1932
0
  1. Home
  2. A-Z Publications
  3. Annual Review of Chemical and Biomolecular Engineering
  4. Volume 15, 2024
  5. Article

Annual Review of Chemical and Biomolecular Engineering

Volume 15, 2024

Deductive Machine Learning Challenges and Opportunities in Chemical Applications

Abstract

Contemporary machine learning algorithms have largely succeeded in automating the development of mathematical models from data. Although this is a striking accomplishment, it leaves unaddressed the multitude of scenarios, especially across the chemical sciences and engineering, where deductive, rather than inductive, reasoning is required and still depends on manual intervention by an expert. This review describes the characteristics of deductive reasoning that are helpful for understanding the role played by expert intervention in problem-solving and explains why such interventions are often relatively resistant to disruption by typical machine learning strategies. The article then discusses the factors that contribute to creating a deductive bottleneck, how deductive bottlenecks are currently addressed in several application areas, and how machine learning models capable of deduction can be designed. The review concludes with a tutorial case study that illustrates the challenges of deduction problems and a notebook for readers to experiment with on their own.

Keyword(s): artificial intelligence, automation, deduction, machine learning
Loading

Article metrics loading...

/content/journals/10.1146/annurev-chembioeng-100722-111917
2024-07-24
2025-04-29
Loading full text...

Full text loading...

/deliver/fulltext/chembioeng/15/1/annurev-chembioeng-100722-111917.html?itemId=/content/journals/10.1146/annurev-chembioeng-100722-111917&mimeType=html&fmt=ahah

