TorchMD: A Deep Learning Framework for Molecular Simulations

Abstract

Molecular dynamics simulations provide a mechanistic description of molecules by relying on empirical potentials. The quality and transferability of such potentials can be improved leveraging data-driven models derived with machine learning approaches. Here, we present TorchMD, a framework for molecular simulations with mixed classical and machine learning potentials. All force computations including bond, angle, dihedral, Lennard-Jones, and Coulomb interactions are expressed as PyTorch arrays and operations. Moreover, TorchMD enables learning and simulating neural network potentials. We validate it using standard Amber all-atom simulations, learning an ab initio potential, performing an end-to-end training, and finally learning and simulating a coarse-grained model for protein folding. We believe that TorchMD provides a useful tool set to support molecular simulations of machine learning potentials. Code and data are freely available at github.com/torchmd.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 54

1. 1.

   Lee E. H.; Hsin J.; Sotomayor M.; Comellas G.; Schulten K. Discovery Through the Computational Microscope. Structure 2009, 17, 1295–1306..

   Not in our library10.1016/j.str.2009.09.001

2. 2.

   Ponder J. W.; Case D. A. Advances in Protein Chemistry; Protein Simulations; Academic Press: 2003; Vol. 66, pp 27–85,.

   Not in our library10.1016/s0065-3233(03)66002-x

3. 3.

   Martínez-Rosell G.; Giorgino T.; Harvey M. J.; de Fabritiis G. Drug Discovery and Molecular Dynamics: Methods, Applications and Perspective Beyond the Second Timescale. Current Topics in Medicinal Chemistry 2017, 17, 2617–2625..

   Not in our library10.2174/1568026617666170414142549

4. 4.

   Schütt K.; Kindermans P.-J.; Felix H. E. S.; Chmiela S.; Tkatchenko A.; Müller K.-R. Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. Advances in neural information processing systems 2017, 991–1001.

   Not in our library

5. 5.

   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. 2018, 148, 241722.

   Not in our library10.1063/1.5019779

6. 6.

   Ruza J.; Wang W.; Schwalbe-Koda D.; Axelrod S.; Harris W. H.; Gómez-Bombarelli R. Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks. J. Chem. Phys. 2020, 153, 164501.

   Not in our library10.1063/5.0022431

7. 7.

   Duvenaud D. K.; Maclaurin D.; Iparraguirre J.; Bombarell R.; Hirzel T.; Aspuru-Guzik A.; Adams R. P. Convolutional networks on graphs for learning molecular fingerprints. Advances in neural information processing systems 2015, 2224–2232.

   Not in our library

8. 8.

   Husic B. E.; Charron N. E.; Lemm D.; Wang J.; Pérez A.; Majewski M.; Krämer A.; Chen Y.; Olsson S.; de Fabritiis G.; Noé F.; et al. Coarse Graining Molecular Dynamics with Graph Neural Networks. J. Chem. Phys. 2020, 153, 194101.

   Not in our library10.1063/5.0026133

9. 9.

   Wang J.; Olsson S.; Wehmeyer C.; Pérez A.; Charron N. E.; De Fabritiis G.; Noé F.; Clementi C. Machine learning of coarse-grained molecular dynamics force fields. ACS central science 2019, 5, 755–767..

   Not in our library10.1021/acscentsci.8b00913

10. 10.

    Nüske F.; Boninsegna L.; Clementi C. Coarse-graining molecular systems by spectral matching. J. Chem. Phys. 2019, 151, 044116.

    Not in our library10.1063/1.5100131

11. 11.

    Wang J.; Chmiela S.; Müller K.-R.; Noé F.; Clementi C. Ensemble learning of coarse-grained molecular dynamics force fields with a kernel approach. J. Chem. Phys. 2020, 152, 194106.

    Not in our library10.1063/5.0007276

12. 12.

    Zhang L.; Han J.; Wang H.; Car R.; E W. DeePCG: constructing coarse-grained models via deep neural networks. 2018, arXiv:1802.08549. arXiv.org e-Print archive. https://arxiv.org/abs/1802.08549 (accessed 2021-03-14).

