Papers
Topics
Authors
Recent
Search
2000 character limit reached

Kernel-Elastic Autoencoder for Molecular Design

Published 12 Oct 2023 in cs.LG | (2310.08685v2)

Abstract: We introduce the Kernel-Elastic Autoencoder (KAE), a self-supervised generative model based on the transformer architecture with enhanced performance for molecular design. KAE is formulated based on two novel loss functions: modified maximum mean discrepancy and weighted reconstruction. KAE addresses the long-standing challenge of achieving valid generation and accurate reconstruction at the same time. KAE achieves remarkable diversity in molecule generation while maintaining near-perfect reconstructions on the independent testing dataset, surpassing previous molecule-generating models. KAE enables conditional generation and allows for decoding based on beam search resulting in state-of-the-art performance in constrained optimizations. Furthermore, KAE can generate molecules conditional to favorable binding affinities in docking applications as confirmed by AutoDock Vina and Glide scores, outperforming all existing candidates from the training dataset. Beyond molecular design, we anticipate KAE could be applied to solve problems by generation in a wide range of applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Mol-cyclegan: a generative model for molecular optimization. Journal of Cheminformatics, 12(1):1–18, 2020.
  2. Generative molecular design in low data regimes. Nature Machine Intelligence, 2(3):171–180, 2020.
  3. Shape-based generative modeling for de novo drug design. Journal of chemical information and modeling, 59(3):1205–1214, 2019.
  4. Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning. Nature Machine Intelligence, 3(10):914–922, 2021.
  5. Gflownet foundations. arXiv preprint arXiv:2111.09266, 2021.
  6. Equivariant diffusion for molecule generation in 3d. In International Conference on Machine Learning, pages 8867–8887. PMLR, 2022.
  7. A de novo molecular generation method using latent vector based generative adversarial network. Journal of Cheminformatics, 11(1):1–13, 2019.
  8. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  9. Automatic chemical design using a data-driven continuous representation of molecules. ACS central science, 4(2):268–276, 2018.
  10. Grammar variational autoencoder. In International conference on machine learning, pages 1945–1954. PMLR, 2017.
  11. Junction tree variational autoencoder for molecular graph generation. In International conference on machine learning, pages 2323–2332. PMLR, 2018.
  12. Dana H Ballard. Modular learning in neural networks. In Aaai, volume 647, pages 279–284, 1987.
  13. Optimizing molecules using efficient queries from property evaluations. Nature Machine Intelligence, 4(1):21–31, 2022.
  14. Property-based design: optimization of drug absorption and pharmacokinetics. Journal of medicinal chemistry, 44(9):1313–1333, 2001.
  15. Molecular optimization by capturing chemist’s intuition using deep neural networks. Journal of cheminformatics, 13(1):1–17, 2021.
  16. A deep generative model for molecule optimization via one fragment modification. Nature machine intelligence, 3(12):1040–1049, 2021.
  17. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  18. Attention-based generative models for de novo molecular design. Chemical Science, 12(24):8362–8372, 2021.
  19. Transformer vae: A hierarchical model for structure-aware and interpretable music representation learning. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 516–520. IEEE, 2020.
  20. T-cvae: Transformer-based conditioned variational autoencoder for story completion. In IJCAI, pages 5233–5239, 2019.
  21. Infovae: Balancing learning and inference in variational autoencoders. In Proceedings of the aaai conference on artificial intelligence, volume 33, pages 5885–5892, 2019.
  22. Talip Ucar. Bridging the elbo and mmd. arXiv preprint arXiv:1910.13181, 2019.
  23. The variational fair autoencoder. arXiv preprint arXiv:1511.00830, 2015.
  24. Conditional β𝛽\betaitalic_β-vae for de novo molecular generation. arXiv preprint arXiv:2205.01592, 2022.
  25. Autodock vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. Journal of computational chemistry, 31(2):455–461, 2010.
  26. Glide: A New Approach for Rapid, Accurate Docking and Scoring. 2. Enrichment Factors in Database Screening. Journal of Medicinal Chemistry, 47(7):1750–1759, 2004.
  27. Extra precision glide: Docking and scoring incorporating a model of hydrophobic enclosure for protein-ligand complexes. Journal of Medicinal Chemistry, 49(21):6177–6196, 2006.
  28. Moflow: an invertible flow model for generating molecular graphs. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 617–626, 2020.
  29. Molecule sequence generation with rebalanced variational autoencoder loss. Journal of Computational Biology, 2022.
  30. Graphdf: A discrete flow model for molecular graph generation. In International Conference on Machine Learning, pages 7192–7203. PMLR, 2021.
  31. All smiles variational autoencoder. arXiv preprint arXiv:1905.13343, 2019.
  32. Greg Landrum et al. Rdkit: Open-source cheminformatics software. 2016.
  33. Hiroshi Kajino. Molecular hypergraph grammar with its application to molecular optimization. In International Conference on Machine Learning, pages 3183–3191. PMLR, 2019.
  34. Graph convolutional policy network for goal-directed molecular graph generation. Advances in neural information processing systems, 31, 2018.
  35. Optimization of molecules via deep reinforcement learning. Scientific reports, 9(1):1–10, 2019.
  36. Reinforced molecular optimization with neighborhood-controlled grammars. Advances in Neural Information Processing Systems, 33:8366–8377, 2020.
  37. Prediction of physicochemical parameters by atomic contributions. Journal of chemical information and computer sciences, 39(5):868–873, 1999.
  38. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. Journal of cheminformatics, 1(1):1–11, 2009.
  39. Molecular generative model based on conditional variational autoencoder for de novo molecular design. Journal of cheminformatics, 10(1):1–9, 2018.
  40. Gf-vae: a flow-based variational autoencoder for molecule generation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pages 1181–1190, 2021.
  41. Flow network based generative models for non-iterative diverse candidate generation. Advances in Neural Information Processing Systems, 34:27381–27394, 2021.
  42. M.; Korablyov M.; Precup D.; Bengio Y. Bengio, E.; Jain. Flow network based generative models for non-iterative diverse candidate generation. https://github.com/GFNOrg/gflownet, 2022.
  43. Alex Graves. Sequence transduction with recurrent neural networks. arXiv preprint arXiv:1211.3711, 2012.
  44. Advances in optimizing recurrent networks. In 2013 IEEE international conference on acoustics, speech and signal processing, pages 8624–8628. IEEE, 2013.
  45. Beam enumeration: Probabilistic explainability for sample efficient self-conditioned molecular design. arXiv preprint arXiv:2309.13957, 2023.
  46. beta-vae: Learning basic visual concepts with a constrained variational framework. In International conference on learning representations, 2017.
  47. A kernel two-sample test. The Journal of Machine Learning Research, 13(1):723–773, 2012.
  48. New York NY Schrödinger, LLC. Schrödinger release 2023-2: Maestro, 2023.
  49. OPLS4: Improving Force Field Accuracy on Challenging Regimes of Chemical Space. Journal of Chemical Theory and Computation, 17(7):4291–4300, 2021.
  50. Towards the comprehensive, rapid, and accurate prediction of the favorable tautomeric states of drug-like molecules in aqueous solution. Journal of Computer-Aided Molecular Design, 24(6-7):591–604, 2010.
Citations (3)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up