DMCP is aimed to implement DFT-based and Machine-learning-accelerated (DFT-ML) scheme for captureing QSPR in intricate system . It is possible to predict the property of intricate system such as HEAs and to reveal the intrinsic descriptors which determine the underlying property of them with appropriate algorithm and train data features.
DMCP is developed within Prof. Yuzheng Guo's group in Wuhan University, in colloboration with Prof. John Robertson's group in Cambridge University. Core developer: Xuhao Wan, Yuzheng Guo Email: xhwanrm@whu.edu.cn, yguo@whu.edu.cn
- Ten machine learning algorithms: GBR, KNR, SVR, GPR, FNN, RFR, ETR, KRR, LASSO, and ENR.
- Multiple methods to improve model accuracy: dataset split, cross validation, repeated trails.
- Visualization module for research.
- Generally, you need some data obtained from DFT calculations such as VASP, QE, and CP2K or available material database.
- DMCP requires Python 3 with the packages specified in requirements.txt. This is taken care of by pip.
If you use DMCP in your research, please cite the following paper:
- X. Wan, Z. Zhang*, W. Yu, Y. Guo*, A State-of-the-art Density-functional-theory-based and Machine-learning-accelerated Hybrid Method for Intricate System Catalysis. Materials Reports: Energy. doi.org/10.1016/j.matre.2021.100046.
The work applied DMCP are listed as following:
- Dou B, Zhu Z, Merkurjev E, et al. Machine learning methods for small data challenges in molecular science. Chemical Reviews, 2023, 123(13): 8736-8780.
- Tamtaji M, Gao H, Hossain M D, et al. Machine learning for design principles for single atom catalysts towards electrochemical reactions. Journal of Materials Chemistry A, 2022, 10(29): 15309-15331.
- Liu X, Zhang Y, Wang W, et al. Transition metal and N doping on AlP monolayers for bifunctional oxygen electrocatalysts: density functional theory study assisted by machine learning description. ACS Applied Materials & Interfaces, 2021, 14(1): 1249-1259.
- Huang Y, Rehman F, Tamtaji M, et al. Mechanistic understanding and design of non-noble metal-based single-atom catalysts supported on two-dimensional materials for CO 2 electroreduction. Journal of Materials Chemistry A, 2022, 10(11): 5813-5834.
- Liu T, Zhao X, Liu X, et al. Understanding the hydrogen evolution reaction activity of doped single-atom catalysts on two-dimensional GaPS4 by DFT and machine learning. Journal of Energy Chemistry, 2023, 81: 93-100.
- X. Wan, Z. Zhang*, H. Niu, Y. Yin, C. Kuai, J. Wang, C. Shao, Y. Guo*, Machine-Learning-Accelerated Catalytic Activity Predictions of Transition Metal Phthalocyanine Dual-Metal-Sites Catalysts for CO2 Reduction. The Journal of Physical Chemistry Letters, 2021.
- H. Niu#, X. Wan#, X. Wang, C. Chen, J. Robertson, Z. Zhang*, Y. Guo*, Single-Atom Rhodium on Defective g-C3N4: A Promising Bifunctional Oxygen Electrocatalyst. ACS Sustainable Chem. Eng., 9(9), 3590-3599, 2021.
- Wan X, Yu W, Niu H, ea al. Revealing the Oxygen Reduction/Evoluti on Reaction Activity Origin of Carbon-Nitride-Related Single-Atom catalysts: Quantum Chemistry in Artificial Intelligence. Chemical Engineering Journal. 2022,440:135946.
- Khrabrov K, Shenbin I, Ryabov A, et al. nablaDFT: Large-Scale Conformational Energy and Hamiltonian Prediction benchmark and dataset. Physical Chemistry Chemical Physics, 2022, 24(42): 25853-25863.
- Pant D, Pokharel S, Mandal S, et al. DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides. Scientific Reports, 2023, 13(1): 3277.
Welcome to join the DMCP exchange Wechat group. 欢迎加入DMCP微信交流群。
If it is invalid, please contact us by Email.