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]
  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
2. [2]
  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 Networ. Acta Physico-Chimica Sinica, 2025, 41(2): 100017-. doi: 10.3866/PKU.WHXB202310045
3. [3]
  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
4. [4]
  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
5. [5]
  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
6. [6]
  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
7. [7]
  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
8. [8]
  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
9. [9]
  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
10. [10]
  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
11. [11]
  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
12. [12]
  Yiwen Lin , Yijie Chen , Chunhui Deng , Nianrong Sun . Integration of resol/block-copolymer carbonization and machine learning: A convenient approach for precise monitoring of glycan-associated disorders. Chinese Chemical Letters, 2024, 35(12): 109813-. doi: 10.1016/j.cclet.2024.109813
13. [13]
  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
14. [14]
  Ran Wu , Dongxu Jiang , Hao Hu , Chenyu Yang , Liang Qin , Lulu Chen , Zehui Hu , Hualei Xu , Jinrong Li , Haiqiang Liu , Hua Guo , Jinxiang Fu , Qichen Hao , Yijun Zhou , Jinchao Feng , Qiang Wang , Xiaodong Wang . 4-Aminoazobenzene: A novel negative ion matrix for enhanced MALDI tissue imaging of metabolites. Chinese Chemical Letters, 2024, 35(11): 109624-. doi: 10.1016/j.cclet.2024.109624
15. [15]
  Haijun Shen , Yi Qiao , Chun Zhang , Yane Ma , Jialing Chen , Yingying Cao , Wenna Zheng . A matrix metalloproteinase-sensitive hydrogel combined with photothermal therapy for transdermal delivery of deferoxamine to accelerate diabetic pressure ulcer healing. Chinese Chemical Letters, 2024, 35(12): 110283-. doi: 10.1016/j.cclet.2024.110283
16. [16]
  Tianyi Yang , Fangxi Su , Dehuan Shi , Shenghong Zhong , Yalin Guo , Zhaohui Liu , Jianfeng Huang . Efficient propane dehydrogenation catalyzed by Ru nanoparticles anchored on a porous nitrogen-doped carbon matrix. Chinese Chemical Letters, 2025, 36(2): 110444-. doi: 10.1016/j.cclet.2024.110444
17. [17]
  Yao-Hua Gu , Yu Chen , Qing Li , Neng-Bin Xie , Xue Xing , Jun Xiong , Min Hu , Tian-Zhou Li , Ke-Yu Yuan , Yu Liu , Tang Tang , Fan He , Bi-Feng Yuan . Metabolome profiling by widely-targeted metabolomics and biomarker panel selection using machine-learning for patients in different stages of chronic kidney disease. Chinese Chemical Letters, 2024, 35(11): 109627-. doi: 10.1016/j.cclet.2024.109627
18. [18]
  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
19. [19]
  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
20. [20]
  Jiahao Liu , Peng Liu , Junhong Duan , Qiongxuan Xie , Jie Feng , Hongpei Tan , Ze Mi , Ying Li , Yunjie Liao , Pengfei Rong , Wenhu Zhou , Xiang Gao . Macrophages-mediated tumor accumulation and deep penetration of bismuth/manganese biomineralized nanoparticles for enhanced radiotherapy. Chinese Chemical Letters, 2024, 35(12): 109632-. doi: 10.1016/j.cclet.2024.109632

Get Citation

PDF

XML

Metrics

PDF Downloads(2)
Abstract views(475)
HTML views(25)

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