    Not in our library10.1063/1.5027645

13. 13.

    Wang W.; Gómez-Bombarelli R. Coarse-graining auto-encoders for molecular dynamics. npj Computational Materials 2019, 5, 125.

    Not in our library10.1038/s41524-019-0261-5

14. 14.

    Wang W.; Yang T.; Harris W. H.; Gómez-Bombarelli R. Active learning and neural network potentials accelerate molecular screening of ether-based solvate ionic liquids. Chem. Commun. 2020, 56, 8920–8923..

    Not in our library10.1039/d0cc03512b

15. 15.

    Marrink S. J.; Tieleman D. P. Perspective on the Martini model. Chem. Soc. Rev. 2013, 42, 6801–6822..

    Not in our library10.1039/c3cs60093a

16. 16.

    Machado M. R.; Barrera E. E.; Klein F.; Sóñora M.; Silva S.; Pantano S. The SIRAH 2.0 Force Field: Altius, Fortius, Citius. J. Chem. Theory Comput. 2019, 15, 2719–2733..

    Not in our library10.1021/acs.jctc.9b00006

17. 17.

    Saunders M. G.; Voth G. A. Coarse-Graining Methods for Computational Biology. Annu. Rev. Biophys. 2013, 42, 73–93..

    Not in our library10.1146/annurev-biophys-083012-130348

18. 18.

    Izvekov S.; Voth G. A. A Multiscale Coarse-Graining Method for Biomolecular Systems. J. Phys. Chem. B 2005, 109, 2469–2473..

    Not in our library10.1021/jp044629q

19. 19.

    Noid W. G. Perspective: Coarse-grained models for biomolecular systems. J. Chem. Phys. 2013, 139, 090901.

    Not in our library10.1063/1.4818908

20. 20.

    Clementi C. Coarse-grained models of protein folding: Toy-models or predictive tools?. Curr. Opin. Struct. Biol. 2008, 18, 10–15..

    Not in our library10.1016/j.sbi.2007.10.005

21. 21.

    Paszke A.; Gross S.; Massa F.; Lerer A.; Bradbury J.; Chanan G.; Killeen T.; Lin Z.; Gimelshein N.; Antiga L.; Desmaison A.; Kopf A.; Yang E.; DeVito Z.; Raison M.; Tejani A.; Chilamkurthy S.; Steiner B.; Fang L.; Bai J.; Chintala S. In Advances in Neural Information Processing Systems 32; Wallach H., Larochelle H., Beygelzimer A., d’Alché-Buc F., Fox E., Garnett R., Eds.; Curran Associates, Inc.: 2019; pp 8024–8035.

    Not in our library

22. 22.

    Gao X.; Ramezanghorbani F.; Isayev O.; Smith J.; Roitberg A. TorchANI: A Free and Open Source PyTorch Based Deep Learning Implementation of the ANI Neural Network Potentials. 2020, ChemRxiv. https://chemrxiv.org/articles/preprint/TorchANI_A_Free_and_Open_Source_PyTorch_Based_Deep_Learning_Implementation_of_the_ANI_Neural_Network_Potentials/12218294 (accessed 2021-03-14).

    Not in our library10.1021/acs.jcim.0c00451

23. 23.

    Wang Y.; Fass J.; Chodera J. D. End-to-End Differentiable Molecular Mechanics Force Field Construction. 2020, preprint arXiv:2010.01196. arXiv.org e-Print archive. https://arxiv.org/abs/2010.01196 (accessed 2021-03-14).

    Not in our library

24. 24.

    Greener J. G.; Jones D. T. Differentiable molecular simulation can learn all the parameters in a coarse-grained force field for proteins. 2021, bioRxiv. https://www.biorxiv.org/content/10.1101/2021.02.05.429941v1 (accessed 2021-03-14).

    Not in our library10.1371/journal.pone.0256990

25. 25.

