Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Molecular Conformation Generation via Shifting Scores (2309.09985v2)

Published 12 Sep 2023 in physics.comp-ph and cs.AI

Abstract: Molecular conformation generation, a critical aspect of computational chemistry, involves producing the three-dimensional conformer geometry for a given molecule. Generating molecular conformation via diffusion requires learning to reverse a noising process. Diffusion on inter-atomic distances instead of conformation preserves SE(3)-equivalence and shows superior performance compared to alternative techniques, whereas related generative modelings are predominantly based upon heuristical assumptions. In response to this, we propose a novel molecular conformation generation approach driven by the observation that the disintegration of a molecule can be viewed as casting increasing force fields to its composing atoms, such that the distribution of the change of inter-atomic distance shifts from Gaussian to Maxwell-Boltzmann distribution. The corresponding generative modeling ensures a feasible inter-atomic distance geometry and exhibits time reversibility. Experimental results on molecular datasets demonstrate the advantages of the proposed shifting distribution compared to the state-of-the-art.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Geom, energy-annotated molecular conformations for property prediction and molecular generation. Scientific Data, 9(1):185, 2022. doi: 10.1038/s41597-022-01288-4. URL https://doi.org/10.1038/s41597-022-01288-4.
  2. E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature communications, 13(1):2453, 2022.
  3. Iterative bregman projections for regularized transportation problems. SIAM Journal on Scientific Computing, 37(2):A1111–A1138, 2015.
  4. sgdml: Constructing accurate and data efficient molecular force fields using machine learning. Computer Physics Communications, 240:38–45, 2019.
  5. Se (3)-transformers: 3d roto-translation equivariant attention networks. Advances in Neural Information Processing Systems, 33:1970–1981, 2020.
  6. Geomol: Torsional geometric generation of molecular 3d conformer ensembles. Advances in Neural Information Processing Systems, 34:13757–13769, 2021.
  7. Directional message passing for molecular graphs. arXiv preprint arXiv:2003.03123, 2020.
  8. Neural message passing for quantum chemistry. In International conference on machine learning, pp.  1263–1272. PMLR, 2017.
  9. Introduction to quantum mechanics. Cambridge university press, 2018.
  10. Equivariant graph hierarchy-based neural networks. Advances in Neural Information Processing Systems, 35:9176–9187, 2022.
  11. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
  12. Equivariant diffusion for molecule generation in 3d. In International Conference on Machine Learning, pp.  8867–8887. PMLR, 2022.
  13. Torsional diffusion for molecular conformer generation. In Advances in Neural Information Processing Systems.
  14. Wolfgang Kabsch. A solution for the best rotation to relate two sets of vectors. Acta Crystallographica Section A: Crystal Physics, Diffraction, Theoretical and General Crystallography, 32(5):922–923, 1976.
  15. Paul Labute. Lowmodemd-implicit low-mode velocity filtering applied to conformational search of macrocycles and protein loops. Journal of chemical information and modeling, 50(5):792–800, 2010.
  16. Relevance of rotationally equivariant convolutions for predicting molecular properties. arXiv preprint arXiv:2008.08461, 2020.
  17. Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning. Science, 365(6457):eaaw1147, 2019.
  18. Quantum chemistry structures and properties of 134 kilo molecules. Scientific data, 1(1):1–7, 2014.
  19. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  10684–10695, 2022.
  20. E (n) equivariant graph neural networks. In International conference on machine learning, pp.  9323–9332. PMLR, 2021.
  21. Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. Advances in neural information processing systems, 30, 2017.
  22. Learning gradient fields for molecular conformation generation. In International Conference on Machine Learning, pp.  9558–9568. PMLR, 2021.
  23. A generative model for molecular distance geometry. In Proceedings of the 37th International Conference on Machine Learning, pp.  8949–8958, 2020.
  24. Symmetry-aware actor-critic for 3d molecular design. arXiv preprint arXiv:2011.12747, 2020.
  25. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502, 2020a.
  26. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, 32, 2019.
  27. Improved techniques for training score-based generative models. Advances in neural information processing systems, 33:12438–12448, 2020.
  28. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020b.
  29. Birgit Strodel. Energy landscapes of protein aggregation and conformation switching in intrinsically disordered proteins. Journal of Molecular Biology, 433(20):167182, 2021.
  30. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv preprint arXiv:1802.08219, 2018.
  31. Camdas: An automated conformational analysis system using molecular dynamics. Journal of computer-aided molecular design, 11:305–315, 1997.
  32. Pascal Vincent. A connection between score matching and denoising autoencoders. Neural computation, 23(7):1661–1674, 2011.
  33. 3d steerable cnns: Learning rotationally equivariant features in volumetric data. Advances in Neural Information Processing Systems, 31, 2018.
  34. Bayesian learning via stochastic gradient langevin dynamics. In Proceedings of the 28th international conference on machine learning (ICML-11), pp.  681–688, 2011.
  35. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826, 2018.
  36. Learning neural generative dynamics for molecular conformation generation. In International Conference on Learning Representations.
  37. An end-to-end framework for molecular conformation generation via bilevel programming. In International Conference on Machine Learning, pp.  11537–11547. PMLR, 2021a.
  38. Geodiff: A geometric diffusion model for molecular conformation generation. In International Conference on Learning Representations, 2021b.
  39. University physics 12th edition, 2008.
  40. Uni-mol: A universal 3d molecular representation learning framework. In The Eleventh International Conference on Learning Representations, 2023a. URL https://openreview.net/forum?id=6K2RM6wVqKu.
  41. Do deep learning methods really perform better in molecular conformation generation? arXiv preprint arXiv:2302.07061, 2023b.
  42. Direct molecular conformation generation. Transactions on Machine Learning Research.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Zihan Zhou (90 papers)
  2. Ruiying Liu (5 papers)
  3. Chaolong Ying (8 papers)
  4. Ruimao Zhang (84 papers)
  5. Tianshu Yu (40 papers)
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now