Literature Cited

  1. 1.
    Saravanan R, Sujatha P. 2018.. A state of art techniques on machine learning algorithms: a perspective of supervised learning approaches in data classification. . In 2018 2nd International Conference on Intelligent Computing and Control Systems (ICICCS), pp. 945–49. Piscataway, NJ:: IEEE
     [Google Scholar]
  2. 2.
    Wu J, Pun SM, Zheng X, Chen G. 2023.. Construct exchange-correlation functional via machine learning. . J. Chem. Phys. 159::090901
     [Crossref] [Google Scholar]
  3. 3.
    Cheng L, Welborn M, Christensen AS, Miller TF. 2019.. A universal density matrix functional from molecular orbital–based machine learning: transferability across organic molecules. . J. Chem. Phys. 150::131103
     [Crossref] [Google Scholar]
  4. 4.
    Focassio B, Domina M, Patil U, Fazzio A, Sanvito S. 2023.. Linear Jacobi-Legendre expansion of the charge density for machine learning–accelerated electronic structure calculations. . npj Comput. Mater. 9::87
     [Crossref] [Google Scholar]
  5. 5.
    Fiedler L, Modine NA, Schmerler S, Vogel DJ, Popoola GA, et al. 2023.. Predicting electronic structures at any length scale with machine learning. . npj Comput. Mater. 9::115
     [Crossref] [Google Scholar]
  6. 6.
    Haghighatlari M, Vishwakarma G, Altarawy D, Subramanian R, Kota BU, et al. 2020.. ChemML: a machine learning and informatics program package for the analysis, mining, and modeling of chemical and materials data. . Wiley Interdiscip. Rev. Comput. Mol. Sci. 10:(4):e1458
     [Crossref] [Google Scholar]
  7. 7.
    Zhao Q, Anstine DM, Isayev O, Savoie BM. 2023.. Δ2 machine learning for reaction property prediction. . Chem. Sci. 14::13392–401
     [Crossref] [Google Scholar]
  8. 8.
    Weinreich J, Browning NJ, von Lilienfeld OA. 2021.. Machine learning of free energies in chemical compound space using ensemble representations: reaching experimental uncertainty for solvation. . J. Chem. Phys. 154::134113
     [Crossref] [Google Scholar]
  9. 9.
    Anstine DM, Isayev O. 2023.. Machine learning interatomic potentials and long-range physics. . J. Phys. Chem. A 127:(11):2417–31
     [Crossref] [Google Scholar]
  10. 10.
    Hamilton BW, Yoo P, Sakano MN, Islam MM, Strachan A. 2023.. High-pressure and temperature neural network reactive force field for energetic materials. . J. Chem. Phys. 158::144117
     [Crossref] [Google Scholar]
  11. 11.
    Novelli P, Bonati L, Pontil M, Parrinello M. 2022.. Characterizing metastable states with the help of machine learning. . J. Chem. Theory Comput. 18:(9):5195–202
     [Crossref] [Google Scholar]
  12. 12.
    Goodlett SM, Turney JM, Schaefer HF. 2023.. Comparison of multifidelity machine learning models for potential energy surfaces. . J. Chem. Phys. 159::044111
     [Crossref] [Google Scholar]
  13. 13.
    Kushwaha A, Dhilip Kumar TJ 2023.. Benchmarking PES-Learn's machine learning models predicting accurate potential energy surface for quantum scattering. . Int. J. Quantum Chem. 123:(1):e27007
     [Crossref] [Google Scholar]
  14. 14.
    Jiang B, Li J, Guo H. 2020.. High-fidelity potential energy surfaces for gas-phase and gas–surface scattering processes from machine learning. . J. Phys. Chem. Lett. 11:(13):5120–31
     [Crossref] [Google Scholar]
  15. 15.
    Pablo-García S, Morandi S, Vargas-Hernández RA, Jorner K, Ivković Ž, et al. 2023.. Fast evaluation of the adsorption energy of organic molecules on metals via graph neural networks. . Nat. Comput. Sci. 3::433–42
     [Crossref] [Google Scholar]
  16. 16.
    Choudhary K, DeCost B, Chen C, Jain A, Tavazza F, et al. 2022.. Recent advances and applications of deep learning methods in materials science. . npj Comput. Mater. 8::59
     [Crossref] [Google Scholar]
  17. 17.
    Ghanekar PG, Deshpande S, Greeley J. 2022.. Adsorbate chemical environment–based machine learning framework for heterogeneous catalysis. . Nat. Commun. 13::5788
     [Crossref] [Google Scholar]
  18. 18.
    Borodinov N, Lorenz M, King ST, Ievlev AV, Ovchinnikova OS. 2020.. Toward nanoscale molecular mass spectrometry imaging via physically constrained machine learning on co-registered multimodal data. . npj Comput. Mater. 6::83
     [Crossref] [Google Scholar]
  19. 19.
    Iqbal Z, Nguyen D, Hangel G, Motyka S, Bogner W, Jiang S. 2019.. Super-resolution 1H magnetic resonance spectroscopic imaging utilizing deep learning. . Front. Oncol. 9::1010
     [Crossref] [Google Scholar]
  20. 20.
    Ihara Y, Yamagishi H, Naito M, Yamamoto Y. 2023.. Machine learning of organic solvents reveals an extraordinary axis in Hansen space as indicator of spherical precipitation of polymers. . Aggregate 4:(5):e365
     [Crossref] [Google Scholar]
  21. 21.
    Bobbitt NS, Allers JP, Harvey JA, Poe D, Wemhoner JD, et al. 2023.. Machine learning predictions of diffusion in bulk and confined ionic liquids using simple descriptors. . Mol. Syst. Des. Eng. 8:(10):1257–74
     [Crossref] [Google Scholar]
  22. 22.
    Duan C, Liu F, Nandy A, Kulik HJ. 2020.. Data-driven approaches can overcome the cost–accuracy trade-off in multireference diagnostics. . J. Chem. Theory Comput. 16:(7):4373–87
     [Crossref] [Google Scholar]
  23. 23.
    Meloun M, Militky` J, Hill M, Brereton RG. 2002.. Crucial problems in regression modelling and their solutions. . Analyst 127:(4):433–50
     [Crossref] [Google Scholar]
  24. 24.
    Tian J, Sun X, Du Y, Zhao S, Liu Q, et al. 2023.. Recent advances for quantum neural networks in generative learning. . IEEE Trans. Pattern Anal. Mach. Intell. 45::12321–40
     [Crossref] [Google Scholar]
  25. 25.
    Iovanac NC, Savoie BM. 2020.. Simpler is better: how linear prediction tasks improve transfer learning in chemical autoencoders. . J. Phys. Chem. A 124:(18):3679–85
     [Crossref] [Google Scholar]
  26. 26.
