Efficient and interpretable graph network representation for angle-dependent properties applied to optical spectroscopy
Source abstract
Abstract
Abstract Graph neural networks are attractive for learning properties of atomic structures thanks to their intuitive graph encoding of atoms and bonds. However, conventional encoding does not include angular information, which is critical for describing atomic arrangements in disordered systems. In this work, we extend the recently proposed ALIGNN (Atomistic Line Graph Neural Network) encoding, which incorporates bond angles, to also include dihedral angles (ALIGNN-d). This simple extension leads to a memory-efficient graph representation that captures the complete geometry of atomic structures. ALIGNN-d is applied to predict the infrared optical response of dynamically disordered Cu(II) aqua complexes, leveraging the intrinsic interpretability to elucidate the relative contributions of individual structural components. Bond and dihedral angles are found to be critical contributors to the fine structure of the absorption response, with distortions that represent transitions between more common geometries exhibiting the strongest absorption intensity. Future directions for further development of ALIGNN-d are discussed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Computational Drug Discovery Methods · Spectroscopy and Quantum Chemical Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. PMLR. 70, 1263–1272 (2017).
2. Coley, C. W., Barzilay, R., Green, W. H., Jaakkola, T. S. & Jensen, K. F. Convolutional embedding of attributed molecular graphs for physical property prediction. J. Chem. Inf. Model 57, 1757–1772 (2017).10.1021/acs.jcim.6b00601 ↗
3. Schütt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A. & Müller, K.-R. Schnet–a deep learning architecture for molecules and materials. J. Chem. Phys. 148, 241722 (2018).10.1063/1.5019779 ↗
4. Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120, 145301 (2018).10.1103/PhysRevLett.120.145301 ↗
5. Yang, K. et al. Analyzing learned molecular representations for property prediction. J. Chem. Inf. Model. 59, 3370–3388 (2019).10.1021/acs.jcim.9b00237 ↗
6. Chen, C., Ye, W., Zuo, Y., Zheng, C. & Ong, S. P. Graph networks as a universal machine learning framework for molecules and crystals. Chem. Mater. 31, 3564–3572 (2019).10.1021/acs.chemmater.9b01294 ↗
7. Linker, G.-J., van Duijnen, P. T. & Broer, R. Understanding trends in molecular bond angles. J. Phys. Chem. A 124, 1306–1311 (2020).10.1021/acs.jpca.9b10248 ↗
8. Timoshenko, J. & Frenkel, A. I. "inverting” x-ray absorption spectra of catalysts by machine learning in search for activity descriptors. ACS Catal. 9, 10192–10211 (2019).10.1021/acscatal.9b03599 ↗
9. Guda, A. et al. Machine learning approaches to xanes spectra for quantitative 3d structural determination: The case of co2 adsorption on cpo-27-ni mof. Radiat. Phys. Chem. 175, 108430 (2020).10.1016/j.radphyschem.2019.108430 ↗
10. Guda, A. A. et al. Quantitative structural determination of active sites from in situ and operando xanes spectra: from standard ab initio simulations to chemometric and machine learning approaches. Catal Today 336, 3–21 (2019).10.1016/j.cattod.2018.10.071 ↗
11. Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett 98, 146401 (2007).10.1103/PhysRevLett.98.146401 ↗
12. Samanta, A. Representing local atomic environment using descriptors based on local correlations. J. Chem. Phys. 149, 244102 (2018).10.1063/1.5055772 ↗
13. Lindsey, R. K., Fried, L. E. & Goldman, N. Chimes: A force matched potential with explicit three-body interactions for molten carbon. J. Chem. Theory Comput. 13, 6222–6229 (2017).10.1021/acs.jctc.7b00867 ↗
14. Pham, T. A. et al. Integrating ab initio simulations and x-ray photoelectron spectroscopy: Toward a realistic description of oxidized solid/liquid interfaces. J. Phys. Chem. Lett. 9, 194–203 (2018).10.1021/acs.jpclett.7b01382 ↗
15. Velasco-Velez, J.-J. et al. The structure of interfacial water on gold electrodes studied by x-ray absorption spectroscopy. Science 346, 831–834 (2014).10.1126/science.1259437 ↗
16. Pham, T. A. et al. Electronic structure of aqueous solutions: Bridging the gap between theory and experiments. Sci. Adv. 3, e1603210 (2017).10.1126/sciadv.1603210 ↗
17. Wan, L. F. & Prendergast, D. The solvation structure of mg ions in dichloro complex solutions from first-principles molecular dynamics and simulated x-ray absorption spectra. J. Am. Chem. Soc. 136, 14456–14464 (2014).10.1021/ja505967u ↗
18. Park, C. W. & Wolverton, C. Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery. Phys. Rev. Mater. 4, 063801 (2020).10.1103/PhysRevMaterials.4.063801 ↗
19. Klicpera, J., Groß, J. & Günnemann, S. Directional message passing for molecular graphs. Preprint at https://arxiv.org/abs/2003.03123 (2020).