    Bradbury J.; Frostig R.; Hawkins P.; Johnson M. J.; Leary C.; Maclaurin D.; Wanderman-Milne S. JAX: composable transformations of Python+NumPy programs. 2018, GitHub. http://github.com/google/jax (accessed 2021-03-14).

    Not in our library

26. 26.

    Schoenholz S. S.; Cubuk E. D. JAX M. D. End-to-End Differentiable, Hardware Accelerated, Molecular Dynamics in Pure Python. 2019, https://arxiv.org/abs/1912.04232 (accessed 2021-03-16).

    Not in our library

27. 27.

    Zhao Y. Time Machine. 2020, GitHub. https://github.com/proteneer/timemachine (accessed 2021-03-14).

    Not in our library

28. 28.

    Yao K.; Herr J. E.; Toth D. W.; Mckintyre R.; Parkhill J. The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics. Chem. Sci. 2018, 9, 2261–2269..

    Not in our library10.1039/c7sc04934j

29. 29.

    Schütt K. T.; Kessel P.; Gastegger M.; Nicoli K. A.; Tkatchenko A.; Müller K.-R. SchNetPack: A Deep Learning Toolbox For Atomistic Systems. J. Chem. Theory Comput. 2019, 15, 448–455..

    Not in our library10.1021/acs.jctc.8b00908

30. 30.

    Tironi I. G.; Sperb R.; Smith P. E.; van Gunsteren W. F. A generalized reaction field method for molecular dynamics simulations. J. Chem. Phys. 1995, 102, 5451–5459..

    Not in our library10.1063/1.469273

31. 31.

    Harvey M. J.; Giupponi G.; Fabritiis G. D. ACEMD: accelerating biomolecular dynamics in the microsecond time scale. J. Chem. Theory Comput. 2009, 5, 1632–1639..

    Not in our library10.1021/ct9000685

32. 32.

    Shirts M. R.; Klein C.; Swails J. M.; Yin J.; Gilson M. K.; Mobley D. L.; Case D. A.; Zhong E. D. Lessons learned from comparing molecular dynamics engines on the SAMPL5 dataset. J. Comput.-Aided Mol. Des. 2017, 31, 147–161..

    Not in our library10.1007/s10822-016-9977-1

33. 33.

    Maier J. A.; Martinez C.; Kasavajhala K.; Wickstrom L.; Hauser K. E.; Simmerling C. ff14SB: Improving the Accuracy of Protein Side Chain and Backbone Parameters from ff99SB. J. Chem. Theory Comput. 2015, 11, 3696–3713..

    Not in our library10.1021/acs.jctc.5b00255

34. 34.

    Christensen A. S.; Bratholm L. A.; Faber F. A.; Anatole von Lilienfeld O. FCHL revisited: Faster and more accurate quantum machine learning. J. Chem. Phys. 2020, 152, 044107.

    Not in our library10.1063/1.5126701

35. 35.

    Falcon W. PyTorch Lightning. 2019, GitHub. https://github.com/PyTorchLightning/pytorch-lightning (accessed 2021-03-14).

    Not in our library

36. 36.

    Ramakrishnan R.; Dral P. O.; Rupp M.; von Lilienfeld O. A. Quantum chemistry structures and properties of 134 kilo molecules. Scientific Data 2014, 1, 140022.

    Not in our library10.1038/sdata.2014.22

37. 37.

    Honda S.; Akiba T.; Kato Y. S.; Sawada Y.; Sekijima M.; Ishimura M.; Ooishi A.; Watanabe H.; Odahara T.; Harata K. Crystal structure of a ten-amino acid protein. J. Am. Chem. Soc. 2008, 130, 15327–15331..

    Not in our library10.1021/ja8030533

38. 38.

    Kingma D. P.; Ba J. Adam: A method for stochastic optimization. 2014, preprint arXiv:1412.6980. arXiv.org e-Print archive. https://arxiv.org/abs/1412.6980 (accessed 2021-03-14).

    Not in our library

39. 39.

    Vapnik V. The nature of statistical learning theory; Springer Science & Business Media: 2013;.

    Not in our library10.1007/978-1-4757-3264-1

40. 40.

