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

Abstract

One of the grand challenges in modern theoretical chemistry is designing and implementing approximations that expedite ab initio methods without loss of accuracy. Machine learning (ML) methods are emerging as a powerful approach to constructing various forms of transferable atomistic potentials. They have been successfully applied in a variety of applications in chemistry, biology, catalysis, and solid-state physics. However, these models are heavily dependent on the quality and quantity of data used in their fitting. Fitting highly flexible ML potentials, such as neural networks, comes at a cost: a vast amount of reference data is required to properly train these models. We address this need by providing access to a large computational DFT database, which consists of more than 20 M off equilibrium conformations for 57,462 small organic molecules. We believe it will become a new standard benchmark for comparison of current and future methods in the ML potential community.

Full text

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

References 39

1. 1.

   FigshareSmith J. S. Isayev O. Roitberg A. E. 2017 https://doi.org/10.6084/m9.figshare.c.3846712

   Not in our library

2. 2.

   Becke A. D. Perspective: Fifty years of density-functional theory in chemical physics. J. Chem. Phys. 140, 18A301 (2014 ).

   Not in our library10.1063/1.4869598

3. 3.

   Grimme S., Antony J., Schwabe T. & Mück-Lichtenfeld C. Density functional theory with dispersion corrections for supramolecular structures, aggregates, and complexes of (bio)organic molecules. Org. Biomol. Chem. 5, 741–758 (2007 ).

   Not in our library10.1039/b615319b

4. 4.

   te Velde G. et al. Chemistry with ADF. J. Comput. Chem. 22, 931–967 (2001 ).

   Not in our library

5. 5.

   Brunk E. & Rothlisberger U. Mixed Quantum Mechanical/Molecular Mechanical Molecular Dynamics Simulations of Biological Systems in Ground and Electronically Excited States. Chemical Reviews 115, 6217–6263 (2015 ).

   Not in our library10.1021/cr500628b

6. 6.

   Norskov J. K., Abild-Pedersen F., Studt F. & Bligaard T. Density functional theory in surface chemistry and catalysis. Proc. Natl. Acad. Sci 108, 937–943 (2011 ).

   Not in our library10.1073/pnas.1006652108

7. 7.

   Hafner J. Ab-initio simulations of materials using VASP: Density-functional theory and beyond. J. Comput. Chem. 29, 2044–2078 (2008 ).

   Not in our library10.1002/jcc.21057

8. 8.

   Landers J., Gor G. Y. & Neimark A. V. Density functional theory methods for characterization of porous materials. Colloids Surfaces A Physicochem. Eng. Asp 437, 3–32 (2013 ).

   Not in our library

9. 9.

   Behler J. First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems. Angew. Chemie Int. Ed 56, 12828–12840 (2017 ).

   Not in our library10.1002/anie.201703114

10. 10.

    Smith J. S., Isayev O. & Roitberg A. E. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci 27, 479–496 (2017 ).

    Not in our library10.1039/c6sc05720a

11. 11.

    Gilmer J., Schoenholz S. S., Riley P. F., Vinyals O. & Dahl G. E. Neural Message Passing for Quantum Chemistry. Preprint at https://arxiv.org/abs/1704.01212 (2017 ).

    Not in our library

12. 12.

    Faber F. A. et al. Prediction errors of molecular machine learning models lower than hybrid DFT error. J. Chem. Theory Comput. 13, 5255–5264 (2017 ).

    Not in our library10.1021/acs.jctc.7b00577

13. 13.

    Hellström M. et al. Structure of aqueous NaOH solutions: insights from neural-network-based molecular dynamics simulations. Phys. Chem. Chem. Phys. 146, 359–374 (2016 ).

    Not in our library10.1039/c6cp06547c

14. 14.

    Behler J. Constructing high-dimensional neural network potentials: A tutorial review. Int. J. Quantum Chem. 115, 1032–1050 (2015 ).

    Not in our library

15. 15.

    Behler J. & Parrinello M. Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces. Phys. Rev. Lett. 98, 146401 (2007 ).

    Not in our library10.1103/physrevlett.98.146401

16. 16.

    Lubbers N., Smith J. S. & Barros K. Hierarchical modeling of molecular energies using a deep neural network. Preprint at https://arxiv.org/abs/1710.00017 (2017 ).

    Not in our library10.1063/1.5011181

17. 17.

    Reymond J. L. The Chemical Space Project. Acc. Chem. Res. 48, 722–730 (2015 ).

    Not in our library10.1021/ar500432k

18. 18.

    Ruddigkeit L., Van Deursen R., Blum L. C. & Reymond J. L. Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J. Chem. Inf. Model. 52, 2864–2875 (2012 ).

    Not in our library10.1021/ci300415d

19. 19.

    Rupp M., Tkatchenko A., Muller K.-R. & von Lilienfeld O. A. Fast and accurate modeling of molecular atomization energies with machine learning. Phys. Rev. Lett. 108, 58301 (2012 ).

    Not in our library10.1103/physrevlett.108.058301

20. 20.