    Gupta J, Pathak S, Kumar G. 2022.. Deep learning (CNN) and transfer learning: a review. . J. Phys. Conf. Ser. 2273::012029
     [Crossref] [Google Scholar]
  27. 27.
    Xu P, Ji X, Li M, Lu W. 2023.. Small data machine learning in materials science. . npj Comput. Mater. 9::42
     [Crossref] [Google Scholar]
  28. 28.
    Thoreau R, Achard V, Risser L, Berthelot B, Briottet X. 2022.. Active learning for hyperspectral image classification: a comparative review. . IEEE Geosci. Remote Sens. 10:(3):256–78
     [Crossref] [Google Scholar]
  29. 29.
    Wang H, Fu T, Du Y, Gao W, Huang K, et al. 2023.. Scientific discovery in the age of artificial intelligence. . Nature 620:(7972):47–60
     [Crossref] [Google Scholar]
  30. 30.
    Boddupalli N, Matchen T, Moehlis J. 2023.. Symbolic regression via neural networks. . Chaos 33::083150
     [Crossref] [Google Scholar]
  31. 31.
    Cho K, Van Merriënboer B, Bahdanau D, Bengio Y. 2014.. On the properties of neural machine translation: encoder-decoder approaches. . arXiv:1409.1259 [cs.CL]
  32. 32.
    Anstine DM, Isayev O. 2023.. Generative models as an emerging paradigm in the chemical sciences. . J. Am. Chem. Soc. 145:(16):8736–50
     [Crossref] [Google Scholar]
  33. 33.
    Sanchez-Lengeling B, Aspuru-Guzik A. 2018.. Inverse molecular design using machine learning: generative models for matter engineering. . Science 361:(6400):360–65
     [Crossref] [Google Scholar]
  34. 34.
    Mi JX, Li AD, Zhou LF. 2020.. Review study of interpretation methods for future interpretable machine learning. . IEEE Access 8::191969–85
     [Crossref] [Google Scholar]
  35. 35.
    Ren Z, Wan J, Deng P. 2022.. Machine-learning-driven digital twin for lifecycle management of complex equipment. . IEEE Trans. Emerg. Top. Comput. 10::9–22
     [Crossref] [Google Scholar]
  36. 36.
    Gawlikowski J, Saha S, Kruspe A, Zhu XX. 2022.. An advanced Dirichlet prior network for out-of-distribution detection in remote sensing. . IEEE Trans. Geosci. Remote Sens. 60::5616819
     [Crossref] [Google Scholar]
  37. 37.
    Staszak M, Staszak K, Wieszczycka K, Bajek A, Roszkowski K, Tylkowski B. 2022.. Machine learning in drug design: use of artificial intelligence to explore the chemical structure–biological activity relationship. . Wiley Interdiscip. Rev. Comput. Mol. Sci. 12:(2):e1568
     [Crossref] [Google Scholar]
  38. 38.
    Heifetz A. 2022.. Artificial Intelligence in Drug Design. Berlin:: Springer
     [Google Scholar]
  39. 39.
    Mukaidaisi M, Vu A, Grantham K, Tchagang A, Li Y. 2022.. Multi-objective drug design based on graph-fragment molecular representation and deep evolutionary learning. . Front. Pharmacol. 13::920747
     [Crossref] [Google Scholar]
  40. 40.
    Priya S, Tripathi G, Singh DB, Jain P, Kumar A. 2022.. Machine learning approaches and their applications in drug discovery and design. . Chem. Biol. Drug Des. 100:(1):136–53
     [Crossref] [Google Scholar]
  41. 41.
    Leist AK, Klee M, Kim JH, Rehkopf DH, Bordas SP, et al. 2022.. Mapping of machine learning approaches for description, prediction, and causal inference in the social and health sciences. . Sci. Adv. 8:(42):eabk1942
     [Crossref] [Google Scholar]
  42. 42.
    Cui P, Athey S. 2022.. Stable learning establishes some common ground between causal inference and machine learning. . Nat. Mach. Intell. 4:(2):110–15
     [Crossref] [Google Scholar]
  43. 43.
    Yao H, Wang Y, Li S, Zhang L, Liang W, et al. 2022.. Improving out-of-distribution robustness via selective augmentation. . Proc. Mach. Learn. Res. 162::25407–37
     [Google Scholar]
  44. 44.
    Ghaffari S, Saleh E, Schwing AG, Wang YX, Burke MD, Sinha S. 2023.. Property-guided generative modelling for robust model-based design with imbalanced data. . arXiv:2305.13650 [cs.LG]
  45. 45.
    Granda JM, Donina L, Dragone V, Long DL, Cronin L. 2018.. Controlling an organic synthesis robot with machine learning to search for new reactivity. . Nature 559:(7714):377–81
     [Crossref] [Google Scholar]
  46. 46.
    Bilodeau C, Jin W, Jaakkola T, Barzilay R, Jensen KF. 2022.. Generative models for molecular discovery: recent advances and challenges. . Wiley Interdiscip. Rev. Comput. Mol. Sci. 12:(5):e1608
     [Crossref] [Google Scholar]
  47. 47.
    Mroz AM, Posligua V, Tarzia A, Wolpert EH, Jelfs KE. 2022.. Into the unknown: how computation can help explore uncharted material space. . J. Am. Chem. Soc. 144:(41):18730–43
     [Crossref] [Google Scholar]
  48. 48.
    Korshunova M, Huang N, Capuzzi S, Radchenko DS, Savych O, et al. 2022.. Generative and reinforcement learning approaches for the automated de novo design of bioactive compounds. . Commun. Chem. 5::129
     [Crossref] [Google Scholar]
  49. 49.
    Madin OC, Shirts MR. 2023.. Using physical property surrogate models to perform accelerated multi-fidelity optimization of force field parameters. . Digit. Discov. 2:(3):828–47
     [Crossref] [Google Scholar]
  50. 50.
    Yungbluth JC, Medvedev GA, Savoie BM, Caruthers JM. 2020.. Temperature and pressure dependence of the α relaxation in ortho-terphenyl. . J. Chem. Phys. 152::094504
     [Crossref] [Google Scholar]
  51. 51.
    Jin T, Zhao Q, Schofield AB, Savoie BM. 2023.. Machine learning models capable of chemical deduction for identifying reaction products. . ChemRxiv l6lzp. https://doi.org/10.26434/chemrxiv-2023-l6lzp
    [Google Scholar]
/content/journals/10.1146/annurev-chembioeng-100722-111917
Loading
Deductive Machine Learning Challenges and Opportunities in Chemical Applications
Annual Review of Chemical and Biomolecular Engineering 15, 343 (2024); https://doi.org/10.1146/annurev-chembioeng-100722-111917
/content/journals/10.1146/annurev-chembioeng-100722-111917
/content/journals/10.1146/annurev-chembioeng-100722-111917
Loading

Data & Media loading...

  • Article Type: Review Article

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error