of complex porous materials. Chinese Journal of Structural Chemistry, 2024, 43(3): 100209-100209. doi: 10.1016/j.cjsc.2023.100209
18. [18]
  Yuhang Li , Yang Ling , Yanhang Ma . Application of three-dimensional electron diffraction in structure determination of zeolites. Chinese Journal of Structural Chemistry, 2024, 43(4): 100237-100237. doi: 10.1016/j.cjsc.2024.100237
19. [19]
  Hai-Ling Wang , Zhong-Hong Zhu , Hua-Hong Zou . Structure and assembly mechanism of high-nuclear lanthanide-oxo clusters. Chinese Journal of Structural Chemistry, 2024, 43(9): 100372-100372. doi: 10.1016/j.cjsc.2024.100372
20. [20]
  Hui Liu , Xiangyang Tang , Zhuang Cheng , Yin Hu , Yan Yan , Yangze Xu , Zihan Su , Futong Liu , Ping Lu . Constructing multifunctional deep-blue emitters with weak charge transfer excited state for high-performance non-doped blue OLEDs and single-emissive-layer hybrid white OLEDs. Chinese Chemical Letters, 2024, 35(10): 109809-. doi: 10.1016/j.cclet.2024.109809

Get Citation

PDF

XML

Metrics

PDF Downloads(2)
Abstract views(247)
HTML views(14)

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142