20. Choudhary, K. & DeCost, B. Atomistic line graph neural network for improved materials property predictions. npj Comput Mater 7, 1–8 (2021).10.1038/s41524-021-00650-1 ↗
21. Schütt, K., Unke, O. & Gastegger, M. Equivariant message passing for the prediction of tensorial properties and molecular spectra. PMLR 139, 9377–9388 (2021).
22. Chapman, J., Batra, R. & Ramprasad, R. Machine learning models for the prediction of energy, forces, and stresses for platinum. Comput. Mater. Sci. 174, 109483 (2020).10.1016/j.commatsci.2019.109483 ↗
23. Chapman, J., Goldman, N. & Wood, B. C. Efficient and universal characterization of atomic structures through a topological graph order parameter. npj Comput. Mater. 8, 37 (2022).10.1038/s41524-022-00717-7 ↗
24. Qiu, S. R. et al. Origins of optical absorption characteristics of cu 2+ complexes in aqueous solutions. Phys. Chem. Chem. Phys. 17, 18913–18923 (2015).10.1039/C5CP01688F ↗
25. Pasquarello, A. et al. First solvation shell of the cu (ii) aqua ion: evidence for fivefold coordination. Science 291, 856–859 (2001).10.1126/science.291.5505.856 ↗
26. Parsons, J., Holmes, J. B., Rojas, J. M., Tsai, J. & Strauss, C. E. Practical conversion from torsion space to cartesian space for in silico protein synthesis. J. Comput. Chem. 26, 1063–1068 (2005).10.1002/jcc.20237 ↗
27. Giannozzi, P. et al. Quantum espresso: a modular and open-source software project for quantum simulations of materials. J. Phys. Condens. Matter. 21, 395502 (2009).10.1088/0953-8984/21/39/395502 ↗
28. Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865 (1996).10.1103/PhysRevLett.77.3865 ↗
29. Vanderbilt, D. Soft self-consistent pseudopotentials in a generalized eigenvalue formalism. Phys. Rev. B 41, 7892 (1990).10.1103/PhysRevB.41.7892 ↗
30. Grossman, J. C., Schwegler, E., Draeger, E. W., Gygi, F. & Galli, G. Towards an assessment of the accuracy of density functional theory for first principles simulations of water. J. Chem. Phys. 120, 300–311 (2004).10.1063/1.1630560 ↗
31. Runge, E. & Gross, E. K. Density-functional theory for time-dependent systems. Phys. Rev. Lett. 52, 997 (1984).10.1103/PhysRevLett.52.997 ↗
32. Hirata, S. & Head-Gordon, M. Time-dependent density functional theory within the tamm–dancoff approximation. Chem. Phys. Lett. 314, 291–299 (1999).10.1016/S0009-2614(99)01149-5 ↗
33. Apra, E. et al. Nwchem: Past, present, and future. J. Chem. Phys. 152, 184102 (2020).10.1063/5.0004997 ↗
34. Huber, S. P. et al. Aiida 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance. Sci. Data 7, 1–18 (2020).10.1038/s41597-020-00638-4 ↗
35. Casanova, D. et al. Minimal distortion pathways in polyhedral rearrangements. J. Am. Chem. Soc. 126, 1755–1763 (2004).10.1021/ja036479n ↗
36. Larsen, A. H. et al. The atomic simulation environment-a python library for working with atoms. J. Phys. Condens. Matter. 29, 273002 (2017).10.1088/1361-648X/aa680e ↗
37. Fey, M. & Lenssen, J. E. Fast graph representation learning with pytorch geometric. Preprint at https://arxiv.org/abs/1903.02428 (2019).
38. Paszke, A. et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32, 8026–8037 (2019).
39. Bresson, X. & Laurent, T. Residual gated graph convnets. Preprint at https://arxiv.org/abs/1711.07553 (2017) .
40. Dwivedi, V. P., Joshi, C. K., Laurent, T., Bengio, Y. & Bresson, X. Benchmarking graph neural networks. Preprint at https://arxiv.org/abs/2003.00982 (2020).
41. Elfwing, S., Uchibe, E. & Doya, K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw 107, 3–11 (2018).10.1016/j.neunet.2017.12.012 ↗
42. Ba, J. L., Kiros, J. R. & Hinton, G. E. Layer normalization. Preprint at https://arxiv.org/abs/1607.06450 (2016).
43. Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2014).
44. Smith, L. N. & Topin, N. Super-convergence: Very fast training of neural networks using large learning rates. Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications 11006, 1100612 (2019).