    Montavon G. et al. Machine learning of molecular electronic properties in chemical compound space. New J. Phys. 15, 95003 (2013 ).

    Not in our library

21. 21.

    Hansen K. et al. Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space. J. Phys. Chem. Lett. 6, 2326–2331 (2015 ).

    Not in our library10.1021/acs.jpclett.5b00831

22. 22.
    Quantum-chemical insights from deep tensor neural networks · 2017

    No notice
23. 23.

    Ramakrishnan R., Dral P. O., Rupp M. & von Lilienfeld O. A. Quantum chemistry structures and properties of 134 kilo molecules. Sci. data 1, 140022 (2014 ).

    Not in our library10.1038/sdata.2014.22

24. 24.

    Faber F. A. et al. Fast machine learning models of electronic and energetic properties consistently reach approximation errors better than DFT accuracy. Preprint at https://arxiv.org/abs/1702.05532 (2017 ).

    Not in our library

25. 25.

    Huang B. & von Lilienfeld O. A. Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity. J. Chem. Phys. 145, 161102 (2016 ).

    Not in our library10.1063/1.4964627

26. 26.

    Chmiela S. et al. Machine learning of accurate energy-conserving molecular force fields. Sci. Adv. 3, e1603015 (2017 ).

    Not in our library10.1126/sciadv.1603015

27. 27.

    Fink T. & Raymond J. L. Virtual exploration of the chemical universe up to 11 atoms of C, N, O, F: Assembly of 26.4 million structures (110.9 million stereoisomers) and analysis for new ring systems, stereochemistry, physicochemical properties, compound classes, and drug discove. J. Chem. Inf. Model. 47, 342–353 (2007 ).

    Not in our library10.1021/ci600423u

28. 28.

    Fink T., Bruggesser H. & Reymond J. L. Virtual exploration of the small-molecule chemical universe below 160 daltons. Angew. Chemie—Int. Ed 44, 1504–1508 (2005 ).

    Not in our library10.1002/anie.200462457

29. 29.
    Machine learning molecular dynamics for the simulation of infrared spectra · 2017

    No notice
30. 30.

    Huang B. & Anatole Von Lilienfeld O. Chemical space exploration with molecular genes and machine learning. Preprint at https://arxiv.org/abs/1707.04146 (2017 ).

    Not in our library

31. 31.

    Chai J. D. A. & Head-Gordon M. Systematic optimization of long-range corrected hybrid density functionals. J. Chem. Phys. 128, 84106 (2008 ).

    Not in our library10.1063/1.2834918

32. 32.

    Ditchfield R., Hehre W. J. & Pople J. A. Self-Consistent Molecular-Orbital Methods. IX. An Extended Gaussian-Type Basis for Molecular-Orbital Studies of Organic Molecules. J. Chem. Phys. 54, 724–728 (1971 ).

    Not in our library

33. 33.

    M. J. Frisch G. et al. Gaussian 09, Revision E.01 (Gaussian, Inc., 2009 ).

    Not in our library

34. 34.

    Thanthiriwatte K. S., Hohenstein E. G., Burns L. A. & Sherrill C. D. Assessment of the performance of DFT and DFT-D methods for describing distance dependence of hydrogen-bonded interactions. J. Chem. Theory Comput. 7, 88–96 (2011 ).

    Not in our library10.1021/ct100469b

35. 35.

    Alecu I. M., Zheng J., Zhao Y. & Truhlar D. G. Computational thermochemistry: Scale factor databases and scale factors for vibrational frequencies obtained from electronic model chemistries. J. Chem. Theory Comput. 6, 2872–2887 (2010 ).

    Not in our library10.1021/ct100326h

36. 36.

    Riley K. E., Pitončák M., Jurecčka P. & Hobza P. Stabilization and structure calculations for noncovalent interactions in extended molecular systems based on wave function and density functional theories. Chem. Rev. 110, 5023–5063 (2010 ).

    Not in our library10.1021/cr1000173

37. 37.

    Goerigk L. & Grimme S. A thorough benchmark of density functional methods for general main group thermochemistry, kinetics, and noncovalent interactions. Phys. Chem. Chem. Phys. 13, 6670 (2011 ).

    Not in our library10.1039/c0cp02984j

38. 38.

    Shao Y. et al. Advances in molecular quantum chemistry contained in the Q-Chem 4 program package. Mol. Phys. 113, 184–215 (2015 ).

    Not in our library

39. 39.

    Halgren T. A. Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94. J. Comput. Chem. 17, 490–519 (1996 ).

    Not in our library

Cited by papers we hold 7

• MACE-OFF: Short-Range Transferable Machine Learning Force Fields for Organic Molecules · 2025
  No notice
• SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials · 2023
  No notice
• GEOM, energy-annotated molecular conformations for property prediction and molecular generation · 2022
  No notice
• Complex reaction processes in combustion unraveled by neural network-based molecular dynamics simulation · 2020
  Not checked
• The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules · 2020
  No notice
• Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning · 2019
  No notice
• Artificial Intelligence in Drug Design · 2018
  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.