SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

Abstract

Machine learning potentials are an important tool for molecular simulation, but their development is held back by a shortage of high quality datasets to train them on. We describe the SPICE dataset, a new quantum chemistry dataset for training potentials relevant to simulating drug-like small molecules interacting with proteins. It contains over 1.1 million conformations for a diverse set of small molecules, dimers, dipeptides, and solvated amino acids. It includes 15 elements, charged and uncharged molecules, and a wide range of covalent and non-covalent interactions. It provides both forces and energies calculated at the ωB97M-D3(BJ)/def2-TZVPPD level of theory, along with other useful quantities such as multipole moments and bond orders. We train a set of machine learning potentials on it and demonstrate that they can achieve chemical accuracy across a broad region of chemical space. It can serve as a valuable resource for the creation of transferable, ready to use potential functions for use in molecular simulations.

Full text

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

References 50

1. 1.

   Kocer E, Ko TW, Behler J. Neural Network Potentials: A Concise Overview of Methods. Annu. Rev. Phys. Chem. 2022;73:163-186.

   Not in our library10.1146/annurev-physchem-082720-034254

2. 2.
   Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning · 2019

   No notice
3. 3.

   Gastegger M, Kauffmann C, Behler J, Marquetand P. Comparing the accuracy of high-dimensional neural network potentials and the systematic molecular fragmentation method: A benchmark study for all-trans alkanes. J. Chem. Phys. 2016;144:194110.

   Not in our library10.1063/1.4950815

4. 4.

   Lahey S-LJ, Rowley CN. Simulating protein–ligand binding with neural network potentials. Chem. Sci. 2020;11:2362-2368.

   Not in our library10.1039/c9sc06017k

5. 5.

   Rufa, D. A. et al. Towards chemical accuracy for alchemical free energy calculations with hybrid physics-based machine learning/molecular mechanics potentials. 2020.07.29.227959 Preprint at 10.1101/2020.07.29.227959 (2020).

   Not in our library

6. 6.

   Schütt, K., Unke, O. & Gastegger, M. Equivariant message passing for the prediction of tensorial properties and molecular spectra. in Proceedings of the 38th International Conference on Machine Learning 9377–9388 (PMLR, 2021).

   Not in our library

7. 7.
   SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects · 2021

   No notice
8. 8.

   Thölke, P. & De Fabritiis, G. TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials. Preprint at, 10.48550/arXiv.2202.02541 (2022).

   Not in our library

9. 9.
   E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials · 2022

   No notice
10. 10.

    Haghighatlari M, et al. NewtonNet: a Newtonian message passing network for deep learning of interatomic potentials and forces. Digit. Discov. 2022;1:333-343.

    Not in our library10.1039/d2dd00008c

11. 11.

    Batatia, I., Kovács, D. P., Simm, G. N. C., Ortner, C. & Csányi, G. MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields. Preprint at 10.48550/arXiv.2206.07697 (2022).

    Not in our library

12. 12.

    Christensen AS, von Lilienfeld OA. On the role of gradients for machine learning of molecular energies and forces. Mach. Learn. Sci. Technol. 2020;1:045018.

    Not in our library10.1088/2632-2153/abba6f

13. 13.

    Cooper AM, Kästner J, Urban A, Artrith N. Efficient training of ANN potentials by including atomic forces via Taylor expansion and application to water and a transition-metal oxide. Npj Comput. Mater. 2020;6:1-14.

    Not in our library10.1038/s41524-020-0323-8

14. 14.

    Montes-Campos H, Carrete J, Bichelmaier S, Varela LM, Madsen GKH. A Differentiable Neural-Network Force Field for Ionic Liquids. J. Chem. Inf. Model. 2022;62:88-101.

    Not in our library10.1021/acs.jcim.1c01380

15. 15.

    Christensen AS, et al. OrbNet Denali: A machine learning potential for biological and organic chemistry with semi-empirical cost and DFT accuracy. J. Chem. Phys. 2021;155:204103.

    Not in our library10.1063/5.0061990

16. 16.

    Isert C, Atz K, Jiménez-Luna J, Schneider G. QMugs, quantum mechanical properties of drug-like molecules. Sci. Data. 2022;9:273.

    Not in our library10.1038/s41597-022-01390-7

17. 17.
    ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules · 2017

    No notice
18. 18.
    The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules · 2020

    No notice
19. 19.

    Blum LC, Reymond J-L. 970 Million Druglike Small Molecules for Virtual Screening in the Chemical Universe Database GDB-13. J. Am. Chem. Soc. 2009;131:8732-8733.

    Not in our library10.1021/ja902302h

20. 20.

    Rupp M, Tkatchenko A, Müller K-R, von Lilienfeld OA. Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning. Phys. Rev. Lett. 2012;108:058301.

    Not in our library10.1103/physrevlett.108.058301

21. 21.

    Ruddigkeit L, van Deursen R, Blum LC, Reymond J-L. Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17. J. Chem. Inf. Model. 2012;52:2864-2875.

    Not in our library10.1021/ci300415d

22. 22.

    Ramakrishnan R, Hartmann M, Tapavicza E, von Lilienfeld OA. Electronic spectra from TDDFT and machine learning in chemical space. J. Chem. Phys. 2015;143:084111.

    Not in our library10.1063/1.4928757

23. 23.

    Ramakrishnan R, Dral PO, Rupp M, von Lilienfeld OA. Quantum chemistry structures and properties of 134 kilo molecules. Sci. Data. 2014;1:140022.

    Not in our library10.1038/sdata.2014.22

24. 24.

