GEOM, energy-annotated molecular conformations for property prediction and molecular generation

Abstract

Machine learning (ML) outperforms traditional approaches in many molecular design tasks. ML models usually predict molecular properties from a 2D chemical graph or a single 3D structure, but neither of these representations accounts for the ensemble of 3D conformers that are accessible to a molecule. Property prediction could be improved by using conformer ensembles as input, but there is no large-scale dataset that contains graphs annotated with accurate conformers and experimental data. Here we use advanced sampling and semi-empirical density functional theory (DFT) to generate 37 million molecular conformations for over 450,000 molecules. The Geometric Ensemble Of Molecules (GEOM) dataset contains conformers for 133,000 species from QM9, and 317,000 species with experimental data related to biophysics, physiology, and physical chemistry. Ensembles of 1,511 species with BACE-1 inhibition data are also labeled with high-quality DFT free energies in an implicit water solvent, and 534 ensembles are further optimized with DFT. GEOM will assist in the development of models that predict properties from conformer ensembles, and generative models that sample 3D conformations.

Full text

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

References 107

1. 1.

   Norinder U, Lidén P, Boström H. Discrimination between modes of toxic action of phenols using rule based methods. Molecular diversity. 2006;10:207-212.

   Not in our library10.1007/s11030-006-9019-3

2. 2.
   Molecular dynamics simulations and drug discovery · 2011

   No notice
3. 3.

   Stokes JM, et al. A deep learning approach to antibiotic discovery. Cell. 2020;180:688-702.

   Not in our library10.1016/j.cell.2020.01.021

4. 4.

   Gómez-Bombarelli R, et al. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach. Nature Materials. 2016;15:1120-1127.

   Not in our library10.1038/nmat4717

5. 5.

   Zhavoronkov A, et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nature biotechnology. 2019;37:1038-1040.

   Not in our library10.1038/s41587-019-0224-x

6. 6.

   Schwalbe-Koda, D. & Gómez-Bombarelli, R. Generative models for automatic chemical design. In Machine Learning Meets Quantum Physics, 445–467 10.1007/978-3-030-40245-7_21 (Springer, 2020).

   Not in our library

7. 7.
   Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules · 2018

   Not checked
8. 8.

   Jin, W., Barzilay, R. & Jaakkola, T. Junction Tree Variational Autoencoder for Molecular Graph Generation. In International Conference on Machine Learning, https://proceedings.mlr.press/v80/jin18a.html (2018).

   Not in our library

9. 9.

   Dai, H., Tian, Y., Dai, B., Skiena, S. & Song, L. Syntax-directed variational autoencoder for structured data. In International Conference on Learning Representations, https://openreview.net/forum?id=SyqShMZRb (2018).

   Not in our library

10. 10.

    Noé F, Olsson S, Köhler J, Wu H. Boltzmann generators: Sampling equilibrium states of many-body systems with deep. Science. 2019;365:eaaw1147.

    Not in our library10.1126/science.aaw1147

11. 11.
    Molecular de-novo design through deep reinforcement learning · 2017

    No notice
12. 12.

    Gottipati, S. K. et al. Learning to navigate the synthetically accessible chemical space using reinforcement learning. In International Conference on Machine Learning, 3668–3679, https://proceedings.mlr.press/v119/gottipati20a.html (PMLR, 2020)

    Not in our library

13. 13.

    Popova M, Isayev O, Tropsha A. Deep reinforcement learning for de novo drug design. Science Advances. 2018;4:eaap7885.

    Not in our library10.1126/sciadv.aap7885

14. 14.

    AlQuraishi M. End-to-end differentiable learning of protein structure. Cell Systems. 2019;8:292-301.e3.

    Not in our library10.1016/j.cels.2019.03.006

15. 15.

    Ingraham, J., Riesselman, A., Sander, C. & Marks, D. Learning protein structure with a differentiable simulator. In International Conference on Learning Representations, https://openreview.net/forum?id=Byg3y3C9Km (2019).

    Not in our library

16. 16.

    Segler MHS, Preuss M, Waller MP. Planning chemical syntheses with deep neural networks and symbolic AI. Nature. 2018;555:604-610.

    Not in our library10.1038/nature25978

17. 17.

    Coley CW, Barzilay R, Jaakkola TS, Green WH, Jensen KF. Prediction of organic reaction outcomes using machine learning. ACS Central Science. 2017;3:434-443.

    Not in our library10.1021/acscentsci.7b00064

18. 18.

    Duvenaud, D. K. et al. Convolutional networks on graphs for learning molecular fingerprints. In Advances in Neural Information Processing Systems, 2215–2223, https://proceedings.neurips.cc/paper/2015/file/f9be311e65d81a9ad8150a60844bb94c-Paper.pdf (2015).

