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]
  Xi Xue , Kai Chen , Hanyu Sun , Xiangying Liu , Xue Liu , Shize Li , Jingjie Yan , Yu Peng , Mohammad S. Mubarak , Ahmed Al-Harrasi , Hai-Yu Hu , Yafeng Deng , Xiandao Pan , Xiaojian Wang . Bidirectional Chemical Intelligent Net: A unified deep learning–based framework for predicting chemical reaction. Chinese Chemical Letters, 2025, 36(11): 110968-. doi: 10.1016/j.cclet.2025.110968
2. [2]
  Feihu Wu , Gengwen Chen , Kaitao Lai , Shiqing Zhang , Yingchao Liu , Ruijian Luo , Xiaocong Wang , Pinzhi Cao , Yi Ye , Jiarong Lian , Junle Qu , Zhigang Yang , Xiaojun Peng . Non-specific/specific SERS spectra concatenation for precise bacteria classifications with few samples using a residual neural network. Chinese Chemical Letters, 2025, 36(1): 109884-. doi: 10.1016/j.cclet.2024.109884
3. [3]
  Lu Li , Jianing Shen , Qinkun Xiao , Chaozheng He , Jinzhou Zheng , Chaoqin Chu , Chen Chen . Stable crystal structure prediction using machine learning-based formation energy and empirical potential function. Chinese Chemical Letters, 2025, 36(11): 110421-. doi: 10.1016/j.cclet.2024.110421
4. [4]
  Yunzhe Zheng , Si Sun , Jiali Liu , Qingyu Zhao , Heng Zhang , Jing Zhang , Peng Zhou , Zhaokun Xiong , Chuan-Shu He , Bo Lai . Application of machine learning for material prediction and design in the environmental remediation. Chinese Chemical Letters, 2025, 36(9): 110722-. doi: 10.1016/j.cclet.2024.110722
5. [5]
  Chang Guo , Haipeng Yang , Hui Fang , Yingguo Zhao , Yating Li . 基于深度学习的物理化学课程DOK教学实践初探——以弯曲液面附加压力和蒸气压教学为例. University Chemistry, 2025, 40(6): 28-36. doi: 10.12461/PKU.DXHX202408049
6. [6]
  Jun Jiang , Quan Lan , Yuan Zheng , Zhenggen Zha . Teaching Exploration and Practice of the Organic Chemistry Laboratory English Course Based on the “Flipped Classroom + MOOC” Teaching Model. University Chemistry, 2025, 40(9): 279-286. doi: 10.12461/PKU.DXHX202410094
7. [7]
  Haolin Zhan , Qiyuan Fang , Jiawei Liu , Xiaoqi Shi , Xinyu Chen , Yuqing Huang , Zhong Chen . Noise Reduction of Nuclear Magnetic Resonance Spectroscopy Using Lightweight Deep Neural Network. Acta Physico-Chimica Sinica, 2025, 41(2): 100017-0. doi: 10.3866/PKU.WHXB202310045
8. [8]
  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
9. [9]
  Liping Wang , Huanfeng Wang , Yuling Li , Lingchuan Li , Xiaojing Li , Huifeng Chen , Bowen Ji , Linna Wang . Exploring the Full Process of a Research-Based Teaching Model through the Deep Integration of Theory and Practice: A Case Study of the Self-Designed Scheme for “Determination of Total Acid Content in White Vinegar”. University Chemistry, 2025, 40(5): 244-251. doi: 10.12461/PKU.DXHX202406035
10. [10]
  Zhaojing Huang , Hao Li , Jiayi Luo , Shunxing Li , Ming Zhao , Fengjiao Liu , Haijiao Xie . Deep learning-based simultaneous bioavailability assessment and speciation analysis of dissolved organic copper. Chinese Chemical Letters, 2025, 36(5): 110209-. doi: 10.1016/j.cclet.2024.110209
11. [11]
  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
12. [12]
  Qingyun Hu , Wei Wang , Junyuan Lu , He Zhu , Qi Liu , Yang Ren , Hong Wang , Jian Hui . High-throughput screening of high energy density LiMn_1-xFe_xPO₄ via active learning. Chinese Chemical Letters, 2025, 36(2): 110344-. doi: 10.1016/j.cclet.2024.110344
13. [13]
  Guilong Li , Wenbo Ma , Jialing Zhou , Caiqin Wu , Chenling Yao , Huan Zeng , Jian Wang . A composite hydrogel with porous and homogeneous structure for efficient osmotic energy conversion. Chinese Chemical Letters, 2025, 36(2): 110449-. doi: 10.1016/j.cclet.2024.110449
14. [14]
  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
15. [15]
  Jian Wang , Baohui Wang , Pin Ma , Yifei Zhang , Honghong Gong , Biyun Peng , Sen Liang , Yunchuan Xie , Hailong Wang . Regulation of uniformity and electric field distribution achieved highly energy storage performance in PVDF-based nanocomposites via continuous gradient structure. Chinese Chemical Letters, 2025, 36(4): 109714-. doi: 10.1016/j.cclet.2024.109714
16. [16]
  Hongyang Li , Yue Liu , Xiuwen Wang , Haijing Yan , Guimin Wang , Dongxu Wang , Yilong Wang , Shuo Yang , Yanqing Jiao . Morphology engineering and electronic structure remodeling of manganese-incorporated VN for boosting urea-assisted energy-saving hydrogen production. Chinese Chemical Letters, 2025, 36(6): 110042-. doi: 10.1016/j.cclet.2024.110042
17. [17]
  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
18. [18]
  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
19. [19]
  Yao Zou , Difei Gong , Haiguang Yang , Hongmei Yu , Guorong He , Ningbo Gong , Lianhua Fang , Guanhua Du , Yang Lu . Prediction, screening, characterization, antioxidant and antihypoxic effects of multi-component zwitterionic cocrystals of dietary flavonoids with picolinic acid. Chinese Chemical Letters, 2025, 36(9): 110768-. doi: 10.1016/j.cclet.2024.110768
20. [20]
  Zonglin Li , Shihua Zou , Zining Wang , Georgeta Postole , Liang Hu , Hongying Zhao . Machine learning in electrochemical oxidation process: A mini-review. Chinese Chemical Letters, 2025, 36(8): 110526-. doi: 10.1016/j.cclet.2024.110526

Get Citation

PDF

XML

Metrics

PDF Downloads(2)
Abstract views(1223)
HTML views(66)

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