    Hoja J, et al. QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules. Sci. Data. 2021;8:43.

    Not in our library10.1038/s41597-021-00812-2

25. 25.

    Donchev AG, et al. Quantum chemical benchmark databases of gold-standard dimer interaction energies. Sci. Data. 2021;8:55.

    Not in our library10.1038/s41597-021-00833-x

26. 26.

    Zubatyuk R, Smith JS, Nebgen BT, Tretiak S, Isayev O. Teaching a neural network to attach and detach electrons from molecules. Nat. Commun. 2021;12:4870.

    Not in our library10.1038/s41467-021-24904-0

27. 27.

    RDKit: Open-source cheminformatics. https://www.rdkit.org.

    Not in our library

28. 28.
    OpenMM 7: Rapid development of high performance algorithms for molecular dynamics · 2017

    No notice
29. 29.

    Maier JA, et al. 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

30. 30.

    Liu T, Lin Y, Wen X, Jorissen RN, Gilson MK. BindingDB: a web-accessible database of experimentally determined protein–ligand binding affinities. Nucleic Acids Res. 2007;35:D198-D201.

    Not in our library10.1093/nar/gkl999

31. 31.

    ChemIDplus Advanced - Chemical information with searchable synonyms, structures, and formulas. https://chem.nlm.nih.gov/chemidplus/.

    Not in our library

32. 32.

    Qiu Y, et al. Development and Benchmarking of Open Force Field v1.0.0—the Parsley Small-Molecule Force Field. J. Chem. Theory Comput. 2021;17:6262-6280.

    Not in our library10.1021/acs.jctc.1c00571

33. 33.

    Tanimoto, T. T. An elementary mathematical theory of classification and prediction. (International Business Machines Corporation, 1958).

    Not in our library

34. 34.

    Rogers D, Hahn M. Extended-Connectivity Fingerprints. J. Chem. Inf. Model. 2010;50:742-754.

    Not in our library10.1021/ci100050t

35. 35.

    Horton, J. et al. Open Force Field BespokeFit: Automating Bespoke Torsion Parametrization At Scale. 10.26434/chemrxiv-2022-6h628 (2022).

    Not in our library10.1021/acs.jcim.2c01153

36. 36.

    Smith DGA, et al. Quantum Chemistry Common Driver and Databases (QCDB) and Quantum Chemistry Engine (QCEngine): Automation and interoperability among computational chemistry programs. J. Chem. Phys. 2021;155:204801.

    Not in our library10.1063/5.0059356

37. 37.

    Smith DGA, et al. PSI4 1.4: Open-source software for high-throughput quantum chemistry. J. Chem. Phys. 2020;152:184108.

    Not in our library10.1063/5.0006002

38. 38.

    Najibi A, Goerigk L. The Nonlocal Kernel in van der Waals Density Functionals as an Additive Correction: An Extensive Analysis with Special Emphasis on the B97M-V and ωB97M-V Approaches. J. Chem. Theory Comput. 2018;14:5725-5738.

    Not in our library10.1021/acs.jctc.8b00842

39. 39.

    Mardirossian N, Head-Gordon M. ωB97M-V: A combinatorially optimized, range-separated hybrid, meta-GGA density functional with VV10 nonlocal correlation. J. Chem. Phys. 2016;144:214110.

    Not in our library10.1063/1.4952647

40. 40.

    Weigend F, Ahlrichs R. Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: Design and assessment of accuracy. Phys. Chem. Chem. Phys. 2005;7:3297-3305.

    Not in our library10.1039/b508541a

41. 41.

    Rappoport D, Furche F. Property-optimized Gaussian basis sets for molecular response calculations. J. Chem. Phys. 2010;133:134105.

    Not in our library10.1063/1.3484283

42. 42.

    Mardirossian, N. & Head-Gordon, M. Thirty years of density functional theory in computational chemistry: an overview and extensive assessment of 200 density functionals. Mol. Phys. (2017).

    Not in our library

43. 43.

    Santra G, Martin JML. Some observations on the performance of the most recent exchange-correlation functionals for the large and chemically diverse GMTKN55 benchmark. AIP Conf. Proc. 2019;2186:030004.

    Not in our library10.1063/1.5137915

44. 44.

    Mehta N, Fellowes T, White JM, Goerigk L. CHAL336 Benchmark Set: How Well Do Quantum-Chemical Methods Describe Chalcogen-Bonding Interactions? J. Chem. Theory Comput. 2021;17:2783-2806.

    Not in our library10.1021/acs.jctc.1c00006

45. 45.

    Schwalbe-Koda D, Tan AR, Gómez-Bombarelli R. Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks. Nat. Commun. 2021;12:5104.

    Not in our library10.1038/s41467-021-25342-8

46. 46.

    Eastman, P. et al. SPICE 1.1.2. Zenodo10.5281/zenodo.7338495 (2022).

    Not in our library

47. 47.

    Unke OT, Meuwly M. PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges. J. Chem. Theory Comput. 2019;15:3678-3693.

    Not in our library10.1021/acs.jctc.9b00181

48. 48.
    A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer · 2021

    No notice
49. 49.

    Smith JS, Isayev O, Roitberg AE. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci. 2017;8:3192-3203.

    Not in our library10.1039/c6sc05720a

50. 50.

    Pople JA. Nobel Lecture: Quantum chemical models. Rev. Mod. Phys. 1999;71:1267-1274.

    Not in our library10.1103/revmodphys.71.1267

Cited by papers we hold 1

• MACE-OFF: Short-Range Transferable Machine Learning Force Fields for Organic Molecules · 2025
  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.