    Not in our library

19. 19.

    Kearnes S, McCloskey K, Berndl M, Pande V, Riley P. Molecular graph convolutions: moving beyond fingerprints. Journal of Computer-Aided Molecular Design. 2016;30:595-608.

    Not in our library10.1007/s10822-016-9938-8

20. 20.

    Yang K, et al. Analyzing learned molecular representations for property prediction. Journal of Chemical Information and Modeling. 2019;59:3370-3388.

    Not in our library10.1021/acs.jcim.9b00237

21. 21.

    Anderson, B., Hy, T. S. & Kondor, R. Cormorant: Covariant molecular neural networks. In Advances in Neural Information Processing Systems, 14537–14546, https://proceedings.neurips.cc/paper/2019/file/03573b32b2746e6e8ca98b9123f2249b-Paper.pdf (2019).

    Not in our library

22. 22.

    Klicpera, J., Groß, J. & Günnemann, S. Directional message passing for molecular graphs. In International Conference on Learning Representations, https://openreview.net/forum?id=B1eWbxStPH (2019).

    Not in our library

23. 23.

    Ramsundar, B. et al. Deep Learning for the Life Sciences (O’Reilly Media, 2019).

    Not in our library

24. 24.
    ChEMBL: towards direct deposition of bioassay data · 2018

    No notice
25. 25.

    Sterling T, Irwin JJ. ZINC 15–Ligand discovery for everyone. Journal of chemical information and modeling. 2015;55:2324-37.

    Not in our library10.1021/acs.jcim.5b00559

26. 26.

    Brown N, Fiscato M, Segler MHS, Vaucher AC. GuacaMol: Benchmarking models for de novo molecular design. J. Chem. Inf. Model. 2019;59:1096-1108.

    Not in our library10.1021/acs.jcim.8b00839

27. 27.
    Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models · 2020

    No notice
28. 28.

    Delaney JS. ESOL: Estimating aqueous solubility directly from molecular structure. Journal of Chemical Information and Computer Sciences. 2004;44:1000-1005.

    Not in our library10.1021/ci034243x

29. 29.

    Mobley DL, Guthrie JP. FreeSolv: A database of experimental and calculated hydration free energies, with input files. Journal of Computer-Aided Molecular Design. 2014;28:711-720.

    Not in our library10.1007/s10822-014-9747-x

30. 30.

    Wang R, Fang X, Lu Y, Wang S. The PDBbind database: Collection of binding affinities for protein-ligand complexes with known three-dimensional structures. Journal of Medicinal Chemistry. 2004;47:2977-2980.

    Not in our library10.1021/jm030580l

31. 31.

    Wu Z, et al. MoleculeNet: a benchmark for molecular machine learning. Chemical science. 2018;9:513-530.

    Not in our library10.1039/c7sc02664a

32. 32.

    Weininger D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. Journal of Chemical Information and Modeling. 1988;28:31-36.

    Not in our library10.1021/ci00057a005

33. 33.
    InChI, the IUPAC International Chemical Identifier · 2015

    No notice
34. 34.

    Kuhn B, et al. A real-world perspective on molecular design: Miniperspective. Journal of medicinal chemistry. 2016;59:4087-4102.

    Not in our library10.1021/acs.jmedchem.5b01875

35. 35.

    Hawkins PC. Conformation generation: The state of the art. Journal of chemical information and modeling. 2017;57:1747-1756.

    Not in our library10.1021/acs.jcim.7b00221

36. 36.

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

    Not in our library10.1038/sdata.2014.22

37. 37.

    Pracht P, Bohle F, Grimme S. Automated exploration of the low-energy chemical space with fast quantum chemical methods. Physical Chemistry Chemical Physics. 2020;22:7169-7192.

    Not in our library10.1039/c9cp06869d

38. 38.

    Bannwarth C, Ehlert S, Grimme S. GFN2-xTB—An accurate and broadly parametrized self-consistent tight-binding quantum chemical method with multipole electrostatics and density-dependent dispersion contributions. Journal of chemical theory and computation. 2019;15:1652-1671.

    Not in our library10.1021/acs.jctc.8b01176

39. 39.

    Subramanian G, Ramsundar B, Pande V, Denny RA. Computational modeling of β-secretase 1 (BACE-1) inhibitors using ligand based approaches. Journal of chemical information and modeling. 2016;56:1936-1949.

    Not in our library10.1021/acs.jcim.6b00290

40. 40.
    Crystallography Open Database – an open-access collection of crystal structures · 2009

    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.