    Lindorff-Larsen K.; Piana S.; Dror R. O.; Shaw D. E. How fast-folding proteins fold. Science 2011, 334, 517–520..

    Not in our library10.1126/science.1208351

41. 41.

    Beauchamp K. A.; McGibbon R.; Lin Y.-S.; Pande V. S. Simple few-state models reveal hidden complexity in protein folding. Proc. Natl. Acad. Sci. U. S. A. 2012, 109, 17807–17813..

    Not in our library10.1073/pnas.1201810109

42. 42.

    Husic B. E.; McGibbon R. T.; Sultan M. M.; Pande V. S. Optimized parameter selection reveals trends in Markov state models for protein folding. J. Chem. Phys. 2016, 145, 194103.

    Not in our library10.1063/1.4967809

43. 43.

    McKiernan K. A.; Husic B. E.; Pande V. S. Modeling the mechanism of CLN025 beta-hairpin formation. J. Chem. Phys. 2017, 147, 104107.

    Not in our library10.1063/1.4993207

44. 44.

    Sultan M. M.; Pande V. S. Automated design of collective variables using supervised machine learning. J. Chem. Phys. 2018, 149, 094106.

    Not in our library10.1063/1.5029972

45. 45.

    Scherer M. K.; Husic B. E.; Hoffmann M.; Paul F.; Wu H.; Noé F. Variational selection of features for molecular kinetics. J. Chem. Phys. 2019, 150, 194108.

    Not in our library10.1063/1.5083040

46. 46.

    Buch I.; Harvey M. J.; Giorgino T.; Anderson D. P.; De Fabritiis G. High-throughput all-atom molecular dynamics simulations using distributed computing. J. Chem. Inf. Model. 2010, 50, 397–403..

    Not in our library10.1021/ci900455r

47. 47.

    Piana S.; Lindorff-Larsen K.; Shaw D. E. How robust are protein folding simulations with respect to force field parameterization?. Biophys. J. 2011, 100, L47.

    Not in our library10.1016/j.bpj.2011.03.051

48. 48.

    Jorgensen W. L.; Chandrasekhar J.; Madura J. D.; Impey R. W.; Klein M. L. Comparison of simple potential functions for simulating liquid water. J. Chem. Phys. 1983, 79, 926–935..

    Not in our library10.1063/1.445869

49. 49.

    Feenstra K. A.; Hess B.; Berendsen H. J. Improving efficiency of large time-scale molecular dynamics simulations of hydrogen-rich systems. J. Comput. Chem. 1999, 20, 786–798..

    Not in our library10.1002/(sici)1096-987x(199906)20:8<786::aid-jcc5>3.0.co;2-b

50. 50.

    Doerr S.; De Fabritiis G. On-the-Fly Learning and Sampling of Ligand Binding by High- Throughput Molecular Simulations. J. Chem. Theory Comput. 2014, 10, 2064.

    Not in our library10.1021/ct400919u

51. 51.
    SciPy 1.0: fundamental algorithms for scientific computing in Python · 2020

    Corrected
52. 52.

    Pérez-Hernández G.; Paul F.; Giorgino T.; De Fabritiis G.; Noé F. Identification of slow molecular order parameters for Markov model construction. J. Chem. Phys. 2013, 139, 015102.

    Not in our library10.1063/1.4811489

53. 53.

    Mobley D. L.; Bannan C. C.; Rizzi A.; Bayly C. I.; Chodera J. D.; Lim V. T.; Lim N. M.; Beauchamp K. A.; Shirts M. R.; Gilson M. K.; Eastman P. K. Open Force Field Consortium: Escaping atom types using direct chemical perception with SMIRNOFF v0.1. 2018, Biorxiv preprint. https://www.biorxiv.org/content/10.1101/286542v2 (accessed 2021-03-14),.

    Not in our library10.1101/286542

54. 54.
    OpenMM 7: Rapid development of high performance algorithms for molecular dynamics · 2017

    No notice

Cited by papers we hold 1

• Bottom-up Coarse-Graining: Principles and Perspectives · 2022
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.